Deep Learning for Generating Computational PIN-4 Immunohistochemistry Staining from Prostate Biopsy H&E Images
2026-06-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a special dataset combining regular prostate tissue images (H&E stained) with matching images showing specific protein markers (PIN-4 stained) to help diagnose cancer. They trained an AI model to predict these protein marker patterns directly from the regular tissue images without needing extra staining. The AI showed good accuracy and kept important features that pathologists look for in diagnosis, though it was less accurate in very complex cancer areas. This method could help doctors see important protein information right on the usual tissue images, overcoming a common problem where these details are on separate slides.
Immunohistochemistry (IHC)Hematoxylin and eosin stain (H&E)PIN-4 stainingProstate cancer biopsyGenerative adversarial network (GAN)Patch-based image synthesisAMACRBasal cellsStructural similarity index measure (SSIM)Histopathology
Authors
Vietbao Tran, Pratik Shah
Abstract
Immunohistochemistry (IHC)is frequently used to resolve diagnostically ambiguous prostate cancer biopsy findings on hematoxylin and eosin (H&E)-stained tissue. However, PIN-4 IHC staining is typically performed on adjacent tissue sections, limiting direct spatial comparison between the H&E morphology and the corresponding immunophenotypic signal. A paired, registered H&E/PIN-4 dataset was constructed from routine clinical prostate biopsy whole-slide images (WSIs), and a conditional generative adversarial network (cGAN) was trained to synthesize PIN-4 staining patterns directly from native H&E image patches. The final dataset comprised 172 paired WSIs from 93 patients and 27,298 registered 1024x1024 patch pairs, spanning adenocarcinoma-positive and benign cases with representation across age, race, and ethnicity groups. The model was evaluated on a held-out test set of 1,814 patch pairs from 17 WSIs, achieving a mean peak signal-to-noise ratio (PSNR) of 21.88 dB, structural similarity index measure (SSIM) of 0.667, Pearson correlation coefficient (PCC) of 0.684, and learned perceptual image patch similarity (LPIPS) of 0.417. Qualitative review by a board-certified pathologist showed that generated images captured diagnostically relevant PIN-4 staining patterns, including AMACR/racemase expression and basal-cell-associated staining, while preserving spatial correspondence with the source H&E morphology. Accuracy of synthesis varied across morphologically complex regions, including high-grade carcinoma and intraductal carcinoma. These results support the feasibility of supervised PIN-4 synthesis from routinely acquired brightfield H&E prostate biopsy images. The approach enables direct interpretation of predicted PIN-4 marker patterns in the context of the source prostate H&E architecture, addressing a current spatial limitation of conventional adjacent-section IHC.