Self-Supervised ImageNet Representations for In Vivo Confocal Microscopy: Tortuosity Grading without Segmentation Maps
This provides a more efficient method for medical professionals to diagnose diseases via corneal nerve analysis, though it is incremental as it adapts an existing model to a new domain.
The paper tackled the problem of grading corneal nerve fiber tortuosity for disease diagnosis by demonstrating that self-supervised ImageNet-pretrained DINO features can be transferred to in vivo confocal microscopy, achieving 84.25% accuracy and 77.97% sensitivity without requiring expensive segmentation maps.
The tortuosity of corneal nerve fibers are used as indication for different diseases. Current state-of-the-art methods for grading the tortuosity heavily rely on expensive segmentation maps of these nerve fibers. In this paper, we demonstrate that self-supervised pretrained features from ImageNet are transferable to the domain of in vivo confocal microscopy. We show that DINO should not be disregarded as a deep learning model for medical imaging, although it was superseded by two later versions. After careful fine-tuning, DINO improves upon the state-of-the-art in terms of accuracy (84,25%) and sensitivity (77,97%). Our fine-tuned model focuses on the key morphological elements in grading without the use of segmentation maps.