Deep learning for automated detection of breast cancer in deep ultraviolet fluorescence images with diffusion probabilistic model
This work addresses data scarcity for breast cancer detection in intraoperative margin assessment, but it is incremental as it applies existing methods to a specific medical imaging domain.
The paper tackled the problem of limited data for deep learning in medical imaging by using a diffusion probabilistic model to augment deep ultraviolet fluorescence images, resulting in improved breast cancer detection accuracy from 93% to 97%.
Data limitation is a significant challenge in applying deep learning to medical images. Recently, the diffusion probabilistic model (DPM) has shown the potential to generate high-quality images by converting Gaussian random noise into realistic images. In this paper, we apply the DPM to augment the deep ultraviolet fluorescence (DUV) image dataset with an aim to improve breast cancer classification for intraoperative margin assessment. For classification, we divide the whole surface DUV image into small patches and extract convolutional features for each patch by utilizing the pre-trained ResNet. Then, we feed them into an XGBoost classifier for patch-level decisions and then fuse them with a regional importance map computed by Grad-CAM++ for whole surface-level prediction. Our experimental results show that augmenting the training dataset with the DPM significantly improves breast cancer detection performance in DUV images, increasing accuracy from 93% to 97%, compared to using Affine transformations and ProGAN.