Back

Light weight deep learning-based auto-quantification system for bright-filed HER2 dual in situ hybridization image analysis

Huang, C.-Y.; Lin, J.-R.; Huang, P.-C.; Liao, C.-H.; Yen, C.-C.; Chu, L.-A.

2025-07-28 pathology
10.1101/2025.07.27.25331550 medRxiv
Show abstract

The evaluation of erb-b2 receptor tyrosine kinase 2 (ERBB2 or HER2) gene amplification status through Dual in Situ Hybridization (DISH) currently relies on manual assessment by pathologists. There are several deep learning-based algorithms for H&E or ISH analysis. However, DISH analysis tools are still lacking. We developed a fully automated deep learning-based quantification system to assist pathologists in identifying the most relevant cells throughout the entire DISH image. In the comparison between pathologists and the auto-quantification system, the overall percentage agreement (OPA) by case was 88. 9% (80/90). These results demonstrate that each image, with a processing time of approximately 1 minute, achieves similar results compared to pathologists assessments, while the manual procedure will take 10-20 times longer to examine the same specimen. This approach offers a versatile system for bright-field HER2 DISH image analysis. The system provides faster, cheaper, standardized, and versatile diagnostic tools to aid pathologists in the HER2 DISH diagnostic process.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
Journal of Pathology Informatics
13 papers in training set
Top 0.1%
23.9%
2
PLOS ONE
4510 papers in training set
Top 16%
11.1%
3
Modern Pathology
21 papers in training set
Top 0.1%
7.6%
4
Laboratory Investigation
13 papers in training set
Top 0.1%
6.8%
5
The Journal of Molecular Diagnostics
36 papers in training set
Top 0.1%
6.7%
50% of probability mass above
6
Diagnostics
48 papers in training set
Top 0.2%
5.1%
7
Scientific Reports
3102 papers in training set
Top 21%
5.1%
8
Clinical Chemistry
22 papers in training set
Top 0.2%
2.2%
9
Cancers
200 papers in training set
Top 3%
1.6%
10
The American Journal of Pathology
31 papers in training set
Top 0.2%
1.6%
11
Nature Communications
4913 papers in training set
Top 54%
1.4%
12
Cureus
67 papers in training set
Top 3%
1.4%
13
Cells
232 papers in training set
Top 3%
1.3%
14
Journal of Clinical Pathology
12 papers in training set
Top 0.3%
1.3%
15
The Journal of Pathology
22 papers in training set
Top 0.3%
1.2%
16
Plant Methods
39 papers in training set
Top 0.6%
0.9%
17
eLife
5422 papers in training set
Top 52%
0.9%
18
BMC Cancer
52 papers in training set
Top 2%
0.9%
19
Heliyon
146 papers in training set
Top 6%
0.8%
20
Bioinformatics
1061 papers in training set
Top 9%
0.8%
21
Scientific Data
174 papers in training set
Top 2%
0.8%
22
IEEE Journal of Biomedical and Health Informatics
34 papers in training set
Top 2%
0.8%
23
Frontiers in Medicine
113 papers in training set
Top 7%
0.8%
24
Journal of Visualized Experiments
30 papers in training set
Top 0.7%
0.8%
25
Journal of Medical Internet Research
85 papers in training set
Top 5%
0.7%
26
Animals
20 papers in training set
Top 1%
0.7%
27
Biology Methods and Protocols
53 papers in training set
Top 3%
0.7%
28
Analytical Chemistry
205 papers in training set
Top 3%
0.7%
29
Journal of Clinical Microbiology
120 papers in training set
Top 2%
0.5%