M3-Net: A Multi-Scale Nuclei Segmentation Model for Breast Cancer Histopathology Using Contextual Patches and Attention Mechanism

Citation

Sufyan, Arbab and Fauzi, Mohammad Faizal Ahmad and Kuan, Wong Lai (2025) M3-Net: A Multi-Scale Nuclei Segmentation Model for Breast Cancer Histopathology Using Contextual Patches and Attention Mechanism. In: 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI), 14-17 April 2025, Houston, TX, USA.

[img] Text
1.pdf - Published Version
Restricted to Repository staff only

Download (7MB)

Abstract

Histopathological analysis, particularly of nuclear morphology, is critical for identifying malignancies. Accurate nuclei segmentation plays a pivotal role in this process, as it enables detailed assessment of nuclear size, shape, and distribution patterns. Traditional segmentation methods, however, often fail to capture fine details, lack broader context, and struggle with overlapping nuclei of varying sizes and shapes, especially when relying on single-scale approaches. To address these challenges, we propose a multi-scale context-based encoder-decoder model named M3-Net (Multi-Scale, Multi-Level, Multi-Stream Network) that integrates both global and local tissue features. Evaluations demonstrate that M3-Net effectively segments overlapping nuclei and diverse structures, providing a robust solution for automated nuclei segmentation in breast cancer pathology.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Histopathology, Multi-Scale, Nuclei Segmentation, Breast Cance
Subjects: R Medicine > RG Gynecology and obstetrics > RG491 Diseases of the Breast
Divisions: Faculty of Engineering (FOE)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 30 Jun 2025 06:41
Last Modified: 30 Jun 2025 06:41
URII: http://shdl.mmu.edu.my/id/eprint/14172

Downloads

Downloads per month over past year

View ItemEdit (login required)