A method and system for tumor detection and identification based on MRI images

By constructing a gradient direction stability matrix and a morphological consistency matrix of multiple sequence MRI images, artifact interference is automatically eliminated and structural continuity features are dynamically captured. This solves the problem of false detection and false negative detection in traditional tumor detection and identification methods under complex backgrounds, and achieves high-precision tumor lesion identification.

CN122089736AActive Publication Date: 2026-05-26SICHUAN LILAISI NUO BIOTECHNOLOGY CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SICHUAN LILAISI NUO BIOTECHNOLOGY CO LTD
Filing Date
2026-04-24
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Traditional tumor detection and identification methods rely on manually set grayscale thresholds or empirical texture features, which are difficult to cope with signal fluctuations in complex tissue backgrounds, leading to false positives and false negatives, and failing to meet the needs of precise diagnosis.

Method used

By constructing a gradient direction stability matrix, contour boundary analysis, and a dynamic boundary framework, and combining the morphological consistency matrix of multiple sequence MRI images, artifact interference is automatically eliminated, structural continuity features are dynamically captured, and the geometric accuracy and structural integrity of tumor lesion identification are improved.

Benefits of technology

Under complex imaging conditions, it significantly improves the accuracy and robustness of tumor lesion identification, reduces the false positive rate, and meets the needs of precision diagnosis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122089736A_ABST
    Figure CN122089736A_ABST
Patent Text Reader

Abstract

This invention relates to the field of image recognition technology, specifically to a tumor detection and recognition method and system based on MRI images. The method includes the following steps: screening candidate lesion regions based on a gradient orientation stability matrix; constructing a spatial projection displacement map; establishing a dynamic boundary framework by combining boundary variation rate; dividing into levels according to a sequence morphological consistency matrix; and performing differential reshaping to generate recognition results. This invention, by constructing a gradient orientation stability matrix and an anisotropy scoring mechanism, quantitatively evaluates the distribution of pixel vector angles; utilizes spatial projection displacement maps and boundary variation rate analysis to dynamically capture structural continuity features between slices; automatically eliminates artifact interference and constructs a high-fidelity dynamic boundary framework; divides into differential levels by combining a sequence morphological consistency matrix; and performs mean adjustment and edge reshaping for regions with different confidence levels. This improves the geometric accuracy and structural integrity of tumor lesion recognition under complex imaging conditions.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Tumor prediction method and system based on image segmentation processing

    CN121073969A

  • Glioma boundary identification method and system based on image fusion

    CN121169956A

  • Anorectal focus automatic segmentation method based on deep learning

    CN121353666A

  • Urinary CT image tumor benign and malignant identification method based on deep learning

    CN121685460A

  • An orientation tracking device for MRI

    WO2017021804A1