Self-learned representation-guided latent diffusion model for breast cancer classification in deep ultraviolet whole surface images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Afshin, Pouya, Helminiak, David, Niu, Tianling, Jorns, Julie M., Yen, Tina, Yu, Bing, Ye, Dong Hye
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908784816816128
author Afshin, Pouya
Helminiak, David
Niu, Tianling
Jorns, Julie M.
Yen, Tina
Yu, Bing
Ye, Dong Hye
author_facet Afshin, Pouya
Helminiak, David
Niu, Tianling
Jorns, Julie M.
Yen, Tina
Yu, Bing
Ye, Dong Hye
contents Breast-Conserving Surgery (BCS) requires precise intraoperative margin assessment to preserve healthy tissue. Deep Ultraviolet Fluorescence Scanning Microscopy (DUV-FSM) offers rapid, high-resolution surface imaging for this purpose; however, the scarcity of annotated DUV data hinders the training of robust deep learning models. To address this, we propose an Self-Supervised Learning (SSL)-guided Latent Diffusion Model (LDM) to generate high-quality synthetic training patches. By guiding the LDM with embeddings from a fine-tuned DINO teacher, we inject rich semantic details of cellular structures into the synthetic data. We combine real and synthetic patches to fine-tune a Vision Transformer (ViT), utilizing patch prediction aggregation for WSI-level classification. Experiments using 5-fold cross-validation demonstrate that our method achieves 96.47 % accuracy and reduces the FID score to 45.72, significantly outperforming class-conditioned baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2601_10917
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Self-learned representation-guided latent diffusion model for breast cancer classification in deep ultraviolet whole surface images
Afshin, Pouya
Helminiak, David
Niu, Tianling
Jorns, Julie M.
Yen, Tina
Yu, Bing
Ye, Dong Hye
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Breast-Conserving Surgery (BCS) requires precise intraoperative margin assessment to preserve healthy tissue. Deep Ultraviolet Fluorescence Scanning Microscopy (DUV-FSM) offers rapid, high-resolution surface imaging for this purpose; however, the scarcity of annotated DUV data hinders the training of robust deep learning models. To address this, we propose an Self-Supervised Learning (SSL)-guided Latent Diffusion Model (LDM) to generate high-quality synthetic training patches. By guiding the LDM with embeddings from a fine-tuned DINO teacher, we inject rich semantic details of cellular structures into the synthetic data. We combine real and synthetic patches to fine-tune a Vision Transformer (ViT), utilizing patch prediction aggregation for WSI-level classification. Experiments using 5-fold cross-validation demonstrate that our method achieves 96.47 % accuracy and reduces the FID score to 45.72, significantly outperforming class-conditioned baselines.
title Self-learned representation-guided latent diffusion model for breast cancer classification in deep ultraviolet whole surface images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2601.10917