Campus Units

Computer Science

Document Type

Article

Conference

2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS)

Publication Version

Accepted Manuscript

Publication Date

2021

Journal or Book Title

Proceedings of the 2021 IEEE 34th International Symposium on Computer-Based Medical Systems

First Page

25

Last Page

30

DOI

10.1109/CBMS52027.2021.00012

Conference Title

2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS)

Conference Date

June 7-9, 2021

Abstract

Most state-of-the-art local interpretation methods explain the behavior of deep learning classification models by assigning importance scores to image pixels based on how influential each pixel was towards the final decision. These interpretations are unable to provide further details to aid understanding of a complex concept in a domain such as medicine. We propose a novel Hierarchical Visual Concept (HVC) interpretation framework for CNN-based image classification models. As an explanation of the classification decision of a given image, HVC presents a concept hierarchy of most relevant visual concepts at multiple semantic levels. These concepts are automatically learned during training such that the lower-level concepts in the hierarchy support the corresponding higher-level concepts. Our quantitative and qualitative evaluation of the interpretation of VGG16 and ResNet50 classifiers on public and private colonoscopy image datasets shows very promising results.

Comments

This is a manuscript of a proceeding published as M. Khaleel, W. Tavanapong, J. Wong, J. Oh and P. de Groen, "Hierarchical Visual Concept Interpretation for Medical Image Classification," 2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS), 2021, pp. 25-30, Virtual Event. doi:10.1109/CBMS52027.2021.00012. Posted with permission.

Rights

© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Copyright Owner

IEEE

Language

en

File Format

application/pdf

Share

 
COinS