Skin Lesion Phenotyping via Nested Multi-modal Contrastive Learning
This addresses skin cancer diagnosis for clinicians by integrating multiple data modalities, though it appears incremental as it builds on existing contrastive learning methods.
The paper tackles the challenge of melanoma detection and skin lesion classification by introducing SLIMP, a pre-training strategy that uses nested contrastive learning to combine skin lesion images with patient metadata, improving performance on downstream classification tasks.
We introduce SLIMP (Skin Lesion Image-Metadata Pre-training) for learning rich representations of skin lesions through a novel nested contrastive learning approach that captures complex relationships between images and metadata. Melanoma detection and skin lesion classification based solely on images, pose significant challenges due to large variations in imaging conditions (lighting, color, resolution, distance, etc.) and lack of clinical and phenotypical context. Clinicians typically follow a holistic approach for assessing the risk level of the patient and for deciding which lesions may be malignant and need to be excised, by considering the patient's medical history as well as the appearance of other lesions of the patient. Inspired by this, SLIMP combines the appearance and the metadata of individual skin lesions with patient-level metadata relating to their medical record and other clinically relevant information. By fully exploiting all available data modalities throughout the learning process, the proposed pre-training strategy improves performance compared to other pre-training strategies on downstream skin lesions classification tasks highlighting the learned representations quality.