Saved in:
Bibliographic Details
Main Authors: Torda, Tommaso, Ciardiello, Andrea, Gargiulo, Simona, Grillo, Greta, Scardapane, Simone, Voena, Cecilia, Giagu, Stefano
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.12222
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909207615242240
author Torda, Tommaso
Ciardiello, Andrea
Gargiulo, Simona
Grillo, Greta
Scardapane, Simone
Voena, Cecilia
Giagu, Stefano
author_facet Torda, Tommaso
Ciardiello, Andrea
Gargiulo, Simona
Grillo, Greta
Scardapane, Simone
Voena, Cecilia
Giagu, Stefano
contents In recent years Artificial Intelligence has emerged as a fundamental tool in medical applications. Despite this rapid development, deep neural networks remain black boxes that are difficult to explain, and this represents a major limitation for their use in clinical practice. We focus on the segmentation of medical images task, where most explainability methods proposed so far provide a visual explanation in terms of an input saliency map. The aim of this work is to extend, implement and test instead an influence-based explainability algorithm, TracIn, proposed originally for classification tasks, in a challenging clinical problem, i.e., multiclass segmentation of tumor brains in multimodal Magnetic Resonance Imaging. We verify the faithfulness of the proposed algorithm linking the similarities of the latent representation of the network to the TracIn output. We further test the capacity of the algorithm to provide local and global explanations, and we suggest that it can be adopted as a tool to select the most relevant features used in the decision process. The method is generalizable for all semantic segmentation tasks where classes are mutually exclusive, which is the standard framework in these cases.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12222
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Influence based explainability of brain tumors segmentation in multimodal Magnetic Resonance Imaging
Torda, Tommaso
Ciardiello, Andrea
Gargiulo, Simona
Grillo, Greta
Scardapane, Simone
Voena, Cecilia
Giagu, Stefano
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
In recent years Artificial Intelligence has emerged as a fundamental tool in medical applications. Despite this rapid development, deep neural networks remain black boxes that are difficult to explain, and this represents a major limitation for their use in clinical practice. We focus on the segmentation of medical images task, where most explainability methods proposed so far provide a visual explanation in terms of an input saliency map. The aim of this work is to extend, implement and test instead an influence-based explainability algorithm, TracIn, proposed originally for classification tasks, in a challenging clinical problem, i.e., multiclass segmentation of tumor brains in multimodal Magnetic Resonance Imaging. We verify the faithfulness of the proposed algorithm linking the similarities of the latent representation of the network to the TracIn output. We further test the capacity of the algorithm to provide local and global explanations, and we suggest that it can be adopted as a tool to select the most relevant features used in the decision process. The method is generalizable for all semantic segmentation tasks where classes are mutually exclusive, which is the standard framework in these cases.
title Influence based explainability of brain tumors segmentation in multimodal Magnetic Resonance Imaging
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.12222