AI auxiliary diagnosis system and method for liver digital pathology

Abstract

The invention relates to the technical field of medical treatment, in particular to an AI auxiliary diagnosis system and method for liver digital pathology, and the system comprises a data collectionunit which is used for collecting a plurality of liver digital pathology images; a labeling unit connected with the data acquisition unit and used for distinguishing each tissue region in each digitalpathological image and labeling a corresponding tissue type; a training unit connected with the labeling unit and used for training a training set in the digital pathological image and testing a testset so as to obtain a liver digital pathological model image through processing; and a recognition unit connected with the training unit and used for recognizing each tissue region in the liver digital pathological model image. The technical scheme of the invention has the beneficial effects that the tissue type of each tissue region on the liver digital pathological image is distinguished, and the cancer tissues, para-carcinoma liver tissues and other tissues are subjected to region identification, so that a pathologist is assisted in disease diagnosis, and the workload of the pathologist isreduced.

Description

technical field [0001] The present invention relates to the field of medical technology, in particular to an AI-assisted diagnosis system and method for liver digital pathology. Background technique [0002] Cancer is a common primary malignant tumor, and interventional therapy based on arterial chemoembolization (TACE) is applied to non-surgical therapy. Due to the special anatomical structure of certain organs of the human body (such as the liver), abundant sinusoids and dense distribution of blood vessels have brought great difficulties to traditional surgical operations. [0003] It takes a lot of time for pathologists to view liver tissue and determine whether the patient has liver cancer or other tissue lesions, because pathological images generally have pixels on the order of 100,000 by 100,000, and pathologists need to review each liver tissue slice. A lot of time is consumed, and the pathologist's time is often not enough. Therefore, aiming at the above problems, ...

AI Technical Summary

Problems solved by technology

Due to the special anatomical structure of certain organs of the human body (such as the liver), rich sinusoids and dense distribution of blood vessels have brought great difficulties to traditional surgical operations.

[0003] It takes a lot of time for pathologists to look at liver tissue and determine whether the patient has liver cancer or other tissue lesions, because pathological images generally have pixels on the order of 100,000 by 100,000, and pathologists need to review each liver tissue slice. Takes a lot of time, and the time of the pathologist is often not enough

Images