Faculty, Staff and Student Publications
Publication Date
9-1-2024
Journal
Medical Physics
Abstract
Background: Adequate image enhancement of organs and blood vessels of interest is an important aspect of image quality in contrast-enhanced computed tomography (CT). There is a need for an objective method for evaluation of vessel contrast that can be automatically and systematically applied to large sets of CT exams.
Purpose: The purpose of this work was to develop a method to automatically segment and measure attenuation Hounsfield Unit (HU) in the portal vein (PV) in contrast-enhanced abdomen CT examinations.
Methods: Input CT images were processed by a vessel enhancing filter to determine candidate PV segmentations. Multiple machine learning (ML) classifiers were evaluated for classifying a segmentation as corresponding to the PV based on segmentation shape, location, and intensity features. A public data set of 82 contrast-enhanced abdomen CT examinations was used to train the method. An optimal ML classifier was selected by training and tuning on 66 out of the 82 exams (80% training split) in the public data set. The method was evaluated in terms of segmentation classification accuracy and PV attenuation measurement accuracy, compared to manually determined ground truth, on a test set of the remaining 16 exams (20% test split) held out from public data set. The method was further evaluated on a separate, independently collected test set of 21 examinations.
Results: The best classifier was found to be a random forest, with a precision of 0.892 in the held-out test set to correctly identify the PV from among the input candidate segmentations. The mean absolute error of the measured PV attenuation relative to ground truth manual measurement was 13.4 HU. On the independent test set, the overall precision decreased to 0.684. However, the PV attenuation measurement remained relatively accurate with a mean absolute error of 15.2 HU.
Conclusions: The method was shown to accurately measure PV attenuation over a large range of attenuation values, and was validated in an independently collected dataset. The method did not require time-consuming manual contouring to supervise training. The method may be applied to systematic quality control of contrast-enhanced CT examinations.
Keywords
Portal Vein, Tomography, X-Ray Computed, Quality Control, Contrast Media, Humans, Image Processing, Computer-Assisted, Machine Learning, Automation, Computed tomography, Contrast enhancement, Image quality, Quality control, Random forest, Machine learning
DOI
10.1002/mp.17267
PMID
39031758
PMCID
PMC11771118
PubMedCentral® Posted Date
1-27-2025
PubMedCentral® Full Text Version
Author MSS
Published Open-Access
yes
Included in
Bioinformatics Commons, Biomedical Informatics Commons, Health and Medical Physics Commons, Medical Sciences Commons