Search

Domain Generalization techniques aim to enhance model robustness by simulating novel data distributions during training, typically through various augmentation or stylization strategies. However, these methods frequently suffer from limited control over the diversity of generated images and lack assurance that these images span distinct distributions. To address these challenges, we propose FDS, Feedback-guided Domain Synthesis, a novel strategy that employs diffusion models to synthesize novel, pseudo-domains by training a single model on all source domains and performing domain mixing based on learned features. By incorporating images that pose classification challenges to models trained on original samples, alongside the original dataset, we ensure the generation of a training set that spans a broad distribution spectrum. Our comprehensive evaluations demonstrate that this methodology sets new benchmarks in domain generalization performance across a range of challenging datasets, effectively managing diverse types of domain shifts. The implementation is available at: \url{https://github.com/Mehrdad-Noori/FDS.git}.

Vision-Language Models (VLMs) such as CLIP have yielded unprecedented performance for zero-shot image classification, yet their generalization capability may still be seriously challenged when confronted to domain shifts. In response, we present Weight Average Test-Time Adaptation (WATT) of CLIP, a pioneering approach facilitating full test-time adaptation (TTA) of this VLM. Our method employs a diverse set of templates for text prompts, augmenting the existing framework of CLIP. Predictions are utilized as pseudo labels for model updates, followed by weight averaging to consolidate the learned information globally. Furthermore, we introduce a text ensemble strategy, enhancing overall test performance by aggregating diverse textual cues. Our findings underscore the efficacy of WATT in enhancing performance across diverse datasets, including CIFAR-10-C, CIFAR-10.1, CIFAR-100-C, VisDA-C, and several other challenging datasets, effectively covering a wide range of domain shifts. Notably, these enhancements are achieved without necessitating additional model transformations or trainable modules. Moreover, compared to other Test-Time Adaptation methods, our approach can operate effectively with just a single image. Highlighting the potential of innovative test-time strategies, this research emphasizes their role in fortifying the adaptability of VLMs. The implementation is available at: \url{https://github.com/Mehrdad-Noori/WATT.git}.

We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the efficiency of Masked Auto Encoders (MAE). Unlike the conventional method of random masking, our technique utilizes a teacher-student model to focus on intricate areas within the data, guiding the model's focus toward regions with higher geometric complexity. This strategy is grounded in the hypothesis that concentrating on harder patches yields a more robust feature representation, as evidenced by the improved performance on downstream tasks. Our method also presents a complete-to-partial feature-level knowledge distillation technique designed to guide the prediction of geometric complexity utilizing a comprehensive context from feature-level information. Extensive experiments confirm our method's superiority over State-Of-The-Art (SOTA) baselines, demonstrating marked improvements in classification, and few-shot tasks.

Pre-trained vision-language models (VLMs), exemplified by CLIP, demonstrate remarkable adaptability across zero-shot classification tasks without additional training. However, their performance diminishes in the presence of domain shifts. In this study, we introduce CLIP Adaptation duRing Test-Time (CLIPArTT), a fully test-time adaptation (TTA) approach for CLIP, which involves automatic text prompts construction during inference for their use as text supervision. Our method employs a unique, minimally invasive text prompt tuning process, wherein multiple predicted classes are aggregated into a single new text prompt, used as pseudo label to re-classify inputs in a transductive manner. Additionally, we pioneer the standardization of TTA benchmarks (e.g., TENT) in the realm of VLMs. Our findings demonstrate that, without requiring additional transformations nor new trainable modules, CLIPArTT enhances performance dynamically across non-corrupted datasets such as CIFAR-10, corrupted datasets like CIFAR-10-C and CIFAR-10.1, alongside synthetic datasets such as VisDA-C. This research underscores the potential for improving VLMs' adaptability through novel test-time strategies, offering insights for robust performance across varied datasets and environments. The code can be found at: https://github.com/dosowiechi/CLIPArTT.git

Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing. Test-Time Training (TTT) methods have recently gained popularity by their ability to enhance the robustness of models through the addition of an auxiliary objective that is jointly optimized with the main task. Being strictly unsupervised, this auxiliary objective is used at test time to adapt the model without any access to labels. In this work, we propose Noise-Contrastive Test-Time Training (NC-TTT), a novel unsupervised TTT technique based on the discrimination of noisy feature maps. By learning to classify noisy views of projected feature maps, and then adapting the model accordingly on new domains, classification performance can be recovered by an important margin. Experiments on several popular test-time adaptation baselines demonstrate the advantages of our method compared to recent approaches for this task. The code can be found at:https://github.com/GustavoVargasHakim/NCTTT.git

With the increasing demand for audiovisual services, telecom service providers and application developers are compelled to ensure that their services provide the best possible user experience. Particularly, services such as videoconferencing are very sensitive to network conditions. Therefore, their performance should be monitored in real time in order to adjust parameters to any network perturbation. In this paper, we developed a parametric model for estimating the perceived audiovisual quality in videoconference services. Our model is developed with the nonlinear autoregressive exogenous (NARX) recurrent neural network and estimates the perceived quality in terms of mean opinion score (MOS). We validate our model using the publicly available INRS bitstream audiovisual quality dataset. This dataset contains bitstream parameters such as loss per frame, bit rate and video duration. We compare the proposed model against state-of-the-art methods based on machine learning and show our model to outperform these methods in terms of mean square error (MSE=0.150) and Pearson correlation coefficient (R=0.931)

Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (TTT) methods have been developed in an attempt to mitigate these vulnerabilities, where a secondary task is solved at training time simultaneously with the main task, to be later used as an self-supervised proxy task at test-time. In this work, we propose a novel unsupervised TTT technique based on the maximization of Mutual Information between multi-scale feature maps and a discrete latent representation, which can be integrated to the standard training as an auxiliary clustering task. Experimental results demonstrate competitive classification performance on different popular test-time adaptation benchmarks.

Despite the recent progress in incremental learning, addressing catastrophic forgetting under distributional drift is still an open and important problem. Indeed, while state-of-the-art domain incremental learning (DIL) methods perform satisfactorily within known domains, their performance largely degrades in the presence of novel domains. This limitation hampers their generalizability, and restricts their scalability to more realistic settings where train and test data are drawn from different distributions. To address these limitations, we present a novel DIL approach based on a mixture of prompt-tuned CLIP models (MoP-CLIP), which generalizes the paradigm of S-Prompting to handle both in-distribution and out-of-distribution data at inference. In particular, at the training stage we model the features distribution of every class in each domain, learning individual text and visual prompts to adapt to a given domain. At inference, the learned distributions allow us to identify whether a given test sample belongs to a known domain, selecting the correct prompt for the classification task, or from an unseen domain, leveraging a mixture of the prompt-tuned CLIP models. Our empirical evaluation reveals the poor performance of existing DIL methods under domain shift, and suggests that the proposed MoP-CLIP performs competitively in the standard DIL settings while outperforming state-of-the-art methods in OOD scenarios. These results demonstrate the superiority of MoP-CLIP, offering a robust and general solution to the problem of domain incremental learning., Comment: 13 pages, 5 figures

Privacy protection in medical data is a legitimate obstacle for centralized machine learning applications. Here, we propose a client-server image segmentation system which allows for the analysis of multi-centric medical images while preserving patient privacy. In this approach, the client protects the to-be-segmented patient image by mixing it to a reference image. As shown in our work, it is challenging to separate the image mixture to exact original content, thus making the data unworkable and unrecognizable for an unauthorized person. This proxy image is sent to a server for processing. The server then returns the mixture of segmentation maps, which the client can revert to a correct target segmentation. Our system has two components: 1) a segmentation network on the server side which processes the image mixture, and 2) a segmentation unmixing network which recovers the correct segmentation map from the segmentation mixture. Furthermore, the whole system is trained end-to-end. The proposed method is validated on the task of MRI brain segmentation using images from two different datasets. Results show that the segmentation accuracy of our method is comparable to a system trained on raw images, and outperforms other privacy-preserving methods with little computational overhead.

Recently, deep reinforcement learning (RL) has been proposed to learn the tractography procedure and train agents to reconstruct the structure of the white matter without manually curated reference streamlines. While the performances reported were competitive, the proposed framework is complex, and little is still known about the role and impact of its multiple parts. In this work, we thoroughly explore the different components of the proposed framework, such as the choice of the RL algorithm, seeding strategy, the input signal and reward function, and shed light on their impact. Approximately 7,400 models were trained for this work, totalling nearly 41,000 hours of GPU time. Our goal is to guide researchers eager to explore the possibilities of deep RL for tractography by exposing what works and what does not work with the category of approach. As such, we ultimately propose a series of recommendations concerning the choice of RL algorithm, the input to the agents, the reward function and more to help future work using reinforcement learning for tractography. We also release the open source codebase, trained models, and datasets for users and researchers wanting to explore reinforcement learning for tractography.

Standard deep learning models such as convolutional neural networks (CNNs) lack the ability of generalizing to domains which have not been seen during training. This problem is mainly due to the common but often wrong assumption of such models that the source and target data come from the same i.i.d. distribution. Recently, Vision Transformers (ViTs) have shown outstanding performance for a broad range of computer vision tasks. However, very few studies have investigated their ability to generalize to new domains. This paper presents a first Token-level Feature Stylization (TFS-ViT) approach for domain generalization, which improves the performance of ViTs to unseen data by synthesizing new domains. Our approach transforms token features by mixing the normalization statistics of images from different domains. We further improve this approach with a novel strategy for attention-aware stylization, which uses the attention maps of class (CLS) tokens to compute and mix normalization statistics of tokens corresponding to different image regions. The proposed method is flexible to the choice of backbone model and can be easily applied to any ViT-based architecture with a negligible increase in computational complexity. Comprehensive experiments show that our approach is able to achieve state-of-the-art performance on five challenging benchmarks for domain generalization, and demonstrate its ability to deal with different types of domain shifts. The implementation is available at: https://github.com/Mehrdad-Noori/TFS-ViT_Token-level_Feature_Stylization.

In this paper, we propose an unsupervised framework based on normalizing flows that harmonizes MR images to mimic the distribution of the source domain. The proposed framework consists of three steps. First, a shallow harmonizer network is trained to recover images of the source domain from their augmented versions. A normalizing flow network is then trained to learn the distribution of the source domain. Finally, at test time, a harmonizer network is modified so that the output images match the source domain's distribution learned by the normalizing flow model. Our unsupervised, source-free and task-independent approach is evaluated on cross-domain brain MRI segmentation using data from four different sites. Results demonstrate its superior performance compared to existing methods., Comment: 10 pages

The performance of learning-based algorithms improves with the amount of labelled data used for training. Yet, manually annotating data is particularly difficult for medical image segmentation tasks because of the limited expert availability and intensive manual effort required. To reduce manual labelling, active learning (AL) targets the most informative samples from the unlabelled set to annotate and add to the labelled training set. On the one hand, most active learning works have focused on the classification or limited segmentation of natural images, despite active learning being highly desirable in the difficult task of medical image segmentation. On the other hand, uncertainty-based AL approaches notoriously offer sub-optimal batch-query strategies, while diversity-based methods tend to be computationally expensive. Over and above methodological hurdles, random sampling has proven an extremely difficult baseline to outperform when varying learning and sampling conditions. This work aims to take advantage of the diversity and speed offered by random sampling to improve the selection of uncertainty-based AL methods for segmenting medical images. More specifically, we propose to compute uncertainty at the level of batches instead of samples through an original use of stochastic batches (SB) during sampling in AL. Stochastic batch querying is a simple and effective add-on that can be used on top of any uncertainty-based metric. Extensive experiments on two medical image segmentation datasets show that our strategy consistently improves conventional uncertainty-based sampling methods. Our method can hence act as a strong baseline for medical image segmentation. The code is available on: https://github.com/Minimel/StochasticBatchAL.git., Comment: Accepted to Medical Image Analysis, 17 pages

Deep learning methods typically depend on the availability of labeled data, which is expensive and time-consuming to obtain. Active learning addresses such effort by prioritizing which samples are best to annotate in order to maximize the performance of the task model. While frameworks for active learning have been widely explored in the context of classification of natural images, they have been only sparsely used in medical image segmentation. The challenge resides in obtaining an uncertainty measure that reveals the best candidate data for annotation. This paper proposes Test-time Augmentation for Active Learning (TAAL), a novel semi-supervised active learning approach for segmentation that exploits the uncertainty information offered by data transformations. Our method applies cross-augmentation consistency during training and inference to both improve model learning in a semi-supervised fashion and identify the most relevant unlabeled samples to annotate next. In addition, our consistency loss uses a modified version of the JSD to further improve model performance. By relying on data transformations rather than on external modules or simple heuristics typically used in uncertainty-based strategies, TAAL emerges as a simple, yet powerful task-agnostic semi-supervised active learning approach applicable to the medical domain. Our results on a publicly-available dataset of cardiac images show that TAAL outperforms existing baseline methods in both fully-supervised and semi-supervised settings. Our implementation is publicly available on https://github.com/melinphd/TAAL., Comment: Accepted to MICCAI-DALI 2022 (LNCS Proceedings, vol.13567), 11 pages

Systems for person re-identification (ReID) can achieve a high accuracy when trained on large fully-labeled image datasets. However, the domain shift typically associated with diverse operational capture conditions (e.g., camera viewpoints and lighting) may translate to a significant decline in performance. This paper focuses on unsupervised domain adaptation (UDA) for video-based ReID - a relevant scenario that is less explored in the literature. In this scenario, the ReID model must adapt to a complex target domain defined by a network of diverse video cameras based on tracklet information. State-of-art methods cluster unlabeled target data, yet domain shifts across target cameras (sub-domains) can lead to poor initialization of clustering methods that propagates noise across epochs, thus preventing the ReID model to accurately associate samples of same identity. In this paper, an UDA method is introduced for video person ReID that leverages knowledge on video tracklets, and on the distribution of frames captured over target cameras to improve the performance of CNN backbones trained using pseudo-labels. Our method relies on an adversarial approach, where a camera-discriminator network is introduced to extract discriminant camera-independent representations, facilitating the subsequent clustering. In addition, a weighted contrastive loss is proposed to leverage the confidence of clusters, and mitigate the risk of incorrect identity associations. Experimental results obtained on three challenging video-based person ReID datasets - PRID2011, iLIDS-VID, and MARS - indicate that our proposed method can outperform related state-of-the-art methods. Our code is available at: \url{https://github.com/dmekhazni/CAWCL-ReID}, Comment: IEEE/CVF Winter Conference on Applications of Computer Vision(WACV) 2023

A major problem of deep neural networks for image classification is their vulnerability to domain changes at test-time. Recent methods have proposed to address this problem with test-time training (TTT), where a two-branch model is trained to learn a main classification task and also a self-supervised task used to perform test-time adaptation. However, these techniques require defining a proxy task specific to the target application. To tackle this limitation, we propose TTTFlow: a Y-shaped architecture using an unsupervised head based on Normalizing Flows to learn the normal distribution of latent features and detect domain shifts in test examples. At inference, keeping the unsupervised head fixed, we adapt the model to domain-shifted examples by maximizing the log likelihood of the Normalizing Flow. Our results show that our method can significantly improve the accuracy with respect to previous works.

Imaging biomarkers offer a non-invasive way to predict the response of immunotherapy prior to treatment. In this work, we propose a novel type of deep radiomic features (DRFs) computed from a convolutional neural network (CNN), which capture tumor characteristics related to immune cell markers and overall survival. Our study uses four MRI sequences (T1-weighted, T1-weighted post-contrast, T2-weighted and FLAIR) with corresponding immune cell markers of 151 patients with brain tumor. The proposed method extracts a total of 180 DRFs by aggregating the activation maps of a pre-trained 3D-CNN within labeled tumor regions of MRI scans. These features offer a compact, yet powerful representation of regional texture encoding tissue heterogeneity. A comprehensive set of experiments is performed to assess the relationship between the proposed DRFs and immune cell markers, and measure their association with overall survival. Results show a high correlation between DRFs and various markers, as well as significant differences between patients grouped based on these markers. Moreover, combining DRFs, clinical features and immune cell markers as input to a random forest classifier helps discriminate between short and long survival outcomes, with AUC of 72\% and p=2.36$\times$10$^{-5}$. These results demonstrate the usefulness of proposed DRFs as non-invasive biomarker for predicting treatment response in patients with brain tumors.

Radiomics with deep learning models have become popular in computer-aided diagnosis and have outperformed human experts on many clinical tasks. Specifically, radiomic models based on artificial intelligence (AI) are using medical data (i.e., images, molecular data, clinical variables, etc.) for predicting clinical tasks like Autism Spectrum Disorder (ASD). In this review, we summarized and discussed the radiomic techniques used for ASD analysis. Currently, the limited radiomic work of ASD is related to variation of morphological features of brain thickness that is different from texture analysis. These techniques are based on imaging shape features that can be used with predictive models for predicting ASD. This review explores the progress of ASD-based radiomics with a brief description of ASD and the current non-invasive technique used to classify between ASD and Healthy Control (HC) subjects. With AI, new radiomic models using the deep learning techniques will be also described. To consider the texture analysis with deep CNNs, more investigations are suggested to be integrated with additional validation steps on various MRI sites.

This paper proposes to encode the distribution of features learned from a convolutional neural network using a Gaussian Mixture Model. These parametric features, called GMM-CNN, are derived from chest computed tomography and X-ray scans of patients with Coronavirus Disease 2019. We use the proposed GMM-CNN features as input to a robust classifier based on random forests to differentiate between COVID-19 and other pneumonia cases. Our experiments assess the advantage of GMM-CNN features compared to standard CNN classification on test images. Using a random forest classifier (80\% samples for training; 20\% samples for testing), GMM-CNN features encoded with two mixture components provided a significantly better performance than standard CNN classification (p\,$<$\,0.05). Specifically, our method achieved an accuracy in the range of 96.00\,--\,96.70\% and an area under the ROC curve in the range of 99.29\,--\,99.45\%, with the best performance obtained by combining GMM-CNN features from both computed tomography and X-ray images. Our results suggest that the proposed GMM-CNN features could improve the prediction of COVID-19 in chest computed tomography and X-ray scans.

Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and negative pairs. However, it is not trivial to build reasonable pairs for a segmentation task in an unsupervised way. In this work, we propose a novel unsupervised pre-training framework that avoids the drawback of contrastive learning. Our framework consists of two principles: unsupervised over-segmentation as a pre-train task using mutual information maximization and boundary-aware preserving learning. Experimental results on two benchmark medical segmentation datasets reveal our method's effectiveness in improving segmentation performance when few annotated images are available.

This work considers semi-supervised segmentation as a dense prediction problem based on prototype vector correlation and proposes a simple way to represent each segmentation class with multiple prototypes. To avoid degenerate solutions, two regularization strategies are applied on unlabeled images. The first one leverages mutual information maximization to ensure that all prototype vectors are considered by the network. The second explicitly enforces prototypes to be orthogonal by minimizing their cosine distance. Experimental results on two benchmark medical segmentation datasets reveal our method's effectiveness in improving segmentation performance when few annotated images are available.

Despite achieving promising results in a breadth of medical image segmentation tasks, deep neural networks require large training datasets with pixel-wise annotations. Obtaining these curated datasets is a cumbersome process which limits the applicability in scenarios. Mixed supervision is an appealing alternative for mitigating this obstacle. In this work, we propose a dual-branch architecture, where the upper branch (teacher) receives strong annotations, while the bottom one (student) is driven by limited supervision and guided by the upper branch. Combined with a standard cross-entropy loss over the labeled pixels, our novel formulation integrates two important terms: (i) a Shannon entropy loss defined over the less-supervised images, which encourages confident student predictions in the bottom branch; and (ii) a KL divergence term, which transfers the knowledge (i.e., predictions) of the strongly supervised branch to the less-supervised branch and guides the entropy (student-confidence) term to avoid trivial solutions. We show that the synergy between the entropy and KL divergence yields substantial improvements in performance. We also discuss an interesting link between Shannon-entropy minimization and standard pseudo-mask generation, and argue that the former should be preferred over the latter for leveraging information from unlabeled pixels. We evaluate the effectiveness of the proposed formulation through a series of quantitative and qualitative experiments using two publicly available datasets. Results demonstrate that our method significantly outperforms other strategies for semantic segmentation within a mixed-supervision framework, as well as recent semi-supervised approaches. Our code is publicly available: https://github.com/by-liu/ConfKD., Comment: To be published at Medical Image Analysis (Volume 83, January 2023). Code: https://github.com/by-liu/ConfKD. Note: this article is a journal extension of our paper in IPMI 2021 arXiv:2012.08051

Collaborative recommendation approaches based on nearest-neighbors are still highly popular today due to their simplicity, their efficiency, and their ability to produce accurate and personalized recommendations. This chapter offers a comprehensive survey of neighborhood-based methods for the item recommendation problem. It presents the main characteristics and benefits of such methods, describes key design choices for implementing a neighborhood-based recommender system, and gives practical information on how to make these choices. A broad range of methods is covered in the chapter, including traditional algorithms like k-nearest neighbors as well as advanced approaches based on matrix factorization, sparse coding and random walks., Comment: 50 pages; Chapter in the Recommender Systems Handbook, 3rd Edition (to appear)

The physical and clinical constraints surrounding diffusion-weighted imaging (DWI) often limit the spatial resolution of the produced images to voxels up to 8 times larger than those of T1w images. Thus, the detailed information contained in T1w imagescould help in the synthesis of diffusion images in higher resolution. However, the non-Euclidean nature of diffusion imaging hinders current deep generative models from synthesizing physically plausible images. In this work, we propose the first Riemannian network architecture for the direct generation of diffusion tensors (DT) and diffusion orientation distribution functions (dODFs) from high-resolution T1w images. Our integration of the Log-Euclidean Metric into a learning objective guarantees, unlike standard Euclidean networks, the mathematically-valid synthesis of diffusion. Furthermore, our approach improves the fractional anisotropy mean squared error (FA MSE) between the synthesized diffusion and the ground-truth by more than 23% and the cosine similarity between principal directions by almost 5% when compared to our baselines. We validate our generated diffusion by comparing the resulting tractograms to our expected real data. We observe similar fiber bundles with streamlines having less than 3% difference in length, less than 1% difference in volume, and a visually close shape. While our method is able to generate high-resolution diffusion images from structural inputs in less than 15 seconds, we acknowledge and discuss the limits of diffusion inference solely relying on T1w images. Our results nonetheless suggest a relationship between the high-level geometry of the brain and the overall white matter architecture., Comment: Preprint submitted for review

Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by clinicians, for instance, containing holes or disconnected regions. To solve this problem, we present a Context-aware Virtual Adversarial Training (CaVAT) method for generating anatomically plausible segmentation. Unlike approaches focusing solely on accuracy, our method also considers complex topological constraints like connectivity which cannot be easily modeled in a differentiable loss function. We use adversarial training to generate examples violating the constraints, so the network can learn to avoid making such incorrect predictions on new examples, and employ the Reinforce algorithm to handle non-differentiable segmentation constraints. The proposed method offers a generic and efficient way to add any constraint on top of any segmentation network. Experiments on two clinically-relevant datasets show our method to produce segmentations that are both accurate and anatomically-plausible in terms of region connectivity., Comment: This paper is accepted at MICCAI2021

We propose a novel pairwise distance measure between image keypoint sets, for the purpose of large-scale medical image indexing. Our measure generalizes the Jaccard index to account for soft set equivalence (SSE) between keypoint elements, via an adaptive kernel framework modeling uncertainty in keypoint appearance and geometry. A new kernel is proposed to quantify the variability of keypoint geometry in location and scale. Our distance measure may be estimated between $O(N^2)$ image pairs in $O(N~\log~N)$ operations via keypoint indexing. Experiments report the first results for the task of predicting family relationships from medical images, using 1010 T1-weighted MRI brain volumes of 434 families including monozygotic and dizygotic twins, siblings and half-siblings sharing 100%-25% of their polymorphic genes. Soft set equivalence and the keypoint geometry kernel improve upon standard hard set equivalence (HSE) and appearance kernels alone in predicting family relationships. Monozygotic twin identification is near 100%, and three subjects with uncertain genotyping are automatically paired with their self-reported families, the first reported practical application of image-based family identification. Our distance measure can also be used to predict group categories, sex is predicted with an AUC=0.97. Software is provided for efficient fine-grained curation of large, generic image datasets., Comment: 10 pages, 8 figures

The scarcity of labeled data often impedes the application of deep learning to the segmentation of medical images. Semi-supervised learning seeks to overcome this limitation by exploiting unlabeled examples in the learning process. In this paper, we present a novel semi-supervised segmentation method that leverages mutual information (MI) on categorical distributions to achieve both global representation invariance and local smoothness. In this method, we maximize the MI for intermediate feature embeddings that are taken from both the encoder and decoder of a segmentation network. We first propose a global MI loss constraining the encoder to learn an image representation that is invariant to geometric transformations. Instead of resorting to computationally-expensive techniques for estimating the MI on continuous feature embeddings, we use projection heads to map them to a discrete cluster assignment where MI can be computed efficiently. Our method also includes a local MI loss to promote spatial consistency in the feature maps of the decoder and provide a smoother segmentation. Since mutual information does not require a strict ordering of clusters in two different assignments, we incorporate a final consistency regularization loss on the output which helps align the cluster labels throughout the network. We evaluate the method on four challenging publicly-available datasets for medical image segmentation. Experimental results show our method to outperform recently-proposed approaches for semi-supervised segmentation and provide an accuracy near to full supervision while training with very few annotated images.

Deep segmentation neural networks require large training datasets with pixel-wise segmentations, which are expensive to obtain in practice. Mixed supervision could mitigate this difficulty, with a small fraction of the data containing complete pixel-wise annotations, while the rest being less supervised, e.g., only a handful of pixels are labeled. In this work, we propose a dual-branch architecture, where the upper branch (teacher) receives strong annotations, while the bottom one (student) is driven by limited supervision and guided by the upper branch. In conjunction with a standard cross-entropy over the labeled pixels, our novel formulation integrates two important terms: (i) a Shannon entropy loss defined over the less-supervised images, which encourages confident student predictions at the bottom branch; and (ii) a Kullback-Leibler (KL) divergence, which transfers the knowledge from the predictions generated by the strongly supervised branch to the less-supervised branch, and guides the entropy (student-confidence) term to avoid trivial solutions. Very interestingly, we show that the synergy between the entropy and KL divergence yields substantial improvements in performances. Furthermore, we discuss an interesting link between Shannon-entropy minimization and standard pseudo-mask generation and argue that the former should be preferred over the latter for leveraging information from unlabeled pixels. Through a series of quantitative and qualitative experiments, we show the effectiveness of the proposed formulation in segmenting the left-ventricle endocardium in MRI images. We demonstrate that our method significantly outperforms other strategies to tackle semantic segmentation within a mixed-supervision framework. More interestingly, and in line with recent observations in classification, we show that the branch trained with reduced supervision largely outperforms the teacher.

We propose a client-server system which allows for the analysis of multi-centric medical images while preserving patient identity. In our approach, the client protects the patient identity by applying a pseudo-random non-linear deformation to the input image. This results into a proxy image which is sent to the server for processing. The server then returns back the deformed processed image which the client reverts to a canonical form. Our system has three components: 1) a flow-field generator which produces a pseudo-random deformation function, 2) a Siamese discriminator that learns the patient identity from the processed image, 3) a medical image processing network that analyzes the content of the proxy images. The system is trained end-to-end in an adversarial manner. By fooling the discriminator, the flow-field generator learns to produce a bi-directional non-linear deformation which allows to remove and recover the identity of the subject from both the input image and output result. After end-to-end training, the flow-field generator is deployed on the client side and the segmentation network is deployed on the server side. The proposed method is validated on the task of MRI brain segmentation using images from two different datasets. Results show that the segmentation accuracy of our method is similar to a system trained on non-encoded images, while considerably reducing the ability to recover subject identity.

Deep co-training has recently been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-supervised segmentation with a self-paced and self-consistent co-training method. To help distillate information from unlabeled images, we first design a self-paced learning strategy for co-training that lets jointly-trained neural networks focus on easier-to-segment regions first, and then gradually consider harder ones.This is achieved via an end-to-end differentiable loss inthe form of a generalized Jensen Shannon Divergence(JSD). Moreover, to encourage predictions from different networks to be both consistent and confident, we enhance this generalized JSD loss with an uncertainty regularizer based on entropy. The robustness of individual models is further improved using a self-ensembling loss that enforces their prediction to be consistent across different training iterations. We demonstrate the potential of our method on three challenging image segmentation problems with different image modalities, using small fraction of labeled data. Results show clear advantages in terms of performance compared to the standard co-training baselines and recently proposed state-of-the-art approaches for semi-supervised segmentation

Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, traditional diagnostic approaches may suffer from subjectivity as they rely on the evaluation of movements that are sometimes subtle to human eyes and therefore difficult to classify, leading to possible misclassification. In the meantime, early non-motor symptoms of PD may be mild and can be caused by many other conditions. Therefore, these symptoms are often overlooked, making diagnosis of PD at an early stage challenging. To address these difficulties and to refine the diagnosis and assessment procedures of PD, machine learning methods have been implemented for the classification of PD and healthy controls or patients with similar clinical presentations (e.g., movement disorders or other Parkinsonian syndromes). To provide a comprehensive overview of data modalities and machine learning methods that have been used in the diagnosis and differential diagnosis of PD, in this study, we conducted a systematic literature review of studies published until February 14, 2020, using the PubMed and IEEE Xplore databases. A total of 209 studies were included, extracted for relevant information and presented in this systematic review, with an investigation of their aims, sources of data, types of data, machine learning methods and associated outcomes. These studies demonstrate a high potential for adaptation of machine learning methods and novel biomarkers in clinical decision making, leading to increasingly systematic, informed diagnosis of PD.

Image normalization is a building block in medical image analysis. Conventional approaches are customarily utilized on a per-dataset basis. This strategy, however, prevents the current normalization algorithms from fully exploiting the complex joint information available across multiple datasets. Consequently, ignoring such joint information has a direct impact on the performance of segmentation algorithms. This paper proposes to revisit the conventional image normalization approach by instead learning a common normalizing function across multiple datasets. Jointly normalizing multiple datasets is shown to yield consistent normalized images as well as an improved image segmentation. To do so, a fully automated adversarial and task-driven normalization approach is employed as it facilitates the training of realistic and interpretable images while keeping performance on-par with the state-of-the-art. The adversarial training of our network aims at finding the optimal transfer function to improve both the segmentation accuracy and the generation of realistic images. We evaluated the performance of our normalizer on both infant and adult brains images from the iSEG, MRBrainS and ABIDE datasets. Results reveal the potential of our normalization approach for segmentation, with Dice improvements of up to 57.5% over our baseline. Our method can also enhance data availability by increasing the number of samples available when learning from multiple imaging domains.

The varying cortical geometry of the brain creates numerous challenges for its analysis. Recent developments have enabled learning surface data directly across multiple brain surfaces via graph convolutions on cortical data. However, current graph learning algorithms do fail when brain surface data are misaligned across subjects, thereby affecting their ability to deal with data from multiple domains. Adversarial training is widely used for domain adaptation to improve the segmentation performance across domains. In this paper, adversarial training is exploited to learn surface data across inconsistent graph alignments. This novel approach comprises a segmentator that uses a set of graph convolution layers to enable parcellation directly across brain surfaces in a source domain, and a discriminator that predicts a graph domain from segmentations. More precisely, the proposed adversarial network learns to generalize a parcellation across both, source and target domains. We demonstrate an 8% mean improvement in performance over a non-adversarial training strategy applied on multiple target domains extracted from MindBoggle, the largest publicly available manually-labeled brain surface dataset.

Unpaired image-to-image translation has been applied successfully to natural images but has received very little attention for manifold-valued data such as in diffusion tensor imaging (DTI). The non-Euclidean nature of DTI prevents current generative adversarial networks (GANs) from generating plausible images and has mainly limited their application to diffusion MRI scalar maps, such as fractional anisotropy (FA) or mean diffusivity (MD). Even if these scalar maps are clinically useful, they mostly ignore fiber orientations and therefore have limited applications for analyzing brain fibers. Here, we propose a manifold-aware CycleGAN that learns the generation of high-resolution DTI from unpaired T1w images. We formulate the objective as a Wasserstein distance minimization problem of data distributions on a Riemannian manifold of symmetric positive definite 3x3 matrices SPD(3), using adversarial and cycle-consistency losses. To ensure that the generated diffusion tensors lie on the SPD(3) manifold, we exploit the theoretical properties of the exponential and logarithm maps of the Log-Euclidean metric. We demonstrate that, unlike standard GANs, our method is able to generate realistic high-resolution DTI that can be used to compute diffusion-based metrics and potentially run fiber tractography algorithms. To evaluate our model's performance, we compute the cosine similarity between the generated tensors principal orientation and their ground-truth orientation, the mean squared error (MSE) of their derived FA values and the Log-Euclidean distance between the tensors. We demonstrate that our method produces 2.5 times better FA MSE than a standard CycleGAN and up to 30% better cosine similarity than a manifold-aware Wasserstein GAN while synthesizing sharp high-resolution DTI., Comment: Accepted at MICCAI 2020 International Workshop on Computational Diffusion MRI

In this paper, we study the problem of out-of-distribution detection in skin disease images. Publicly available medical datasets normally have a limited number of lesion classes (e.g. HAM10000 has 8 lesion classes). However, there exists a few thousands of clinically identified diseases. Hence, it is important if lesions not in the training data can be differentiated. Toward this goal, we propose DeepIF, a non-parametric Isolation Forest based approach combined with deep convolutional networks. We conduct comprehensive experiments to compare our DeepIF with three baseline models. Results demonstrate state-of-the-art performance of our proposed approach on the task of detecting abnormal skin lesions.

Image normalization is a critical step in medical imaging. This step is often done on a per-dataset basis, preventing current segmentation algorithms from the full potential of exploiting jointly normalized information across multiple datasets. To solve this problem, we propose an adversarial normalization approach for image segmentation which learns common normalizing functions across multiple datasets while retaining image realism. The adversarial training provides an optimal normalizer that improves both the segmentation accuracy and the discrimination of unrealistic normalizing functions. Our contribution therefore leverages common imaging information from multiple domains. The optimality of our common normalizer is evaluated by combining brain images from both infants and adults. Results on the challenging iSEG and MRBrainS datasets reveal the potential of our adversarial normalization approach for segmentation, with Dice improvements of up to 59.6% over the baseline., Comment: Submitted to ISBI 2020

Brain surface analysis is essential to neuroscience, however, the complex geometry of the brain cortex hinders computational methods for this task. The difficulty arises from a discrepancy between 3D imaging data, which is represented in Euclidean space, and the non-Euclidean geometry of the highly-convoluted brain surface. Recent advances in machine learning have enabled the use of neural networks for non-Euclidean spaces. These facilitate the learning of surface data, yet pooling strategies often remain constrained to a single fixed-graph. This paper proposes a new learnable graph pooling method for processing multiple surface-valued data to output subject-based information. The proposed method innovates by learning an intrinsic aggregation of graph nodes based on graph spectral embedding. We illustrate the advantages of our approach with in-depth experiments on two large-scale benchmark datasets. The flexibility of the pooling strategy is evaluated on four different prediction tasks, namely, subject-sex classification, regression of cortical region sizes, classification of Alzheimer's disease stages, and brain age regression. Our experiments demonstrate the superiority of our learnable pooling approach compared to other pooling techniques for graph convolution networks, with results improving the state-of-the-art in brain surface analysis.

The analysis of the brain surface modeled as a graph mesh is a challenging task. Conventional deep learning approaches often rely on data lying in the Euclidean space. As an extension to irregular graphs, convolution operations are defined in the Fourier or spectral domain. This spectral domain is obtained by decomposing the graph Laplacian, which captures relevant shape information. However, the spectral decomposition across different brain graphs causes inconsistencies between the eigenvectors of individual spectral domains, causing the graph learning algorithm to fail. Current spectral graph convolution methods handle this variance by separately aligning the eigenvectors to a reference brain in a slow iterative step. This paper presents a novel approach for learning the transformation matrix required for aligning brain meshes using a direct data-driven approach. Our alignment and graph processing method provides a fast analysis of brain surfaces. The novel Spectral Graph Transformer (SGT) network proposed in this paper uses very few randomly sub-sampled nodes in the spectral domain to learn the alignment matrix for multiple brain surfaces. We validate the use of this SGT network along with a graph convolution network to perform cortical parcellation. Our method on 101 manually-labeled brain surfaces shows improved parcellation performance over a no-alignment strategy, gaining a significant speed (1400 fold) over traditional iterative alignment approaches., Comment: Equal contribution of R. He and K. Gopinath

This paper proposes to use deep radiomic features (DRFs) from a convolutional neural network (CNN) to model fine-grained texture signatures in the radiomic analysis of recurrent glioblastoma (rGBM). We use DRFs to predict survival of rGBM patients with preoperative T1-weighted post-contrast MR images (n=100). DRFs are extracted from regions of interest labelled by a radiation oncologist and used to compare between short-term and long-term survival patient groups. Random forest (RF) classification is employed to predict survival outcome (i.e., short or long survival), as well as to identify highly group-informative descriptors. Classification using DRFs results in an area under the ROC curve (AUC) of 89.15% (p<0.01) in predicting rGBM patient survival, compared to 78.07% (p<0.01) when using standard radiomic features (SRF). These results indicate the potential of DRFs as a prognostic marker for patients with rGBM., Comment: Accepted in MICCAI RNO workshop

Recently, two methods have shown outstanding performance for clustering images and jointly learning the feature representation. The first, called Information Maximiz-ing Self-Augmented Training (IMSAT), maximizes the mutual information between input and clusters while using a regularization term based on virtual adversarial examples. The second, named Invariant Information Clustering (IIC), maximizes the mutual information between the clustering of a sample and its geometrically transformed version. These methods use mutual information in distinct ways and leverage different kinds of transformations. This work proposes a comprehensive analysis of transformation and losses for deep clustering, where we compare numerous combinations of these two components and evaluate how they interact with one another. Results suggest that mutual information between a sample and its transformed representation leads to state-of-the-art performance for deep clustering, especially when used jointly with geometrical and adversarial transformations.