Towards a quantitative analysis of class activation mapping for deep learning-based computer-aided diagnosis

Hanul Kang; Ho-min Park; Yuju Ahn; Arnout Van Messem; Wesley De Neve

doi:10.1117/12.2580819

15 February 2021 Towards a quantitative analysis of class activation mapping for deep learning-based computer-aided diagnosis

Hanul Kang, Ho-min Park, Yuju Ahn, Arnout Van Messem, Wesley De Neve

Author Affiliations +

Proceedings Volume 11599, Medical Imaging 2021: Image Perception, Observer Performance, and Technology Assessment; 115990M (2021) https://doi.org/10.1117/12.2580819
Event: SPIE Medical Imaging, 2021, Online Only

Abstract

Class Activation Mapping (CAM) can be used to obtain a visual understanding of the predictions made by Convolutional Neural Networks (CNNs), facilitating qualitative insight into these neural networks when they are, for instance, used for the purpose of medical image analysis. In this paper, we investigate to what extent CAM also enables a quantitative understanding of CNN-based classification models through the creation of segmentation masks out of class activation maps, hereby targeting the use case of brain tumor classification. To that end, when a class activation map has been created for a correctly classified brain tumor, we additionally perform tumor segmentation by binarization of the aforementioned map, leveraging different methods for thresholding. In a next step, we compare this CAM-based segmentation mask to the segmentation ground truth, measuring similarity through the use of Intersection over Union (IoU). Our experimental results show that, although our CNN-based classification models have a similarly high accuracy between 86.0% and 90.8%, their generated masks are different. For example, our Modified VGG-16 model scores an mIoU of 12.2%, whereas AlexNet scores an mIoU of 2.1%. When comparing with the mIoU obtained by our U-Net-based models, which is between 66.6% and 67.3%, and where U-Net is a dedicated pixel-wise segmentation model, our experimental results point to a significant difference in terms of segmentation effectiveness. As such, the use of CAM for the purpose of proxy segmentation or as a ground truth segmentation mask generator comes with several limitations.

Conference Presentation

Citation Download Citation

Hanul Kang, Ho-min Park, Yuju Ahn, Arnout Van Messem, and Wesley De Neve "Towards a quantitative analysis of class activation mapping for deep learning-based computer-aided diagnosis", Proc. SPIE 11599, Medical Imaging 2021: Image Perception, Observer Performance, and Technology Assessment, 115990M (15 February 2021); https://doi.org/10.1117/12.2580819

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available