An Active Learning Approach for Reducing Annotation Cost in Skin Lesion Analysis
This work addresses the problem of reducing annotation costs for clinicians and researchers in medical imaging, specifically for skin cancer diagnosis, though it is incremental as it builds on existing active learning methods.
The paper tackles the high annotation cost in skin lesion analysis by proposing an active learning framework that selects fewer labeled samples based on informativeness and representativeness, achieving state-of-the-art performance on ISIC 2017 tasks using only up to 50% of samples, with accuracies comparable to full-data training.
Automated skin lesion analysis is very crucial in clinical practice, as skin cancer is among the most common human malignancy. Existing approaches with deep learning have achieved remarkable performance on this challenging task, however, heavily relying on large-scale labelled datasets. In this paper, we present a novel active learning framework for cost-effective skin lesion analysis. The goal is to effectively select and utilize much fewer labelled samples, while the network can still achieve state-of-the-art performance. Our sample selection criteria complementarily consider both informativeness and representativeness, derived from decoupled aspects of measuring model certainty and covering sample diversity. To make wise use of the selected samples, we further design a simple yet effective strategy to aggregate intra-class images in pixel space, as a new form of data augmentation. We validate our proposed method on data of ISIC 2017 Skin Lesion Classification Challenge for two tasks. Using only up to 50% of samples, our approach can achieve state-of-the-art performances on both tasks, which are comparable or exceeding the accuracies with full-data training, and outperform other well-known active learning methods by a large margin.