While success of Deep Learning (DL) in automated diagnosis can be transformative to the medicinal practice especially for people with little or no access to doctors, its widespread acceptability is severely limited by inherent black-box decision making and unsafe failure modes. While saliency methods attempt to tackle this problem in non-medical contexts, their apriori explanations do not transfer well to medical usecases. With this study we validate a model design element agnostic to both architecture complexity and model task, and show how introducing this element gives an inherently self-explanatory model. We compare our results with state of the art non-trainable saliency maps on RSNA Pneumonia Dataset and demonstrate a much higher localization efficacy using our adopted technique. We also compare, with a fully supervised baseline and provide a reasonable alternative to it's high data labelling overhead. We further investigate the validity of our claims through qualitative evaluation from an expert reader.
Deep learning models are now used in many different industries, while in certain domains safety is not a critical issue in the medical field it is a huge concern. Not only, we want the models to generalize well but we also want to know the models confidence respect to its decision and which features matter the most. Our team aims to develop a full pipeline in which not only displays the uncertainty of the models decision but also, the saliency map to show which sets of pixels of the input image contribute most to the predictions.
Inception Institute of Artificial Intelligence（英赛普申人工智能研究院）
In many real world medical image classification settings we do not have access to samples of all possible disease classes, while a robust system is expected to give high performance in recognizing novel test data. We propose a generalized zero shot learning (GZSL) method that uses self supervised learning (SSL) for: 1) selecting anchor vectors of different disease classes; and 2) training a feature generator. Our approach does not require class attribute vectors which are available for natural images but not for medical images. SSL ensures that the anchor vectors are representative of each cla…
Simon Fraser University（西蒙弗雷泽大学）；The University of British Columbia（不列颠哥伦比亚大学）
Being able to explain the prediction to clinical end-users is a necessity to leverage the power of AI models for clinical decision support. For medical images, saliency maps are the most common form of explanation. The maps highlight important features for AI model's prediction. Although many saliency map methods have been proposed, it is unknown how well they perform on explaining decisions on multi-modal medical images, where each modality/channel carries distinct clinical meanings of the same underlying biomedical phenomenon. Understanding such modality-dependent features is essential for c…
Wayne State University（韦恩州立大学）；Michigan State University（密歇根州立大学）
This work tackles a central machine learning problem of performance degradation on out-of-distribution (OOD) test sets. The problem is particularly salient in medical imaging based diagnosis system that appears to be accurate but fails when tested in new hospitals/datasets. Recent studies indicate the system might learn shortcut and non-relevant features instead of generalizable features, so-called good features. We hypothesize that adversarial training can eliminate shortcut features whereas saliency guided training can filter out non-relevant features; both are nuisance features accounting f…
Athinoula A. Martinos Center for Biomedical Imaging（阿西诺拉·A·马蒂诺斯生物医学成像中心）；Massachusetts General Hospital（麻省总医院）；Arizona State University-Mayo Clinic Center for Innovative Imaging（亚利桑那州立大学-梅奥诊所创新成像中心）；School of Computing, Informatics, and Decision Systems Engineering（计算、信息学与决策系统工程学院）
Saliency maps have become a widely used method to assess which areas of the input image are most pertinent to the prediction of a trained neural network. However, in the context of medical imaging, there is no study to our knowledge that has examined the efficacy of these techniques and quantified them using overlap with ground truth bounding boxes. In this work, we explored the credibility of the various existing saliency map methods on the RSNA Pneumonia dataset. We found that GradCAM was the most sensitive to model parameter and label randomization, and was highly agnostic to model architec…
Medical image quality assessment is an important aspect of image acquisition, as poor-quality images may lead to misdiagnosis. Manual labelling of image quality is a tedious task for population studies and can lead to misleading results. While much research has been done on automated analysis of image quality to address this issue, relatively little work has been done to explain the methodologies. In this work, we propose an explainable image quality assessment system and validate our idea on two different objectives which are foreign object detection on Chest X-Rays (Object-CXR) and Left Vent…
Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy, ignoring the important role of uncertainty quantification. Empirically, neural networks are often miscalibrated and overconfident in their predictions. This miscalibration could be problematic in any automatic decision-making system, but we focus on the medical field in which neural network miscalibration has the potential to lead to significant treatment errors.…
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Shiv Nadar University（希夫纳达尔大学）；Georgia Institute of Technology（佐治亚理工学院）；Massachusetts Institute of Technology（麻省理工学院）
Saliency maps have become a widely used method to make deep learning models more interpretable by providing post-hoc explanations of classifiers through identification of the most pertinent areas of the input medical image. They are increasingly being used in medical imaging to provide clinically plausible explanations for the decisions the neural network makes. However, the utility and robustness of these visualization maps has not yet been rigorously examined in the context of medical imaging. We posit that trustworthiness in this context requires 1) localization utility, 2) sensitivity to m…
University of Waterloo（滑铁卢大学）；Sunnybrook Health Sciences Centre（新宁健康科学中心）
Good results on image classification and retrieval using support vector machines (SVM) with local binary patterns (LBPs) as features have been extensively reported in the literature where an entire image is retrieved or classified. In contrast, in medical imaging, not all parts of the image may be equally significant or relevant to the image retrieval application at hand. For instance, in lung x-ray image, the lung region may contain a tumour, hence being highly significant whereas the surrounding area does not contain significant information from medical diagnosis perspective. In this paper, …
Clinical applicability of automated decision support systems depends on a robust, well-understood classification interpretation. Artificial neural networks while achieving class-leading scores fall short in this regard. Therefore, numerous approaches have been proposed that map a salient region of an image to a diagnostic classification. Utilizing heuristic methodology, like blurring and noise, they tend to produce diffuse, sometimes misleading results, hindering their general adoption. In this work we overcome these issues by presenting a model agnostic saliency mapping framework tailored to …
Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）；Imagia Cybernetics（Imagia控制论公司）
With too few samples or too many model parameters, overfitting can inhibit the ability to generalise predictions to new data. Within medical imaging, this can occur when features are incorrectly assigned importance such as distinct hospital specific artifacts, leading to poor performance on a new dataset from a different institution without those features, which is undesirable. Most regularization methods do not explicitly penalize the incorrect association of these features to the target class and hence fail to address this issue. We propose a regularization method, GradMask, which penalizes …
Bridging visual saliency and large language models for explainable deep learning in medical imaging
Department of Mathematics and Computer science（数学与计算机科学系）；Institute of Cognitive Science（认知科学研究所）；Rhodes University（罗德斯大学）；National Institute for Theoretical and Computational Sciences (NITheCS)（理论与计算科学国家研究所）
Peter Munk Cardiac Center（彼得·芒克心脏中心）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University of Waterloo（滑铁卢大学）
Medical image segmentation is a difficult but important task for many clinical operations such as cardiac bi-ventricular volume estimation. More recently, there has been a shift to utilizing deep learning and fully convolutional neural networks (CNNs) to perform image segmentation that has yielded state-of-the-art results in many public benchmark datasets. Despite the progress of deep learning in medical image segmentation, standard CNNs are still not fully adopted in clinical settings as they lack robustness and interpretability. Shapes are generally more meaningful features than solely textu…
UNSW（新南威尔士大学）；Dongguk University（东国大学）；Defence Science and Technology Group（国防科学技术集团）
Image segmentation is an important task in medical imaging. It constitutes the backbone of a wide variety of clinical diagnostic methods, treatments, and computer-aided surgeries. In this paper, we propose a multi-kernel image segmentation net (MKIS-Net), which uses multiple kernels to create an efficient receptive field and enhance segmentation performance. As a result of its multi-kernel design, MKIS-Net is a light-weight architecture with a small number of trainable parameters. Moreover, these multi-kernel receptive fields also contribute to better segmentation results. We demonstrate the e…
Human visual attention has recently shown its distinct capability in boosting machine learning models. However, studies that aim to facilitate medical tasks with human visual attention are still scarce. To support the use of visual attention, this paper describes a novel deep learning model for visual saliency prediction on chest X-ray (CXR) images. To cope with data deficiency, we exploit the multi-task learning method and tackles disease classification on CXR simultaneously. For a more robust training process, we propose a further optimized multi-task learning scheme to better handle model o…
Isfahan University of Technology（伊斯法罕理工大学）；McMaster University（麦克马斯特大学）；Seattle University（西雅图大学）
Endoscopy is a valuable tool for the early diagnosis of colon cancer. However, it requires the expertise of endoscopists and is a time-consuming process. In this work, we propose a new multi-label classification method, which considers two aspects of learning approaches (local and global views) for endoscopic image classification. The model consists of a Swin transformer branch and a modified VGG16 model as a CNN branch. To help the learning process of the CNN branch, the model employs saliency maps and endoscopy images and concatenates them. The results demonstrate that this method performed …
Signature Activation: A Sparse Signal View for Holistic Saliency
Harvard University（哈佛大学）；Broad Institute of Massachusetts Institute of Technology and Harvard（麻省理工学院与哈佛大学博德研究所）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
Australian Institute for Machine Learning, The University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）；Institute for Systems and Robotics, Instituto Superior Tecnico（高等技术学院系统与机器人研究所）
The deployment of automated systems to diagnose diseases from medical images is challenged by the requirement to localise the diagnosed diseases to justify or explain the classification decision. This requirement is hard to fulfil because most of the training sets available to develop these systems only contain global annotations, making the localisation of diseases a weakly supervised approach. The main methods designed for weakly supervised disease classification and localisation rely on saliency or attention maps that are not specifically trained for localisation, or on region proposals tha…
Mila, Québec Artificial Intelligence Institute（米拉魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；Imagia Cybernetics；CIFAR（加拿大高等研究院）
Poor generalization is one symptom of models that learn to predict target variables using spuriously-correlated image features present only in the training distribution instead of the true image features that denote a class. It is often thought that this can be diagnosed visually using attribution (aka saliency) maps. We study if this assumption is correct. In some prediction tasks, such as for medical images, one may have some images with masks drawn by a human expert, indicating a region of the image containing relevant information to make the prediction. We study multiple methods that take …
Transfer learning from ImageNet is the go-to approach when applying deep learning to medical images. The approach is either to fine-tune a pre-trained model or use it as a feature extractor. Most modern architecture contain batch normalisation layers, and fine-tuning a model with such layers requires taking a few precautions as they consist of trainable and non-trainable weights and have two operating modes: training and inference. Attention is primarily given to the non-trainable weights used during inference, as they are the primary source of unexpected behaviour or degradation in performanc…
Comparing radiologists' gaze and saliency maps generated by interpretability methods for chest x-rays
Scientific Computing and Imaging Institute, University of Utah（犹他大学科学计算与成像研究所）；School of Computing, University of Utah（犹他大学计算学院）；Department of Psychology, University of Utah（犹他大学心理学系）；Department of Radiology and Imaging Sciences, University of Utah（犹他大学放射学与影像科学系）
The University of Adelaide（阿德莱德大学）；Australian Institute for Machine Learning（澳大利亚机器学习研究所）；Delft University of Technology（代尔夫特理工大学）；Queensland University of Technology（昆士兰科技大学）
There is a heated debate on how to interpret the decisions provided by deep learning models (DLM), where the main approaches rely on the visualization of salient regions to interpret the DLM classification process. However, these approaches generally fail to satisfy three conditions for the problem of lesion detection from medical images: 1) for images with lesions, all salient regions should represent lesions, 2) for images containing no lesions, no salient region should be produced,and 3) lesions are generally small with relatively smooth borders. We propose a new model-agnostic paradigm to …
Utah State University（犹他州立大学）；Harbin Institute of Technology（哈尔滨工业大学）；University of Idaho（爱达荷大学）；The Affiliated Hospital of Qingdao University（青岛大学附属医院）；The Second Hospital of Hebei Medical University（河北医科大学第二医院）
Tumor saliency estimation aims to localize tumors by modeling the visual stimuli in medical images. However, it is a challenging task for breast ultrasound due to the complicated anatomic structure of the breast and poor image quality; and existing saliency estimation approaches only model generic visual stimuli, e.g., local and global contrast, location, and feature correlation, and achieve poor performance for tumor saliency estimation. In this paper, we propose a novel optimization model to estimate tumor saliency by utilizing breast anatomy. First, we model breast anatomy and decompose bre…
Jaypee University of Information Technology（贾皮尔信息技术大学）
Colon and Lung cancer is one of the most perilous and dangerous ailments that individuals are enduring worldwide and has become a general medical problem. To lessen the risk of death, a legitimate and early finding is particularly required. In any case, it is a truly troublesome task that depends on the experience of histopathologists. If a histologist is under-prepared it may even hazard the life of a patient. As of late, deep learning has picked up energy, and it is being valued in the analysis of Medical Imaging. This paper intends to utilize and alter the current pre-trained CNN-based mode…
University of Central Florida（中佛罗里达大学）；National Institutes of Health（美国国立卫生研究院）；Soochow University（苏州大学）
This study introduced a novel system, called Gaze2Segment, integrating biological and computer vision techniques to support radiologists' reading experience with an automatic image segmentation task. During diagnostic assessment of lung CT scans, the radiologists' gaze information were used to create a visual attention map. This map was then combined with a computer-derived saliency map, extracted from the gray-scale CT images. The visual attention map was used as an input for indicating roughly the location of a object of interest. With computer-derived saliency information, on the other hand…
This report describes my research activities in the Hasso Plattner Institute and summarizes my Ph.D. plan and several novels, end-to-end trainable approaches for analyzing medical images using deep learning algorithm. In this report, as an example, we explore different novel methods based on deep learning for brain abnormality detection, recognition, and segmentation. This report prepared for the doctoral consortium in the AIME-2017 conference.
Graph convolutional networks (GCNs) allow to apply traditional convolution operations in non-Euclidean domains, where data are commonly modelled as irregular graphs. Medical imaging and, in particular, neuroscience studies often rely on such graph representations, with brain connectivity networks being a characteristic example, while ultimately seeking the locus of phenotypic or disease-related differences in the brain. These regions of interest (ROIs) are, then, considered to be closely associated with function and/or behaviour. Driven by this, we explore GCNs for the task of ROI identificati…
Medical Slice Transformer: Improved Diagnosis and Explainability on 3D Medical Images with DINOv2
University Hospital Aachen（亚琛大学医院）；Technical University Dresden（德累斯顿工业大学）；University Hospital Dresden（德累斯顿大学医院）；University Hospital Heidelberg（海德堡大学医院）
Saratoga High School（萨拉托加高中）；Stanford University（斯坦福大学）；University of California, Los Angeles（加州大学洛杉矶分校）；VoxelCloud, Inc.（体云公司）
Semi-supervised learning via learning from limited quantities of labeled data has been investigated as an alternative to supervised counterparts. Maximizing knowledge gains from copious unlabeled data benefit semi-supervised learning settings. Moreover, learning multiple tasks within the same model further improves model generalizability. We propose a novel multitask learning model, namely MultiMix, which jointly learns disease classification and anatomical segmentation in a sparingly supervised manner, while preserving explainability through bridge saliency between the two tasks. Our extensiv…
Northwestern Polytechnical University（西北工业大学）；University of Georgia（佐治亚大学）；University of Electronic Science and Technology of China（电子科技大学）；Athens Academy（雅典学院）；ShanghaiTech University（上海科技大学）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）
Shortcut learning is common but harmful to deep learning models, leading to degenerated feature representations and consequently jeopardizing the model's generalizability and interpretability. However, shortcut learning in the widely used Vision Transformer framework is largely unknown. Meanwhile, introducing domain-specific knowledge is a major approach to rectifying the shortcuts, which are predominated by background related factors. For example, in the medical imaging field, eye-gaze data from radiologists is an effective human visual prior knowledge that has the great potential to guide th…
Recent advances in deep learning have achieved promising performance for medical image analysis, while in most cases ground-truth annotations from human experts are necessary to train the deep model. In practice, such annotations are expensive to collect and can be scarce for medical imaging applications. Therefore, there is significant interest in learning representations from unlabelled raw data. In this paper, we propose a self-supervised learning approach to learn meaningful and transferable representations from medical imaging video without any type of human annotation. We assume that in …
Uppsala University（乌普萨拉大学）；Antaros Medical AB（安塔罗斯医疗公司）
Large-scale medical studies such as the UK Biobank examine thousands of volunteer participants with medical imaging techniques. Combined with the vast amount of collected metadata, anatomical information from these images has the potential for medical analyses at unprecedented scale. However, their evaluation often requires manual input and long processing times, limiting the amount of reference values for biomarkers and other measurements available for research. Recent approaches with convolutional neural networks for regression can perform these evaluations automatically. On magnetic resonan…
University of Notre Dame（圣母大学）；The Hong Kong Polytechnic University（香港理工大学）
Segmentation maps of medical images annotated by medical experts contain rich spatial information. In this paper, we propose to decompose annotation maps to learn disentangled and richer feature transforms for segmentation problems in medical images. Our new scheme consists of two main stages: decompose and integrate. Decompose: by annotation map decomposition, the original segmentation problem is decomposed into multiple segmentation sub-problems; these new segmentation sub-problems are modeled by training multiple deep learning modules, each with its own set of feature transforms. Integrate:…
MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation
German Cancer Research Center (DKFZ)（德国癌症研究中心）；Heidelberg University（海德堡大学）；National Center for Tumor Diseases (NCT)（国家肿瘤疾病中心）；University Medical Center Heidelberg（海德堡大学医院）；Helmholtz Imaging（亥姆霍兹成像机构）
Stanford University（斯坦福大学）；Harvard T.H. Chan School of Public Health（哈佛陈曾熙公共卫生学院）
We propose a selective learning method using meta-learning and deep reinforcement learning for medical image interpretation in the setting of limited labeling resources. Our method, MedSelect, consists of a trainable deep learning selector that uses image embeddings obtained from contrastive pretraining for determining which images to label, and a non-parametric selector that uses cosine similarity to classify unseen images. We demonstrate that MedSelect learns an effective selection strategy outperforming baseline selection strategies across seen and unseen medical conditions for chest X-ray …
INESC TEC（葡萄牙系统与计算机工程研究所）；University of Porto（波尔图大学）
The increasing popularity of attention mechanisms in deep learning algorithms for computer vision and natural language processing made these models attractive to other research domains. In healthcare, there is a strong need for tools that may improve the routines of the clinicians and the patients. Naturally, the use of attention-based algorithms for medical applications occurred smoothly. However, being healthcare a domain that depends on high-stake decisions, the scientific community must ponder if these high-performing algorithms fit the needs of medical applications. With this motto, this …
MeLo: Low-rank Adaptation is Better than Fine-tuning for Medical Image Diagnosis
ShanghaiTech University（上海科技大学）；Shanghai Jiao Tong University（上海交通大学）；Shanghai United Imaging Intelligence Co., Ltd.（上海联影智能医疗科技有限公司）；Shanghai Clinical Research and Trial Center（上海临床研究与试验中心）
Evaluating Post-hoc Interpretability with Intrinsic Interpretability
University of Coimbra（科英布拉大学）；IPO-Porto Research Centre（波尔图肿瘤学研究所研究中心）；University of Applied Sciences Western Switzerland (HES-SO Valais)（瑞士西部应用科学大学（瓦莱州高等专业学院））
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Under the global pandemic of COVID-19, the use of artificial intelligence to analyze chest X-ray (CXR) image for COVID-19 diagnosis and patient triage is becoming important. Unfortunately, due to the emergent nature of the COVID-19 pandemic, a systematic collection of the CXR data set for deep neural network training is difficult. To address this problem, here we propose a patch-based convolutional neural network approach with a relatively small number of trainable parameters for COVID-19 diagnosis. The proposed method is inspired by our statistical analysis of the potential imaging biomarkers…
Towards Multi-dimensional Explanation Alignment for Medical Classification
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；HKUST(GZ)（香港科技大学（广州））；Tongji University（同济大学）；Ant Group（蚂蚁集团）；The University of Auckland（奥克兰大学）；RIKEN Center for Advanced Intelligence Project (AIP)（理化学研究所先进智能项目中心）
Clinical decision support using deep neural networks has become a topic of steadily growing interest. While recent work has repeatedly demonstrated that deep learning offers major advantages for medical image classification over traditional methods, clinicians are often hesitant to adopt the technology because its underlying decision-making process is considered to be intransparent and difficult to comprehend. In recent years, this has been addressed by a variety of approaches that have successfully contributed to providing deeper insight. Most notably, additive feature attribution methods are…
Modality-Projection Universal Model for Comprehensive Full-Body Medical Imaging Segmentation
the Institute of Medical Technology and National Biomedical Imaging Center, Peking University（北京大学医学技术研究所暨国家生物医学成像中心）；The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital（山东第一医科大学第一附属医院暨山东省千佛山医院）；Peking University Third Hospital（北京大学第三医院）；Guangdong Provincial People’s Hospital（广东省人民医院）；Peking University Cancer Hospital & Institute（北京大学肿瘤医院暨肿瘤研究所）
