Journal of Zhejiang University

Journal of Zhejiang University SCIENCE A 2026 Vol.27 No.3 P.288-305

Deep-learning-enabled automatic gene abnormality detection via fluorescence in situ hybridization

Author(s): Lemin SHI, Yuqiang ZHANG, Haoyu QI, Chengyue LU, Menglei HU, Mingye LI, Dianxin SONG, Hao ZHANG, Xin FENG, Ping GONG, Shan JIANG
Affiliation(s): 1. School of Computer Science and Technology, School of Life Science and Technology, Changchun University of Science and Technology, Changchun 130022, China more
Corresponding email(s): fengxin@cust.edu.cn, gp@cust.edu.cn, jiangshan@xidian.edu.cn
Key Words: Fluorescence in situ hybridization (FISH), Image enhancement, Nuclei segmentation, Fluorescence feature fusion, Abnormal gene classification

Share this article to： More

Lemin SHI, Yuqiang ZHANG, Haoyu QI, Chengyue LU, Menglei HU, Mingye LI, Dianxin SONG, Hao ZHANG, Xin FENG, Ping GONG, Shan JIANG. Deep-learning-enabled automatic gene abnormality detection via fluorescence in situ hybridization[J]. Journal of Zhejiang University Science A, 2026, 27(3): 288-305.

@article{title="Deep-learning-enabled automatic gene abnormality detection via fluorescence in situ hybridization",
author="Lemin SHI, Yuqiang ZHANG, Haoyu QI, Chengyue LU, Menglei HU, Mingye LI, Dianxin SONG, Hao ZHANG, Xin FENG, Ping GONG, Shan JIANG",
journal="Journal of Zhejiang University Science A",
volume="27",
number="3",
pages="288-305",
year="2026",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.A2500360"
}

%0 Journal Article
%T Deep-learning-enabled automatic gene abnormality detection via fluorescence in situ hybridization
%A Lemin SHI
%A Yuqiang ZHANG
%A Haoyu QI
%A Chengyue LU
%A Menglei HU
%A Mingye LI
%A Dianxin SONG
%A Hao ZHANG
%A Xin FENG
%A Ping GONG
%A Shan JIANG
%J Journal of Zhejiang University SCIENCE A
%V 27
%N 3
%P 288-305
%@ 1673-565X
%D 2026
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.A2500360

TY - JOUR
T1 - Deep-learning-enabled automatic gene abnormality detection via fluorescence in situ hybridization
A1 - Lemin SHI
A1 - Yuqiang ZHANG
A1 - Haoyu QI
A1 - Chengyue LU
A1 - Menglei HU
A1 - Mingye LI
A1 - Dianxin SONG
A1 - Hao ZHANG
A1 - Xin FENG
A1 - Ping GONG
A1 - Shan JIANG
J0 - Journal of Zhejiang University Science A
VL - 27
IS - 3
SP - 288
EP - 305
%@ 1673-565X
Y1 - 2026
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.A2500360

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: fluorescence in situ hybridization (FISH) is widely used for diagnosing cancer and genetic disorders due to its high specificity and accuracy. However, traditional methods face challenges such as suboptimal focus adjustments, subjective signal counting errors, and inefficiencies in imaging, limiting their use in high-throughput screening. To address these issues, we introduced the integrated FISH imaging and analysis system (FAST), an innovative solution that combines rapid filter switching, automated focusing, multilayer fluorescence signal fusion, and the improved ResNet152 deep learning framework. Compared with clinical manual counts and analysis of case reports of 10 patients with chronic lymphocytic leukemia (CLL), the FAST achieved an average nuclei segmentation accuracy of 98.28%. For abnormal gene detection, the model achieved an accuracy of 97.86%. Additionally, its intuitive interface allows the operator to complete the entire workflow—from scanning to report generation—within 45 min. FAST represents a significant advancement in cancer and genetic disorder diagnostics, offering a powerful tool for early detection.