.png){kind=icon}
返回
Validating Automatic Concept-Based Explanations for AI-Based Digital Histopathology
.png){kind=icon}
OA
AI
DOI：10.3390/s22145346.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Digital histopathology poses several challenges such as label noise, class imbalance, limited availability of labelled data, and several latent biases to deep learning, negatively influencing transparency, reproducibility, and classification performance. In particular, biases are well known to cause poor generalization. Proposed tools from explainable artificial intelligence (XAI), bias detection, and bias discovery suffer from technical challenges, complexity, unintuitive usage, inherent biases, or a semantic gap. A promising XAI method, not studied in the context of digital histopathology is automated concept-based explanation (ACE). It automatically extracts visual concepts from image data. Our objective is to evaluate ACE's technical validity following design science principals and to compare it to Guided Gradient-weighted Class Activation Mapping (Grad-CAM), a conventional pixel-wise explanation method. To that extent, we created and studied five convolutional neural networks (CNNs) in four different skin cancer settings. Our results demonstrate that ACE is a valid tool for gaining insights into the decision process of histopathological CNNs that can go beyond explanations from the control method. ACE validly visualized a class sampling ratio bias, measurement bias, sampling bias, and class-correlated bias. Furthermore, the complementary use with Guided Grad-CAM offers several benefits. Finally, we propose practical solutions for several technical challenges. In contradiction to results from the literature, we noticed lower intuitiveness in some dermatopathology scenarios as compared to concept-based explanations on real-world images.
Keyword:
explainable AI
bias discovery
concept attribution
saliency map
computational histopathology
malignant melanoma
basal cell carcinoma
squamous cell carcinoma
intra-epidermal carcinoma
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.5
论文数:
7.2W
被引数:
20.9W
机构
引用论文
.png){kind=icon}
TOWARDS EXPLAINABLE CLASSIFIERS USING THE COUNTERFACTUAL APPROACH - GLOBAL EXPLANATIONS FOR DISCOVERING BIAS IN DATA使用反事实方法走向可解释的分类器 -- 发现数据偏差的全局解释
OAAI
OAAI分享收藏Hidden Variables in Deep Learning Digital Pathology and Their Potential to Cause Batch Effects: Prediction Model Study深度学习数字病理学中的隐藏变量及其导致批量效应的潜力: 预测模型研究OAAI
OAAI分享收藏分享收藏
查看更多内容