Abdominal cavity CT image peritoneal metastasis marking method based on deep convolutional neural network

Abstract

The invention discloses an abdominal cavity CT image peritoneal metastasis marking method based on a deep convolutional neural network. The method includes the following steps: 1) performing CT imagepreprocessing; 2) dividing the preprocessed CT image by using a watershed method to extract candidate nodules; 3) constructing a corresponding neural network input for the candidate nodules; 4) constructing a deep convolutional neural network model, using the neural network input corresponding to the marked candidate nodules to train the neural network model; and 5) predicting the probability thatthe unmarked candidate nodules are tumor nodules by using the neural network model, and finally outputting all the CT images of the determined markers, wherein the negative markers indicate that no tumor metastasis has occurred, and the positive markers indicate that peritoneal metastasis has occurred. The method can complete the automatic marking of the peritoneal metastasis of a large number ofabdominal cavity CT images, provides a basis for the diagnosis and treatment of malignant tumors, is easy to understand and simple to implement, is suitable for automatic marking of massive abdominalcavity CT images, and has good expansibility, robustness and practicability. .

Description

technical field [0001] The invention belongs to the field of medical image processing, and relates to an automatic marking method for tumor peritoneal metastasis in abdominal CT images based on a deep convolutional neural network. Image processing technology and deep learning methods are used to realize automatic marking of tumor nodules in a large number of abdominal CT images. Background technique [0002] The peritoneum is a common metastatic site of various malignant tumors in the abdominal cavity, and marking peritoneal metastasis is an important basis for evaluating the curative effect of malignant tumors. Tumor patients with peritoneal metastases develop rapidly, have poor prognosis, and are difficult to treat clinically, requiring early diagnosis and timely treatment. Marking peritoneal metastases can be accomplished through nodule detection, and abdominal CT images are an important diagnostic basis for detecting tumor nodules. However, CT will generate a large numb...

AI Technical Summary

Problems solved by technology

However, CT will generate a large number of images, which contain image particles similar to nodules, such as lymph nodes and blood vessels. The detection of abdominal metastases through nodules requires experienced physicians to complete. The existing manual image reading method will consume a lot of manpower and time resources. , and affected by subjective factors, the detection accuracy is low and difficult to repeat

Images