Masked Image Modeling Advances 3D Medical Image Analysis
Zekai Chen, Devansh Agarwal, K.K. Aggarwal, Wiem Safta, Mariann Micsinai Balan, Kevin M. Brown
Abstract
Recently, masked image modeling (MIM) has gained considerable attention due to its ability to learn from vast amounts of unlabeled data and has been demonstrated to be effective on various vision tasks involving natural images. Meanwhile, the potential of self-supervised learning in modeling 3D medical images is anticipated to be immense due to the high quantities of unlabeled images and the expense and difficulty of quality labels. However, MIM’s applicability to medical images remains uncertain. In this paper, we demonstrate that masked image modeling approaches can also advance 3D medical image analysis in addition to natural images. We study how masked image modeling strategies leverage performance from the viewpoints of 3D medical image segmentation as a representative downstream task: i) when compared to naive contrastive learning, masked image modeling approaches accelerate the convergence of supervised training even faster (1.40×) and ultimately produce a higher dice score; ii) predicting raw voxel values with a high masking ratio and a relatively smaller patch size is nontrivial self-supervised pretext-task for medical images modeling; iii) a lightweight decoder or projection head design for reconstruction is robust for masked image modeling on 3D medical images which speeds up training and reduce cost; iv) finally, we also investigate the effectiveness of MIM methods under different practical scenarios where different image resolutions and labeled data ratios are applied. Anonymized codes are available at https://github.com/ZEKAICHEN/MIM-Med3D.