Citation

Hasan, Md Jahid and Wan Ahmad, Wan Siti Halimatul Munirah and Ahmad Fauzi, Mohammad Faizal and Lee, Jenny Tung Hiong and Khor, See Yee and Looi, Lai Meng and Abas, Fazly Salleh (2023) Real-Time Segmentation of IHC Images From Microscope Using Deep Learning Architecture. In: 2023 IEEE 2nd National Biomedical Engineering Conference (NBEC), 05-07 September 2023, Melaka, Malaysia.

Text 34.pdf - Published Version Restricted to Repository staff only Download (7MB)

Abstract

Segmentation of nuclei in digital histopathology image analysis plays a critical role in the early assessment of breast cancer and may enable patients to get appropriate treatment. In this paper, we create a real-time application that thoroughly examines the effectiveness of various deep learning models, including U-Net, SegNet, ResNet50-Unet, and ResNet50- SegNet, in the domain of real-time segmentation. For real-time implementation, we use an industrial machine vision camera mounted to the microscope, stream the image from the microscope glass slide and segment it using the model. This experiment aims to identify the best deep-learning model for real-time segmentation of nuclei for immunohistochemistry (IHC)-stained glass slides. The models are evaluated in offline mode using test images from estrogen receptor IHC stains, taken from whole-slide images. The effectiveness of the model for real-time work is based on its segmentation computational time. For offline evaluation, the highest F1-score and Jaccard index is achieved by ResNet50- SegNet (85.21%) and ResNet50-Unet (0.725) accordingly. These findings support the proof of concept that deep learning models can effectively segment nuclei in real-time from IHC-stained glass slides. This research serves as a foundation for the future construction of fast and efficient deep learning models for realtime histopathological analysis directly from the microscope

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Breast cancer, deep learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics R Medicine > RC Internal medicine
Divisions:	Faculty of Engineering (FOE)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	22 Feb 2024 06:57
Last Modified:	22 Feb 2024 06:57
URII:	http://shdl.mmu.edu.my/id/eprint/12113

Downloads

Edit (login required)