Pierre Vera

Ling Huang, Thierry Denoeux, Pierre Vera et al.

As information sources are usually imperfect, it is necessary to take into account their reliability in multi-source information fusion tasks. In this paper, we propose a new deep framework allowing us to merge multi-MR image segmentation results using the formalism of Dempster-Shafer theory while taking into account the reliability of different modalities relative to different classes. The framework is composed of an encoder-decoder feature extraction module, an evidential segmentation module that computes a belief function at each voxel for each modality, and a multi-modality evidence fusion module, which assigns a vector of discount rates to each modality evidence and combines the discounted evidence using Dempster's rule. The whole framework is trained by minimizing a new loss function based on a discounted Dice index to increase segmentation accuracy and reliability. The method was evaluated on the BraTs 2021 database of 1251 patients with brain tumors. Quantitative and qualitative results show that our method outperforms the state of the art, and implements an effective new idea for merging multi-information within deep neural networks.

Amine Amyar, Romain Modzelewski, Pierre Vera et al.

Background and Objectives: Predicting patient response to treatment and survival in oncology is a prominent way towards precision medicine. To that end, radiomics was proposed as a field of study where images are used instead of invasive methods. The first step in radiomic analysis is the segmentation of the lesion. However, this task is time consuming and can be physician subjective. Automated tools based on supervised deep learning have made great progress to assist physicians. However, they are data hungry, and annotated data remains a major issue in the medical field where only a small subset of annotated images is available. Methods: In this work, we propose a multi-task learning framework to predict patient's survival and response. We show that the encoder can leverage multiple tasks to extract meaningful and powerful features that improve radiomics performance. We show also that subsidiary tasks serve as an inductive bias so that the model can better generalize. Results: Our model was tested and validated for treatment response and survival in lung and esophageal cancers, with an area under the ROC curve of 77% and 71% respectively, outperforming single task learning methods. Conclusions: We show that, by using a multi-task learning approach, we can boost the performance of radiomic analysis by extracting rich information of intratumoral and peritumoral regions.

Thibaud Brochet, Jérôme Lapuyade-Lahorgue, Pierre Vera et al.

In this paper, we propose to quantitatively compare loss functions based on parameterized Tsallis-Havrda-Charvat entropy and classical Shannon entropy for the training of a deep network in the case of small datasets which are usually encountered in medical applications. Shannon cross-entropy is widely used as a loss function for most neural networks applied to the segmentation, classification and detection of images. Shannon entropy is a particular case of Tsallis-Havrda-Charvat entropy. In this work, we compare these two entropies through a medical application for predicting recurrence in patients with head-neck and lung cancers after treatment. Based on both CT images and patient information, a multitask deep neural network is proposed to perform a recurrence prediction task using cross-entropy as a loss function and an image reconstruction task. Tsallis-Havrda-Charvat cross-entropy is a parameterized cross entropy with the parameter $α$. Shannon entropy is a particular case of Tsallis-Havrda-Charvat entropy for $α$ = 1. The influence of this parameter on the final prediction results is studied. In this paper, the experiments are conducted on two datasets including in total 580 patients, of whom 434 suffered from head-neck cancers and 146 from lung cancers. The results show that Tsallis-Havrda-Charvat entropy can achieve better performance in terms of prediction accuracy with some values of $α$.

Zexin Ji, Beiji Zou, Xiaoyan Kui et al.

In this paper, we propose a new architecture, called Deform-Mamba, for MR image super-resolution. Unlike conventional CNN or Transformer-based super-resolution approaches which encounter challenges related to the local respective field or heavy computational cost, our approach aims to effectively explore the local and global information of images. Specifically, we develop a Deform-Mamba encoder which is composed of two branches, modulated deform block and vision Mamba block. We also design a multi-view context module in the bottleneck layer to explore the multi-view contextual content. Thanks to the extracted features of the encoder, which include content-adaptive local and efficient global information, the vision Mamba decoder finally generates high-quality MR images. Moreover, we introduce a contrastive edge loss to promote the reconstruction of edge and contrast related content. Quantitative and qualitative experimental results indicate that our approach on IXI and fastMRI datasets achieves competitive performance.

Zexin Ji, Beiji Zou, Xiaoyan Kui et al.

In this paper, we propose a self-prior guided Mamba-UNet network (SMamba-UNet) for medical image super-resolution. Existing methods are primarily based on convolutional neural networks (CNNs) or Transformers. CNNs-based methods fail to capture long-range dependencies, while Transformer-based approaches face heavy calculation challenges due to their quadratic computational complexity. Recently, State Space Models (SSMs) especially Mamba have emerged, capable of modeling long-range dependencies with linear computational complexity. Inspired by Mamba, our approach aims to learn the self-prior multi-scale contextual features under Mamba-UNet networks, which may help to super-resolve low-resolution medical images in an efficient way. Specifically, we obtain self-priors by perturbing the brightness inpainting of the input image during network training, which can learn detailed texture and brightness information that is beneficial for super-resolution. Furthermore, we combine Mamba with Unet network to mine global features at different levels. We also design an improved 2D-Selective-Scan (ISS2D) module to divide image features into different directional sequences to learn long-range dependencies in multiple directions, and adaptively fuse sequence information to enhance super-resolved feature representation. Both qualitative and quantitative experimental results demonstrate that our approach outperforms current state-of-the-art methods on two public medical datasets: the IXI and fastMRI.

Aghiles Kebaili, Jérôme Lapuyade-Lahorgue, Pierre Vera et al.

Despite the increasing use of deep learning in medical image segmentation, acquiring sufficient training data remains a challenge in the medical field. In response, data augmentation techniques have been proposed; however, the generation of diverse and realistic medical images and their corresponding masks remains a difficult task, especially when working with insufficient training sets. To address these limitations, we present an end-to-end architecture based on the Hamiltonian Variational Autoencoder (HVAE). This approach yields an improved posterior distribution approximation compared to traditional Variational Autoencoders (VAE), resulting in higher image generation quality. Our method outperforms generative adversarial architectures under data-scarce conditions, showcasing enhancements in image quality and precise tumor mask synthesis. We conduct experiments on two publicly available datasets, MICCAI's Brain Tumor Segmentation Challenge (BRATS), and Head and Neck Tumor Segmentation Challenge (HECKTOR), demonstrating the effectiveness of our method on different medical imaging modalities.

Aghiles Kebaili, Jérôme Lapuyade-Lahorgue, Pierre Vera et al.

In clinical practice, full imaging is not always feasible, often due to complex acquisition protocols, stringent privacy regulations, or specific clinical needs. However, missing MR modalities pose significant challenges for tasks like brain tumor segmentation, especially in deep learning-based segmentation, as each modality provides complementary information crucial for improving accuracy. A promising solution is missing data imputation, where absent modalities are generated from available ones. While generative models have been widely used for this purpose, most state-of-the-art approaches are limited to single or dual target translations, lacking the adaptability to generate missing modalities based on varying input configurations. To address this, we propose an Adaptive Multi-Modality Diffusion Network (AMM-Diff), a novel diffusion-based generative model capable of handling any number of input modalities and generating the missing ones. We designed an Image-Frequency Fusion Network (IFFN) that learns a unified feature representation through a self-supervised pretext task across the full input modalities and their selected high-frequency Fourier components. The proposed diffusion model leverages this representation, encapsulating prior knowledge of the complete modalities, and combines it with an adaptive reconstruction strategy to achieve missing modality completion. Experimental results on the BraTS 2021 dataset demonstrate the effectiveness of our approach.

Zexin Ji, Beiji Zou, Xiaoyan Kui et al.

Multi-modal 3D medical image segmentation aims to accurately identify tumor regions across different modalities, facing challenges from variations in image intensity and tumor morphology. Traditional convolutional neural network (CNN)-based methods struggle with capturing global features, while Transformers-based methods, despite effectively capturing global context, encounter high computational costs in 3D medical image segmentation. The Mamba model combines linear scalability with long-distance modeling, making it a promising approach for visual representation learning. However, Mamba-based 3D multi-modal segmentation still struggles to leverage modality-specific features and fuse complementary information effectively. In this paper, we propose a Mamba based feature extraction and adaptive multilevel feature fusion for 3D tumor segmentation using multi-modal medical image. We first develop the specific modality Mamba encoder to efficiently extract long-range relevant features that represent anatomical and pathological structures present in each modality. Moreover, we design an bi-level synergistic integration block that dynamically merges multi-modal and multi-level complementary features by the modality attention and channel attention learning. Lastly, the decoder combines deep semantic information with fine-grained details to generate the tumor segmentation map. Experimental results on medical image datasets (PET/CT and MRI multi-sequence) show that our approach achieve competitive performance compared to the state-of-the-art CNN, Transformer, and Mamba-based approaches.

Aghiles Kebaili, Jérôme Lapuyade-Lahorgue, Pierre Vera et al.

Deep learning has gained significant attention in medical image segmentation. However, the limited availability of annotated training data presents a challenge to achieving accurate results. In efforts to overcome this challenge, data augmentation techniques have been proposed. However, the majority of these approaches primarily focus on image generation. For segmentation tasks, providing both images and their corresponding target masks is crucial, and the generation of diverse and realistic samples remains a complex task, especially when working with limited training datasets. To this end, we propose a new end-to-end hybrid architecture based on Hamiltonian Variational Autoencoders (HVAE) and a discriminative regularization to improve the quality of generated images. Our method provides an accuracte estimation of the joint distribution of the images and masks, resulting in the generation of realistic medical images with reduced artifacts and off-distribution instances. As generating 3D volumes requires substantial time and memory, our architecture operates on a slice-by-slice basis to segment 3D volumes, capitilizing on the richly augmented dataset. Experiments conducted on two public datasets, BRATS (MRI modality) and HECKTOR (PET modality), demonstrate the efficacy of our proposed method on different medical imaging modalities with limited data.

Aghiles Kebaili, Jérôme Lapuyade-Lahorgue, Pierre Vera et al.

Despite the increasing use of deep learning in medical image segmentation, the limited availability of annotated training data remains a major challenge due to the time-consuming data acquisition and privacy regulations. In the context of segmentation tasks, providing both medical images and their corresponding target masks is essential. However, conventional data augmentation approaches mainly focus on image synthesis. In this study, we propose a novel slice-based latent diffusion architecture designed to address the complexities of volumetric data generation in a slice-by-slice fashion. This approach extends the joint distribution modeling of medical images and their associated masks, allowing a simultaneous generation of both under data-scarce regimes. Our approach mitigates the computational complexity and memory expensiveness typically associated with diffusion models. Furthermore, our architecture can be conditioned by tumor characteristics, including size, shape, and relative position, thereby providing a diverse range of tumor variations. Experiments on a segmentation task using the BRATS2022 confirm the effectiveness of the synthesized volumes and masks for data augmentation.

Tongxue Zhou, Stéphane Canu, Pierre Vera et al.

Using multimodal Magnetic Resonance Imaging (MRI) is necessary for accurate brain tumor segmentation. The main problem is that not all types of MRIs are always available in clinical exams. Based on the fact that there is a strong correlation between MR modalities of the same patient, in this work, we propose a novel brain tumor segmentation network in the case of missing one or more modalities. The proposed network consists of three sub-networks: a feature-enhanced generator, a correlation constraint block and a segmentation network. The feature-enhanced generator utilizes the available modalities to generate 3D feature-enhanced image representing the missing modality. The correlation constraint block can exploit the multi-source correlation between the modalities and also constrain the generator to synthesize a feature-enhanced modality which must have a coherent correlation with the available modalities. The segmentation network is a multi-encoder based U-Net to achieve the final brain tumor segmentation. The proposed method is evaluated on BraTS 2018 dataset. Experimental results demonstrate the effectiveness of the proposed method which achieves the average Dice Score of 82.9, 74.9 and 59.1 on whole tumor, tumor core and enhancing tumor, respectively across all the situations, and outperforms the best method by 3.5%, 17% and 18.2%.

Tongxue Zhou, Su Ruan, Pierre Vera et al.

In the field of multimodal segmentation, the correlation between different modalities can be considered for improving the segmentation results. Considering the correlation between different MR modalities, in this paper, we propose a multi-modality segmentation network guided by a novel tri-attention fusion. Our network includes N model-independent encoding paths with N image sources, a tri-attention fusion block, a dual-attention fusion block, and a decoding path. The model independent encoding paths can capture modality-specific features from the N modalities. Considering that not all the features extracted from the encoders are useful for segmentation, we propose to use dual attention based fusion to re-weight the features along the modality and space paths, which can suppress less informative features and emphasize the useful ones for each modality at different positions. Since there exists a strong correlation between different modalities, based on the dual attention fusion block, we propose a correlation attention module to form the tri-attention fusion block. In the correlation attention module, a correlation description block is first used to learn the correlation between modalities and then a constraint based on the correlation is used to guide the network to learn the latent correlated features which are more relevant for segmentation. Finally, the obtained fused feature representation is projected by the decoder to obtain the segmentation results. Our experiment results tested on BraTS 2018 dataset for brain tumor segmentation demonstrate the effectiveness of our proposed method.

Tongxue Zhou, Stéphane Canu, Pierre Vera et al.

Magnetic Resonance Imaging (MRI) is a widely used imaging technique to assess brain tumor. Accurately segmenting brain tumor from MR images is the key to clinical diagnostics and treatment planning. In addition, multi-modal MR images can provide complementary information for accurate brain tumor segmentation. However, it's common to miss some imaging modalities in clinical practice. In this paper, we present a novel brain tumor segmentation algorithm with missing modalities. Since it exists a strong correlation between multi-modalities, a correlation model is proposed to specially represent the latent multi-source correlation. Thanks to the obtained correlation representation, the segmentation becomes more robust in the case of missing modality. First, the individual representation produced by each encoder is used to estimate the modality independent parameter. Then, the correlation model transforms all the individual representations to the latent multi-source correlation representations. Finally, the correlation representations across modalities are fused via attention mechanism into a shared representation to emphasize the most important features for segmentation. We evaluate our model on BraTS 2018 and BraTS 2019 dataset, it outperforms the current state-of-the-art methods and produces robust results when one or more modalities are missing.

Tongxue Zhou, Stéphane Canu, Pierre Vera et al.

In the field of multimodal segmentation, the correlation between different modalities can be considered for improving the segmentation results. In this paper, we propose a multi-modality segmentation network with a correlation constraint. Our network includes N model-independent encoding paths with N image sources, a correlation constraint block, a feature fusion block, and a decoding path. The model independent encoding path can capture modality-specific features from the N modalities. Since there exists a strong correlation between different modalities, we first propose a linear correlation block to learn the correlation between modalities, then a loss function is used to guide the network to learn the correlated features based on the linear correlation block. This block forces the network to learn the latent correlated features which are more relevant for segmentation. Considering that not all the features extracted from the encoders are useful for segmentation, we propose to use dual attention based fusion block to recalibrate the features along the modality and spatial paths, which can suppress less informative features and emphasize the useful ones. The fused feature representation is finally projected by the decoder to obtain the segmentation result. Our experiment results tested on BraTS-2018 dataset for brain tumor segmentation demonstrate the effectiveness of our proposed method.

Tongxue Zhou, Stéphane Canu, Pierre Vera et al.

Multimodal MR images can provide complementary information for accurate brain tumor segmentation. However, it's common to have missing imaging modalities in clinical practice. Since there exists a strong correlation between multi modalities, a novel correlation representation block is proposed to specially discover the latent multi-source correlation. Thanks to the obtained correlation representation, the segmentation becomes more robust in the case of missing modalities. The model parameter estimation module first maps the individual representation produced by each encoder to obtain independent parameters, then, under these parameters, the correlation expression module transforms all the individual representations to form a latent multi-source correlation representation. Finally, the correlation representations across modalities are fused via the attention mechanism into a shared representation to emphasize the most important features for segmentation. We evaluate our model on BraTS 2018 datasets, it outperforms the current state-of-the-art method and produces robust results when one or more modalities are missing.

Amine Amyar, Su Ruan, Pierre Vera et al.

One of the most challenges in medical imaging is the lack of data. It is proven that classical data augmentation methods are useful but still limited due to the huge variation in images. Using generative adversarial networks (GAN) is a promising way to address this problem, however, it is challenging to train one model to generate different classes of lesions. In this paper, we propose a deep convolutional conditional generative adversarial network to generate MIP positron emission tomography image (PET) which is a 2D image that represents a 3D volume for fast interpretation, according to different lesions or non lesion (normal). The advantage of our proposed method consists of one model that is capable of generating different classes of lesions trained on a small sample size for each class of lesion, and showing a very promising results. In addition, we show that a walk through a latent space can be used as a tool to evaluate the images generated.

Amine Amyar, Romain Modzelewski, Pierre Vera et al.

One of the most challenges in medical imaging is the lack of data and annotated data. It is proven that classical segmentation methods such as U-NET are useful but still limited due to the lack of annotated data. Using a weakly supervised learning is a promising way to address this problem, however, it is challenging to train one model to detect and locate efficiently different type of lesions due to the huge variation in images. In this paper, we present a novel approach to locate different type of lesions in positron emission tomography (PET) images using only a class label at the image-level. First, a simple convolutional neural network classifier is trained to predict the type of cancer on two 2D MIP images. Then, a pseudo-localization of the tumor is generated using class activation maps, back-propagated and corrected in a multitask learning approach with prior knowledge, resulting in a tumor detection mask. Finally, we use the mask generated from the two 2D images to detect the tumor in the 3D image. The advantage of our proposed method consists of detecting the whole tumor volume in 3D images, using only two 2D images of PET image, and showing a very promising results. It can be used as a tool to locate very efficiently tumors in a PET scan, which is a time-consuming task for physicians. In addition, we show that our proposed method can be used to conduct a radiomics study with state of the art results.