Masked pretraining of U-Net for ultrasound image segmentation
Open Access
- 28 August 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-18
Abstract
Computer-aided segmentation of ultrasound images can assist less experienced sonographers in making a diagnosis or performing early screening for diseases in vast rural areas. U-Net is the mainstream method for ultrasound image segmentation, offering advantages of efficient feature extraction and context integration. However, existing U-Net-based segmentation methods can only yield modest performance due to the low quality of ultrasound imaging and the usually small amount of available labeled data. This research proposes a self-supervised pretraining method to promote the performance of U-Net-based models for ultrasound image segmentation, when limited labeled images but numerous relevant unlabeled ones are available, which is a common situation in ultrasonography scenarios such as rare disease detection. By randomly masking out part of pixels in the input ultrasound image, the U-Net based model is pretrained to predict the unknown content, to adapt the model to the current fitting scenario before the formal training. A lightweight but effective variant of U-Net named MS-UNet is also proposed to better fit the scenario of ultrasound image segmentation. Experimental results show that the masked pretraining can boost the segmentation performance of U-Net models on small-size ultrasound image datasets, with Dice score improvements of 6-20 percentage points across four datasets under minimal labeled data conditions. Furthermore, our proposed MS-UNet achieves a relatively high segmentation accuracy while reducing computational complexity by 80.3% in FLOPs and 53.2% in parameters compared to the standard U-Net.Keywords
Funding Information
- Key Research Project of Sichuan Provincial Science and Technology Department (2021YFS0381)
- Chengdu Municipal Science and Technology Program (2024YF0501871SN)
This publication has 46 references indexed in Scilit:
- A Systematic Survey on Segmentation Algorithms for Musculoskeletal Tissues in Ultrasound ImagingArchives of Computational Methods in Engineering, 2024
- Self-supervised Pre-training for Nuclei Segmentation2022
- DDU-Net: A dual dense U-structure network for medical image segmentationApplied Soft Computing, 2022
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- Deep-Stacked Auto Encoder for Liver Segmentation2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- A comparison of the Accuracy of Ultrasound and Computed Tomography in common diagnoses causing acute abdominal painEuropean Radiology, 2011
- Comparison between ultrasound and magnetic resonance imaging in assessment of fetal cytomegalovirus infectionPrenatal Diagnosis, 2008
- Ultrasound and magnetic resonance imaging in Crohn's disease: a comparisonEuropean Radiology, 2001