Local Contrastive Learning for Medical Image Recognition
This work addresses the need for interpretable and accurate medical image recognition for radiologists, though it appears incremental as it builds on existing self-supervised frameworks.
The paper tackled the problem of distinguishing subtle differences between pathologies in medical images and providing interpretability between image regions and text, proposing Local Region Contrastive Learning (LRCLR) which improved zero-shot performance on several chest x-ray findings.
The proliferation of Deep Learning (DL)-based methods for radiographic image analysis has created a great demand for expert-labeled radiology data. Recent self-supervised frameworks have alleviated the need for expert labeling by obtaining supervision from associated radiology reports. These frameworks, however, struggle to distinguish the subtle differences between different pathologies in medical images. Additionally, many of them do not provide interpretation between image regions and text, making it difficult for radiologists to assess model predictions. In this work, we propose Local Region Contrastive Learning (LRCLR), a flexible fine-tuning framework that adds layers for significant image region selection as well as cross-modality interaction. Our results on an external validation set of chest x-rays suggest that LRCLR identifies significant local image regions and provides meaningful interpretation against radiology text while improving zero-shot performance on several chest x-ray medical findings.