Fever to-be-checked computer aided diagnosis method based on PET/CT images

Abstract

The invention provides a fever to-be-checked computer aided diagnosis method based on PET / CT images. Full-automatic analysis of the PET / CT bone images is achieved, and a doctor is assisted in diagnosing fever to-be-checked patients. Firstly, lossless interpolation of the PET images is conducted; secondly, hospital beds in the CT images are automatically removed; thirdly, full-automatic bone segmentation of the CT images is conducted; fourthly, bone segmentation is conducted on the whole-body CT images through an optimal active contour model of a CV active contour region; fifthly, after-treatment of the CT segmented images is conducted; sixthly, bone tissue information of the PET images is acquired; seventhly, bone tissue SUVs and bone tissue BSI values are acquired through calculation, wherein the SUVs of bones, marrow and bone cortices are acquired through calculation respectively, and the BSI values of the bones, the marrow and the bone cortices of the patients are acquired through calculation via the SUVs; eighthly, diagnosis is conducted based on the BSI values, wherein the SUVs and the BSI values are compared with SUVs and BSI values in an existing confirmed patient database, and a diagnosis report is made.

Description

technical field [0001] The invention relates to a computer-aided diagnosis method for fever of unknown origin (FUO) based on PET / CT images, which is suitable for the diagnosis and treatment of clinical fever of unknown origin. Background technique [0002] Fever of Unknown Origin (FUO) refers to a group of diseases in which fever lasts for more than 3 weeks, body temperature exceeds 38.3°C several times, and cannot be diagnosed after at least 1 week of in-depth and detailed examination. Despite many new advances in diagnostic techniques, undiagnosed fever remains a major medical problem, with as many as 51% of cases undiagnosed. Among diagnosed patients, there were three main categories, namely infectious disease, malignancy, and noninfectious inflammation. Fluoro-deoxyglucose (Fluoro-18-fluoro-2-deoxy-D-glucose, FDG) is a fluorinated derivative of 2-deoxyglucose, FDG not only accumulates in malignant tissues, but also in infectious diseases and inflammatory tissues Gather...

AI Technical Summary

Problems solved by technology

[0007] 1. The current bone segmentation methods are all designed for extracting the outline of the bone. The bone marrow has a lower CT value than the bone cortex. It is difficult for the existing methods to accurately segment the bone marrow tissue of the whole body.

[0008] 2. The existing bone segmentation methods for CT images are all designed for a certain bone. The adaptability and robustness of the algorithm are relatively poor, and good segmentation results cannot be achieved when segmenting the whole body bones.

[0009] 3. Due to differences in imaging principles, the resolution of PET images is much lower than that of CT images

[0010] 4. The existing indicators for evaluating PET images are mainly the average value of the region of interest, which is difficult to deal with heterogeneous lesion tissue and diffuse lesion tissue

However, the existing analysis methods for PET / CT fusion images are very limited, mainly relying on doctors to observe and analyze limited regions of interest, so they are highly subjective

The clinical diagnosis process often requires doctors to have strong professional knowledge and a lot of operating experience

Images