A 3D liver lesion detection method and device

By combining 3D data with multi-phase CT images, and utilizing detection models and false positive filtering technology, the problem of detecting small-sized liver cancer lesions in existing technologies has been solved, achieving high-precision and low-false-positive 3D liver lesion detection.

CN113658105BActive Publication Date: 2026-05-22HANGZHOU SHENRUI BOLIAN TECH CO LTD +2
2 Cites 0 Cited by

Patent Information

Application Number
CN202110823905.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-07-21
Publication Date
2026-05-22
Estimated Expiration
2041-07-21

AI Technical Summary

Technical Problem

Existing technologies struggle to effectively identify and detect small-sized liver cancer lesions, especially in CT images. They lack end-to-end automated detection capabilities, cannot fully utilize 3D contextual features, and suffer from severe false positives.

Method used

3D data centered on each slice layer to be detected is constructed, and multi-phase CT images are combined. Multi-size feature extraction and false positive filtering are performed through the detection model. Using the central cutting and global attention mechanism, 2D lesion features are fused to generate 3D lesion detection results, and the results are filtered through the false positive identification model.

Benefits of technology

It improves the detection accuracy of small-sized liver cancer lesions, reduces false positives, and achieves efficient and accurate identification of 3D liver lesions.

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

Abstract

The application provides a 3D liver lesion detection method and device. The method comprises the following steps: acquiring multi-phase CT images to be detected, constructing 3D data including upper and lower layers of each slice layer to be detected as the center; inputting the 3D data into a detection model, extracting 3D context features of the images, and detecting 2D lesions obtained by center cutting; combining 2D lesions of continuous layer slices belonging to the same lesion into a 3D lesion; inputting the 3D lesion cut in the local image of multiple phases output by the detection model into a false positive identification model to obtain a detection result of the 3D lesion. The application can extract 3D context features by constructing 3D data, can fully utilize lesion information of each phase for lesion detection, and thus improves the lesion detection accuracy; and the false positive identification model is set to filter false positives of the 3D lesion, which can further improve the lesion detection accuracy.
Need to check novelty before this filing date? Find Prior Art