On Interpretability of Deep Learning based Skin Lesion Classifiers using Concept Activation Vectors

Abstract

Deep learning based medical image classifiers have shown remarkable prowess in various application areas like ophthalmology, dermatology, pathology, and radiology. However, the acceptance of these Computer-Aided Diagnosis (CAD) systems in real clinical setups is severely limited primarily because their decision-making process remains largely obscure. This work aims at elucidating a deep learning based medical image classifier by verifying that the model learns and utilizes similar disease-related concepts as described and employed by dermatologists. We used a well-trained and high performing neural network developed by REasoning for COmplex Data (RECOD) Lab for classification of three skin tumours, i.e. Melanocytic Naevi, Melanoma and Seborrheic Keratosis and performed a detailed analysis on its latent space. Two well established and publicly available skin disease datasets, PH2 and derm7pt, are used for experimentation. Human understandable concepts are mapped to RECOD image classification model with the help of Concept Activation Vectors (CAVs), introducing a novel training and significance testing paradigm for CAVs. Our results on an independent evaluation set clearly shows that the classifier learns and encodes human understandable concepts in its latent representation. Additionally, TCAV scores (Testing with CAVs) suggest that the neural network indeed makes use of disease-related concepts in the correct way when making predictions. We anticipate that this work can not only increase confidence of medical practitioners on CAD but also serve as a stepping stone for further development of CAV-based neural network interpretation methods.

Accepted for the IEEE International Joint Conference on Neural Networks (IJCNN) 2020

References in corpus (8)

• Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
• SmoothGrad: removing noise by adding noise
• Grad-CAM: Why did you say that?
• Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning
• RECOD Titans at ISIC Challenge 2017
• Deep neural network or dermatologist?
• TSXplain: Demystification of DNN Decisions for Time-Series using Natural Language and Statistical Features
• What evidence does deep learning model use to classify Skin Lesions?

Cited by in corpus (6)

• How to Assess Trustworthy AI in Practice
• Achievements and Challenges in Explaining Deep Learning based Computer-Aided Diagnosis Systems
• Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: Evaluation in Alzheimer's disease
• Deep Learning Based Decision Support for Medicine -- A Case Study on Skin Cancer Diagnosis
• Explaining AI-based Decision Support Systems using Concept Localization Maps
• Meta Pattern Concern Score: A Novel Evaluation Measure with Human Values for Multi-classifiers