Intelligent analysis system for pathological section image under microscope

Abstract

The invention relates to a pathological section image intelligent analysis system under a microscope. The system comprises the microscope, a microscope camera, a mechanical arm, a processor, a memory and a display, the microscope camera is used for collecting images of pathological sections under the microscope, and the mechanical arm achieves section movement under the microscope objective lens. The processor receives a pathological section image from the microscope camera, the system matches an adaptive algorithm model for the digital pathological section image, performs algorithm processing on the pathological section image through intelligent diagnosis to obtain a preliminary diagnosis result, and outputs the labeled pathological section image; carrying out manual judgment on the pathological section image with the label, and if a labeling result meets a requirement, not carrying out correction labeling; otherwise, manually correcting the labeled information of the pathological section image, and outputting a manual judgment result; and processing the manually corrected pathological section image, retraining the model through local data, enhancing the adaptability of the model to the local data, and outputting a final pathological report.

Description

technical field [0001] The invention belongs to the technical field of pathological slice diagnosis, in particular to an intelligent analysis system for pathological slice images under a microscope. Background technique [0002] At present, all kinds of domestic tertiary hospitals and second-level comprehensive, integrated traditional Chinese and Western medicine, foot tumors, children and obstetrics and gynecology specialized hospitals can set up pathology departments if qualified. [0003] However, the efficiency, accuracy, ease of use, and cost-effectiveness of traditional microscopes need to be improved. Doctors need to switch between the screen and the microscope repeatedly, and the judgment results vary from person to person, and pathological sections also rely on doctors to manually identify them. If the field of view under the microscope is digitized, the accuracy and real-time performance can meet the practical application requirements of pathological diagnosis, and...

AI Technical Summary

Problems solved by technology

Since most of these smart microscopes that integrate multiple functions are all-in-one devices, they are not only expensive, but also unable to independently add artificial intelligence algorithms developed by others according to the actual diagnosis of the hospital’s condition.

[0007] 2. After the current artificial intelligence algorithm processes the pathological images, doctors can only passively accept the detection results, and cannot manually correct the processing results

Therefore, doctors often have doubts about this black box mechanism that cannot be manually involved

[0008] 3. Due to differences in microscopes and staining agents between hospitals, most smart microscopes have poor diagnostic results under fixed models, poor adaptability to local model processing, and low accuracy of detection results

Images