What question did this study set out to answer?

This research aims to develop a fully automated framework for quantifying immunohistochemistry stains in breast cancer.

Fully Automated Stain Quantification Framework for IHC Whole Slide Images in Breast Cancer

View Full Paper

Ask AI

Bookmark

Authors

Automated quantification framework improves H-scoring in breast cancer, suggesting greater diagnostic reliability.

This research aims to develop a fully automated framework for quantifying immunohistochemistry stains in breast cancer.
Developed a three-module deep learning framework for tumor-stroma segmentation, nuclei segmentation, and H-score estimation.
Fine-tuned using 87 expert-annotated patches for accuracy in scoring.
Validated the framework internally and externally on 100 WSIs and HER2 classification.
Achieved a Spearman's rank correlation of 0.84 in internal validation, matching expert pathologist variability.
Demonstrated 86% accuracy in HER2 classification and a mean absolute error of 21 in CD73 scoring.

Yin et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Automated quantification framework improves H-scoring in breast cancer, suggesting greater diagnostic reliability.

This research aims to develop a fully automated framework for quantifying immunohistochemistry stains in breast cancer.
Developed a three-module deep learning framework for tumor-stroma segmentation, nuclei segmentation, and H-score estimation.
Fine-tuned using 87 expert-annotated patches for accuracy in scoring.
Validated the framework internally and externally on 100 WSIs and HER2 classification.
Achieved a Spearman's rank correlation of 0.84 in internal validation, matching expert pathologist variability.
Demonstrated 86% accuracy in HER2 classification and a mean absolute error of 21 in CD73 scoring.

Yin et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark