English

Learning to segment with limited annotations: Self-supervised pretraining with regression and contrastive loss in MRI

Computer Vision and Pattern Recognition 2022-05-27 v1 Artificial Intelligence Machine Learning Image and Video Processing

Abstract

Obtaining manual annotations for large datasets for supervised training of deep learning (DL) models is challenging. The availability of large unlabeled datasets compared to labeled ones motivate the use of self-supervised pretraining to initialize DL models for subsequent segmentation tasks. In this work, we consider two pre-training approaches for driving a DL model to learn different representations using: a) regression loss that exploits spatial dependencies within an image and b) contrastive loss that exploits semantic similarity between pairs of images. The effect of pretraining techniques is evaluated in two downstream segmentation applications using Magnetic Resonance (MR) images: a) liver segmentation in abdominal T2-weighted MR images and b) prostate segmentation in T2-weighted MR images of the prostate. We observed that DL models pretrained using self-supervision can be finetuned for comparable performance with fewer labeled datasets. Additionally, we also observed that initializing the DL model using contrastive loss based pretraining performed better than the regression loss.

Keywords

Cite

@article{arxiv.2205.13109,
  title  = {Learning to segment with limited annotations: Self-supervised pretraining with regression and contrastive loss in MRI},
  author = {Lavanya Umapathy and Zhiyang Fu and Rohit Philip and Diego Martin and Maria Altbach and Ali Bilgin},
  journal= {arXiv preprint arXiv:2205.13109},
  year   = {2022}
}

Comments

Presented at the Annual Conference of International Society for Magnetic Resonance in Medicine, London, UK. May 2022

R2 v1 2026-06-24T11:29:06.396Z