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 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.