Lei Bi

Qiwei Zeng, Hao Wang, Jinghao Lin et al.

Medical vision-language models (VLMs) have shown increasing potential for clinical image interpretation, including lesion detection and report generation. However, their practical utility remains limited by insufficient sensitivity to subtle lesions, whose visual evidence is often sparse, low-contrast, and embedded within complex anatomical context. As local visual tokens are aggregated, these weak lesion cues can become underrepresented in global image representations, making them difficult for medical VLMs to recognize. Existing efforts to improve lesion sensitivity mainly rely on medical-domain vision-encoder pre-training, clinical-term-guided alignment, or trainable pathological representation enhancement. Although effective, these approaches usually require additional training or model-specific adaptation and may overfit to particular disease morphologies, limiting their applicability to frozen medical VLMs. To address these limitations, we propose EasyLens, a training-free plug-and-play subtle-lesion representation amplifier for medical VLMs. EasyLens first constructs EasyBank, a pathology-anatomy prototype space that provides lesion-related prototypes and anatomy-aware normal references for comparing suspicious patches against both pathological and normal anatomical patterns. To avoid blindly amplifying normal tissues, EasyTag selects lesion-relevant patches through counterfactual prototype reasoning. To counteract the dilution of subtle lesion cues in global image representations, EasyAmplifier strengthens the selected lesion-relevant patch representations through morphology-guided residual enhancement, thereby increasing their contribution to the global image embedding. Experiments on multiple medical image datasets and frozen medical VLM backbones show that EasyLens improves subtle-lesion detection and outperforms existing encoder-enhancement baselines.

Yige Peng, Jinman Kim, Dagan Feng et al.

Multi-modality Fluorodeoxyglucose (FDG) positron emission tomography / computed tomography (PET/CT) has been routinely used in the assessment of common cancers, such as lung cancer, lymphoma, and melanoma. This is mainly attributed to the fact that PET/CT combines the high sensitivity for tumor detection of PET and anatomical information from CT. In PET/CT image assessment, automatic tumor segmentation is an important step, and in recent years, deep learning based methods have become the state-of-the-art. Unfortunately, existing methods tend to over-segment the tumor regions and include regions such as the normal high uptake organs, inflammation, and other infections. In this study, we introduce a false positive reduction network to overcome this limitation. We firstly introduced a self-supervised pre-trained global segmentation module to coarsely delineate the candidate tumor regions using a self-supervised pre-trained encoder. The candidate tumor regions were then refined by removing false positives via a local refinement module. Our experiments with the MICCAI 2022 Automated Lesion Segmentation in Whole-Body FDG-PET/CT (AutoPET) challenge dataset showed that our method achieved a dice score of 0.9324 with the preliminary testing data and was ranked 1st place in dice on the leaderboard. Our method was also ranked in the top 7 methods on the final testing data, the final ranking will be announced during the 2022 MICCAI AutoPET workshop. Our code is available at: https://github.com/YigePeng/AutoPET_False_Positive_Reduction.

Mingyuan Meng, Lei Bi, Michael Fulham et al.

Image registration is a fundamental requirement for medical image analysis. Deep registration methods based on deep learning have been widely recognized for their capabilities to perform fast end-to-end registration. Many deep registration methods achieved state-of-the-art performance by performing coarse-to-fine registration, where multiple registration steps were iterated with cascaded networks. Recently, Non-Iterative Coarse-to-finE (NICE) registration methods have been proposed to perform coarse-to-fine registration in a single network and showed advantages in both registration accuracy and runtime. However, existing NICE registration methods mainly focus on deformable registration, while affine registration, a common prerequisite, is still reliant on time-consuming traditional optimization-based methods or extra affine registration networks. In addition, existing NICE registration methods are limited by the intrinsic locality of convolution operations. Transformers may address this limitation for their capabilities to capture long-range dependency, but the benefits of using transformers for NICE registration have not been explored. In this study, we propose a Non-Iterative Coarse-to-finE Transformer network (NICE-Trans) for image registration. Our NICE-Trans is the first deep registration method that (i) performs joint affine and deformable coarse-to-fine registration within a single network, and (ii) embeds transformers into a NICE registration framework to model long-range relevance between images. Extensive experiments with seven public datasets show that our NICE-Trans outperforms state-of-the-art registration methods on both registration accuracy and runtime.

Mingyuan Meng, Michael Fulham, Dagan Feng et al.

Deformable image registration aims to find a dense non-linear spatial correspondence between a pair of images, which is a crucial step for many medical tasks such as tumor growth monitoring and population analysis. Recently, Deep Neural Networks (DNNs) have been widely recognized for their ability to perform fast end-to-end registration. However, DNN-based registration needs to explore the spatial information of each image and fuse this information to characterize spatial correspondence. This raises an essential question: what is the optimal fusion strategy to characterize spatial correspondence? Existing fusion strategies (e.g., early fusion, late fusion) were empirically designed to fuse information by manually defined prior knowledge, which inevitably constrains the registration performance within the limits of empirical designs. In this study, we depart from existing empirically-designed fusion strategies and develop a data-driven fusion strategy for deformable image registration. To achieve this, we propose an Automatic Fusion network (AutoFuse) that provides flexibility to fuse information at many potential locations within the network. A Fusion Gate (FG) module is also proposed to control how to fuse information at each potential network location based on training data. Our AutoFuse can automatically optimize its fusion strategy during training and can be generalizable to both unsupervised registration (without any labels) and semi-supervised registration (with weak labels provided for partial training data). Extensive experiments on two well-benchmarked medical registration tasks (inter- and intra-patient registration) with eight public datasets show that our AutoFuse outperforms state-of-the-art unsupervised and semi-supervised registration methods.

Yuezhe Yang, Hao Wang, Yige Peng et al.

Automated clinical diagnosis remains a core challenge in medical AI, which usually requires models to integrate multi-modal data and reason across complex, case-specific contexts. Although recent methods have advanced medical report generation (MRG) and visual question answering (VQA) with medical vision-language models (VLMs), these methods, however, predominantly operate under a sample-isolated inference paradigm, as such processing cases independently without access to longitudinal electronic health records (EHRs) or structurally related patient examples. This paradigm limits reasoning to image-derived information alone, which ignores external complementary medical evidence for potentially more accurate diagnosis. To overcome this limitation, we propose \textbf{HyperWalker}, a \textit{Deep Diagnosis} framework that reformulates clinical reasoning via dynamic hypergraphs and test-time training. First, we construct a dynamic hypergraph, termed \textbf{iBrochure}, to model the structural heterogeneity of EHR data and implicit high-order associations among multimodal clinical information. Within this hypergraph, a reinforcement learning agent, \textbf{Walker}, navigates to and identifies optimal diagnostic paths. To ensure comprehensive coverage of diverse clinical characteristics in test samples, we incorporate a \textit{linger mechanism}, a multi-hop orthogonal retrieval strategy that iteratively selects clinically complementary neighborhood cases reflecting distinct clinical attributes. Experiments on MRG with MIMIC and medical VQA on EHRXQA demonstrate that HyperWalker achieves state-of-the-art performance. Code is available at: https://github.com/Bean-Young/HyperWalker

Mingyuan Meng, Lei Bi, Michael Fulham et al.

Survival prediction is crucial for cancer patients as it provides early prognostic information for treatment planning. Recently, deep survival models based on deep learning and medical images have shown promising performance for survival prediction. However, existing deep survival models are not well developed in utilizing multi-modality images (e.g., PET-CT) and in extracting region-specific information (e.g., the prognostic information in Primary Tumor (PT) and Metastatic Lymph Node (MLN) regions). In view of this, we propose a merging-diverging learning framework for survival prediction from multi-modality images. This framework has a merging encoder to fuse multi-modality information and a diverging decoder to extract region-specific information. In the merging encoder, we propose a Hybrid Parallel Cross-Attention (HPCA) block to effectively fuse multi-modality features via parallel convolutional layers and cross-attention transformers. In the diverging decoder, we propose a Region-specific Attention Gate (RAG) block to screen out the features related to lesion regions. Our framework is demonstrated on survival prediction from PET-CT images in Head and Neck (H&N) cancer, by designing an X-shape merging-diverging hybrid transformer network (named XSurv). Our XSurv combines the complementary information in PET and CT images and extracts the region-specific prognostic information in PT and MLN regions. Extensive experiments on the public dataset of HEad and neCK TumOR segmentation and outcome prediction challenge (HECKTOR 2022) demonstrate that our XSurv outperforms state-of-the-art survival prediction methods.

Mingyuan Meng, Lei Bi, Dagan Feng et al.

Deformable image registration is a crucial step in medical image analysis for finding a non-linear spatial transformation between a pair of fixed and moving images. Deep registration methods based on Convolutional Neural Networks (CNNs) have been widely used as they can perform image registration in a fast and end-to-end manner. However, these methods usually have limited performance for image pairs with large deformations. Recently, iterative deep registration methods have been used to alleviate this limitation, where the transformations are iteratively learned in a coarse-to-fine manner. However, iterative methods inevitably prolong the registration runtime, and tend to learn separate image features for each iteration, which hinders the features from being leveraged to facilitate the registration at later iterations. In this study, we propose a Non-Iterative Coarse-to-finE registration Network (NICE-Net) for deformable image registration. In the NICE-Net, we propose: (i) a Single-pass Deep Cumulative Learning (SDCL) decoder that can cumulatively learn coarse-to-fine transformations within a single pass (iteration) of the network, and (ii) a Selectively-propagated Feature Learning (SFL) encoder that can learn common image features for the whole coarse-to-fine registration process and selectively propagate the features as needed. Extensive experiments on six public datasets of 3D brain Magnetic Resonance Imaging (MRI) show that our proposed NICE-Net can outperform state-of-the-art iterative deep registration methods while only requiring similar runtime to non-iterative methods.

Mingyuan Meng, Lei Bi, Dagan Feng et al.

Outcome prediction is crucial for head and neck cancer patients as it can provide prognostic information for early treatment planning. Radiomics methods have been widely used for outcome prediction from medical images. However, these methods are limited by their reliance on intractable manual segmentation of tumor regions. Recently, deep learning methods have been proposed to perform end-to-end outcome prediction so as to remove the reliance on manual segmentation. Unfortunately, without segmentation masks, these methods will take the whole image as input, such that makes them difficult to focus on tumor regions and potentially unable to fully leverage the prognostic information within the tumor regions. In this study, we propose a radiomics-enhanced deep multi-task framework for outcome prediction from PET/CT images, in the context of HEad and neCK TumOR segmentation and outcome prediction challenge (HECKTOR 2022). In our framework, our novelty is to incorporate radiomics as an enhancement to our recently proposed Deep Multi-task Survival model (DeepMTS). The DeepMTS jointly learns to predict the survival risk scores of patients and the segmentation masks of tumor regions. Radiomics features are extracted from the predicted tumor regions and combined with the predicted survival risk scores for final outcome prediction, through which the prognostic information in tumor regions can be further leveraged. Our method achieved a C-index of 0.681 on the testing set, placing the 2nd on the leaderboard with only 0.00068 lower in C-index than the 1st place.

Yuxin Xue, Lei Bi, Yige Peng et al.

Positron emission tomography (PET) is a widely used, highly sensitive molecular imaging in clinical diagnosis. There is interest in reducing the radiation exposure from PET but also maintaining adequate image quality. Recent methods using convolutional neural networks (CNNs) to generate synthesized high-quality PET images from low-dose counterparts have been reported to be state-of-the-art for low-to-high image recovery methods. However, these methods are prone to exhibiting discrepancies in texture and structure between synthesized and real images. Furthermore, the distribution shift between low-dose PET and standard PET has not been fully investigated. To address these issues, we developed a self-supervised adaptive residual estimation generative adversarial network (SS-AEGAN). We introduce (1) An adaptive residual estimation mapping mechanism, AE-Net, designed to dynamically rectify the preliminary synthesized PET images by taking the residual map between the low-dose PET and synthesized output as the input, and (2) A self-supervised pre-training strategy to enhance the feature representation of the coarse generator. Our experiments with a public benchmark dataset of total-body PET images show that SS-AEGAN consistently outperformed the state-of-the-art synthesis methods with various dose reduction factors.

Mingyuan Meng, Lei Bi, Dagan Feng et al.

In this study, we focus on brain tumor sequence registration between pre-operative and follow-up Magnetic Resonance Imaging (MRI) scans of brain glioma patients, in the context of Brain Tumor Sequence Registration challenge (BraTS-Reg 2022). Brain tumor registration is a fundamental requirement in brain image analysis for quantifying tumor changes. This is a challenging task due to large deformations and missing correspondences between pre-operative and follow-up scans. For this task, we adopt our recently proposed Non-Iterative Coarse-to-finE registration Networks (NICE-Net) - a deep learning-based method for coarse-to-fine registering images with large deformations. To overcome missing correspondences, we extend the NICE-Net by introducing dual deep supervision, where a deep self-supervised loss based on image similarity and a deep weakly-supervised loss based on manually annotated landmarks are deeply embedded into the NICE-Net. At the BraTS-Reg 2022, our method achieved a competitive result on the validation set (mean absolute error: 3.387) and placed 4th in the final testing phase (Score: 0.3544).

Lei Bi, Michael Fulham, Shaoli Song et al.

[18F]-Fluorodeoxyglucose (FDG) positron emission tomography - computed tomography (PET-CT) has become the imaging modality of choice for diagnosing many cancers. Co-learning complementary PET-CT imaging features is a fundamental requirement for automatic tumor segmentation and for developing computer aided cancer diagnosis systems. In this study, we propose a hyper-connected transformer (HCT) network that integrates a transformer network (TN) with a hyper connected fusion for multi-modality PET-CT images. The TN was leveraged for its ability to provide global dependencies in image feature learning, which was achieved by using image patch embeddings with a self-attention mechanism to capture image-wide contextual information. We extended the single-modality definition of TN with multiple TN based branches to separately extract image features. We also introduced a hyper connected fusion to fuse the contextual and complementary image features across multiple transformers in an iterative manner. Our results with two clinical datasets show that HCT achieved better performance in segmentation accuracy when compared to the existing methods.

Hao Wang, Euijoon Ahn, Lei Bi et al.

The clinical diagnosis of skin lesion involves the analysis of dermoscopic and clinical modalities. Dermoscopic images provide a detailed view of the surface structures whereas clinical images offer a complementary macroscopic information. The visual diagnosis of melanoma is also based on seven-point checklist which involves identifying different visual attributes. Recently, supervised learning approaches such as convolutional neural networks (CNNs) have shown great performances using both dermoscopic and clinical modalities (Multi-modality). The seven different visual attributes in the checklist are also used to further improve the the diagnosis. The performances of these approaches, however, are still reliant on the availability of large-scaled labeled data. The acquisition of annotated dataset is an expensive and time-consuming task, more so with annotating multi-attributes. To overcome this limitation, we propose a self-supervised learning (SSL) algorithm for multi-modality skin lesion classification. Our algorithm enables the multi-modality learning by maximizing the similarities between paired dermoscopic and clinical images from different views. In addition, we generate surrogate pseudo-multi-labels that represent seven attributes via clustering analysis. We also propose a label-relation-aware module to refine each pseudo-label embedding and capture the interrelationships between pseudo-multi-labels. We validated the effectiveness of our algorithm using well-benchmarked seven-point skin lesion dataset. Our results show that our algorithm achieved better performances than other state-of-the-art SSL counterparts.

Yuxin Xue, Yige Peng, Lei Bi et al.

Positron emission tomography (PET) is the most sensitive molecular imaging modality routinely applied in our modern healthcare. High radioactivity caused by the injected tracer dose is a major concern in PET imaging and limits its clinical applications. However, reducing the dose leads to inadequate image quality for diagnostic practice. Motivated by the need to produce high quality images with minimum low-dose, Convolutional Neural Networks (CNNs) based methods have been developed for high quality PET synthesis from its low-dose counterparts. Previous CNNs-based studies usually directly map low-dose PET into features space without consideration of different dose reduction level. In this study, a novel approach named CG-3DSRGAN (Classification-Guided Generative Adversarial Network with Super Resolution Refinement) is presented. Specifically, a multi-tasking coarse generator, guided by a classification head, allows for a more comprehensive understanding of the noise-level features present in the low-dose data, resulting in improved image synthesis. Moreover, to recover spatial details of standard PET, an auxiliary super resolution network - Contextual-Net - is proposed as a second-stage training to narrow the gap between coarse prediction and standard PET. We compared our method to the state-of-the-art methods on whole-body PET with different dose reduction factors (DRFs). Experiments demonstrate our method can outperform others on all DRF.

Mingyuan Meng, Yuxin Xue, Dagan Feng et al.

Dense prediction is a fundamental requirement for many medical vision tasks such as medical image restoration, registration, and segmentation. The most popular vision model, Convolutional Neural Networks (CNNs), has reached bottlenecks due to the intrinsic locality of convolution operations. Recently, transformers have been widely adopted for dense prediction for their capability to capture long-range visual dependence. However, due to the high computational complexity and large memory consumption of self-attention operations, transformers are usually used at downsampled feature resolutions. Such usage cannot effectively leverage the tissue-level textural information available only at the full image resolution. This textural information is crucial for medical dense prediction as it can differentiate the subtle human anatomy in medical images. In this study, we hypothesize that Multi-layer Perceptrons (MLPs) are superior alternatives to transformers in medical dense prediction where tissue-level details dominate the performance, as MLPs enable long-range dependence at the full image resolution. To validate our hypothesis, we develop a full-resolution hierarchical MLP framework that uses MLPs beginning from the full image resolution. We evaluate this framework with various MLP blocks on a wide range of medical dense prediction tasks including restoration, registration, and segmentation. Extensive experiments on six public well-benchmarked datasets show that, by simply using MLPs at full resolution, our framework outperforms its CNN and transformer counterparts and achieves state-of-the-art performance on various medical dense prediction tasks.

Xiaoshuang Li, Mingyuan Meng, Zimo Huang et al.

Panoramic X-ray (PX) is a prevalent modality in dental practice for its wide availability and low cost. However, as a 2D projection image, PX does not contain 3D anatomical information, and therefore has limited use in dental applications that can benefit from 3D information, e.g., tooth angular misa-lignment detection and classification. Reconstructing 3D structures directly from 2D PX has recently been explored to address limitations with existing methods primarily reliant on Convolutional Neural Networks (CNNs) for direct 2D-to-3D mapping. These methods, however, are unable to correctly infer depth-axis spatial information. In addition, they are limited by the in-trinsic locality of convolution operations, as the convolution kernels only capture the information of immediate neighborhood pixels. In this study, we propose a progressive hybrid Multilayer Perceptron (MLP)-CNN pyra-mid network (3DPX) for 2D-to-3D oral PX reconstruction. We introduce a progressive reconstruction strategy, where 3D images are progressively re-constructed in the 3DPX with guidance imposed on the intermediate recon-struction result at each pyramid level. Further, motivated by the recent ad-vancement of MLPs that show promise in capturing fine-grained long-range dependency, our 3DPX integrates MLPs and CNNs to improve the semantic understanding during reconstruction. Extensive experiments on two large datasets involving 464 studies demonstrate that our 3DPX outperforms state-of-the-art 2D-to-3D oral reconstruction methods, including standalone MLP and transformers, in reconstruction quality, and also im-proves the performance of downstream angular misalignment classification tasks.

Xiaoshuang Li, Zimo Huang, Mingyuan Meng et al.

Panoramic X-ray (PX) is a prevalent modality in dentistry practice owing to its wide availability and low cost. However, as a 2D projection of a 3D structure, PX suffers from anatomical information loss and PX diagnosis is limited compared to that with 3D imaging modalities. 2D-to-3D reconstruction methods have been explored for the ability to synthesize the absent 3D anatomical information from 2D PX for use in PX image analysis. However, there are challenges in leveraging such 3D synthesized reconstructions. First, inferring 3D depth from 2D images remains a challenging task with limited accuracy. The second challenge is the joint analysis of 2D PX with its 3D synthesized counterpart, with the aim to maximize the 2D-3D synergy while minimizing the errors arising from the synthesized image. In this study, we propose a new method termed 3DPX - PX image analysis guided by 2D-to-3D reconstruction, to overcome these challenges. 3DPX consists of (i) a novel progressive reconstruction network to improve 2D-to-3D reconstruction and, (ii) a contrastive-guided bidirectional multimodality alignment module for 3D-guided 2D PX classification and segmentation tasks. The reconstruction network progressively reconstructs 3D images with knowledge imposed on the intermediate reconstructions at multiple pyramid levels and incorporates Multilayer Perceptrons to improve semantic understanding. The downstream networks leverage the reconstructed images as 3D anatomical guidance to the PX analysis through feature alignment, which increases the 2D-3D synergy with bidirectional feature projection and decease the impact of potential errors with contrastive guidance. Extensive experiments on two oral datasets involving 464 studies demonstrate that 3DPX outperforms the state-of-the-art methods in various tasks including 2D-to-3D reconstruction, PX classification and lesion segmentation.

Lei Bi, Michael Fulham, Jinman Kim

Automatic skin lesion segmentation methods based on fully convolutional networks (FCNs) are regarded as the state-of-the-art for accuracy. When there are, however, insufficient training data to cover all the variations in skin lesions, where lesions from different patients may have major differences in size/shape/texture, these methods failed to segment the lesions that have image characteristics, which are less common in the training datasets. FCN-based semi-automatic segmentation methods, which fuse user-inputs with high-level semantic image features derived from FCNs offer an ideal complement to overcome limitations of automatic segmentation methods. These semi-automatic methods rely on the automated state-of-the-art FCNs coupled with user-inputs for refinements, and therefore being able to tackle challenging skin lesions. However, there are a limited number of FCN-based semi-automatic segmentation methods and all these methods focused on early-fusion, where the first few convolutional layers are used to fuse image features and user-inputs and then derive fused image features for segmentation. For early-fusion based methods, because the user-input information can be lost after the first few convolutional layers, consequently, the user-input information will have limited guidance and constraint in segmenting the challenging skin lesions with inhomogeneous textures and fuzzy boundaries. Hence, in this work, we introduce a hyper-fusion network (HFN) to fuse the extracted user-inputs and image features over multiple stages. We separately extract complementary features which then allows for an iterative use of user-inputs along all the fusion stages to refine the segmentation. We evaluated our HFN on ISIC 2017, ISIC 2016 and PH2 datasets, and our results show that the HFN is more accurate and generalizable than the state-of-the-art methods.

Mingjian Li, Mingyuan Meng, Shuchang Ye et al.

Medical image segmentation is crucial in modern medical image analysis, which can aid into diagnosis of various disease conditions. Recently, language-guided segmentation methods have shown promising results in automating image segmentation where text reports are incorporated as guidance. These text reports, containing image impressions and insights given by clinicians, provides auxiliary guidance. However, these methods neglect the inherent pattern gaps between the two distinct modalities, which leads to sub-optimal image-text feature fusion without proper cross-modality feature alignments. Contrastive alignments are widely used to associate image-text semantics in representation learning; however, it has not been exploited to bridge the pattern gaps in language-guided segmentation that relies on subtle low level image details to represent diseases. Existing contrastive alignment methods typically algin high-level global image semantics without involving low-level, localized target information, and therefore fails to explore fine-grained text guidance for language-guided segmentation. In this study, we propose a language-guided segmentation network with Target-informed Multi-level Contrastive Alignments (TMCA). TMCA enables target-informed cross-modality alignments and fine-grained text guidance to bridge the pattern gaps in language-guided segmentation. Specifically, we introduce: 1) a target-sensitive semantic distance module that enables granular image-text alignment modelling, and 2) a multi-level alignment strategy that directs text guidance on low-level image features. In addition, a language-guided target enhancement module is proposed to leverage the aligned text to redirect attention to focus on critical localized image features. Extensive experiments on 4 image-text datasets, involving 3 medical imaging modalities, demonstrated that our TMCA achieved superior performances.

Mingyuan Meng, Michael Fulham, Lei Bi et al.

Deformable image registration is a fundamental requirement for medical image analysis. Recently, transformers have been widely used in deep learning-based registration methods for their ability to capture long-range dependency via self-attention (SA). However, the high computation and memory loads of SA (growing quadratically with the spatial resolution) hinder transformers from processing subtle textural information in high-resolution image features, e.g., at the full and half image resolutions. This limits deformable registration as the high-resolution textural information is crucial for finding precise pixel-wise correspondence between subtle anatomical structures. Cross-covariance Attention (XCA), as a "transposed" version of SA that operates across feature channels, has complexity growing linearly with the spatial resolution, providing the feasibility of capturing long-range dependency among high-resolution image features. However, existing XCA-based transformers merely capture coarse global long-range dependency, which are unsuitable for deformable image registration relying primarily on fine-grained local correspondence. In this study, we propose to improve existing deep learning-based registration methods by embedding a new XCA mechanism. To this end, we design an XCA-based transformer block optimized for deformable medical image registration, named Multi-Axis XCA (MAXCA). Our MAXCA serves as a general network block that can be embedded into various registration network architectures. It can capture both global and local long-range dependency among high-resolution image features by applying regional and dilated XCA in parallel via a multi-axis design. Extensive experiments on two well-benchmarked inter-/intra-patient registration tasks with seven public medical datasets demonstrate that our MAXCA block enables state-of-the-art registration performance.

Yuyu Guo, Lei Bi, Zhengbin Zhu et al.

Automated segmentation of left ventricular cavity (LVC) in temporal cardiac image sequences (multiple time points) is a fundamental requirement for quantitative analysis of its structural and functional changes. Deep learning based methods for the segmentation of LVC are the state of the art; however, these methods are generally formulated to work on single time points, and fails to exploit the complementary information from the temporal image sequences that can aid in segmentation accuracy and consistency among the images across the time points. Furthermore, these segmentation methods perform poorly in segmenting the end-systole (ES) phase images, where the left ventricle deforms to the smallest irregular shape, and the boundary between the blood chamber and myocardium becomes inconspicuous. To overcome these limitations, we propose a new method to automatically segment temporal cardiac images where we introduce a spatial sequential (SS) network to learn the deformation and motion characteristics of the LVC in an unsupervised manner; these characteristics were then integrated with sequential context information derived from bi-directional learning (BL) where both chronological and reverse-chronological directions of the image sequence were used. Our experimental results on a cardiac computed tomography (CT) dataset demonstrated that our spatial-sequential network with bi-directional learning (SS-BL) method outperformed existing methods for LVC segmentation. Our method was also applied to MRI cardiac dataset and the results demonstrated the generalizability of our method.

Mingjian Li, Mingyuan Meng, Michael Fulham et al.

Medical image representations can be learned through medical vision-language contrastive learning (mVLCL) where medical imaging reports are used as weak supervision through image-text alignment. These learned image representations can be transferred to and benefit various downstream medical vision tasks such as disease classification and segmentation. Recent mVLCL methods attempt to align image sub-regions and the report keywords as local-matchings. However, these methods aggregate all local-matchings via simple pooling operations while ignoring the inherent relations between them. These methods therefore fail to reason between local-matchings that are semantically related, e.g., local-matchings that correspond to the disease word and the location word (semantic-relations), and also fail to differentiate such clinically important local-matchings from others that correspond to less meaningful words, e.g., conjunction words (importance-relations). Hence, we propose a mVLCL method that models the inter-matching relations between local-matchings via a relation-enhanced contrastive learning framework (RECLF). In RECLF, we introduce a semantic-relation reasoning module (SRM) and an importance-relation reasoning module (IRM) to enable more fine-grained report supervision for image representation learning. We evaluated our method using six public benchmark datasets on four downstream tasks, including segmentation, zero-shot classification, linear classification, and cross-modal retrieval. Our results demonstrated the superiority of our RECLF over the state-of-the-art mVLCL methods with consistent improvements across single-modal and cross-modal tasks. These results suggest that our RECLF, by modelling the inter-matching relations, can learn improved medical image representations with better generalization capabilities.

Mingyuan Meng, Bingxin Gu, Michael Fulham et al.

Survival prediction is a major concern for cancer management. Deep survival models based on deep learning have been widely adopted to perform end-to-end survival prediction from medical images. Recent deep survival models achieved promising performance by jointly performing tumor segmentation with survival prediction, where the models were guided to extract tumor-related information through Multi-Task Learning (MTL). However, these deep survival models have difficulties in exploring out-of-tumor prognostic information. In addition, existing deep survival models are unable to effectively leverage multi-modality images. Empirically-designed fusion strategies were commonly adopted to fuse multi-modality information via task-specific manually-designed networks, thus limiting the adaptability to different scenarios. In this study, we propose an Adaptive Multi-modality Segmentation-to-Survival model (AdaMSS) for survival prediction from PET/CT images. Instead of adopting MTL, we propose a novel Segmentation-to-Survival Learning (SSL) strategy, where our AdaMSS is trained for tumor segmentation and survival prediction sequentially in two stages. This strategy enables the AdaMSS to focus on tumor regions in the first stage and gradually expand its focus to include other prognosis-related regions in the second stage. We also propose a data-driven strategy to fuse multi-modality information, which realizes adaptive optimization of fusion strategies based on training data during training. With the SSL and data-driven fusion strategies, our AdaMSS is designed as an adaptive model that can self-adapt its focus regions and fusion strategy for different training stages. Extensive experiments with two large clinical datasets show that our AdaMSS outperforms state-of-the-art survival prediction methods.

Bhakti Baheti, Satrajit Chakrabarty, Hamed Akbari et al.

Registration of longitudinal brain MRI scans containing pathologies is challenging due to dramatic changes in tissue appearance. Although there has been progress in developing general-purpose medical image registration techniques, they have not yet attained the requisite precision and reliability for this task, highlighting its inherent complexity. Here we describe the Brain Tumor Sequence Registration (BraTS-Reg) challenge, as the first public benchmark environment for deformable registration algorithms focusing on estimating correspondences between pre-operative and follow-up scans of the same patient diagnosed with a diffuse brain glioma. The BraTS-Reg data comprise de-identified multi-institutional multi-parametric MRI (mpMRI) scans, curated for size and resolution according to a canonical anatomical template, and divided into training, validation, and testing sets. Clinical experts annotated ground truth (GT) landmark points of anatomical locations distinct across the temporal domain. Quantitative evaluation and ranking were based on the Median Euclidean Error (MEE), Robustness, and the determinant of the Jacobian of the displacement field. The top-ranked methodologies yielded similar performance across all evaluation metrics and shared several methodological commonalities, including pre-alignment, deep neural networks, inverse consistency analysis, and test-time instance optimization per-case basis as a post-processing step. The top-ranked method attained the MEE at or below that of the inter-rater variability for approximately 60% of the evaluated landmarks, underscoring the scope for further accuracy and robustness improvements, especially relative to human experts. The aim of BraTS-Reg is to continue to serve as an active resource for research, with the data and online evaluation tools accessible at https://bratsreg.github.io/.

Yuyu Guo, Lei Bi, Dongming Wei et al.

Motion estimation is a fundamental step in dynamic medical image processing for the assessment of target organ anatomy and function. However, existing image-based motion estimation methods, which optimize the motion field by evaluating the local image similarity, are prone to produce implausible estimation, especially in the presence of large motion. In this study, we provide a novel motion estimation framework of Dense-Sparse-Dense (DSD), which comprises two stages. In the first stage, we process the raw dense image to extract sparse landmarks to represent the target organ anatomical topology and discard the redundant information that is unnecessary for motion estimation. For this purpose, we introduce an unsupervised 3D landmark detection network to extract spatially sparse but representative landmarks for the target organ motion estimation. In the second stage, we derive the sparse motion displacement from the extracted sparse landmarks of two images of different time points. Then, we present a motion reconstruction network to construct the motion field by projecting the sparse landmarks displacement back into the dense image domain. Furthermore, we employ the estimated motion field from our two-stage DSD framework as initialization and boost the motion estimation quality in light-weight yet effective iterative optimization. We evaluate our method on two dynamic medical imaging tasks to model cardiac motion and lung respiratory motion, respectively. Our method has produced superior motion estimation accuracy compared to existing comparative methods. Besides, the extensive experimental results demonstrate that our solution can extract well representative anatomical landmarks without any requirement of manual annotation. Our code is publicly available online.

Mingyuan Meng, Bingxin Gu, Lei Bi et al.

Nasopharyngeal Carcinoma (NPC) is a malignant epithelial cancer arising from the nasopharynx. Survival prediction is a major concern for NPC patients, as it provides early prognostic information to plan treatments. Recently, deep survival models based on deep learning have demonstrated the potential to outperform traditional radiomics-based survival prediction models. Deep survival models usually use image patches covering the whole target regions (e.g., nasopharynx for NPC) or containing only segmented tumor regions as the input. However, the models using the whole target regions will also include non-relevant background information, while the models using segmented tumor regions will disregard potentially prognostic information existing out of primary tumors (e.g., local lymph node metastasis and adjacent tissue invasion). In this study, we propose a 3D end-to-end Deep Multi-Task Survival model (DeepMTS) for joint survival prediction and tumor segmentation in advanced NPC from pretreatment PET/CT. Our novelty is the introduction of a hard-sharing segmentation backbone to guide the extraction of local features related to the primary tumors, which reduces the interference from non-relevant background information. In addition, we also introduce a cascaded survival network to capture the prognostic information existing out of primary tumors and further leverage the global tumor information (e.g., tumor size, shape, and locations) derived from the segmentation backbone. Our experiments with two clinical datasets demonstrate that our DeepMTS can consistently outperform traditional radiomics-based survival prediction models and existing deep survival models.

Kai-Chieh Liang, Lei Bi, Ashnil Kumar et al.

Sequential whole-body 18F-Fluorodeoxyglucose (FDG) positron emission tomography (PET) scans are regarded as the imaging modality of choice for the assessment of treatment response in the lymphomas because they detect treatment response when there may not be changes on anatomical imaging. Any computerized analysis of lymphomas in whole-body PET requires automatic segmentation of the studies so that sites of disease can be quantitatively monitored over time. State-of-the-art PET image segmentation methods are based on convolutional neural networks (CNNs) given their ability to leverage annotated datasets to derive high-level features about the disease process. Such methods, however, focus on PET images from a single time-point and discard information from other scans or are targeted towards specific organs and cannot cater for the multiple structures in whole-body PET images. In this study, we propose a spatio-temporal 'dual-stream' neural network (ST-DSNN) to segment sequential whole-body PET scans. Our ST-DSNN learns and accumulates image features from the PET images done over time. The accumulated image features are used to enhance the organs / structures that are consistent over time to allow easier identification of sites of active lymphoma. Our results show that our method outperforms the state-of-the-art PET image segmentation methods.

Yige Peng, Lei Bi, Ashnil Kumar et al.

Distant metastases (DM) refer to the dissemination of tumors, usually, beyond the organ where the tumor originated. They are the leading cause of death in patients with soft-tissue sarcomas (STSs). Positron emission tomography-computed tomography (PET-CT) is regarded as the imaging modality of choice for the management of STSs. It is difficult to determine from imaging studies which STS patients will develop metastases. 'Radiomics' refers to the extraction and analysis of quantitative features from medical images and it has been employed to help identify such tumors. The state-of-the-art in radiomics is based on convolutional neural networks (CNNs). Most CNNs are designed for single-modality imaging data (CT or PET alone) and do not exploit the information embedded in PET-CT where there is a combination of an anatomical and functional imaging modality. Furthermore, most radiomic methods rely on manual input from imaging specialists for tumor delineation, definition and selection of radiomic features. This approach, however, may not be scalable to tumors with complex boundaries and where there are multiple other sites of disease. We outline a new 3D CNN to help predict DM in STS patients from PET-CT data. The 3D CNN uses a constrained feature learning module and a hierarchical multi-modality feature learning module that leverages the complementary information from the modalities to focus on semantically important regions. Our results on a public PET-CT dataset of STS patients show that multi-modal information improves the ability to identify those patients who develop DM. Further our method outperformed all other related state-of-the-art methods.

Xiaohang Fu, Lei Bi, Ashnil Kumar et al.

The identification of melanoma involves an integrated analysis of skin lesion images acquired using the clinical and dermoscopy modalities. Dermoscopic images provide a detailed view of the subsurface visual structures that supplement the macroscopic clinical images. Melanoma diagnosis is commonly based on the 7-point visual category checklist (7PC). The 7PC contains intrinsic relationships between categories that can aid classification, such as shared features, correlations, and the contributions of categories towards diagnosis. Manual classification is subjective and prone to intra- and interobserver variability. This presents an opportunity for automated methods to improve diagnosis. Current state-of-the-art methods focus on a single image modality and ignore information from the other, or do not fully leverage the complementary information from both modalities. Further, there is not a method to exploit the intercategory relationships in the 7PC. In this study, we address these issues by proposing a graph-based intercategory and intermodality network (GIIN) with two modules. A graph-based relational module (GRM) leverages intercategorical relations, intermodal relations, and prioritises the visual structure details from dermoscopy by encoding category representations in a graph network. The category embedding learning module (CELM) captures representations that are specialised for each category and support the GRM. We show that our modules are effective at enhancing classification performance using a public dataset of dermoscopy-clinical images, and show that our method outperforms the state-of-the-art at classifying the 7PC categories and diagnosis.

Bingxin Gu, Mingyuan Meng, Lei Bi et al.

Objective: Deep Learning-based Radiomics (DLR) has achieved great success in medical image analysis and has been considered a replacement for conventional radiomics that relies on handcrafted features. In this study, we aimed to explore the capability of DLR for the prediction of 5-year Progression-Free Survival (PFS) in Nasopharyngeal Carcinoma (NPC) using pretreatment PET/CT. Methods: A total of 257 patients (170/87 in internal/external cohorts) with advanced NPC (TNM stage III or IVa) were enrolled. We developed an end-to-end multi-modality DLR model, in which a 3D convolutional neural network was optimized to extract deep features from pretreatment PET/CT images and predict the probability of 5-year PFS. TNM stage, as a high-level clinical feature, could be integrated into our DLR model to further improve the prognostic performance. To compare conventional radiomics and DLR, 1456 handcrafted features were extracted, and optimal conventional radiomics methods were selected from 54 cross-combinations of 6 feature selection methods and 9 classification methods. In addition, risk group stratification was performed with clinical signature, conventional radiomics signature, and DLR signature. Results: Our multi-modality DLR model using both PET and CT achieved higher prognostic performance than the optimal conventional radiomics method. Furthermore, the multi-modality DLR model outperformed single-modality DLR models using only PET or only CT. For risk group stratification, the conventional radiomics signature and DLR signature enabled significant differences between the high- and low-risk patient groups in both internal and external cohorts, while the clinical signature failed in the external cohort. Conclusion: Our study identified potential prognostic tools for survival prediction in advanced NPC, suggesting that DLR could provide complementary values to the current TNM staging.

Mingyuan Meng, Lei Bi, Michael Fulham et al.

Deformable image registration is fundamental for many medical image analyses. A key obstacle for accurate image registration lies in image appearance variations such as the variations in texture, intensities, and noise. These variations are readily apparent in medical images, especially in brain images where registration is frequently used. Recently, deep learning-based registration methods (DLRs), using deep neural networks, have shown computational efficiency that is several orders of magnitude faster than traditional optimization-based registration methods (ORs). DLRs rely on a globally optimized network that is trained with a set of training samples to achieve faster registration. DLRs tend, however, to disregard the target-pair-specific optimization inherent in ORs and thus have degraded adaptability to variations in testing samples. This limitation is severe for registering medical images with large appearance variations, especially since few existing DLRs explicitly take into account appearance variations. In this study, we propose an Appearance Adjustment Network (AAN) to enhance the adaptability of DLRs to appearance variations. Our AAN, when integrated into a DLR, provides appearance transformations to reduce the appearance variations during registration. In addition, we propose an anatomy-constrained loss function through which our AAN generates anatomy-preserving transformations. Our AAN has been purposely designed to be readily inserted into a wide range of DLRs and can be trained cooperatively in an unsupervised and end-to-end manner. We evaluated our AAN with three state-of-the-art DLRs on three well-established public datasets of 3D brain magnetic resonance imaging (MRI). The results show that our AAN consistently improved existing DLRs and outperformed state-of-the-art ORs on registration accuracy, while adding a fractional computational load to existing DLRs.

Xiaohang Fu, Lei Bi, Ashnil Kumar et al.

Accurate characterisation of visual attributes such as spiculation, lobulation, and calcification of lung nodules is critical in cancer management. The characterisation of these attributes is often subjective, which may lead to high inter- and intra-observer variability. Furthermore, lung nodules are often heterogeneous in the cross-sectional image slices of a 3D volume. Current state-of-the-art methods that score multiple attributes rely on deep learning-based multi-task learning (MTL) schemes. These methods, however, extract shared visual features across attributes and then examine each attribute without explicitly leveraging their inherent intercorrelations. Furthermore, current methods either treat each slice with equal importance without considering their relevance or heterogeneity, which limits performance. In this study, we address these challenges with a new convolutional neural network (CNN)-based MTL model that incorporates multiple attention-based learning modules to simultaneously score 9 visual attributes of lung nodules in computed tomography (CT) image volumes. Our model processes entire nodule volumes of arbitrary depth and uses a slice attention module to filter out irrelevant slices. We also introduce cross-attribute and attribute specialisation attention modules that learn an optimal amalgamation of meaningful representations to leverage relationships between attributes. We demonstrate that our model outperforms previous state-of-the-art methods at scoring attributes using the well-known public LIDC-IDRI dataset of pulmonary nodules from over 1,000 patients. Our model also performs competitively when repurposed for benign-malignant classification. Our attention modules also provide easy-to-interpret weights that offer insights into the predictions of the model.

Xiaohang Fu, Lei Bi, Ashnil Kumar et al.

Multimodal positron emission tomography-computed tomography (PET-CT) is used routinely in the assessment of cancer. PET-CT combines the high sensitivity for tumor detection with PET and anatomical information from CT. Tumor segmentation is a critical element of PET-CT but at present, there is not an accurate automated segmentation method. Segmentation tends to be done manually by different imaging experts and it is labor-intensive and prone to errors and inconsistency. Previous automated segmentation methods largely focused on fusing information that is extracted separately from the PET and CT modalities, with the underlying assumption that each modality contains complementary information. However, these methods do not fully exploit the high PET tumor sensitivity that can guide the segmentation. We introduce a multimodal spatial attention module (MSAM) that automatically learns to emphasize regions (spatial areas) related to tumors and suppress normal regions with physiologic high-uptake. The resulting spatial attention maps are subsequently employed to target a convolutional neural network (CNN) for segmentation of areas with higher tumor likelihood. Our MSAM can be applied to common backbone architectures and trained end-to-end. Our experimental results on two clinical PET-CT datasets of non-small cell lung cancer (NSCLC) and soft tissue sarcoma (STS) validate the effectiveness of the MSAM in these different cancer types. We show that our MSAM, with a conventional U-Net backbone, surpasses the state-of-the-art lung tumor segmentation approach by a margin of 7.6% in Dice similarity coefficient (DSC).

Lei Bi, Jinman Kim, Tingwei Su et al.

The accurate classification of mass lesions in the adrenal glands (adrenal masses), detected with computed tomography (CT), is important for diagnosis and patient management. Adrenal masses can be benign or malignant and benign masses have varying prevalence. Classification methods based on convolutional neural networks (CNNs) are the state-of-the-art in maximizing inter-class differences in large medical imaging training datasets. The application of CNNs, to adrenal masses is challenging due to large intra-class variations, large inter-class similarities and imbalanced training data due to the size of the mass lesions. We developed a deep multi-scale resemblance network (DMRN) to overcome these limitations and leveraged paired CNNs to evaluate the intra-class similarities. We used multi-scale feature embedding to improve the inter-class separability by iteratively combining complementary information produced at different scales of the input to create structured feature descriptors. We augmented the training data with randomly sampled paired adrenal masses to reduce the influence of imbalanced training data. We used 229 CT scans of patients with adrenal masses for evaluation. In a five-fold cross-validation, our method had the best results (89.52% in accuracy) when compared to the state-of-the-art methods (p<0.05). We conducted a generalizability analysis of our method on the ImageCLEF 2016 competition dataset for medical subfigure classification, which consists of a training set of 6,776 images and a test set of 4,166 images across 30 classes. Our method achieved better classification performance (85.90% in accuracy) when compared to the existing methods and was competitive when compared with methods that require additional training data (1.47% lower in accuracy). Our DMRN sub-classified adrenal masses on CT and was superior to state-of-the-art approaches.

Yige Peng, Lei Bi, Michael Fulham et al.

'Radiomics' is a method that extracts mineable quantitative features from radiographic images. These features can then be used to determine prognosis, for example, predicting the development of distant metastases (DM). Existing radiomics methods, however, require complex manual effort including the design of hand-crafted radiomic features and their extraction and selection. Recent radiomics methods, based on convolutional neural networks (CNNs), also require manual input in network architecture design and hyper-parameter tuning. Radiomic complexity is further compounded when there are multiple imaging modalities, for example, combined positron emission tomography - computed tomography (PET-CT) where there is functional information from PET and complementary anatomical localization information from computed tomography (CT). Existing multi-modality radiomics methods manually fuse the data that are extracted separately. Reliance on manual fusion often results in sub-optimal fusion because they are dependent on an 'expert's' understanding of medical images. In this study, we propose a multi-modality neural architecture search method (MM-NAS) to automatically derive optimal multi-modality image features for radiomics and thus negate the dependence on a manual process. We evaluated our MM-NAS on the ability to predict DM using a public PET-CT dataset of patients with soft-tissue sarcomas (STSs). Our results show that our MM-NAS had a higher prediction accuracy when compared to state-of-the-art radiomics methods.

Yuyu Guo, Lei Bi, Euijoon Ahn et al.

Dynamic medical imaging is usually limited in application due to the large radiation doses and longer image scanning and reconstruction times. Existing methods attempt to reduce the dynamic sequence by interpolating the volumes between the acquired image volumes. However, these methods are limited to either 2D images and/or are unable to support large variations in the motion between the image volume sequences. In this paper, we present a spatiotemporal volumetric interpolation network (SVIN) designed for 4D dynamic medical images. SVIN introduces dual networks: first is the spatiotemporal motion network that leverages the 3D convolutional neural network (CNN) for unsupervised parametric volumetric registration to derive spatiotemporal motion field from two-image volumes; the second is the sequential volumetric interpolation network, which uses the derived motion field to interpolate image volumes, together with a new regression-based module to characterize the periodic motion cycles in functional organ structures. We also introduce an adaptive multi-scale architecture to capture the volumetric large anatomy motions. Experimental results demonstrated that our SVIN outperformed state-of-the-art temporal medical interpolation methods and natural video interpolation methods that have been extended to support volumetric images. Our ablation study further exemplified that our motion network was able to better represent the large functional motion compared with the state-of-the-art unsupervised medical registration methods.

Mingyuan Meng, Xingyu Yang, Lei Bi et al.

Spiking Neural Networks (SNNs) are brain-inspired, event-driven machine learning algorithms that have been widely recognized in producing ultra-high-energy-efficient hardware. Among existing SNNs, unsupervised SNNs based on synaptic plasticity, especially Spike-Timing-Dependent Plasticity (STDP), are considered to have great potential in imitating the learning process of the biological brain. Nevertheless, the existing STDP-based SNNs have limitations in constrained learning capability and/or slow learning speed. Most STDP-based SNNs adopted a slow-learning Fully-Connected (FC) architecture and used a sub-optimal vote-based scheme for spike decoding. In this paper, we overcome these limitations with: 1) a design of high-parallelism network architecture, inspired by the Inception module in Artificial Neural Networks (ANNs); 2) use of a Vote-for-All (VFA) decoding layer as a replacement to the standard vote-based spike decoding scheme, to reduce the information loss in spike decoding and, 3) a proposed adaptive repolarization (resetting) mechanism that accelerates SNNs' learning by enhancing spiking activities. Our experimental results on two established benchmark datasets (MNIST/EMNIST) show that our network architecture resulted in superior performance compared to the widely used FC architecture and a more advanced Locally-Connected (LC) architecture, and that our SNN achieved competitive results with state-of-the-art unsupervised SNNs (95.64%/80.11% accuracy on the MNIST/EMNISE dataset) while having superior learning efficiency and robustness against hardware damage. Our SNN achieved great classification accuracy with only hundreds of training iterations, and random destruction of large numbers of synapses or neurons only led to negligible performance degradation.

Lei Bi, Yuyu Guo, Qian Wang et al.

Automated segmentation of the optic cup and disk on retinal fundus images is fundamental for the automated detection / analysis of glaucoma. Traditional segmentation approaches depend heavily upon hand-crafted features and a priori knowledge of the user. As such, these methods are difficult to be adapt to the clinical environment. Recently, deep learning methods based on fully convolutional networks (FCNs) have been successful in resolving segmentation problems. However, the reliance on large annotated training data is problematic when dealing with medical images. If a sufficient amount of annotated training data to cover all possible variations is not available, FCNs do not provide accurate segmentation. In addition, FCNs have a large receptive field in the convolutional layers, and hence produce coarse outputs of boundaries. Hence, we propose a new fully automated method that we refer to as a dual-stage fully convolutional networks (DSFCN). Our approach leverages deep residual architectures and FCNs and learns and infers the location of the optic cup and disk in a step-wise manner with fine-grained details. During training, our approach learns from the training data and the estimated results derived from the previous iteration. The ability to learn from the previous iteration optimizes the learning of the optic cup and the disk boundaries. During testing (prediction), DSFCN uses test (input) images and the estimated probability map derived from previous iterations to gradually improve the segmentation accuracy. Our method achieved an average Dice co-efficient of 0.8488 and 0.9441 for optic cup and disk segmentation and an area under curve (AUC) of 0.9513 for glaucoma detection.

Patrick Bilic, Patrick Christ, Hongwei Bran Li et al.

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in \url{http://medicaldecathlon.com/}. In addition, both data and online evaluation are accessible via \url{www.lits-challenge.com}.

Lei Bi, Dagan Feng, Jinman Kim

Segmentation of skin lesions is considered as an important step in computer aided diagnosis (CAD) for automated melanoma diagnosis. In recent years, segmentation methods based on fully convolutional networks (FCN) have achieved great success in general images. This success is primarily due to the leveraging of large labelled datasets to learn features that correspond to the shallow appearance as well as the deep semantics of the images. However, the dependence on large dataset does not translate well into medical images. To improve the FCN performance for skin lesion segmentations, researchers attempted to use specific cost functions or add post-processing algorithms to refine the coarse boundaries of the FCN results. However, the performance of these methods is heavily reliant on the tuning of many parameters and post-processing techniques. In this paper, we leverage the state-of-the-art image feature learning method of generative adversarial network (GAN) for its inherent ability to produce consistent and realistic image features by using deep neural networks and adversarial learning concept. We improve upon GAN such that skin lesion features can be learned at different level of complexities, in a controlled manner. The outputs from our method is then augmented to the existing FCN training data, thus increasing the overall feature diversity. We evaluated our method on the ISIC 2018 skin lesion segmentation challenge dataset and showed that it was more accurate and robust when compared to the existing skin lesion segmentation methods.

Lei Bi, Jinman Kim, Ashnil Kumar et al.

Positron emission tomography (PET) image synthesis plays an important role, which can be used to boost the training data for computer aided diagnosis systems. However, existing image synthesis methods have problems in synthesizing the low resolution PET images. To address these limitations, we propose multi-channel generative adversarial networks (M-GAN) based PET image synthesis method. Different to the existing methods which rely on using low-level features, the proposed M-GAN is capable to represent the features in a high-level of semantic based on the adversarial learning concept. In addition, M-GAN enables to take the input from the annotation (label) to synthesize the high uptake regions e.g., tumors and from the computed tomography (CT) images to constrain the appearance consistency and output the synthetic PET images directly. Our results on 50 lung cancer PET-CT studies indicate that our method was much closer to the real PET images when compared with the existing methods.

Lei Bi, Jinman Kim, Ashnil Kumar et al.

Automatic segmentation of liver lesions is a fundamental requirement towards the creation of computer aided diagnosis (CAD) and decision support systems (CDS). Traditional segmentation approaches depend heavily upon hand-crafted features and a priori knowledge of the user. As such, these methods are difficult to adopt within a clinical environment. Recently, deep learning methods based on fully convolutional networks (FCNs) have been successful in many segmentation problems primarily because they leverage a large labelled dataset to hierarchically learn the features that best correspond to the shallow visual appearance as well as the deep semantics of the areas to be segmented. However, FCNs based on a 16 layer VGGNet architecture have limited capacity to add additional layers. Therefore, it is challenging to learn more discriminative features among different classes for FCNs. In this study, we overcome these limitations using deep residual networks (ResNet) to segment liver lesions. ResNet contain skip connections between convolutional layers, which solved the problem of the training degradation of training accuracy in very deep networks and thereby enables the use of additional layers for learning more discriminative features. In addition, we achieve more precise boundary definitions through a novel cascaded ResNet architecture with multi-scale fusion to gradually learn and infer the boundaries of both the liver and the liver lesions. Our proposed method achieved 4th place in the ISBI 2017 Liver Tumor Segmentation Challenge by the submission deadline.

Lei Bi, Jinman Kim, Euijoon Ahn et al.

Malignant melanoma has one of the most rapidly increasing incidences in the world and has a considerable mortality rate. Early diagnosis is particularly important since melanoma can be cured with prompt excision. Dermoscopy images play an important role in the non-invasive early detection of melanoma [1]. However, melanoma detection using human vision alone can be subjective, inaccurate and poorly reproducible even among experienced dermatologists. This is attributed to the challenges in interpreting images with diverse characteristics including lesions of varying sizes and shapes, lesions that may have fuzzy boundaries, different skin colors and the presence of hair [2]. Therefore, the automatic analysis of dermoscopy images is a valuable aid for clinical decision making and for image-based diagnosis to identify diseases such as melanoma [1-4]. Deep residual networks (ResNets) has achieved state-of-the-art results in image classification and detection related problems [5-8]. In this ISIC 2017 skin lesion analysis challenge [9], we propose to exploit the deep ResNets for robust visual features learning and representations.