SISE-PC: Semi-supervised Image Subsampling for Explainable Pathology
This reduces training costs for automated pathology classification, particularly in medical imaging, though it is incremental as it builds on existing contrastive learning and active learning methods.
The paper tackles the high data and compute costs of deep learning in pathology classification by proposing a semi-supervised active learning framework that identifies a minimal subset (up to 2%) of uncertain OCT images for labeling, achieving up to 97% classification accuracy after fine-tuning.
Although automated pathology classification using deep learning (DL) has proved to be predictively efficient, DL methods are found to be data and compute cost intensive. In this work, we aim to reduce DL training costs by pre-training a Resnet feature extractor using SimCLR contrastive loss for latent encoding of OCT images. We propose a novel active learning framework that identifies a minimal sub-sampled dataset containing the most uncertain OCT image samples using label propagation on the SimCLR latent encodings. The pre-trained Resnet model is then fine-tuned with the labelled minimal sub-sampled data and the underlying pathological sites are visually explained. Our framework identifies upto 2% of OCT images to be most uncertain that need prioritized specialist attention and that can fine-tune a Resnet model to achieve upto 97% classification accuracy. The proposed method can be extended to other medical images to minimize prediction costs.