Iteration-based image weak supervision segmentation method

Abstract

The invention relates to an iteration-based image weak supervision segmentation method, which comprises the following steps of: taking a thyroid ultrasound image containing a positioning bounding box as weak supervision information, obtaining a training label by utilizing a probability gradient labeling mode, continuously updating deep learning weak supervision segmentation network parameters and the training label in an iterative training mode, and finally, segmenting an image to be processed by adopting the trained network. Through optimization of the iterative network, the initial positioning label is converted into the final segmentation result under the weak supervision condition without manual intervention, and accurate segmentation of the specific area in the thyroid ultrasound image can be realized under the weak supervision condition without manual annotation.

Description

technical field [0001] The invention relates to a technology in the field of image processing, in particular to an iteration-based weakly supervised image segmentation method. Background technique [0002] Most of the existing deep learning image segmentation methods are supervised learning, and their segmentation accuracy depends heavily on a large amount of high-quality labeled data, which is not only time-consuming and labor-intensive, but also prone to subjective bias. Therefore, there is an increasing need to apply weakly supervised methods for automatic segmentation of thyroid ultrasound images in order to improve diagnostic performance and reduce human intervention. Contents of the invention [0003] Aiming at the above-mentioned deficiencies in the prior art, the present invention proposes an iterative-based weakly supervised image segmentation method, through the optimization of the iterative network, the initial positioning label is converted into the final segme...

AI Technical Summary

Problems solved by technology

[0002] Most of the existing deep learning image segmentation methods are supervised learning, and their segmentation accuracy depends heavily on a large amount of high-quality labeled data, which is not only time-consuming and labor-intensive, but also prone to subjective bias

Images