A convolutional neural network-based auto-segmentation pipeline for breast cancer imaging

Leow, L. J. H., Azam, A. B., Tan, H. Q., Nei, W. L., Cao, Q. , Huang, L., Xie, Y. and Cai, Y. (2024) A convolutional neural network-based auto-segmentation pipeline for breast cancer imaging. Mathematics, 12(4), 616. (doi: 10.3390/math12040616)

Abstract

Medical imaging is crucial for the detection and diagnosis of breast cancer. Artificial intelligence and computer vision have rapidly become popular in medical image analyses thanks to technological advancements. To improve the effectiveness and efficiency of medical diagnosis and treatment, significant efforts have been made in the literature on medical image processing, segmentation, volumetric analysis, and prediction. This paper is interested in the development of a prediction pipeline for breast cancer studies based on 3D computed tomography (CT) scans. Several algorithms were designed and integrated to classify the suitability of the CT slices. The selected slices from patients were then further processed in the pipeline. This was followed by data generalization and volume segmentation to reduce the computation complexity. The selected input data were fed into a 3D U-Net architecture in the pipeline for analysis and volumetric predictions of cancer tumors. Three types of U-Net models were designed and compared. The experimental results show that Model 1 of U-Net obtained the highest accuracy at 91.44% with the highest memory usage; Model 2 had the lowest memory usage with the lowest accuracy at 85.18%; and Model 3 achieved a balanced performance in accuracy and memory usage, which is a more suitable configuration for the developed pipeline.

• Item Type: Articles
• Additional Information: Funding: This project is supported by Duke-NUS Oncology Academic Program Goh Foundation Proton Research Program (08/FY2021/EX/12-A42), and the National Medical Research Council Fellowship (NMRC/MOH-000166-00).
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Cao, Dr Qi

Creator Roles

Cao, Q.: Writing – review and editing

• Authors: Leow, L. J. H., Azam, A. B., Tan, H. Q., Nei, W. L., Cao, Q., Huang, L., Xie, Y., and Cai, Y.
• College/School: College of Science and Engineering > School of Computing Science
• Journal Name: Mathematics
• Publisher: MDPI
• ISSN: 2227-7390
• ISSN (Online): 2227-7390
• Published Online: 19 February 2024
• Copyright Holders: Copyright © 2024 by the authors
• First Published: First published in Mathematics 12(4):616
• Publisher Policy: Reproduced under a Creative Commons license