Cancer cell pathology grading method, device and equipment based on a deep learning model and medium

Abstract

The invention relates to artificial intelligence, and provides a cancer cell pathology grading method based on a deep learning model, and the method comprises the steps: obtaining at least two to-be-processed digital medical images of a diagnosed patient, carrying out the position registration, and obtaining at least two registered digital medical images; superposing the at least two registered digital medical images to obtain a superposed digital medical image corresponding to the diagnosed patient; performing image processing on the superimposed digital medical image to obtain a training image set; inputting the training image set into a convolutional neural network for model training to obtain a target deep learning model; obtaining a to-be-diagnosed digital medical image of a to-be-diagnosed patient, inputting the to-be-diagnosed digital medical image into the target deep learning model, and obtaining cancer cell pathological grade of the to-be-diagnosed patient. Therefore, the accuracy of pathological grading of cancer cells is improved while the manual operation is simplified. In addition, the invention further provides a cancer cell pathological grading device and equipmentbased on the deep learning model and a medium.

Description

technical field [0001] The present invention relates to the technical field of medical image processing, in particular to a cancer cell pathological grading method, device, equipment and medium based on a deep learning model. Background technique [0002] The ISUP (International Society of Urological Pathology) pathological grading of cancer cells is related to the prognosis of patients, because low-grade cancer cells tend to have better prognosis than high-grade cancer cells. At the same time, the pathological grading evaluation of cancer cells before surgery is also helpful in formulating treatment and surgery plans for patients. [0003] In the usual pathological grading method, needle biopsy is more reliable, but because it is invasive, it will lead to other complications, such as bleeding, infection, and even tumor rupture and tumor metastasis. Previous studies have shown that tumor size, CT (Computed Tomography, computer tomography) density, MRI (Magnetic Resonance Im...

AI Technical Summary

Problems solved by technology

When these data are used clinically, the measurement and evaluation of certain values ​​are affected by the experience and habits of doctors, which leads to deviations in the grading results affected by subjective factors, and their consistency and reliability are poor

Images