paper-with-me

홈 › Papers

Interpreting Medical Image Classifiers by Optimization Based Counterfactual Impact Analysis

2020-04-03 · David Major, Dimitrios Lenis, Maria Wimmer, Gert Sluiter, Astrid Berg, Katja Bühler

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.

📄 PDF Abstract BibTeX arXiv:2004.01610

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualDiagnosticGeneral Classification

Similar Papers 제목 키워드 기반

Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations

2025-11-25 · Chao Wang, Chengan Che, Xinyue Chen, Sophia Tsoka 외 arxiv

Counterfactual explanations (CFEs) are minimal and semantically meaningful modifications of the input of a model that alter the model predictions. They highlight the decisive features the model relies on, providing contr…

Emotion ClassificationAction Classification

GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learning

2020-12-22 · Silvan Mertes, Tobias Huber, Katharina Weitz, Alexander Heimerl 외

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, man…

counterfactualCounterfactual ExplanationCounterfactual ReasoningFeature Importance+3

Mitigating attribute amplification in counterfactual image generation

2024-03-14 · Tian Xia, Mélanie Roschewitz, Fabio De Sousa Ribeiro, Charles Jones 외

Causal generative modelling is gaining interest in medical imaging due to its ability to answer interventional and counterfactual queries. Most work focuses on generating counterfactual images that look plausible, using …

AttributecounterfactualImage Generation

Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals

2024-06-08 · Susu Sun, Stefano Woerner, Andreas Maier, Lisa M. Koch 외

Interpretability is crucial for machine learning algorithms in high-stakes medical applications. However, high-performing neural networks typically cannot explain their predictions. Post-hoc explanation methods provide a…

Clinical KnowledgeMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation models

2026-03-17 · Ahmed Zeid, Sidney Bender arxiv

Modern neural networks achieve strong performance but remain difficult to interpret in high-dimensional visual domains. Counterfactual explanations (CFEs) provide a principled approach to interpreting black-box predictio…