Fractal-theory-based tumor heterogeneity analysis method and system, terminal and medium

Abstract

The invention discloses a fractal-theory-based tumor heterogeneity analysis method. The method comprises the steps: marking out a tumor range on a maximum tumor cross-section of a CT or MRI image of a sufferer; carrying out gray scale processing on the CT or MRI image of the sufferer, and marking a tumor region; carrying out gray scale processing on a standard photograph of a postoperative cut maximum tumor cross-section, and marking the interior of a tumor; calculating the CT or MRI tumor image and the standard photograph subjected to gray scale processing by employing a box-counting method, so as to figure out a preoperative congested fractal dimension and a postoperative bloodless fractal dimension of the tumor; inputting the fractal dimensions and clinical data of the sufferer into a tumor evaluation model for evaluation, and outputting a weighting-processed tumor fractal dimension; evaluating characteristics of the tumor according to the tumor fractal dimension, and evaluating a treatment effect; and evaluating heterogeneity of the tumor according to the tumor fractal dimension. According to the method, tumor heterogeneity information on a focus can be accurately provided, so as to assist doctors to accurately analyze tumor heterogeneity of a tumor focus.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method, system, terminal and medium for analyzing tumor heterogeneity based on fractal theory. Background technique [0002] Tumor heterogeneity has become a hot spot in the field of liver cancer treatment, including spatial heterogeneity, temporal heterogeneity, inter-tumor and intra-tumor heterogeneity, and immune microenvironment heterogeneity, etc. How to objectively and comprehensively quantify tumor heterogeneity Qualitative is the breakthrough, difficulty and focus of the current treatment of liver cancer. At present, research at home and abroad is focused on some in vivo and in vitro models that simulate liver cancer cells, such as "models derived from tumor cell lines", human-derived tumor xenograft models (PDTX) and human-derived tumor organoids (PDTO), etc., but only It can reflect the biological polymorphism of tumors at a limited level, and cannot fully a...

AI Technical Summary

Problems solved by technology

In medicine, the most commonly used FD calculation method is the box dimension method. In the past few decades, it has been used in nonlinear medical fields such as cardiology, lung tumors, and fetal umbilical blood flow Doppler signals. Staying at the level of imaging diagnosis, the depth of research on tumor heterogeneity has not yet been in-depth, and the bottleneck restricting the expansion of fractal research is the comprehensive analysis and calculation capabilities for complex data

Images