Exploring Content Based Image Retrieval for Highly Imbalanced Melanoma Data using Style Transfer, Semantic Image Segmentation and Ensemble Learning
This work addresses the problem of improving image retrieval for medical diagnosis in dermatology, but it is incremental as it builds on existing CBIR techniques with specific adaptations for imbalanced data.
The paper tackled the challenge of building a content-based image retrieval (CBIR) system for highly imbalanced melanoma lesion images by proposing new similarity measures, including style loss and I1-Score, with the pure style loss approach achieving a remarkable accuracy increase over traditional methods like Euclidean Distance and Cosine Similarity.
Lesion images are frequently taken in open-set settings. Because of this, the image data generated is extremely varied in nature.It is difficult for a convolutional neural network to find proper features and generalise well, as a result content based image retrieval (CBIR) system for lesion images are difficult to build. This paper explores this domain and proposes multiple similarity measures which uses Style Loss and Dice Coefficient via a novel similarity measure called I1-Score. Out of the CBIR similarity measures proposed, pure style loss approach achieves a remarkable accuracy increase over traditional approaches like Euclidean Distance and Cosine Similarity. The I1-Scores using style loss performed better than traditional approaches by a small margin, whereas, I1-Scores with dice-coefficient faired very poorly. The model used is trained using ensemble learning for better generalization.