Title: Multi-resolution dual-encoder self-constrained brain tumour MR image segmentation algorithm

Authors: Weijie Hao; Wenyin Zhang; Yong Wu; Yifang Wang; Yuan Qi; Liang Wu; Ji Chen

Addresses: Linyi University, Linyi, 276000, Shandong, China ' Linyi University, Linyi, 276000, Shandong, China ' Linyi University, Linyi, 276000, Shandong, China ' Linyi University, Linyi, 276000, Shandong, China ' Linyi University, Linyi, 276000, Shandong, China ' Shandong University, Jinan, 250000, Shandong, China ' Linyi University, Linyi, 276000, Shandong, China

Abstract: Efficient segmentation of magnetic resonance (MR) brain tumour images is of the utmost implication for the assessment of the condition. Brain tumours proliferate, metastasize quickly, and easily infiltrate surrounding tissues, and there will be magnetic fields, imaging equipment, and patient movements that affect imaging quality during the imaging process. Therefore, automatic brain tumour MR image segmentation has always been among the most challenging scientific research problems. This paper proposes a multi-resolution dual-encoder self-constrained brain tumour MR image segmentation algorithm that can effectively segment the brain tumour lesion area and normal brain tissue. Experiments show that the dice indexes of brain tumour, cerebrospinal fluid, gray matter, and white matter obtained by this algorithm are: 0.91, 0.78, 0.82, and 0.86, respectively. By comparison, the proposed method demonstrates better efficiency and accuracy and has important implications for brain tumour segmentation.

Keywords: medical image segmentation; brain tumour MR image; multiple resolution dual encoder; CSAM attention decoder; self-constrained network.

DOI: 10.1504/IJBET.2023.135399

International Journal of Biomedical Engineering and Technology, 2023 Vol.43 No.4, pp.390 - 403

Received: 23 Sep 2022
Accepted: 30 Jan 2023
Published online: 08 Dec 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article