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 medical imaging. We replace heuristic techniques with a strong neighborhood conditioned inpainting approach, which avoids anatomically implausible artefacts. We formulate saliency attribution as a map-quality optimization task, enforcing constrained and focused attributions. Experiments on public mammography data show quantitatively and qualitatively more precise localization and clearer conveying results than existing state-of-the-art methods.
Deep neural networks (DNN) have achieved unprecedented performance in computer-vision tasks almost ubiquitously in business, technology, and science. While substantial efforts are made to engineer highly accurate architectures and provide usable model explanations, most state-of-the-art approaches are first designed for natural vision and then translated to the medical domain. This dissertation seeks to address this gap by proposing novel architectures that integrate the domain-specific constraints of medical imaging into the DNN model and explanation design.
University of Copenhagen（哥本哈根大学）；Rigshospitalet（哥本哈根大学国立医院）
Generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) play an increasingly important role in medical image analysis. The latent spaces of these models often show semantically meaningful directions corresponding to human-interpretable image transformations. However, until now, their exploration for medical images has been limited due to the requirement of supervised data. Several methods for unsupervised discovery of interpretable directions in GAN latent spaces have shown interesting results on natural images. This work explores the potential of a…
Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder
Technical University of Munich（慕尼黑工业大学）；Klinikum rechts der Isar（右侧伊萨尔医院）；Institute for Artificial Intelligence and Computer Science in Medicine, Technical University of Munich（慕尼黑工业大学人工智能与医学计算机科学研究所）；Computer Aided Medical Procedures, Technical University of Munich（慕尼黑工业大学计算机辅助医疗程序研究所）；AI for Image-Guided Diagnosis and Therapy, Technical University of Munich（慕尼黑工业大学图像引导诊断与治疗人工智能研究所）
University of Edinburgh（爱丁堡大学）；The Alan Turing Institute（艾伦·图灵研究所）
Due to the limited availability of medical data, deep learning approaches for medical image analysis tend to generalise poorly to unseen data. Augmenting data during training with random transformations has been shown to help and became a ubiquitous technique for training neural networks. Here, we propose a novel adversarial counterfactual augmentation scheme that aims at finding the most \textit{effective} synthesised images to improve downstream tasks, given a pre-trained generative model. Specifically, we construct an adversarial game where we update the input \textit{conditional factor} of…
Counterfactual MRI Data Augmentation using Conditional Denoising Diffusion Generative Models
Instituto Superior Técnico（高等技术学院）；Universidade de Lisboa（里斯本大学）；Digital Surgery LAB（数字外科实验室）；Champalimaud Foundation（尚帕利莫基金会）；Faculdade de Medicina, Universidade de Lisboa（里斯本大学医学院）；Instituto de Telecomunicações（电信研究所）
VRVis Zentrum für Virtual Reality und Visualisierung Forschungs-GmbH（VRVis虚拟现实与可视化研究有限公司）
The success of machine learning methods for computer vision tasks has driven a surge in computer assisted prediction for medicine and biology. Based on a data-driven relationship between input image and pathological classification, these predictors deliver unprecedented accuracy. Yet, the numerous approaches trying to explain the causality of this learned relationship have fallen short: time constraints, coarse, diffuse and at times misleading results, caused by the employment of heuristic techniques like Gaussian noise and blurring, have hindered their clinical adoption. In this work, we disc…
Technical University of Munich（慕尼黑工业大学）；Klinikum rechts der Isar（伊萨尔河畔临床教学中心）
Deep learning models used in medical image analysis are prone to raising reliability concerns due to their black-box nature. To shed light on these black-box models, previous works predominantly focus on identifying the contribution of input features to the diagnosis, i.e., feature attribution. In this work, we explore counterfactual explanations to identify what patterns the models rely on for diagnosis. Specifically, we investigate the effect of changing features within chest X-rays on the classifier's output to understand its decision mechanism. We leverage a StyleGAN-based approach (StyleE…
DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation
National Heart and Lung Institute, Imperial College London（帝国理工学院国家心肺研究所）；Black Sesame Technologies（黑芝麻智能科技）；Imperial College London（帝国理工学院）；Bioengineering Department and Imperial-X, Imperial College London（帝国理工学院生物工程系与Imperial-X）；Cardiovascular Research Centre, Royal Brompton Hospital（皇家布朗普顿医院心血管研究中心）；School of Biomedical Engineering & Imaging Sciences, King’s College London（伦敦国王学院生物医学工程与影像科学学院）
University of Pittsburgh（匹兹堡大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Pittsburgh Medical School（匹兹堡大学医学院）
We propose a BlackBox Counterfactual Explainer, designed to explain image classification models for medical applications. Classical approaches (e.g., saliency maps) that assess feature importance do not explain "how" imaging features in important anatomical regions are relevant to the classification decision. Our framework explains the decision for a target class by gradually "exaggerating" the semantic effect of the class in a query image. We adopted a Generative Adversarial Network (GAN) to generate a progressive set of perturbations to a query image, such that the classification decision ch…
Decoding Decision Reasoning: A Counterfactual-Powered Model for Knowledge Discovery
National Heart and Lung Institute, Imperial College London（伦敦帝国理工学院国家心肺研究所）；Imperial College London（伦敦帝国理工学院）；Imperial-X（帝国理工-X）；Department of Metabolism, Digestion and Reproduction, Imperial College London（伦敦帝国理工学院代谢、消化与生殖系）
When the Edit Changes the Patient: Measuring Identity Preservation in Counterfactual Retinal Images
Technical University of Munich（慕尼黑工业大学）；TUM University Hospital（慕尼黑工业大学医院）；Munich Center of Machine Learning (MCML)（慕尼黑机器学习中心）；Munich Data Science Institute (MDSI)（慕尼黑数据科学研究所）；Sapienza University of Rome（罗马第一大学）；Faculty of Medicine, University of Southampton（南安普顿大学医学院）；Moorfields Eye Hospital NHS Foundation Trust（摩尔菲尔兹眼科医院NHS信托基金）；Imperial College London（伦敦帝国学院）
City Data Science Institute - City, University of London（伦敦城市大学城市数据科学研究所）
A novel explainable AI method called CLEAR Image is introduced in this paper. CLEAR Image is based on the view that a satisfactory explanation should be contrastive, counterfactual and measurable. CLEAR Image explains an image's classification probability by contrasting the image with a corresponding image generated automatically via adversarial learning. This enables both salient segmentation and perturbations that faithfully determine each segment's importance. CLEAR Image was successfully applied to a medical imaging case study where it outperformed methods such as Grad-CAM and LIME by an a…
Evaluation of 3D Counterfactual Brain MRI Generation
Wu Tsai Neurosciences Institute, Stanford University, Stanford, CA, USA Department of Radiology, Stanford University, Stanford, CA, USA Dept. of Psychiatry \& Behavioral Sciences, Stanford University, Stanford, CA, USA Department of Computer Science, Stanford University, Stanford, CA, USA Department of Bioengineering, Stanford University, Stanford, CA, USA Department of Electrical Engineering, Stanford University, Stanford, CA, USA
CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationale
The Key Laboratory of Smart Human-Computer Interaction（智能人机交互关键实验室）；Wearable Technology of Shaanxi Province, Xidian University, Xi'an, China（陕西 wearable 技术, 西安电子科技大学, 中国）；Nanjing University of Science and Technology（南京理工大学）
With the ongoing rise of machine learning, the need for methods for explaining decisions made by artificial intelligence systems is becoming a more and more important topic. Especially for image classification tasks, many state-of-the-art tools to explain such classifiers rely on visual highlighting of important areas of the input data. Contrary, counterfactual explanation systems try to enable a counterfactual reasoning by modifying the input image in a way such that the classifier would have made a different prediction. By doing so, the users of counterfactual explanation systems are equippe…
Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models
Australian Institute for Machine Learning, University of Adelaide, Australia（澳大利亚机器学习研究所，阿德莱德大学，澳大利亚）；Deakin University, Australia（德肯大学，澳大利亚）；Flinders University, Australia（弗林德斯大学，澳大利亚）
Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis
Center for Data Science in Clinical Medicine（临床医学数据科学中心）；The State Key Lab of Brain-Machine Intelligence（脑机智能国家重点实验室）；Department of Gynecology and Obstetrics, 7th Medical Center of Chinese PLA General Hospital（中国人民解放军第七医学中心妇产科部）；School of Computer Science, Peking University（北京大学计算机学院）；School of Psychological and Cognitive Sciences, Peking University（北京大学心理学与认知科学学院）；State Key Lab of General AI, Peking University（通用人工智能国家重点实验室）；Nat’l Eng. Research Center of Visual Technology（视觉技术国家工程研究中心）；Beijing Key Laboratory of Behavior and Mental Health（北京行为与心理健康重点实验室）；Embodied Intelligence Lab, PKU-Wuhan Institute for Artificial Intelligence（具身智能实验室，北京大学-武汉人工智能研究院）
Do Medical Vision Language Models Actually See? A Counterfactual Grounding Framework and Hard-Negative Contrastive Training for Visually-Reliant Medical VLMs
The University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心）；Eisai Inc.（卫材株式会社）；IISc, Bangalore（印度科学研究所班加罗尔分校）；Cohere Labs Community（Cohere实验室社区）
Unifying Image Counterfactuals and Feature Attributions with Latent-Space Adversarial Attacks
Department of Statistics, University of California, Berkeley（加州大学伯克利分校统计学系）；Department of Statistics and Data Science, University of Pennsylvania（宾夕法尼亚大学统计学与数据科学系）
TRACE-Seg3D: Counterfactual Context Auditing For Robust 3D Glioma Segmentation Under Institutional Shift
The University of Melbourne（墨尔本大学）；University of Information Technology, Vietnam National University（越南国立大学信息技术大学）；Industrial University of Ho Chi Minh City（胡志明市工业大学）
Causal Disentanglement for Robust Long-tail Medical Image Generation
School of Electrical and Information Engineering, Tianjin University, China（天津大学电气与信息工程学院）；Department of Information Engineering and Computer Science, University of Trento, Italy（特伦托大学信息工程与计算机科学系）；Fondazione Bruno Kessler, Italy（布鲁诺·克塞勒基金会）
Due to the significant advancement of Natural Language Processing and Computer Vision-based models, Visual Question Answering (VQA) systems are becoming more intelligent and advanced. However, they are still error-prone when dealing with relatively complex questions. Therefore, it is important to understand the behaviour of the VQA models before adopting their results. In this paper, we introduce an interpretability approach for VQA models by generating counterfactual images. Specifically, the generated image is supposed to have the minimal possible change to the original image and leads the V…
What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning
Birla Institute of Technology and Science, Pilani（贝拉理工科学学院皮拉尼分校）；University of California, Merced（加州大学默塞德分校）
Detecting Clinical Hallucinations in LVLMs via Counterfactual Visual Grounding Uncertainty
School of Intelligent Science and Technology, Nanjing University（南京大学智能科学与技术学院）；National Institute of Healthcare Data Science at Nanjing University（南京大学医疗数据科学国家研究院）；School of Biomedical Engineering, Nanjing University（南京大学生物医学工程学院）
Ask4VG: Risk-Aware Question Selection for Reducing Prior-Driven Answers in Medical VQA
School of Microelectronics, Tianjin University, Tianjin 300072, China（天津大学电子工程学院，天津 300072，中国）；DISI, University of Trento, Trento, Italy（特伦托大学DISI研究所，意大利特伦托）；School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China（天津大学电气与信息工程学院，天津 300072，中国）
