Multi-organ medical image segmentation method based on multi-feature fusion Swinin-Unet architecture

By using the CMFSA-UNet model based on the Swin-Unet architecture with multi-feature fusion, the problems of high computational complexity and unstable accuracy in multi-organ medical image segmentation are solved, achieving efficient and accurate multi-organ segmentation, which is suitable for real-time clinical scenarios.

CN121661347APending Publication Date: 2026-03-13南宁桂电电子科技研究院有限公司 +1
0 Cites 5 Cited by

Patent Information

Application Number
CN202511862264.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-11
Publication Date
2026-03-13

AI Technical Summary

Technical Problem

Existing multi-organ medical image segmentation technologies have high computational complexity when processing high-resolution 3D image data, making it difficult to meet real-time clinical needs. They also suffer from problems such as unstable segmentation accuracy, blurred boundaries, and missed segmentation of small organs.

Method used

The CMFSA-UNet model, based on the Swin-Unet architecture with multi-feature fusion, is adopted. Multi-scale feature extraction, fusion and enhancement are performed through the CNN-Swin Transformer dual-branch structure, MAFR module and skip connection layer (MFDF module), and high-precision multi-organ segmentation results are generated by combining deep supervision mechanism.

Benefits of technology

While reducing computational costs, it improves the efficiency and accuracy of multi-organ medical image segmentation, especially boundary accuracy and the integrity of small organs, adapting to the needs of scenarios where medical data is scarce.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a multi-organ medical image segmentation method based on a multi-feature fusion Swindow-Unet architecture, and belongs to the field of medical image processing. The core of the method is that CT and MRI images are input into a pre-trained CMFSA-UNet model for segmentation, and the model comprises an encoder, an MAFR module, an MFDF module, a decoder and a jump connection layer. CNN-Swin Transform double branches are adopted by the encoder, local details and long-range semantics are extracted, and Attention Gate reinforcement is carried out; the MAFR module widens a receptive field through double branches, combines an attention mechanism with residual connection, reduces the calculated amount and gives consideration to local and global features; and the MFDF module fuses multi-scale dense connection and frequency domain processing, so that feature loss is reduced. The decoder extracts features through Swin Transform Block, resolutions are recovered through 4 times of up-sampling, and the segmentation precision is optimized in combination with depth supervision and a mixed loss function. According to the method, local and long-range feature modeling is efficiently cooperated, precision and efficiency are balanced, segmentation global consistency, boundary accuracy and training stability are improved, the method is suitable for multi-modal multi-organ segmentation, and reliable support is provided for clinical diagnosis and the like.
Need to check novelty before this filing date? Find Prior Art