Literature DB >> 30976827

Automated segmentation and quantification of aortic calcification at abdominal CT: application of a deep learning-based algorithm to a longitudinal screening cohort.

Peter M Graffy1, Jiamin Liu2, Stacy O'Connor3, Ronald M Summers2, Perry J Pickhardt4.   

Abstract

OBJECTIVE: To investigate an automated aortic calcium segmentation and scoring tool at abdominal CT in an adult screening cohort.
METHODS: Using instance segmentation with convolutional neural networks (Mask R-CNN), a fully automated vascular calcification algorithm was applied to a data set of 9914 non-contrast CT scans from 9032 consecutive asymptomatic adults (mean age, 57.5 ± 7.8 years; 4467 M/5447F) undergoing colonography screening. Follow-up scans were performed in a subset of 866 individuals (mean interval, 5.4 years). Automated abdominal aortic calcium volume, mass, and Agatston score were assessed. In addition, comparison was made with a separate validated semi-automated approach in a subset of 812 cases.
RESULTS: Mean values were significantly higher in males for Agatston score (924.2 ± 2066.2 vs. 564.2 ± 1484.2, p < 0.001), aortic calcium mass (222.2 ± 526.0 mg vs. 144.5 ± 405.4 mg, p < 0.001) and volume (699.4 ± 1552.4 ml vs. 426.9 ± 1115.5 HU, p < 0.001). Overall age-specific Agatston scores increased an average of 10%/year for the entire cohort; males had a larger Agatston score increase between the ages of 40 to 60 than females (91.2% vs. 75.1%, p < 0.001) and had significantly higher mean Agatston scores between ages 50 and 80 (p < 0.001). For the 812-scan subset with both automated and semi-automated methods, median difference in Agatston score was 66.4 with an r2 agreement value of 0.84. Among the 866-patient cohort with longitudinal follow-up, the average Agatston score change was 524.1 ± 1317.5 (median 130.9), reflecting a mean increase of 25.5% (median 73.6%).
CONCLUSION: This robust, fully automated abdominal aortic calcification scoring tool allows for both individualized and population-based assessment. Such data could be automatically derived at non-contrast abdominal CT, regardless of the study indication, allowing for opportunistic assessment of cardiovascular risk.

Entities:  

Keywords:  Aortic calcium; Artificial intelligence; Cardiovascular disease; Deep learning; Fully automated

Year:  2019        PMID: 30976827     DOI: 10.1007/s00261-019-02014-2

Source DB:  PubMed          Journal:  Abdom Radiol (NY)


  12 in total

1.  Fully Automated Deep Learning Tool for Sarcopenia Assessment on CT: L1 Versus L3 Vertebral Level Muscle Measurements for Opportunistic Prediction of Adverse Clinical Outcomes.

Authors:  Perry J Pickhardt; Alberto A Perez; John W Garrett; Peter M Graffy; Ryan Zea; Ronald M Summers
Journal:  AJR Am J Roentgenol       Date:  2021-08-18       Impact factor: 6.582

2.  Image intensity histograms as imaging biomarkers: application to immune-related colitis.

Authors:  Daniel T Huff; Peter Ferjancic; Mauro Namías; Hamid Emamekhoo; Scott B Perlman; Robert Jeraj
Journal:  Biomed Phys Eng Express       Date:  2021-09-30

3.  Automated CT biomarkers for opportunistic prediction of future cardiovascular events and mortality in an asymptomatic screening population: a retrospective cohort study.

Authors:  Perry J Pickhardt; Peter M Graffy; Ryan Zea; Scott J Lee; Jiamin Liu; Veit Sandfort; Ronald M Summers
Journal:  Lancet Digit Health       Date:  2020-03-02

4.  Atherosclerotic Plaque Burden on Abdominal CT: Automated Assessment With Deep Learning on Noncontrast and Contrast-enhanced Scans.

Authors:  Ronald M Summers; Daniel C Elton; Sungwon Lee; Yingying Zhu; Jiamin Liu; Mohammedhadi Bagheri; Veit Sandfort; Peter C Grayson; Nehal N Mehta; Peter A Pinto; W Marston Linehan; Alberto A Perez; Peter M Graffy; Stacy D O'Connor; Perry J Pickhardt
Journal:  Acad Radiol       Date:  2020-09-18       Impact factor: 3.173

5.  Diagnostic Performance of Multitarget Stool DNA and CT Colonography for Noninvasive Colorectal Cancer Screening.

Authors:  Perry J Pickhardt; Peter M Graffy; Benjamin Weigman; Nimrod Deiss-Yehiely; Cesare Hassan; Jennifer M Weiss
Journal:  Radiology       Date:  2020-08-11       Impact factor: 11.105

6.  Automated Liver Fat Quantification at Nonenhanced Abdominal CT for Population-based Steatosis Assessment.

Authors:  Peter M Graffy; Veit Sandfort; Ronald M Summers; Perry J Pickhardt
Journal:  Radiology       Date:  2019-09-17       Impact factor: 11.105

7.  Automated Abdominal CT Imaging Biomarkers for Opportunistic Prediction of Future Major Osteoporotic Fractures in Asymptomatic Adults.

Authors:  Perry J Pickhardt; Peter M Graffy; Ryan Zea; Scott J Lee; Jiamin Liu; Veit Sandfort; Ronald M Summers
Journal:  Radiology       Date:  2020-08-11       Impact factor: 11.105

8.  Deep learning-based muscle segmentation and quantification at abdominal CT: application to a longitudinal adult screening cohort for sarcopenia assessment.

Authors:  Peter M Graffy; Jiamin Liu; Perry J Pickhardt; Joseph E Burns; Jianhua Yao; Ronald M Summers
Journal:  Br J Radiol       Date:  2019-06-24       Impact factor: 3.039

Review 9.  Opportunistic Screening at Abdominal CT: Use of Automated Body Composition Biomarkers for Added Cardiometabolic Value.

Authors:  Perry J Pickhardt; Peter M Graffy; Alberto A Perez; Meghan G Lubner; Daniel C Elton; Ronald M Summers
Journal:  Radiographics       Date:  2021 Mar-Apr       Impact factor: 5.333

10.  Thoracic Aorta Calcium Detection and Quantification Using Convolutional Neural Networks in a Large Cohort of Intermediate-Risk Patients.

Authors:  Federico N Guilenea; Mariano E Casciaro; Ariel F Pascaner; Gilles Soulat; Elie Mousseaux; Damian Craiem
Journal:  Tomography       Date:  2021-10-28
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.