Preoperative ablation area simulation method and device for tumor thermal ablation

Abstract

A preoperative ablation area simulation method and device for tumor thermal ablation, the method includes: (1) selecting data suitable for training, the doctor marks the preoperative and postoperative images, and obtains the preoperative liver, postoperative ablation area and needle path; (2) Register the postoperative image to the preoperative image, and add rigid restrictions during the registration process so that the ablation area and the needle track area do not undergo elastic deformation, and use the deformation field obtained by registration to project the needle track information and the ablation area (3) Generate the ideal thermal field distribution map according to the projected needle track direction and position information and the corresponding power time used in the operation; (4) Establish a convolutional neural network to convert the ideal thermal field distribution map The preoperative image is cropped according to the preoperative liver mask, and the cropping results are combined as network input, and the deformed ablation area is used as the gold standard for learning to obtain a regression model, and the prediction of the ablation area is realized in the test phase.

Description

technical field [0001] The present invention relates to the technical field of medical image processing, in particular to a preoperative ablation area simulation method for tumor thermal ablation, and a preoperative ablation area simulation device for tumor thermal ablation, which are mainly applicable to ablation operations guided by deep learning. Background technique [0002] During microwave ablation, the doctor punctures the ablation needle percutaneously into the tissue lesion, and emits microwaves at the front pole of the ablation needle. The temperature of the surrounding lesion tissue rises after being irradiated by microwaves. When the thermal damage of the surrounding lesion tissue exceeds a certain limit, other The protein is inactivated, creating an ablation zone, thereby enabling the treatment of the tumor. In order to provide doctors with the best ablation methods corresponding to different patients and realize individualized conformal ablation, it is necessar...

AI Technical Summary

Problems solved by technology

However, the SAR model needs accurate blood vessel segmentation results when calculating the vascular heat sink effect. At the same time, due to the differences in the relevant parameters of tissues and blood in different patients, and the real values ​​of these parameters are difficult to obtain, the ablation area solved by the SAR distribution model is different from that of There is still a big difference in the real ablation effect

This seriously reduces the clinical guiding significance of preoperative planning for subsequent real operations

Images