1
|
Dasegowda G, Bizzo BC, Kaviani P, Karout L, Ebrahimian S, Digumarthy SR, Neumark N, Hillis JM, Kalra MK, Dreyer KJ. Auto-Detection of Motion Artifacts on CT Pulmonary Angiograms with a Physician-Trained AI Algorithm. Diagnostics (Basel) 2023; 13:778. [PMID: 36832266 PMCID: PMC9955317 DOI: 10.3390/diagnostics13040778] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2022] [Revised: 02/02/2023] [Accepted: 02/16/2023] [Indexed: 02/22/2023] Open
Abstract
Purpose: Motion-impaired CT images can result in limited or suboptimal diagnostic interpretation (with missed or miscalled lesions) and patient recall. We trained and tested an artificial intelligence (AI) model for identifying substantial motion artifacts on CT pulmonary angiography (CTPA) that have a negative impact on diagnostic interpretation. Methods: With IRB approval and HIPAA compliance, we queried our multicenter radiology report database (mPower, Nuance) for CTPA reports between July 2015 and March 2022 for the following terms: "motion artifacts", "respiratory motion", "technically inadequate", and "suboptimal" or "limited exam". All CTPA reports were from two quaternary (Site A, n = 335; B, n = 259) and a community (C, n = 199) healthcare sites. A thoracic radiologist reviewed CT images of all positive hits for motion artifacts (present or absent) and their severity (no diagnostic effect or major diagnostic impairment). Coronal multiplanar images from 793 CTPA exams were de-identified and exported offline into an AI model building prototype (Cognex Vision Pro, Cognex Corporation) to train an AI model to perform two-class classification ("motion" or "no motion") with data from the three sites (70% training dataset, n = 554; 30% validation dataset, n = 239). Separately, data from Site A and Site C were used for training and validating; testing was performed on the Site B CTPA exams. A five-fold repeated cross-validation was performed to evaluate the model performance with accuracy and receiver operating characteristics analysis (ROC). Results: Among the CTPA images from 793 patients (mean age 63 ± 17 years; 391 males, 402 females), 372 had no motion artifacts, and 421 had substantial motion artifacts. The statistics for the average performance of the AI model after five-fold repeated cross-validation for the two-class classification included 94% sensitivity, 91% specificity, 93% accuracy, and 0.93 area under the ROC curve (AUC: 95% CI 0.89-0.97). Conclusion: The AI model used in this study can successfully identify CTPA exams with diagnostic interpretation limiting motion artifacts in multicenter training and test datasets. Clinical relevance: The AI model used in the study can help alert technologists about the presence of substantial motion artifacts on CTPA, where a repeat image acquisition can help salvage diagnostic information.
Collapse
Affiliation(s)
- Giridhar Dasegowda
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Bernardo C. Bizzo
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Parisa Kaviani
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Lina Karout
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Shadi Ebrahimian
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
| | - Subba R. Digumarthy
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
| | - Nir Neumark
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - James M. Hillis
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Mannudeep K. Kalra
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| | - Keith J. Dreyer
- Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
- Mass General Brigham Data Science Office, Boston, MA 02114, USA
| |
Collapse
|
2
|
Eslami P, Thondapu V, Karady J, Hartman EMJ, Jin Z, Albaghdadi M, Lu M, Wentzel JJ, Hoffmann U. Physiology and coronary artery disease: emerging insights from computed tomography imaging based computational modeling. Int J Cardiovasc Imaging 2020; 36:2319-2333. [PMID: 32779078 PMCID: PMC8323761 DOI: 10.1007/s10554-020-01954-x] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/02/2020] [Accepted: 07/23/2020] [Indexed: 12/15/2022]
Abstract
Improvements in spatial and temporal resolution now permit robust high quality characterization of presence, morphology and composition of coronary atherosclerosis in computed tomography (CT). These characteristics include high risk features such as large plaque volume, low CT attenuation, napkin-ring sign, spotty calcification and positive remodeling. Because of the high image quality, principles of patient-specific computational fluid dynamics modeling of blood flow through the coronary arteries can now be applied to CT and allow the calculation of local lesion-specific hemodynamics such as endothelial shear stress, fractional flow reserve and axial plaque stress. This review examines recent advances in coronary CT image-based computational modeling and discusses the opportunity to identify lesions at risk for rupture much earlier than today through the combination of anatomic and hemodynamic information.
Collapse
Affiliation(s)
- Parastou Eslami
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
| | - Vikas Thondapu
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Julia Karady
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Eline M J Hartman
- Department of Cardiology, Biomedical Engineering, Erasmus MC, Rotterdam, The Netherlands
| | - Zexi Jin
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Mazen Albaghdadi
- Department of Cardiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Michael Lu
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Jolanda J Wentzel
- Department of Cardiology, Biomedical Engineering, Erasmus MC, Rotterdam, The Netherlands
| | - Udo Hoffmann
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| |
Collapse
|