Image detection segmentation method and system, storage medium, computer program and terminal

Abstract

The invention belongs to the technical field of image information detection, and discloses an image detection segmentation method and system, a storage medium, a computer program and a terminal, and the method comprises the steps: carrying out the preprocessing of initial Dicom medical image data; and constructing a data set by using the image after denoising enhancement preprocessing, and training an improved U-Net neural network by using the constructed data set. The accuracy of the segmentation method is 98.6%, and compared with a traditional segmentation method, a common U-Net and an FCN,the method has a better segmentation effect. The segmentation algorithm provided by the invention can accurately detect and segment tumors, and brings an actual and reliable diagnosis basis for clinical diagnosis. Compared with an existing related method of traditional machine learning, the U-Net convolutional neural network adopted by the method has the advantages of efficient feature extractioncapability, error-tolerant rate, autonomous learning capability, adaptability and the like, and the image segmentation method based on the convolutional network is also a hot spot of current research.

Description

technical field [0001] The invention belongs to the technical field of image information detection, and in particular relates to an image detection and segmentation method, system, storage medium, computer program, and terminal. Background technique [0002] At present, the incidence rate of bladder cancer is the fourth and the death rate is the eighth. It is easy to occur in men over 40 years old. The high incidence stage is 50-60 years old. The male to female ratio is 4:1. The recurrence rate of bladder cancer is high. Most patients are diagnosed, treated, Recurrence and retreatment are repeated cycles. At the same time, the disease is one of the most expensive diseases. Early detection of bladder tumors is beneficial to the prevention of bladder cancer and the reduction of mortality, which is of great significance in modern medical diagnosis. In traditional tumor diagnosis, doctors will diagnose the tumor area based on computerized tomography (CT) and magnetic resonance i...

AI Technical Summary

Problems solved by technology

[0010] (2) Clustering is also in a fuzzy similarity judgment, and the ability to determine the classification of tumors is limited

[0011] (3) Segmentation based on morphology Since the opening (closing) operation of mathematical morphology is used in the early work of image processing, after image processing, there are still a large number of short lines and isolated points that do not match the target; It is not thorough, and a series of point-based opening (closing) operations are required, so the operation speed is not high

The difficulty of segmentation based on morphology is that the processing process is complex, and the intermediate processing process tends to blur some features, and even loss will affect the final result.

Images