JZUS - Journal of Zhejiang University SCIENCE

Journal of Zhejiang University SCIENCE A

Accepted manuscript available online (unedited version)

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

Author(s): Lemin SHI¹, Yuqiang ZHANG², Haoyu QI³, Chengyue LU⁴, Menglei HU⁵, Mingye LI⁶, Dianxin SONG¹, Hao ZHANG¹, Xin FENG¹, Ping GONG¹, Shan JIANG³
Affiliation(s): ¹School of Computer Science and Technology, School of Life Science and Technology, Changchun University of Science and Technology, Changchun 130022, China ²Modern Industrial College, Jilin Jianzhu University, Changchun 130118, China ³Hangzhou Institute of Technology, Xidian University, Hangzhou 311200, China ⁴Department of Electromechanical Engineering and Centre for Artificial Intelligence and Robotics, University of Macau, Macau 999078, China ⁵Department of Electrical and Computer Engineering, University of British Columbia, Vancouver V6T 1Z4, Canada ⁶School of Computing and Information Systems, University of Melbourne, Parkville, Victoria 3010, Australia
Corresponding email(s): Xin FENG, fengxin@cust.edu.cn Ping GONG, gp@cust.edu.cn Shan JIANG, jiangshan@xidian.edu.cn
Key Words: Fluorescence in situ hybridization (FISH); Image enhancement; Cell nucleus segmentation; Fluorescence feature fusion; Abnormal gene classification

Share this article to： More <<< Previous Paper \|Next Paper >>>

Lemin SHI¹, Yuqiang ZHANG², Haoyu QI³, Chengyue LU⁴, Menglei HU⁵, Mingye LI⁶, Dianxin SONG¹, Hao ZHANG¹, Xin FENG¹, Ping GONG¹, Shan JIANG³. Deep-learning-enabled automatic gene abnormality detection via fluorescence in situ hybridization (FISH)[J]. Journal of Zhejiang University Science A,in press.Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/jzus.A2500360

@article{title="Deep-learning-enabled automatic gene abnormality detection via fluorescence in situ hybridization (FISH)",
author="Lemin SHI¹, Yuqiang ZHANG², Haoyu QI³, Chengyue LU⁴, Menglei HU⁵, Mingye LI⁶, Dianxin SONG¹, Hao ZHANG¹, Xin FENG¹, Ping GONG¹, Shan JIANG³",
journal="Journal of Zhejiang University Science A",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/jzus.A2500360"
}

%0 Journal Article
%T Deep-learning-enabled automatic gene abnormality detection via fluorescence in situ hybridization (FISH)
%A Lemin SHI¹
%A Yuqiang ZHANG²
%A Haoyu QI³
%A Chengyue LU⁴
%A Menglei HU⁵
%A Mingye LI⁶
%A Dianxin SONG¹
%A Hao ZHANG¹
%A Xin FENG¹
%A Ping GONG¹
%A Shan JIANG³
%J Journal of Zhejiang University SCIENCE A
%P
%@ 1673-565X
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/jzus.A2500360"

TY - JOUR
T1 - Deep-learning-enabled automatic gene abnormality detection via fluorescence in situ hybridization (FISH)
A1 - Lemin SHI¹
A1 - Yuqiang ZHANG²
A1 - Haoyu QI³
A1 - Chengyue LU⁴
A1 - Menglei HU⁵
A1 - Mingye LI⁶
A1 - Dianxin SONG¹
A1 - Hao ZHANG¹
A1 - Xin FENG¹
A1 - Ping GONG¹
A1 - Shan JIANG³
J0 - Journal of Zhejiang University Science A
SP -
EP -
%@ 1673-565X
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/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 introduce the fluorescence in situ hybridization and analysis system (FAST), an innovative solution that combines rapid filter switching, automated focusing, multi-layer 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 system achieved an average cell segmentation accuracy of 98.28% with a 95% confidence interval (CI) of [97.43%, 99.13%]. For abnormal gene detection, the model achieved an accuracy of 97.86%, and the classification results showed a 95% CI of [97.54%, 98.17%]. Additionally, its intuitive interface allows the operator to complete the entire workflow-from scanning to report generation-within 45 minutes. FAST represents a significant advancement in cancer and genetic disorder diagnostics, offering a powerful tool for early detection.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference