A CNN-based joint segmentation method for multimodal nasopharyngeal tumors

Abstract

The present invention relates to a multimodal nasopharyngeal tumor joint segmentation method based on CNN, which comprises dividing the multimodal nasopharyngeal tumor image into image blocks of the same size, and inputting the segmented image blocks into a coarse segmentation CNN for Coarse segmentation is used to obtain a rough segmented image, and the image block determined to be a tumor area is obtained through rough segmentation processing, and then the coarse segmented image is input into a refined CNN for fine segmentation, and each pixel in the image block determined to be a tumor area is finely segmented. Segment, determine its category, and finally obtain a pixel-level finely segmented image. The segmentation method of the present invention does not need to determine the category of all pixels in the nasopharyngeal tumor image, but only needs to determine a small number of diseased areas, thereby greatly improving the efficiency of the segmentation algorithm and shortening the segmentation time. Furthermore, the present invention uses multi-modal data and CNN for image segmentation, retains more information about the tumor image to be segmented, thereby improving the segmentation accuracy of the algorithm.

Description

technical field [0001] The invention belongs to the field of tumor image segmentation, and in particular relates to a CNN-based multimodal nasopharyngeal tumor joint segmentation method. Background technique [0002] In the field of medical image segmentation, the current research results on head and neck tumor image segmentation algorithms are increasingly fruitful. Especially in the image segmentation method of head tumors, good segmentation results have been achieved. Nasopharyngeal tumor is a common head and neck tumor. According to the statistics of the World Health Organization, about 80% of nasopharyngeal cancers in the world occur in my country. Therefore, it is very useful to find an effective image segmentation method for nasopharyngeal tumors. meaningful. At present, there are few research results on nasopharyngeal carcinoma at home and abroad. The existing nasopharyngeal tumor image segmentation algorithms are either too complicated in method and difficult to be...

AI Technical Summary

Problems solved by technology

However, it turns out that single-modal CT and RT images contain very limited information. In fact, nasopharyngeal tumors are difficult to have obvious boundaries even in enhanced CT images, so only single-modal CT and MR images are used. Difficult to meet high-precision clinical needs

[0005] Nasopharyngeal carcinoma is one of the high-incidence tumors in my country, but there are few studies on image segmentation of nasopharyngeal tumors, and the results of relevant research results are not satisfactory

At present, no relevant research results have been found at home and abroad on the use of convolutional neural network CNN (Convolutional Neural Network) for nasopharyngeal tumor image segmentation

Images