Progressive expansion: Cost-efficient medical image analysis model with reversed once-for-all network training paradigm

Lim, Shin Wei and Chan, Chee Seng and Faizal, Erma Rahayu Mohd and Ewe, Kok Howg (2024) Progressive expansion: Cost-efficient medical image analysis model with reversed once-for-all network training paradigm. Neurocomputing, 581. p. 127512. ISSN 0925-2312, DOI https://doi.org/10.1016/j.neucom.2024.127512.

Full text not available from this repository.
Official URL: https://doi.org/10.1016/j.neucom.2024.127512

Abstract

Low computational cost artificial intelligence (AI) models are vital in promoting the accessibility of real-time medical services in underdeveloped areas. The recent Once -For -All (OFA) network (without retraining) can directly produce a set of sub -network designs with Progressive Shrinking (PS) algorithm; however, the training resource and time inefficiency downfalls are apparent in this method. In this paper, we propose a new OFA training algorithm, namely the Progressive Expansion (ProX) to train the medical image analysis model. It is a reversed paradigm to PS, where technically we train the OFA network from the minimum configuration and gradually expand the training to support larger configurations. Empirical results showed that the proposed paradigm could reduce training time up to 68%; while still being able to produce sub -networks that have either similar or better accuracy compared to those trained with OFA-PS on ROCT (classification), BRATS and Hippocampus (3D -segmentation) public medical datasets. The code implementation for this paper is accessible at: https://github.com/shin-wl/ProX-OFA.

Item Type: Article
Funders: MyIndustry AI Scholarship Programme - Intel Corporation, Malaysia, Universiti Malaya, Malaysia, Malaysia Digital Economy Corporation (MDEC)
Uncontrolled Keywords: Medical image analysis; Machine learning; Model optimization; Cost-effective model
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Computer Science & Information Technology
Depositing User: Ms. Juhaida Abd Rahim
Date Deposited: 22 Oct 2024 06:01
Last Modified: 22 Oct 2024 06:01
URI: http://eprints.um.edu.my/id/eprint/45457

Actions (login required)

View Item View Item