Modality-bridge Transfer Learning for Medical Image Classification
This addresses the challenge of limited labeled data for medical image analysis, particularly in domains like X-ray imaging, though it is an incremental improvement over existing transfer learning methods.
The paper tackles the problem of insufficient labeled data in medical image classification by proposing a modality-bridge transfer learning method that uses a bridge database to mitigate domain differences between source and target images, achieving high classification performance with small labeled target datasets compared to other transfer learning approaches.
This paper presents a new approach of transfer learning-based medical image classification to mitigate insufficient labeled data problem in medical domain. Instead of direct transfer learning from source to small number of labeled target data, we propose a modality-bridge transfer learning which employs the bridge database in the same medical imaging acquisition modality as target database. By learning the projection function from source to bridge and from bridge to target, the domain difference between source (e.g., natural images) and target (e.g., X-ray images) can be mitigated. Experimental results show that the proposed method can achieve a high classification performance even for a small number of labeled target medical images, compared to various transfer learning approaches.