Medical image segmentation method based on deep learning

Abstract

The invention belongs to the technical field of medical image processing and computer vision, and particularly relates to a medical image segmentation method based on deep learning. According to the method, on the basis of U-Net Baseline, multiple technologies such as a multi-scale framework, a dense convolutional network, an attention mechanism, a pyramid model and small sample enhancement are fused, the method is helpful for realizing feature reuse, recovering lost context information, inhibiting response of an unrelated region and improving the performance of a small ROI, solves the problems of few ultrasonic image samples, low pixel, fuzzy boundary, large difference and other pain points, and obtains an optimal segmentation effect.

Description

technical field [0001] The invention belongs to the technical field of medical image processing and computer vision, and in particular relates to a medical image segmentation method based on deep learning. Background technique [0002] With the development of technology, doctors began to use a large number of medical image data as the basis for medical diagnosis and treatment, thus promoting the development and progress of various new technologies. However, with the development of technology, how to correctly segment medical images has become an important bottleneck restricting the development of various technologies. It can even be said that accurate image segmentation has become the most basic and important problem in the field of medical images and needs to be solved urgently. [0003] In recent years, with the continuous improvement of computing power and the continuous increase of data volume, deep learning has made remarkable progress in the field of medical imaging. ...

AI Technical Summary

Problems solved by technology

However, the traditional CNN cannot reasonably propagate the low-level features to the high-level, so the U-Net algorithm is further proposed, which fuses low-dimensional and high-dimensional features through skip connections, and has a good segmentation effect

[0004] Most of the current medical image segmentation algorithms are based on U-Net (U-Net Baseline), but due to the problems of data imbalance, large differences between training samples, and small perceptual regions (ROI) in medical images, the accuracy and It is difficult to balance the recall rate, insufficient feature extraction, redundant computing resources and model parameters, and the segmentation effect is not obvious, so more accurate segmentation of ultrasound images is still a problem that needs to be solved urgently

Images