MS-UNet: Multi-Scale Nested UNet for Medical Image Segmentation with Few Training Data Based on an ELoss and Adaptive Denoising Method
Open Access
- 26 September 2024
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 12 (19) , 2996
Abstract
Traditional U-shape segmentation models can achieve excellent performance with an elegant structure. However, the single-layer decoder structure of U-Net or SwinUnet is too “thin” to exploit enough information, resulting in large semantic differences between the encoder and decoder parts. Things get worse in the field of medical image processing, where annotated data are more difficult to obtain than other tasks. Based on this observation, we propose a U-like model named MS-UNet with a plug-and-play adaptive denoising module and ELoss for the medical image segmentation task in this study. Instead of the single-layer U-Net decoder structure used in Swin-UNet and TransUNet, we specifically designed a multi-scale nested decoder based on the Swin Transformer for U-Net. The proposed multi-scale nested decoder structure allows for the feature mapping between the decoder and encoder to be semantically closer, thus enabling the network to learn more detailed features. In addition, ELoss could improve the attention of the model to the segmentation edges, and the plug-and-play adaptive denoising module could prevent the model from learning the wrong features without losing detailed information. The experimental results show that MS-UNet could effectively improve network performance with more efficient feature learning capability and exhibit more advanced performance, especially in the extreme case with a small amount of training data. Furthermore, the proposed ELoss and denoising module not only significantly enhance the segmentation performance of MS-UNet but can also be applied individually to other models.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFF0606303, 62206054, 2022ZDJS028)
- National Natural Science Foundation of China (2022YFF0606303, 62206054, 2022ZDJS028)
- Research Capacity Enhancement Project of Key Construction Discipline in Guangdong Province (2022YFF0606303, 62206054, 2022ZDJS028)
This publication has 32 references indexed in Scilit:
- A Systematic Collection of Medical Image Datasets for Deep LearningACM Computing Surveys, 2023
- Transformers in medical imaging: A surveyMedical Image Analysis, 2023
- DS-TransUNet: Dual Swin Transformer U-Net for Medical Image SegmentationIEEE Transactions on Instrumentation and Measurement, 2022
- DE-Net: A deep edge network with boundary information for automatic skin lesion segmentationNeurocomputing, 2022
- A Survey of Learning Causality with DataACM Computing Surveys, 2020
- Image denoising review: From classical to state-of-the-art approachesInformation Fusion, 2020
- Using Channel-Wise Attention for Deep CNN Based Real-Time Semantic Segmentation With Class-Aware Edge InformationIEEE Transactions on Intelligent Transportation Systems, 2020
- Brief review of image denoising techniquesVisual Computing for Industry, Biomedicine, and Art, 2019
- Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?IEEE Transactions on Medical Imaging, 2018
- Development of a Digital Image Database for Chest Radiographs With and Without a Lung NoduleAmerican Journal of Roentgenology, 2000