Deep Learning Based Automated HER2 Score Prediction Using Immunohistochemistry Histopathological Images: A Dual-Center Study

Background HER2 is a critical prognostic biomarker in breast cancer and associated with aggressive tumor biology. Current IHC scoring is subjective and labor-intensive. Deep learning has demonstrated success in histopathological image analysis, yet HER2 IHC automation remains underexplored. External-center validation is essential to establish clinical credibility and demonstrate robustness across diverse institutional practices and imaging protocols. Methods This dual-center retrospective study analyzed 135 HER2 IHC whole-slide images from 118 breast cancer patients labeled as 1+, 2+, or 3+ by standard clinical criteria. Two board-certified pathologists manually annotated tumor-enriched ROIs, which were tiled into non-overlapping 512x512 patches; tiles with >60% white background was excluded. Patches were harmonized using a modified Macenko color normalization and augmented during training. Six pretrained deep learning models (AlexNet, VGG16, ResNet34, DenseNet121, Inception, Swin Transformer) were trained with patient-level splits and evaluated on an independent test set using macro-averaged AUC and complementary metrics. Results The cohort included 118 patients with comparable age and largely similar baseline imaging/pathologic characteristics across groups, although clinical symptoms and lymph node status differed. On the independent test set, all models showed good discrimination for three-class HER2 grading, with AlexNet performing best (macro-AUC 0.971), followed by VGG16 (0.967). For AlexNet, per-class AUCs were 0.980 (1+), 0.955 (2+), and 0.979 (3+); most errors occurred between adjacent grades (1+/2+, 2+/3+). Grad-CAM highlighted strongly stained tumor regions driving predictions. Conclusion A dual-center deep learning framework enabled accurate automated three-class HER2 IHC grading from tumor-enriched WSI patches. This approach may assist pathologists by improving scoring consistency and flagging equivocal cases for reflex FISH.