Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classification
This addresses the challenge of noisy labels in medical image analysis, which is crucial for improving diagnostic tools, but it is incremental as it builds on existing methods for robust learning.
The paper tackles the problem of training deep neural networks on medical images with noisy labels, which is critical due to the need for expert annotations, and proposes an iterative learning framework that achieved promising results on skin lesion classification.
Deep neural networks (DNNs) have achieved great success in a wide variety of medical image analysis tasks. However, these achievements indispensably rely on the accurately-annotated datasets. If with the noisy-labeled images, the training procedure will immediately encounter difficulties, leading to a suboptimal classifier. This problem is even more crucial in the medical field, given that the annotation quality requires great expertise. In this paper, we propose an effective iterative learning framework for noisy-labeled medical image classification, to combat the lacking of high quality annotated medical data. Specifically, an online uncertainty sample mining method is proposed to eliminate the disturbance from noisy-labeled images. Next, we design a sample re-weighting strategy to preserve the usefulness of correctly-labeled hard samples. Our proposed method is validated on skin lesion classification task, and achieved very promising results.