Technical Note: Proof of concept for radiomics-based quality assurance for computed tomography

被引:7
作者
Branco, Luciano R. F. [1 ]
Ger, Rachel B. [1 ,2 ]
Mackin, Dennis S. [1 ,2 ]
Zhou, Shouhao [2 ,3 ]
Court, Laurence E. [1 ,2 ,4 ]
Layman, Rick R. [2 ,4 ]
机构
[1] Univ Texas MD Anderson Canc Ctr, Dept Radiat Phys, Houston, TX 77030 USA
[2] Univ Texas MD Anderson Canc Ctr, UTHlth Grad Sch Biomed Sci, Houston, TX 77030 USA
[3] Univ Texas MD Anderson Canc Ctr, Dept Biostat, Houston, TX 77030 USA
[4] Univ Texas MD Anderson Canc Ctr, Dept Imaging Phys, Houston, TX 77030 USA
来源
JOURNAL OF APPLIED CLINICAL MEDICAL PHYSICS | 2019年 / 20卷 / 11期
基金
美国国家卫生研究院;
关键词
CT; QA; quantitative imaging; radiomics; CT; FEATURES;
D O I
10.1002/acm2.12750
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Purpose Routine quality assurance (QA) testing to identify malfunctions in medical imaging devices is a standard practice and plays an important role in meeting quality standards. However, current daily computed tomography (CT) QA techniques have proven to be inadequate for the detection of subtle artifacts on scans. Therefore, we investigated the ability of a radiomics phantom to detect subtle artifacts not detected in conventional daily QA. Methods An updated credence cartridge radiomics phantom was used in this study, with a focus on two of the cartridges (rubber and cork) in the phantom. The phantom was scanned using a Siemens Definition Flash CT scanner, which was reported to produce a subtle line pattern artifact. Images were then imported into the IBEX software program, and 49 features were extracted from the two cartridges using four different preprocessing techniques. Each feature was then compared with features for the same scanner several months previously and with features from controlled CT scans obtained using 100 scanners. Results Of 196 total features for the test scanner, 79 (40%) from the rubber cartridge and 70 (36%) from the cork cartridge were three or more standard deviations away from the mean of the controlled scan population data. Feature values for the artifact-producing scanner were closer to the population mean when features were preprocessed with Butterworth smoothing. The feature most sensitive to the artifact was co-occurrence matrix maximum probability. The deviation from the mean for this feature was more than seven times greater when the scanner was malfunctioning (7.56 versus 1.01). Conclusions Radiomics features extracted from a texture phantom were able to identify an artifact-producing scanner as an outlier among 100 CT scanners. This preliminary analysis demonstrated the potential of radiomics in CT QA to identify subtle artifacts not detected using the currently employed daily QA techniques.
引用
收藏
页码:199 / 205
页数:7
相关论文
共 50 条
  • [1] Computed Tomography Radiomics-Based Prediction of Microvascular Invasion in Hepatocellular Carcinoma
    Yao, Wenjun
    Yang, Shuo
    Ge, Yaqiong
    Fan, Wenlong
    Xiang, Li
    Wan, Yang
    Gu, Kangchen
    Zhao, Yan
    Zha, Rujing
    Bu, Junjie
    FRONTIERS IN MEDICINE, 2022, 9
  • [2] The structural similarity index for IMRT quality assurance: radiomics-based error classification
    Ma, Chaoqiong
    Wang, Ruoxi
    Zhou, Shun
    Wang, Meijiao
    Yue, Haizhen
    Zhang, Yibao
    Wu, Hao
    MEDICAL PHYSICS, 2021, 48 (01) : 80 - 93
  • [3] Free automatic software for quality assurance of computed tomography calibration, edges and radiomics metrics reproducibility
    Saborido-Moral, Juan D.
    Fernandez-Patona, Matias
    Tejedor-Aguilar, Natalia
    Cristian-Marin, Andrei
    Torres-Espallardo, Irene
    Campayo-Esteban, Juan M.
    Perez-Calatayud, Jose
    Baltas, Dimos
    Marti-Bonmati, Luis
    Carles, Montserrat
    PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS, 2023, 114
  • [4] Radiomics-Based Machine Learning Model for Diagnosis of Acute Pancreatitis Using Computed Tomography
    Bette, Stefanie
    Canalini, Luca
    Feitelson, Laura-Marie
    Woznicki, Piotr
    Risch, Franka
    Huber, Adrian
    Decker, Josua A.
    Tehlan, Kartikay
    Becker, Judith
    Wollny, Claudia
    Scheurig-Muenkler, Christian
    Wendler, Thomas
    Schwarz, Florian
    Kroencke, Thomas
    DIAGNOSTICS, 2024, 14 (07)
  • [5] Computed tomography radiomics-based prognosis prediction of patients with chronic obstructive pulmonary disease
    Zhao, Xiaogang
    Qiu, Xiaojiao
    JOURNAL OF RADIATION RESEARCH AND APPLIED SCIENCES, 2024, 17 (04)
  • [6] A computed tomography radiomics-based model for predicting osteoporosis after breast cancer treatment
    Lai, Yu-Hsuan
    Tsai, Yi-Shan
    Su, Pei-Fang
    Li, Chung-, I
    Chen, Helen H. W.
    PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE, 2024, 47 (01) : 239 - 248
  • [7] Radiomics-Based Classification of Tumor and Healthy Liver on Computed Tomography Images
    Zossou, Vincent-Beni Sena
    Gnangnon, Freddy Houehanou Rodrigue
    Biaou, Olivier
    de Vathaire, Florent
    Allodji, Rodrigue S.
    Ezin, Eugene C.
    CANCERS, 2024, 16 (06)
  • [8] Radiomics-based automated machine learning for differentiating focal liver lesions on unenhanced computed tomography
    Yang, Nan
    Ma, Zhuangxuan
    Zhang, Ling
    Ji, Wenbin
    Xi, Qian
    Li, Ming
    Jin, Liang
    ABDOMINAL RADIOLOGY, 2025, 50 (05) : 2126 - 2139
  • [9] Radiomics-Based Precision Phenotyping Identifies Unstable Coronary Plaques From Computed Tomography Angiography
    Lin, Andrew
    Kolossvary, Marton
    Cadet, Sebastien
    McElhinney, Priscilla
    Goeller, Markus
    Han, Donghee
    Yuvaraj, Jeremy
    Nerlekar, Nitesh
    Slomka, Piotr J.
    Marwan, Mohamed
    Nicholls, Stephen J.
    Achenbach, Stephan
    Maurovich-Horvat, Pal
    Wong, Dennis T. L.
    Dey, Damini
    JACC-CARDIOVASCULAR IMAGING, 2022, 15 (05) : 859 - 871
  • [10] Enhanced computed tomography radiomics-based machine-learning methods for predicting the Fuhrman grades of renal clear cell carcinoma
    Yin, Ruo-Han
    Yang, You-Chang
    Tang, Xiao-Qiang
    Shi, Hai-Feng
    Duan, Shao-Feng
    Pan, Chang-Jie
    JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY, 2021, 29 (06) : 1149 - 1160