Liver tumor region segmentation method based on watershed transform and classification through support vector machine

Abstract

The invention relates to an image processing technology and particularly relates to an interactive liver tumor region segmentation method based on watershed transform and classification through a support vector machine. The method comprises the following steps: 1) performing segmentation pretreatment on a liver tumor region; 2) performing watershed transform on an image of the pretreated liver region which is obtained in the step 1) and dividing the image of the pretreated liver region into numerous reception basins; 3) calculating four-dimensional characteristic vectors of all the reception basins which are generated by the watershed transform, marking tumor and normal liver tissues in the image of the liver region in an interactive manner and adopting a support vector machine process to classify the reception basins in a characteristic space; and 4) adopting communicating region detection to eliminate a false positive tumor region generated by the classification, and applying morphological operation to fill voids and smoothen edges. The region class is classified, and user marks are further utilized for training parameters of a classifier, thereby effectively improving the segmentation speed and the precision. The method has important application value in the fields of liver surgical planning and the like.

Description

technical field [0001] The invention relates to image processing and pattern recognition technology, in particular to an interactive liver tumor region segmentation method based on watershed transformation and support vector machine classification. Background technique [0002] The liver is the largest substantial organ in the human body, and it plays a very important role in metabolism, bile production, detoxification, blood coagulation, immunity, heat generation, and water and electrolyte regulation. At the same time, the liver is also one of the organs prone to tumors. Liver cancer is currently among the common human tumors, its incidence rate ranks sixth worldwide, and its mortality rate ranks third worldwide. Moreover, about half of the liver cancer patients in the world are in China, and liver cancer has risen to the second cancer killer in my country, second only to lung cancer in cities, and second to gastric cancer in rural areas. In clinical diagnosis and treatmen...

AI Technical Summary

Problems solved by technology

[0003] Liver tumor region segmentation is the premise of liver tumor size detection, but its automatic segmentation is quite difficult

Due to the blurred boundaries between tumors and normal liver tissue, artifacts and noise in liver CT images, and the large differences in grayscale and shape of liver tumors from different individuals, the segmentation of liver tumor regions has become a challenging problem.

Segmentation methods driven entirely by the underlying data of the image are difficult to obtain accurate segmentation results

The underlying attributes of the image include the visual features of the image itself, such as grayscale, texture, shape, etc. The applications of segmentation driven entirely by the underlying data of the image in the segmentation of liver tumor regions include adaptive threshold, mathematical morphology, region growing and unsupervised Classification methods, etc. These methods are difficult to obtain accurate segmentation results because they do not combine high-level target prior knowledge.

Images