Pituitary tumor texture image grading method based on fine-grained medical image segmentation and true value discovery data amplification

Abstract

The invention discloses a pituitary tumor texture image grading method based on fine-grained medical image segmentation and true value discovery data amplification. The pituitary tumor texture image grading method comprises the following steps: 1, optimizing fruit fly-density peak clustering medical image segmentation based on fine granularity; 2, amplifying pituitary adenoma data discovered on the basis of true values; and 3, grading based on the pituitary adenoma texture images in the step 1 and the step 2. According to the pituitary tumor texture image grading method, the medical image is accurately segmented through fusion of a fine-grained division algorithm and an FOA-DPC algorithm; medical image data amplification based on a true value discovery theory is also realized, and the problem of few available medical image data sets is solved. The pituitary tumor texture image grading method combines a KFOA-DPC segmentation algorithm with deep learning, so as to solve the problems thatthe gray scale of a dicom format image is numerous and jumbled, and features are not easy to extract, realize classification of pituitary adenoma texture softness and toughness and assist clinical diagnosis.

Description

technical field [0001] The invention relates to a pituitary tumor texture image classification method, in particular to a pituitary tumor texture image classification method based on fine-grained medical image segmentation and truth value discovery data amplification, and belongs to the technical field of medical image processing. Background technique [0002] Pituitary tumors are a group of tumors arising from the anterior and posterior pituitary glands and residual epithelial cells of the craniopharynx. They occur frequently, accounting for about 10% of intracranial tumors. The soft and tough texture of pituitary tumors affects the approach and surgical plan of surgical treatment. At present, with the development of minimally invasive technology, minimally invasive surgery via transsphenoidal approach has become the preferred treatment method, but it is only suitable for patients with soft texture. Pituitary tumors, and for a small number of pituitary tumors with tough or ...

AI Technical Summary

Problems solved by technology

[0008] The technical problem to be solved by the present invention is to provide a pituitary tumor texture image classification method based on fine-grained medical image segmentation and truth value discovery data amplification. The problem of too few medical image data sets has also realized the grading of the soft and tough texture of pituitary tumors, thereby assisting clinical diagnosis

Images