Self-learned representation-guided latent diffusion model for breast cancer classification in deep ultraviolet whole surface images
This addresses the need for precise intraoperative margin assessment in breast-conserving surgery, though it is incremental as it builds on existing latent diffusion and self-supervised learning methods.
The paper tackles the problem of training robust deep learning models for breast cancer classification from deep ultraviolet whole surface images when annotated data is scarce, by proposing a self-supervised learning-guided latent diffusion model to generate synthetic training patches, achieving 96.47% accuracy and reducing the FID score to 45.72.
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.