A Stacked Projection Reconstruction Method for Small-area Tumor Blocks after Segmentation

Abstract

The present invention proposes a method for stacking projection reconstruction of small-area tumor blocks after segmentation. Among them, the method includes: step 1, reducing the dimensionality of medical image data into discrete two-dimensional slice sequences, using an improved full convolutional neural network to perform large-scale segmentation of small-area tumor blocks on slices of different modalities; step 2, Tumor-containing sections according to the similarity index patch Calibration, precise positioning of the tumor mass; step 3, stacking small-area tumor mass images, repeatedly constraining multi-column parallel filtering to offset a very small angle, and projecting the calibrated small-area tumor mass to reconstruct the patient body. The goal of the method of the present invention is to achieve rapid segmentation, precise positioning and reverse reconstruction of the disease body, and to display multi-dimensional structural information, to display the distribution and relative position of tumor tissues alone or in combination, and to promote emerging medical solutions such as image-guided minimally invasive surgery. development of.

Description

technical field

[0001] The invention belongs to the technical fields of graphics and computer vision, and in particular relates to a stacking projection reconstruction method of a segmented small-area tumor mass. Background technique

[0002] Medical imaging technology refers to the analysis and processing of patient image data through advanced computer software and hardware, which has become an important part of medical information construction. Among them, imaging technologies such as computed tomography (CT), magnetic resonance imaging (magnetic resonance imaging, MR), and digital radiography (digital radiography, DR) have a great impact on the diagnosis and treatment of tumors. value. The medical visualization interface can allow doctors to instruct and introduce relevant image information to patients in detail, intuitively and accurately understand the size, location and morphological characteristics of the entire lesion area, thereby improving the objectivity of clini...

Images