FocalMix: Semi-Supervised Learning for 3D Medical Image Detection
This addresses the annotation bottleneck for medical imaging practitioners, offering a substantial performance gain with unlabeled data, though it is incremental as it applies existing SSL advances to a new domain.
The paper tackles the problem of costly annotation in medical imaging by proposing FocalMix, a semi-supervised learning method for 3D medical image detection, achieving up to 17.3% improvement over state-of-the-art supervised approaches on lung nodule detection datasets.
Applying artificial intelligence techniques in medical imaging is one of the most promising areas in medicine. However, most of the recent success in this area highly relies on large amounts of carefully annotated data, whereas annotating medical images is a costly process. In this paper, we propose a novel method, called FocalMix, which, to the best of our knowledge, is the first to leverage recent advances in semi-supervised learning (SSL) for 3D medical image detection. We conducted extensive experiments on two widely used datasets for lung nodule detection, LUNA16 and NLST. Results show that our proposed SSL methods can achieve a substantial improvement of up to 17.3% over state-of-the-art supervised learning approaches with 400 unlabeled CT scans.