Marius Staring

Yunjie Chen, Marius Staring, Olaf M. Neve et al.

Multi-sequence magnetic resonance imaging (MRI) has found wide applications in both modern clinical studies and deep learning research. However, in clinical practice, it frequently occurs that one or more of the MRI sequences are missing due to different image acquisition protocols or contrast agent contraindications of patients, limiting the utilization of deep learning models trained on multi-sequence data. One promising approach is to leverage generative models to synthesize the missing sequences, which can serve as a surrogate acquisition. State-of-the-art methods tackling this problem are based on convolutional neural networks (CNN) which usually suffer from spectral biases, resulting in poor reconstruction of high-frequency fine details. In this paper, we propose Conditional Neural fields with Shift modulation (CoNeS), a model that takes voxel coordinates as input and learns a representation of the target images for multi-sequence MRI translation. The proposed model uses a multi-layer perceptron (MLP) instead of a CNN as the decoder for pixel-to-pixel mapping. Hence, each target image is represented as a neural field that is conditioned on the source image via shift modulation with a learned latent code. Experiments on BraTS 2018 and an in-house clinical dataset of vestibular schwannoma patients showed that the proposed method outperformed state-of-the-art methods for multi-sequence MRI translation both visually and quantitatively. Moreover, we conducted spectral analysis, showing that CoNeS was able to overcome the spectral bias issue common in conventional CNN models. To further evaluate the usage of synthesized images in clinical downstream tasks, we tested a segmentation network using the synthesized images at inference.

Viktor van der Valk, Douwe Atsma, Roderick Scherptong et al.

Electrocardiography is the most common method to investigate the condition of the heart through the observation of cardiac rhythm and electrical activity, for both diagnosis and monitoring purposes. Analysis of electrocardiograms (ECGs) is commonly performed through the investigation of specific patterns, which are visually recognizable by trained physicians and are known to reflect cardiac (dis)function. In this work we study the use of $β$-variational autoencoders (VAEs) as an explainable feature extractor, and improve on its predictive capacities by jointly optimizing signal reconstruction and cardiac function prediction. The extracted features are then used for cardiac function prediction using logistic regression. The method is trained and tested on data from 7255 patients, who were treated for acute coronary syndrome at the Leiden University Medical Center between 2010 and 2021. The results show that our method significantly improved prediction and explainability compared to a vanilla $β$-VAE, while still yielding similar reconstruction performance.

Prerak Mody, Nicolas F. Chaves-de-Plaza, Chinmay Rao et al.

Increased usage of automated tools like deep learning in medical image segmentation has alleviated the bottleneck of manual contouring. This has shifted manual labour to quality assessment (QA) of automated contours which involves detecting errors and correcting them. A potential solution to semi-automated QA is to use deep Bayesian uncertainty to recommend potentially erroneous regions, thus reducing time spent on error detection. Previous work has investigated the correspondence between uncertainty and error, however, no work has been done on improving the "utility" of Bayesian uncertainty maps such that it is only present in inaccurate regions and not in the accurate ones. Our work trains the FlipOut model with the Accuracy-vs-Uncertainty (AvU) loss which promotes uncertainty to be present only in inaccurate regions. We apply this method on datasets of two radiotherapy body sites, c.f. head-and-neck CT and prostate MR scans. Uncertainty heatmaps (i.e. predictive entropy) are evaluated against voxel inaccuracies using Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves. Numerical results show that when compared to the Bayesian baseline the proposed method successfully suppresses uncertainty for accurate voxels, with similar presence of uncertainty for inaccurate voxels. Code to reproduce experiments is available at https://github.com/prerakmody/bayesuncertainty-error-correspondence

Chinmay Rao, Matthias van Osch, Nicola Pezzotti et al.

Since multiple MRI contrasts of the same anatomy contain redundant information, one contrast can guide the reconstruction of an undersampled subsequent contrast. To this end, several end-to-end learning-based guided reconstruction methods have been proposed. However, a key challenge is the requirement of large paired training datasets comprising raw data and aligned reference images. We propose a modular two-stage approach that does not require any k-space training data, relying solely on image-domain datasets, a large part of which can be unpaired. Additionally, our approach provides an explanatory framework for the multi-contrast problem based on the shared and non-shared generative factors underlying two given contrasts. A content/style model of two-contrast image data is learned from a largely unpaired image-domain dataset and is subsequently applied as a plug-and-play operator in iterative reconstruction. The disentanglement of content and style allows explicit representation of contrast-independent and contrast-specific factors. Consequently, incorporating prior information into the reconstruction reduces to a simple replacement of the aliased content of the reconstruction iterate with high-quality content derived from the reference scan. Combining this component with a data consistency step and introducing a general corrective process for the content yields an iterative scheme. We name this novel approach PnP-CoSMo. Various aspects like interpretability and convergence are explored via simulations. Furthermore, its practicality is demonstrated on the public NYU fastMRI DICOM dataset, showing improved generalizability compared to end-to-end methods, and on two in-house multi-coil raw datasets, offering up to 32.6\% more acceleration over learning-based non-guided reconstruction for a given SSIM.

Jingnan Jia, Marius Staring, Berend C. Stoel

In response to a concerning trend of selectively emphasizing metrics in medical image segmentation (MIS) studies, we introduce \texttt{seg-metrics}, an open-source Python package for standardized MIS model evaluation. Unlike existing packages, \texttt{seg-metrics} offers user-friendly interfaces for various overlap-based and distance-based metrics, providing a comprehensive solution. \texttt{seg-metrics} supports multiple file formats and is easily installable through the Python Package Index (PyPI). With a focus on speed and convenience, \texttt{seg-metrics} stands as a valuable tool for efficient MIS model assessment.

Jun Ma, Feifei Li, Sumin Kim et al.

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications.

Ruochen Gao, Donghang Lyu, Marius Staring

Medical imaging is essential for the diagnosis and treatment of diseases, with medical image segmentation as a subtask receiving high attention. However, automatic medical image segmentation models are typically task-specific and struggle to handle multiple scenarios, such as different imaging modalities and regions of interest. With the introduction of the Segment Anything Model (SAM), training a universal model for various clinical scenarios has become feasible. Recently, several Medical SAM (MedSAM) methods have been proposed, but these models often rely on heavy image encoders to achieve high performance, which may not be practical for real-world applications due to their high computational demands and slow inference speed. To address this issue, a lightweight version of the MedSAM (LiteMedSAM) can provide a viable solution, achieving high performance while requiring fewer resources and less time. In this work, we introduce Swin-LiteMedSAM, a new variant of LiteMedSAM. This model integrates the tiny Swin Transformer as the image encoder, incorporates multiple types of prompts, including box-based points and scribble generated from a given bounding box, and establishes skip connections between the image encoder and the mask decoder. In the \textit{Segment Anything in Medical Images on Laptop} challenge (CVPR 2024), our approach strikes a good balance between segmentation performance and speed, demonstrating significantly improved overall results across multiple modalities compared to the LiteMedSAM baseline provided by the challenge organizers. Our proposed model achieved a DSC score of \textbf{0.8678} and an NSD score of \textbf{0.8844} on the validation set. On the final test set, it attained a DSC score of \textbf{0.8193} and an NSD score of \textbf{0.8461}, securing fourth place in the challenge.

Yunjie Chen, Jelmer M. Wolterink, Olaf M. Neve et al.

Vestibular schwannomas (VS) are benign tumors that are generally managed by active surveillance with MRI examination. To further assist clinical decision-making and avoid overtreatment, an accurate prediction of tumor growth based on longitudinal imaging is highly desirable. In this paper, we introduce DeepGrowth, a deep learning method that incorporates neural fields and recurrent neural networks for prospective tumor growth prediction. In the proposed method, each tumor is represented as a signed distance function (SDF) conditioned on a low-dimensional latent code. Unlike previous studies that perform tumor shape prediction directly in the image space, we predict the latent codes instead and then reconstruct future shapes from it. To deal with irregular time intervals, we introduce a time-conditioned recurrent module based on a ConvLSTM and a novel temporal encoding strategy, which enables the proposed model to output varying tumor shapes over time. The experiments on an in-house longitudinal VS dataset showed that the proposed model significantly improved the performance ($\ge 1.6\%$ Dice score and $\ge0.20$ mm 95\% Hausdorff distance), in particular for top 20\% tumors that grow or shrink the most ($\ge 4.6\%$ Dice score and $\ge 0.73$ mm 95\% Hausdorff distance). Our code is available at ~\burl{https://github.com/cyjdswx/DeepGrowth}

Donghang Lyu, Ruochen Gao, Marius Staring

Medical image segmentation involves partitioning medical images into meaningful regions, with a focus on identifying anatomical structures and lesions. It has broad applications in healthcare, and deep learning methods have enabled significant advancements in automating this process. Recently, the introduction of the Segmentation Anything Model (SAM), the first foundation model for segmentation task, has prompted researchers to adapt it for the medical domain to improve performance across various tasks. However, SAM's large model size and high GPU requirements hinder its scalability and development in the medical domain. In this work, we propose MCP-MedSAM, a powerful and lightweight medical SAM model designed to be trainable on a single A100 GPU with 40GB of memory within one day while delivering superior segmentation performance. Recognizing the significant internal differences between modalities and the need for direct segmentation target information within bounding boxes, we introduce two kinds of prompts: the modality prompt and the content prompt. After passing through the prompt encoder, their embedding representations can further improve the segmentation performance by incorporating more relevant information without adding significant training overhead. Additionally, we adopt an effective modality-based data sampling strategy to address data imbalance between modalities, ensuring more balanced performance across all modalities. Our method was trained and evaluated using a large-scale challenge dataset, compared to top-ranking methods on the challenge leaderboard, MCP-MedSAM achieved superior performance while requiring only one day of training on a single GPU. The code is publicly available at \textcolor{blue}{https://github.com/dong845/MCP-MedSAM}.}

Sahar Yousefi, Hessam Sokooti, Wouter M. Teeuwisse et al.

Positron Emission Tomography (PET) is an imaging method that can assess physiological function rather than structural disturbances by measuring cerebral perfusion or glucose consumption. However, this imaging technique relies on injection of radioactive tracers and is expensive. On the contrary, Arterial Spin Labeling (ASL) MRI is a non-invasive, non-radioactive, and relatively cheap imaging technique for brain hemodynamic measurements, which allows quantification to some extent. In this paper we propose a convolutional neural network (CNN) based model for translating ASL to PET images, which could benefit patients as well as the healthcare system in terms of expenses and adverse side effects. However, acquiring a sufficient number of paired ASL-PET scans for training a CNN is prohibitive for many reasons. To tackle this problem, we present a new semi-supervised multitask CNN which is trained on both paired data, i.e. ASL and PET scans, and unpaired data, i.e. only ASL scans, which alleviates the problem of training a network on limited paired data. Moreover, we present a new residual-based-attention guided mechanism to improve the contextual features during the training process. Also, we show that incorporating T1-weighted scans as an input, due to its high resolution and availability of anatomical information, improves the results. We performed a two-stage evaluation based on quantitative image metrics by conducting a 7-fold cross validation followed by a double-blind observer study. The proposed network achieved structural similarity index measure (SSIM), mean squared error (MSE) and peak signal-to-noise ratio (PSNR) values of $0.85\pm0.08$, $0.01\pm0.01$, and $21.8\pm4.5$ respectively, for translating from 2D ASL and T1-weighted images to PET data. The proposed model is publicly available via https://github.com/yousefis/ASL2PET.

Sahar Yousefi, Hessam Sokooti, Mohamed S. Elmahdy et al.

Manual or automatic delineation of the esophageal tumor in CT images is known to be very challenging. This is due to the low contrast between the tumor and adjacent tissues, the anatomical variation of the esophagus, as well as the occasional presence of foreign bodies (e.g. feeding tubes). Physicians therefore usually exploit additional knowledge such as endoscopic findings, clinical history, additional imaging modalities like PET scans. Achieving his additional information is time-consuming, while the results are error-prone and might lead to non-deterministic results. In this paper we aim to investigate if and to what extent a simplified clinical workflow based on CT alone, allows one to automatically segment the esophageal tumor with sufficient quality. For this purpose, we present a fully automatic end-to-end esophageal tumor segmentation method based on convolutional neural networks (CNNs). The proposed network, called Dilated Dense Attention Unet (DDAUnet), leverages spatial and channel attention gates in each dense block to selectively concentrate on determinant feature maps and regions. Dilated convolutional layers are used to manage GPU memory and increase the network receptive field. We collected a dataset of 792 scans from 288 distinct patients including varying anatomies with \mbox{air pockets}, feeding tubes and proximal tumors. Repeatability and reproducibility studies were conducted for three distinct splits of training and validation sets. The proposed network achieved a $\mathrm{DSC}$ value of $0.79 \pm 0.20$, a mean surface distance of $5.4 \pm 20.2mm$ and $95\%$ Hausdorff distance of $14.7 \pm 25.0mm$ for 287 test scans, demonstrating promising results with a simplified clinical workflow based on CT alone. Our code is publicly available via \url{https://github.com/yousefis/DenseUnet_Esophagus_Segmentation}.

Donghang Lyu, Chinmay Rao, Marius Staring et al.

Cardiac magnetic resonance imaging (CMR) is vital for diagnosing heart diseases, but long scan time remains a major drawback. To address this, accelerated imaging techniques have been introduced by undersampling k-space, which reduces the quality of the resulting images. Recent deep learning advancements aim to speed up scanning while preserving quality, but adapting to various sampling modes and undersampling factors remains challenging. Therefore, building a universal model is a promising direction. In this work, we introduce UPCMR, a universal unrolled model designed for CMR reconstruction. This model incorporates two kinds of learnable prompts, undersampling-specific prompt and spatial-specific prompt, and integrates them with a UNet structure in each block. Overall, by using the CMRxRecon2024 challenge dataset for training and validation, the UPCMR model highly enhances reconstructed image quality across all random sampling scenarios through an effective training strategy compared to some traditional methods, demonstrating strong adaptability potential for this task.

Ruochen Gao, Marius Staring, Frank Dankers

Purpose: Deep-learning-based three-dimensional (3D) dose prediction is widely used in automated radiotherapy workflows. However, most existing models are trained with voxel-wise regression losses, which are poorly aligned with clinical plan evaluation criteria based on dose-volume histogram (DVH) metrics. This study aims to develop a clinically guided loss formulation that directly optimizes clinically used DVH metrics while remaining computationally efficient for head and neck (H\&N) dose prediction. Methods: We propose a clinical DVH metric loss (CDM loss) that incorporates differentiable \textit{D-metrics} and surrogate \textit{V-metrics}, together with a lossless bit-mask region-of-interest (ROI) encoding to improve training efficiency. The method was evaluated on 174 H\&N patients using a temporal split (137 training, 37 testing). Results: Compared with MAE- and DVH-curve based losses, CDM loss substantially improved target coverage and satisfied all clinical constraints. Using a standard 3D U-Net, the PTV Score was reduced from 1.544 (MAE) to 0.491 (MAE + CDM), while OAR sparing remained comparable. Bit-mask encoding reduced training time by 83\% and lowered GPU memory usage. Conclusion: Directly optimizing clinically used DVH metrics enables 3D dose predictions that are better aligned with clinical treatment planning criteria than conventional voxel-wise or DVH-curve-based supervision. The proposed CDM loss, combined with efficient ROI bit-mask encoding, provides a practical and scalable framework for H\&N dose prediction.

Donghang Lyu, Marius Staring, Hildo Lamb et al.

In recent years, deep learning has attracted increasing attention in the field of Cardiac MRI (CMR) reconstruction due to its superior performance over traditional methods, particularly in handling higher acceleration factors, highlighting its potential for real-world clinical applications. However, current deep learning methods remain limited in generalizability. CMR scans exhibit wide variability in image contrast, sampling patterns, scanner vendors, anatomical structures, and disease types. Most existing models are designed to handle only a single or narrow subset of these variations, leading to performance degradation when faced with distribution shifts. Therefore, it is beneficial to develop a unified model capable of generalizing across diverse CMR scenarios. To this end, we propose CRUNet-MR-Univ, a foundation model that leverages spatio-temporal correlations and prompt-based priors to effectively handle the full diversity of CMR scans. Our approach consistently outperforms baseline methods across a wide range of settings, highlighting its effectiveness and promise.

Yunjie Chen, Rianne A. Weber, Olaf M. Neve et al.

Objectives: To evaluate a deep learning (DL) model for reducing the agent dose of contrast-enhanced T1-weighted MRI (T1ce) of the cerebellopontine angle (CPA) cistern. Materials and methods: In this multi-center retrospective study, T1 and T1ce of vestibular schwannoma (VS) patients were used to simulate low-dose T1ce with varying reductions of contrast agent dose. DL models were trained to restore standard-dose T1ce from the low-dose simulation. The image quality and segmentation performance of the DL-restored T1ce were evaluated. A head and neck radiologist was asked to rate DL-restored images in multiple aspects, including image quality and diagnostic characterization. Results: 203 MRI studies from 72 VS patients (mean age, 58.51 \pm 14.73, 39 men) were evaluated. As the input dose increased, the structural similarity index measure of the restored T1ce increased from 0.639 \pm 0.113 to 0.993 \pm 0.009, and the peak signal-to-noise ratio increased from 21.6 \pm 3.73 dB to 41.4 \pm 4.84 dB. At 10% input dose, using DL-restored T1ce for segmentation improved the Dice from 0.673 to 0.734, the 95% Hausdorff distance from 2.38 mm to 2.07 mm, and the average surface distance from 1.00 mm to 0.59 mm. Both DL-restored T1ce from 10% and 30% input doses showed excellent images, with the latter being considered more informative. Conclusion: The DL model improved the image quality of low-dose MRI of the CPA cistern, which makes lesion detection and diagnostic characterization possible with 10% - 30% of the standard dose.

Tianran Li, Marius Staring, Yuchuan Qiao

Deformable image registration estimates voxel-wise correspondences between images through spatial transformations, and plays a key role in medical imaging. While deep learning methods have significantly reduced runtime, efficiently handling large deformations remains a challenging task. Convolutional networks aggregate local features but lack direct modeling of voxel correspondences, promoting recent works to explore explicit feature matching. Among them, voxel-to-region matching is more efficient for direct correspondence modeling by computing local correlation features whithin neighbourhoods, while region-to-region matching incurs higher redundancy due to excessive correlation pairs across large regions. However, the inherent locality of voxel-to-region matching hinders the capture of long-range correspondences required for large deformations. To address this, we propose a Recurrent Correlation-based framework that dynamically relocates the matching region toward more promising positions. At each step, local matching is performed with low cost, and the estimated offset guides the next search region, supporting efficient convergence toward large deformations. In addition, we uses a lightweight recurrent update module with memory capacity and decouples motion-related and texture features to suppress semantic redundancy. We conduct extensive experiments on brain MRI and abdominal CT datasets under two settings: with and without affine pre-registration. Results show that our method exibits a strong accuracy-computation trade-off, surpassing or matching the state-of-the-art performance. For example, it achieves comparable performance on the non-affine OASIS dataset, while using only 9.5% of the FLOPs and running 96% faster than RDP, a representative high-performing method.

Yuxi Zheng, Jianhui Feng, Tianran Li et al.

Encoder-Decoder architectures are widely used in deep learning-based Deformable Image Registration (DIR), where the encoder extracts multi-scale features and the decoder predicts deformation fields by recovering spatial locations. However, current methods lack specialized extraction of features (that are useful for registration) and predict deformation jointly and homogeneously in all three directions. In this paper, we propose a novel expert-guided DIR network with Mixture of Experts (MoE) mechanism applied in both encoder and decoder, named SHMoAReg. Specifically, we incorporate Mixture of Attention heads (MoA) into encoder layers, while Spatial Heterogeneous Mixture of Experts (SHMoE) into the decoder layers. The MoA enhances the specialization of feature extraction by dynamically selecting the optimal combination of attention heads for each image token. Meanwhile, the SHMoE predicts deformation fields heterogeneously in three directions for each voxel using experts with varying kernel sizes. Extensive experiments conducted on two publicly available datasets show consistent improvements over various methods, with a notable increase from 60.58% to 65.58% in Dice score for the abdominal CT dataset. Furthermore, SHMoAReg enhances model interpretability by differentiating experts' utilities across/within different resolution layers. To the best of our knowledge, we are the first to introduce MoE mechanism into DIR tasks. The code will be released soon.

Donghang Lyu, Marius Staring, Mariya Doneva et al.

Cardiac Magnetic Resonance (CMR) imaging is a non-invasive method for assessing cardiac structure, function, and blood flow. Cine MRI extends this by capturing heart motion, providing detailed insights into cardiac mechanics. To reduce scan time and breath-hold discomfort, fast acquisition techniques have been utilized at the cost of lowering image quality. Recently, Implicit Neural Representation (INR) methods have shown promise in unsupervised reconstruction by learning coordinate-to-value mappings from undersampled data, enabling high-quality image recovery. However, current existing INR methods primarily focus on using coordinate-based positional embeddings to learn the mapping, while overlooking the feature representations of the target point and its neighboring context. In this work, we propose KP-INR, a dual-branch INR method operating in k-space for cardiac cine MRI reconstruction: one branch processes the positional embedding of k-space coordinates, while the other learns from local multi-scale k-space feature representations at those coordinates. By enabling cross-branch interaction and approximating the target k-space values from both branches, KP-INR can achieve strong performance on challenging Cartesian k-space data. Experiments on the CMRxRecon2024 dataset confirms its improved performance over baseline models and highlights its potential in this field.

Mohamed S. Elmahdy, Marius Staring, Patrick J. H. de Koning et al.

Accurate and efficient quantification of cardiac function is essential for the estimation of prognosis of cardiovascular diseases (CVDs). One of the most commonly used metrics for evaluating cardiac pumping performance is left ventricular ejection fraction (LVEF). However, LVEF can be affected by factors such as inter-observer variability and varying pre-load and after-load conditions, which can reduce its reproducibility. Additionally, cardiac dysfunction may not always manifest as alterations in LVEF, such as in heart failure and cardiotoxicity diseases. An alternative measure that can provide a relatively load-independent quantitative assessment of myocardial contractility is myocardial strain and strain rate. By using LVEF in combination with myocardial strain, it is possible to obtain a thorough description of cardiac function. Automated estimation of LVEF and other volumetric measures from cine-MRI sequences can be achieved through segmentation models, while strain calculation requires the estimation of tissue displacement between sequential frames, which can be accomplished using registration models. These tasks are often performed separately, potentially limiting the assessment of cardiac function. To address this issue, in this study we propose an end-to-end deep learning (DL) model that jointly estimates groupwise (GW) registration and segmentation for cardiac cine-MRI images. The proposed anatomically-guided Deep GW network was trained and validated on a large dataset of 4-chamber view cine-MRI image series of 374 subjects. A quantitative comparison with conventional GW registration using elastix and two DL-based methods showed that the proposed model improved performance and substantially reduced computation time.

Prerak Mody, Nicolas Chaves-de-Plaza, Klaus Hildebrandt et al.

Deep learning models for organ contouring in radiotherapy are poised for clinical usage, but currently, there exist few tools for automated quality assessment (QA) of the predicted contours. Using Bayesian models and their associated uncertainty, one can potentially automate the process of detecting inaccurate predictions. We investigate two Bayesian models for auto-contouring, DropOut and FlipOut, using a quantitative measure - expected calibration error (ECE) and a qualitative measure - region-based accuracy-vs-uncertainty (R-AvU) graphs. It is well understood that a model should have low ECE to be considered trustworthy. However, in a QA context, a model should also have high uncertainty in inaccurate regions and low uncertainty in accurate regions. Such behaviour could direct visual attention of expert users to potentially inaccurate regions, leading to a speed up in the QA process. Using R-AvU graphs, we qualitatively compare the behaviour of different models in accurate and inaccurate regions. Experiments are conducted on the MICCAI2015 Head and Neck Segmentation Challenge and on the DeepMindTCIA CT dataset using three models: DropOut-DICE, Dropout-CE (Cross Entropy) and FlipOut-CE. Quantitative results show that DropOut-DICE has the highest ECE, while Dropout-CE and FlipOut-CE have the lowest ECE. To better understand the difference between DropOut-CE and FlipOut-CE, we use the R-AvU graph which shows that FlipOut-CE has better uncertainty coverage in inaccurate regions than DropOut-CE. Such a combination of quantitative and qualitative metrics explores a new approach that helps to select which model can be deployed as a QA tool in clinical settings.

Jingnan Jia, Marius Staring, Irene Hernández-Girón et al.

Visually scoring lung involvement in systemic sclerosis from CT scans plays an important role in monitoring progression, but its labor intensiveness hinders practical application. We proposed, therefore, an automatic scoring framework that consists of two cascaded deep regression neural networks. The first (3D) network aims to predict the craniocaudal position of five anatomically defined scoring levels on the 3D CT scans. The second (2D) network receives the resulting 2D axial slices and predicts the scores. We used 227 3D CT scans to train and validate the first network, and the resulting 1135 axial slices were used in the second network. Two experts scored independently a subset of data to obtain intra- and interobserver variabilities and the ground truth for all data was obtained in consensus. To alleviate the unbalance in training labels in the second network, we introduced a sampling technique and to increase the diversity of the training samples synthetic data was generated, mimicking ground glass and reticulation patterns. The 4-fold cross validation showed that our proposed network achieved an average MAE of 5.90, 4.66 and 4.49, weighted kappa of 0.66, 0.58 and 0.65 for total score (TOT), ground glass (GG) and reticular pattern (RET), respectively. Our network performed slightly worse than the best experts on TOT and GG prediction but it has competitive performance on RET prediction and has the potential to be an objective alternative for the visual scoring of SSc in CT thorax studies.

Mohamed S. Elmahdy, Laurens Beljaards, Sahar Yousefi et al.

Medical image registration and segmentation are two of the most frequent tasks in medical image analysis. As these tasks are complementary and correlated, it would be beneficial to apply them simultaneously in a joint manner. In this paper, we formulate registration and segmentation as a joint problem via a Multi-Task Learning (MTL) setting, allowing these tasks to leverage their strengths and mitigate their weaknesses through the sharing of beneficial information. We propose to merge these tasks not only on the loss level, but on the architectural level as well. We studied this approach in the context of adaptive image-guided radiotherapy for prostate cancer, where planning and follow-up CT images as well as their corresponding contours are available for training. The study involves two datasets from different manufacturers and institutes. The first dataset was divided into training (12 patients) and validation (6 patients), and was used to optimize and validate the methodology, while the second dataset (14 patients) was used as an independent test set. We carried out an extensive quantitative comparison between the quality of the automatically generated contours from different network architectures as well as loss weighting methods. Moreover, we evaluated the quality of the generated deformation vector field (DVF). We show that MTL algorithms outperform their Single-Task Learning (STL) counterparts and achieve better generalization on the independent test set. The best algorithm achieved a mean surface distance of $1.06 \pm 0.3$ mm, $1.27 \pm 0.4$ mm, $0.91 \pm 0.4$ mm, and $1.76 \pm 0.8$ mm on the validation set for the prostate, seminal vesicles, bladder, and rectum, respectively. The high accuracy of the proposed method combined with the fast inference speed, makes it a promising method for automatic re-contouring of follow-up scans for adaptive radiotherapy.

Jingnan Jia, Zhiwei Zhai, M. Els Bakker et al.

Pulmonary lobe segmentation is an important preprocessing task for the analysis of lung diseases. Traditional methods relying on fissure detection or other anatomical features, such as the distribution of pulmonary vessels and airways, could provide reasonably accurate lobe segmentations. Deep learning based methods can outperform these traditional approaches, but require large datasets. Deep multi-task learning is expected to utilize labels of multiple different structures. However, commonly such labels are distributed over multiple datasets. In this paper, we proposed a multi-task semi-supervised model that can leverage information of multiple structures from unannotated datasets and datasets annotated with different structures. A focused alternating training strategy is presented to balance the different tasks. We evaluated the trained model on an external independent CT dataset. The results show that our model significantly outperforms single-task alternatives, improving the mean surface distance from 7.174 mm to 4.196 mm. We also demonstrated that our approach is successful for different network architectures as backbones.

Laurens Beljaards, Mohamed S. Elmahdy, Fons Verbeek et al.

Recently, joint registration and segmentation has been formulated in a deep learning setting, by the definition of joint loss functions. In this work, we investigate joining these tasks at the architectural level. We propose a registration network that integrates segmentation propagation between images, and a segmentation network to predict the segmentation directly. These networks are connected into a single joint architecture via so-called cross-stitch units, allowing information to be exchanged between the tasks in a learnable manner. The proposed method is evaluated in the context of adaptive image-guided radiotherapy, using daily prostate CT imaging. Two datasets from different institutes and manufacturers were involved in the study. The first dataset was used for training (12 patients) and validation (6 patients), while the second dataset was used as an independent test set (14 patients). In terms of mean surface distance, our approach achieved $1.06 \pm 0.3$ mm, $0.91 \pm 0.4$ mm, $1.27 \pm 0.4$ mm, and $1.76 \pm 0.8$ mm on the validation set and $1.82 \pm 2.4$ mm, $2.45 \pm 2.4$ mm, $2.45 \pm 5.0$ mm, and $2.57 \pm 2.3$ mm on the test set for the prostate, bladder, seminal vesicles, and rectum, respectively. The proposed multi-task network outperformed single-task networks, as well as a network only joined through the loss function, thus demonstrating the capability to leverage the individual strengths of the segmentation and registration tasks. The obtained performance as well as the inference speed make this a promising candidate for daily re-contouring in adaptive radiotherapy, potentially reducing treatment-related side effects and improving quality-of-life after treatment.

Nicola Pezzotti, Sahar Yousefi, Mohamed S. Elmahdy et al.

Adaptive intelligence aims at empowering machine learning techniques with the additional use of domain knowledge. In this work, we present the application of adaptive intelligence to accelerate MR acquisition. Starting from undersampled k-space data, an iterative learning-based reconstruction scheme inspired by compressed sensing theory is used to reconstruct the images. We adopt deep neural networks to refine and correct prior reconstruction assumptions given the training data. The network was trained and tested on a knee MRI dataset from the 2019 fastMRI challenge organized by Facebook AI Research and NYU Langone Health. All submissions to the challenge were initially ranked based on similarity with a known groundtruth, after which the top 4 submissions were evaluated radiologically. Our method was evaluated by the fastMRI organizers on an independent challenge dataset. It ranked #1, shared #1, and #3 on respectively the 8x accelerated multi-coil, the 4x multi-coil, and the 4x single-coil track. This demonstrates the superior performance and wide applicability of the method.

Mohamed S. Elmahdy, Tanuj Ahuja, U. A. van der Heide et al.

Contouring of the target volume and Organs-At-Risk (OARs) is a crucial step in radiotherapy treatment planning. In an adaptive radiotherapy setting, updated contours need to be generated based on daily imaging. In this work, we leverage personalized anatomical knowledge accumulated over the treatment sessions, to improve the segmentation accuracy of a pre-trained Convolution Neural Network (CNN), for a specific patient. We investigate a transfer learning approach, fine-tuning the baseline CNN model to a specific patient, based on imaging acquired in earlier treatment fractions. The baseline CNN model is trained on a prostate CT dataset from one hospital of 379 patients. This model is then fine-tuned and tested on an independent dataset of another hospital of 18 patients, each having 7 to 10 daily CT scans. For the prostate, seminal vesicles, bladder and rectum, the model fine-tuned on each specific patient achieved a Mean Surface Distance (MSD) of $1.64 \pm 0.43$ mm, $2.38 \pm 2.76$ mm, $2.30 \pm 0.96$ mm, and $1.24 \pm 0.89$ mm, respectively, which was significantly better than the baseline model. The proposed personalized model adaptation is therefore very promising for clinical implementation in the context of adaptive radiotherapy of prostate cancer.

Hessam Sokooti, Bob de Vos, Floris Berendsen et al.

We propose a supervised nonrigid image registration method, trained using artificial displacement vector fields (DVF), for which we propose and compare three network architectures. The artificial DVFs allow training in a fully supervised and voxel-wise dense manner, but without the cost usually associated with the creation of densely labeled data. We propose a scheme to artificially generate DVFs, and for chest CT registration augment these with simulated respiratory motion. The proposed architectures are embedded in a multi-stage approach, to increase the capture range of the proposed networks in order to more accurately predict larger displacements. The proposed method, RegNet, is evaluated on multiple databases of chest CT scans and achieved a target registration error of 2.32 $\pm$ 5.33 mm and 1.86 $\pm$ 2.12 mm on SPREAD and DIR-Lab-4DCT studies, respectively. The average inference time of RegNet with two stages is about 2.2 s.

Sahar Yousefi, Lydiane Hirschler, Merlijn van der Plas et al.

Hadamard time-encoded pseudo-continuous arterial spin labeling (te-pCASL) is a signal-to-noise ratio (SNR)-efficient MRI technique for acquiring dynamic pCASL signals that encodes the temporal information into the labeling according to a Hadamard matrix. In the decoding step, the contribution of each sub-bolus can be isolated resulting in dynamic perfusion scans. When acquiring te-ASL both with and without flow-crushing, the ASL-signal in the arteries can be isolated resulting in 4D-angiographic information. However, obtaining multi-timepoint perfusion and angiographic data requires two acquisitions. In this study, we propose a 3D Dense-Unet convolutional neural network with a multi-level loss function for reconstructing multi-timepoint perfusion and angiographic information from an interleaved $50\%$-sampled crushed and $50\%$-sampled non-crushed data, thereby negating the additional scan time. We present a framework to generate dynamic pCASL training and validation data, based on models of the intravascular and extravascular te-pCASL signals. The proposed network achieved SSIM values of $97.3 \pm 1.1$ and $96.2 \pm 11.1$ respectively for 4D perfusion and angiographic data reconstruction for 313 test data-sets.

Mohamed S. Elmahdy, Jelmer M. Wolterink, Hessam Sokooti et al.

Joint image registration and segmentation has long been an active area of research in medical imaging. Here, we reformulate this problem in a deep learning setting using adversarial learning. We consider the case in which fixed and moving images as well as their segmentations are available for training, while segmentations are not available during testing; a common scenario in radiotherapy. The proposed framework consists of a 3D end-to-end generator network that estimates the deformation vector field (DVF) between fixed and moving images in an unsupervised fashion and applies this DVF to the moving image and its segmentation. A discriminator network is trained to evaluate how well the moving image and segmentation align with the fixed image and segmentation. The proposed network was trained and evaluated on follow-up prostate CT scans for image-guided radiotherapy, where the planning CT contours are propagated to the daily CT images using the estimated DVF. A quantitative comparison with conventional registration using \texttt{elastix} showed that the proposed method improved performance and substantially reduced computation time, thus enabling real-time contour propagation necessary for online-adaptive radiotherapy.

Hessam Sokooti, Gorkem Saygili, Ben Glocker et al.

Predicting registration error can be useful for evaluation of registration procedures, which is important for the adoption of registration techniques in the clinic. In addition, quantitative error prediction can be helpful in improving the registration quality. The task of predicting registration error is demanding due to the lack of a ground truth in medical images. This paper proposes a new automatic method to predict the registration error in a quantitative manner, and is applied to chest CT scans. A random regression forest is utilized to predict the registration error locally. The forest is built with features related to the transformation model and features related to the dissimilarity after registration. The forest is trained and tested using manually annotated corresponding points between pairs of chest CT scans in two experiments: SPREAD (trained and tested on SPREAD) and inter-database (including three databases SPREAD, DIR-Lab-4DCT and DIR-Lab-COPDgene). The results show that the mean absolute errors of regression are 1.07 $\pm$ 1.86 and 1.76 $\pm$ 2.59 mm for the SPREAD and inter-database experiment, respectively. The overall accuracy of classification in three classes (correct, poor and wrong registration) is 90.7% and 75.4%, for SPREAD and inter-database respectively. The good performance of the proposed method enables important applications such as automatic quality control in large-scale image analysis.

Bob D. de Vos, Floris F. Berendsen, Max A. Viergever et al.

Image registration, the process of aligning two or more images, is the core technique of many (semi-)automatic medical image analysis tasks. Recent studies have shown that deep learning methods, notably convolutional neural networks (ConvNets), can be used for image registration. Thus far training of ConvNets for registration was supervised using predefined example registrations. However, obtaining example registrations is not trivial. To circumvent the need for predefined examples, and thereby to increase convenience of training ConvNets for image registration, we propose the Deep Learning Image Registration (DLIR) framework for \textit{unsupervised} affine and deformable image registration. In the DLIR framework ConvNets are trained for image registration by exploiting image similarity analogous to conventional intensity-based image registration. After a ConvNet has been trained with the DLIR framework, it can be used to register pairs of unseen images in one shot. We propose flexible ConvNets designs for affine image registration and for deformable image registration. By stacking multiple of these ConvNets into a larger architecture, we are able to perform coarse-to-fine image registration. We show for registration of cardiac cine MRI and registration of chest CT that performance of the DLIR framework is comparable to conventional image registration while being several orders of magnitude faster.

Bob D. de Vos, Floris F. Berendsen, Max A. Viergever et al.

In this work we propose a deep learning network for deformable image registration (DIRNet). The DIRNet consists of a convolutional neural network (ConvNet) regressor, a spatial transformer, and a resampler. The ConvNet analyzes a pair of fixed and moving images and outputs parameters for the spatial transformer, which generates the displacement vector field that enables the resampler to warp the moving image to the fixed image. The DIRNet is trained end-to-end by unsupervised optimization of a similarity metric between input image pairs. A trained DIRNet can be applied to perform registration on unseen image pairs in one pass, thus non-iteratively. Evaluation was performed with registration of images of handwritten digits (MNIST) and cardiac cine MR scans (Sunnybrook Cardiac Data). The results demonstrate that registration with DIRNet is as accurate as a conventional deformable image registration method with substantially shorter execution times.

Sahar Yousefi, M. T. Manzuri Shalmani, Jeremy Lin et al.

Recently, there has been a considerable attention given to the motion detection problem due to the explosive growth of its applications in video analysis and surveillance systems. While the previous approaches can produce good results, an accurate detection of motion remains a challenging task due to the difficulties raised by illumination variations, occlusion, camouflage, burst physical motion, dynamic texture, and environmental changes such as those on climate changes, sunlight changes during a day, etc. In this paper, we propose a novel per-pixel motion descriptor for both motion detection and dynamic texture segmentation which outperforms the current methods in the literature particularly in severe scenarios. The proposed descriptor is based on two complementary three-dimensional-discrete wavelet transform (3D-DWT) and three-dimensional wavelet leader. In this approach, a feature vector is extracted for each pixel by applying a novel three dimensional wavelet-based motion descriptor. Then, the extracted features are clustered by a clustering method such as well-known k-means algorithm or Gaussian Mixture Model (GMM). The experimental results demonstrate the effectiveness of our proposed method compared to the other motion detection approaches from the literature. The application of the proposed method and additional experimental results for the different datasets are available at (http://dspl.ce.sharif.edu/motiondetector.html).