Lesion Search with Self-supervised Learning
This work addresses the need for efficient image analysis in medical diagnostics, though it appears incremental as it builds on existing methods like SimCLR.
The paper tackled the problem of accelerating clinicians' interpretation of medical images by developing a content-based image retrieval system using self-supervised learning, resulting in improved performance without manual annotations.
Content-based image retrieval (CBIR) with self-supervised learning (SSL) accelerates clinicians' interpretation of similar images without manual annotations. We develop a CBIR from the contrastive learning SimCLR and incorporate a generalized-mean (GeM) pooling followed by L2 normalization to classify lesion types and retrieve similar images before clinicians' analysis. Results have shown improved performance. We additionally build an open-source application for image analysis and retrieval. The application is easy to integrate, relieving manual efforts and suggesting the potential to support clinicians' everyday activities.