Stacked projection reconstruction method for segmented small-area tumor blocks

Abstract

The invention provides a stacked projection reconstruction method for small-area tumor blocks after segmentation. The method comprises the following steps: step 1, carrying out dimensionality reduction on medical image data to form a discrete two-dimensional slice sequence, and carrying out large-scale segmentation of small-area tumor blocks on different modal slices by utilizing an improved full convolutional neural network; step 2, calibrating the slices containing the tumor according to a similarity index patch, and accurately positioning a tumor block; and step 3, stacking small-area tumor block images, repeatedly constraining multi-column parallel filtering to shift a minimum angle, and projecting the calibrated small-area tumor blocks to reconstruct a sick body. The objective of the method is to realize rapid segmentation, accurate positioning and reverse reconstruction of a sick body so as to display multi-dimensional structure information, display the distribution condition and the relative position of tumor tissues independently or in a combined manner, and promote the development of emerging medical schemes such as image navigation minimally invasive surgery and the like.

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 block. 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 clin...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of the existing medical diagnosis technology, the present invention provides a stacking projection reconstruction method of small-area tumor blocks after segmentation. After reconstruction, the texture information can accurately locate partitions and volumes intuitively, and reversely avoids the problem of inapplicability of specific parts.

Images