A method for segmenting gross tumor volume in lung cancer CT images

CN118691629BActive Publication Date: 2025-03-11江西省肿瘤医院(江西省第二人民医院 江西省癌症中心)
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202410892128.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-04
Publication Date
2025-03-11
Estimated Expiration
2044-07-04

Smart Images

  • Figure CN118691629B_ABST
    Figure CN118691629B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for segmenting the gross tumor volume in a lung cancer CT image, comprising the following steps: A. setting a region of interest extraction network and locating a target frame; B. cropping the region to be segmented according to the target frame, using an AU‑net model for fine segmentation, and remapping the result back to the original size after the segmentation is completed to ensure data consistency; the AU‑net model includes an encoder, a decoder, and an attention module. The present invention can improve the deficiencies of the prior art and improve segmentation accuracy.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Three-stage liver tumor image segmentation method based on adaptive preprocessing

    CN115018864A