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

by   Adriano Lucieri, et al.

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.


page 1

page 4

page 5

page 6

page 7

page 9


Concept Activation Vectors for Generating User-Defined 3D Shapes

We explore the interpretability of 3D geometric deep learning models in ...

SkiNet: A Deep Learning Solution for Skin Lesion Diagnosis with Uncertainty Estimation and Explainability

Skin cancer is considered to be the most common human malignancy. Around...

Automatic Infectious Disease Classification Analysis with Concept Discovery

Automatic infectious disease classification from images can facilitate n...

Explaining AI-based Decision Support Systems using Concept Localization Maps

Human-centric explainability of AI-based Decision Support Systems (DSS) ...

ExAID: A Multimodal Explanation Framework for Computer-Aided Diagnosis of Skin Lesions

One principal impediment in the successful deployment of AI-based Comput...

Expert Opinion Elicitation for Assisting Deep Learning based Lyme Disease Classifier with Patient Data

Diagnosing erythema migrans (EM) skin lesion, the most common early symp...

Global and Local Interpretability for Cardiac MRI Classification

Deep learning methods for classifying medical images have demonstrated i...

Please sign up or login with your details

Forgot password? Click here to reset