Methods, systems, and devices for multi-organ segmentation in medical images based on frequency domain sensing

By constructing a U-shaped network that integrates frequency domain awareness, combining PVT and TAF modules to extract spatial and frequency domain features, and introducing an SRA module in the decoder for relative position encoding, the problem of insufficient accuracy in multi-organ segmentation is solved, and accurate segmentation of multi-organ medical images is achieved.

CN117409202BActive Publication Date: 2026-05-26ANHUI UNIV
2 Cites 0 Cited by

Patent Information

Application Number
CN202311454320.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-03
Publication Date
2026-05-26
Estimated Expiration
2043-11-03

AI Technical Summary

Technical Problem

Existing medical image segmentation technologies lack accuracy in multi-organ segmentation scenarios, especially when organ boundary textures are difficult to distinguish and individual physiological differences lead to frequent missegmentation and omissions.

Method used

A multi-organ segmentation method integrating frequency domain perception is adopted. By constructing a U-shaped network, combining PVT and TAF modules to extract spatial and frequency domain features, and introducing an SRA module in the decoder for relative position encoding and attention calculation, the accuracy of image segmentation is enhanced.

Benefits of technology

It achieves accurate segmentation of multi-organ medical images, overcoming the problems of difficulty in distinguishing organ boundary textures and the influence of individual differences in existing technologies, and improves segmentation accuracy.

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

Abstract

This invention belongs to the field of medical detection, specifically relating to a method, system, and device for multi-organ segmentation in medical images using frequency domain perception. The invention designs a U-shaped network with PVT modules as the initial backbone. The encoder in the U-shaped network uses a four-layer PVT module for downsampling, and the decoder uses a four-layer PE module for upsampling. In addition to the four-layer PVT module branches in the encoder, a feature fusion branch consisting of a five-layer TAF module is added. The TAF module is used to extract frequency domain features and fuse them with spatial features. A three-layer SRA module is added to the decoder. The SRA module adds relative position encoding to the upsampling results between adjacent PE modules, and then uses two layers of attention to calculate refined features. Finally, the newly designed network model is trained using multi-organ medical image samples to obtain a high-precision multi-organ segmentation model. This invention solves the problem of insufficient accuracy of existing image segmentation techniques in multi-organ segmentation scenarios.
Need to check novelty before this filing date? Find Prior Art