Learning to Segment Skin Lesions from Noisy Annotations
This work addresses the bottleneck of requiring expensive expert annotations for medical image segmentation, offering a solution that leverages cheap noisy data, which is incremental in improving training efficiency for this domain-specific task.
The paper tackles the problem of training medical image segmentation networks with noisy pixel-level annotations by proposing a spatially adaptive reweighting framework that uses a small set of clean expert annotations to assign higher importance to reliable pixels, resulting in improved robustness to annotation noise as demonstrated in experiments with varying noise levels.
Deep convolutional neural networks have driven substantial advancements in the automatic understanding of images. Requiring a large collection of images and their associated annotations is one of the main bottlenecks limiting the adoption of deep networks. In the task of medical image segmentation, requiring pixel-level semantic annotations performed by human experts exacerbate this difficulty. This paper proposes a new framework to train a fully convolutional segmentation network from a large set of cheap unreliable annotations and a small set of expert-level clean annotations. We propose a spatially adaptive reweighting approach to treat clean and noisy pixel-level annotations commensurately in the loss function. We deploy a meta-learning approach to assign higher importance to pixels whose loss gradient direction is closer to those of clean data. Our experiments on training the network using segmentation ground truth corrupted with different levels of annotation noise show how spatial reweighting improves the robustness of deep networks to noisy annotations.