An automatic segmentation method of abdominal CT liver lesion image based on three-level cascade network

Abstract

The invention relates to an automatic segmentation method for an abdominal CT liver lesion image based on a three-stage cascade network. The method comprises the following steps: S1, acquiring three-dimensional abdominal liver CT image data; S2, preprocessing and standardizing the obtained three-dimensional abdominal liver CT image data; S3, inputting the three-dimensional abdominal liver CT imagedata after preprocessing and data standardization into AuxResUnet liver image segmentation model, and then taking 3D maximum connected region from the obtained three-dimensional abdominal liver CT image data segmentation result to exclude false positive region, so as to obtain liver VOI; S4, adopting the segmentation result of the three-dimensional abdominal liver CT image data obtained by S3 asa mask of the CT liver image data to cover the liver VOI obtain by S3; S5, inputting the covered liver VOI into AuxResUnet liver image lesion segmentation model for lesion segmentation, and obtainingthe liver image lesion segmentation result. The image segmentation method provided by the invention can realize fast and accurate segmentation of liver and liver pathological changes.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an automatic segmentation method for abdominal CT liver lesion images based on a three-level cascade network. Background technique [0002] Abnormal morphology and texture of the liver and visible lesions on CT are important biomarkers of disease progression in both primary and secondary liver neoplastic diseases. In clinical routine, although manual and semi-manual techniques are used, however, these methods are subjective, heavily operator-dependent, and very time-consuming. Computer-aided methods have been developed in the past to increase the productivity of radiologists, however due to the low contrast of the liver with its lesions, different types of contrast, abnormalities in the tissue (metastatic resection), size and number of lesions vary , automatic liver and its lesion segmentation remains a very challenging problem. Additionally, CT images typi...

AI Technical Summary

Problems solved by technology

In clinical routine, although manual and semi-manual techniques are used, however, these methods are subjective, heavily operator-dependent and very time-consuming

Computer-aided methods have been developed in the past to increase the productivity of radiologists, however due to the low contrast of the liver with its lesions, different types of contrast, abnormalities in the tissue (metastatic resection), size and number of lesions vary , automatic liver and its lesion segmentation is still a very challenging problem

Additionally, CT images typically have low soft tissue contrast and are susceptible to noise and other artifacts

[0003] Existing methods for segmentation of the liver and its lesions based on intensity clustering, region growing, or deformable models have shown limited success in addressing this difficult problem

This complexity of contrasting differences makes it difficult to generalize intensity-based methods to unseen test cases at different clinical points

Furthermore, the varying shape of lesions due to irregular tumor growth and response to treatment (i.e., surgical resection) reduces the efficiency of computational methods that exploit prior knowledge of lesion shape

Therefore several interactive and automatic methods (including gray-scale and texture-based methods, graph-cut methods, level sets, sigmoid edge modeling) that have been developed for segmenting the liver and its lesions in CT volumes are not widely used clinically. application

Images