Utilizing Brain Region Volume Estimations to Enhance Interpretability of Decision Trees for Alzheimer's Disease Classification

Le Sang, Isack Farady, Chia Chen Kuo, Po Chiang Lin, Chih Yang Lin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

While numerous artificial intelligence (AI) models based on deep learning have been proposed for diagnosing Alzheimer's disease from MRI images, their lack of explainability remains a challenge. In this study, we introduce an alternative transparent model using decision trees and propose a novel method for producing explainable predictions. Our approach involves processing MRI data by considering the percentage of brain regions as input to the decision tree, rather than traditional volumetric data. The resulting self-explanatory decision tree model transforms its binary tree graph into a rule-path shape, facilitating easy tracing of the generated tree's path. Our study demonstrates that the accuracy of decision trees can reach 97% using a region-percentage approach, which is an increase from the 71% accuracy obtained with the conventional volumetric approach.

Original languageEnglish
Title of host publication11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages311-312
Number of pages2
ISBN (Electronic)9798350386844
DOIs
StatePublished - 2024
Event11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024 - Taichung, Taiwan
Duration: 9 Jul 202411 Jul 2024

Publication series

Name11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024

Conference

Conference11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024
Country/TerritoryTaiwan
CityTaichung
Period9/07/2411/07/24

Keywords

  • Alzheimer's disease
  • brain volume region
  • decision tree
  • self-explanatory

Fingerprint

Dive into the research topics of 'Utilizing Brain Region Volume Estimations to Enhance Interpretability of Decision Trees for Alzheimer's Disease Classification'. Together they form a unique fingerprint.

Cite this