MAE-Based Self-Supervised Pretraining for Data-Efficient Medical Image Segmentation Using nnFormer

TL;DR

This paper introduces a self-supervised pretraining method based on Masked Autoencoders for nnFormer, significantly improving data efficiency and segmentation performance in medical imaging with limited labeled data.

Contribution

It advances nnFormer's training by integrating MAE-based self-supervised pretraining, enabling better use of unlabeled data for medical image segmentation.

Findings

Higher Dice scores in segmentation tasks

Faster convergence during fine-tuning

Improved generalization with limited labeled data

Abstract

Transformer architectures, including nnFormer,have demonstrated promising results in volumetric medical image segmentation by being able to capture long-range spatial interactions. Although they have high performance, these models need large quantities of labeled training data and are also likely to overfit and become training unstable. This is a serious practical problem because it is not only time-consuming but also expensive to obtain medical images that are annotated by experts. Moreover, fully supervised traditional training pipelines do not take advantage of the available large amounts of unlabeled medical imaging data that can be easily obtained in the clinics. We have solved these drawbacks by advancing the efficiency of the nnFormer with a self-supervised pretraining framework, which is based on the Masked Autoencoders (MAE). In this method, the model is pretrained on unlabeled volumetric medical images to reconstruct randomly masked parts of the input. This allows the encoder to learn meaningful anatomical and structural representations . The encoder is then further fine-tuned on a labeled dataset on the downstream segmentation task. Conducted Experiment shows that the offered method leads to a higher segmentation performance on the count of Dice score, a quicker convergence rate on the course of the fine-tuning procedure, and a superior generalization on the basis of limited labeled data . These findings validate that self-supervised learning combined with transformer-based segmentation models is an appropriate approach to the problem of data shortage in medical image analysis.