Research Article
Similarity-Based Explanations for Deep Interpretation of Capsule Endoscopy Images
@INPROCEEDINGS{10.1007/978-3-031-60665-6_16, author={Miguel Fontes and Danilo Leite and Jo\"{a}o Dallyson and Ant\^{o}nio Cunha}, title={Similarity-Based Explanations for Deep Interpretation of Capsule Endoscopy Images}, proceedings={Wireless Mobile Communication and Healthcare. 12th EAI International Conference, MobiHealth 2023, Vila Real, Portugal, November 29-30, 2023 Proceedings}, proceedings_a={MOBIHEALTH}, year={2024}, month={6}, keywords={XAI Example-based Similarity-based explanations endoscopy}, doi={10.1007/978-3-031-60665-6_16} }- Miguel Fontes
Danilo Leite
João Dallyson
António Cunha
Year: 2024
Similarity-Based Explanations for Deep Interpretation of Capsule Endoscopy Images
MOBIHEALTH
Springer
DOI: 10.1007/978-3-031-60665-6_16
Abstract
Artificial intelligence (AI) is playing a growing role today in several areas, especially in health, where understanding AI models and their predictions is extremely important for health professionals. In this context, Explainable AI (XAI) plays a crucial role in seeking to provide understandable explanations for these models.
This article analyzes two different XAI approaches applied to analyzing gastric endoscopy images. The first, more conventional approach uses Grad CAM, while the second, even less explored but with great potential, is based on “similarity-based explanations”. This example-based XAI technique aims to provide representative examples to support the decisions of AI models.
In this study, we compare these two techniques applied to two different models: one based on the VGG16 architecture and the other based on ResNet50, designed to classify images from the KVASIR-capsule database. The results reveal that Grad-CAM provided intuitive explanations only for the VGG16 model, while the “similarity-based explanations” technique provided consistent explanations for both models. We conclude that exploring other XAI techniques can be a significant asset in improving the understanding of the various AI models.
