Quantitative Imaging Principles Improves Medical Image Learning
This work addresses the challenge of enhancing medical image analysis for healthcare applications, though it appears incremental by building on existing self-supervised learning methods.
The authors tackled the problem of improving self-supervised learning for medical images by incorporating quantitative imaging principles, resulting in better starting states for downstream supervised training and images that validate on clinical analysis software.
Fundamental differences between natural and medical images have recently favored the use of self-supervised learning (SSL) over ImageNet transfer learning for medical image applications. Differences between image types are primarily due to the imaging modality and medical images utilize a wide range of physics based techniques while natural images are captured using only visible light. While many have demonstrated that SSL on medical images has resulted in better downstream task performance, our work suggests that more performance can be gained. The scientific principles which are used to acquire medical images are not often considered when constructing learning problems. For this reason, we propose incorporating quantitative imaging principles during generative SSL to improve image quality and quantitative biological accuracy. We show that this training schema results in better starting states for downstream supervised training on limited data. Our model also generates images that validate on clinical quantitative analysis software.