1
|
Yang W, Chen C, Yang Y, Chen L, Yang C, Gong L, Wang J, Shi F, Wu D, Yan F. Diagnostic performance of deep learning-based vessel extraction and stenosis detection on coronary computed tomography angiography for coronary artery disease: a multi-reader multi-case study. LA RADIOLOGIA MEDICA 2023; 128:307-315. [PMID: 36800112 DOI: 10.1007/s11547-023-01606-9] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/13/2022] [Accepted: 02/03/2023] [Indexed: 02/18/2023]
Abstract
BACKGROUND Post-processing and interpretation of coronary CT angiography (CCTA) imaging are time-consuming and dependent on the reader's experience. An automated deep learning (DL)-based imaging reconstruction and diagnosis system was developed to improve diagnostic accuracy and efficiency. METHODS Our study including 374 cases from five sites, inviting 12 radiologists, assessed the DL-based system in diagnosing obstructive coronary disease with regard to diagnostic performance, imaging post-processing and reporting time of radiologists, with invasive coronary angiography as a standard reference. The diagnostic performance of DL system and DL-assisted human readers was compared with the traditional method of human readers without DL system. RESULTS Comparing the diagnostic performance of human readers without DL system versus with DL system, the AUC was improved from 0.81 to 0.82 (p < 0.05) at patient level and from 0.79 to 0.81 (p < 0.05) at vessel level. An increase in AUC was observed in inexperienced radiologists (p < 0.05), but was absent in experienced radiologists. Regarding diagnostic efficiency, comparing the DL system versus human reader, the average post-processing and reporting time was decreased from 798.60 s to 189.12 s (p < 0.05). The sensitivity and specificity of using DL system alone were 93.55% and 59.57% at patient level and 83.23% and 79.97% at vessel level, respectively. CONCLUSIONS With the DL system serving as a concurrent reader, the overall post-processing and reading time was substantially reduced. The diagnostic accuracy of human readers, especially for inexperienced readers, was improved. DL-assisted human reader had the potential of being the reading mode of choice in clinical routine.
Collapse
Affiliation(s)
- Wenjie Yang
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Chihua Chen
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Yanzhao Yang
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Lei Chen
- Department of Radiology, Peking University People's Hospital, Beijing, China
| | - Changwei Yang
- Department of Radiology, Shanghai East Hospital, Tongji University School of Medicine, Shanghai, China
| | - Lianggeng Gong
- Department of Radiology, Second Affiliated Hospital of Nanchang University, Nanchang, China
| | - Jianing Wang
- Department of Radiology, Affiliated Hospital of Hebei University, Baoding, China
| | - Feng Shi
- Shanghai United Imaging Intelligence Co., Ltd, Shanghai, China
| | - Dijia Wu
- Shanghai United Imaging Intelligence Co., Ltd, Shanghai, China
| | - Fuhua Yan
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
| |
Collapse
|
2
|
Automated Identification of Coronary Arteries in Assisting Inexperienced Readers: Comparison between Two Commercial Vendors. Diagnostics (Basel) 2022; 12:diagnostics12081987. [PMID: 36010337 PMCID: PMC9406865 DOI: 10.3390/diagnostics12081987] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2022] [Revised: 08/14/2022] [Accepted: 08/15/2022] [Indexed: 11/16/2022] Open
Abstract
Background: to assess the performance and speed of two commercially available advanced cardiac software packages in the automated identification of coronary vessels as an aiding tool for inexperienced readers. Methods: Hundred and sixty patients undergoing coronary CT angiography (CCTA) were prospectively enrolled from February until September 2021 and randomized in two groups, each one composed by 80 patients. Patients in group 1 were scanned on Revolution EVO CT Scanner (GE Healthcare), while patients in group 2 had the CCTA performed on Brilliance iCT (Philips Healthcare); each examination was evaluated on the respective vendor proprietary advanced cardiac software (software 1 and 2, respectively). Two inexperienced readers in cardiac imaging verified the software performance in the automated identification of the three major coronary vessels: (RCA, LCx, and LAD) and in the number of identified coronary segments. Time of analysis was also recorded. Results: software 1 correctly and automatically nominated 202/240 (84.2%) of the three main coronary vessels, while software 2 correctly identified 191/240 (79.6%) (p = 0.191). Software 1 achieved greater performances in recognizing the LCx (81.2% versus 67.5%; p = 0.048), while no differences have been reported in detecting the RCA (p = 0.679), and the LAD (p = 0.618). On a per-segment analysis, software 1 outperformed software 2, automatically detecting 942/1062 (88.7%) coronary segments, while software 2 detected 797/1078 (73.9%) (p < 0.001). Average reconstruction and detection time was of 13.8 s for software 1 and 21.9 s for software 2 (p < 0.001). Conclusions: automated cardiac software packages are a reliable and time-saving tool for inexperienced reader. Software 1 outperforms software 2 and might therefore better assist inexperienced CCTA readers in automated identification of the three main vessels and coronaries segments, with a consistent time saving of the reading session.
Collapse
|
3
|
Xu J, Chen L, Wu X, Li C, Ai G, Liu Y, Tian B, Guo D, Fang Z. Do plaque-related factors affect the diagnostic performance of an artificial intelligence coronary-assisted diagnosis system? Comparison with invasive coronary angiography. Eur Radiol 2021; 32:1866-1878. [PMID: 34564743 DOI: 10.1007/s00330-021-08299-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2021] [Revised: 08/12/2021] [Accepted: 08/23/2021] [Indexed: 11/24/2022]
Abstract
OBJECTIVE The aim of this study was to investigate the effects of plaque-related factors on the diagnostic performance of an artificial intelligence coronary-assisted diagnosis system (AI-CADS). METHODS Patients who underwent coronary computed tomography angiography (CCTA) and invasive coronary angiography (ICA) were retrospectively included in this study. The degree of stenosis in each vessel was collected from CCTA and ICA, and the information on plaque-related factors (plaque length, plaque type, and coronary artery calcium score (CAC)) of the vessels with plaques was collected from CCTA. RESULTS In total, 1224 vessels in 306 patients (166 men; 65.7 ± 10.1 years) were analyzed. Of these, 391 vessels in 249 patients showed significant stenosis using ICA as the gold standard. Using per-vessel as the unit, the area under the curves of coronary stenosis ≥ 50% for AI-CADS, doctor, and AI-CADS + doctor was 0.764, 0.837, and 0.853, respectively. The accuracies in interpreting the degree of coronary stenosis were 56.0%, 68.1%, and 71.2%, respectively. Seven hundred fifty vessels showed plaques on CCTA; plaque type did not affect the interpretation results by AI-CADS (chi-square test: p = 0.0093; multiple logistic regression: p = 0.4937). However, the interpretation results for plaque length (chi-square test: p < 0.0001; multiple logistic regression: p = 0.0061) and CACs (chi-square test: p < 0.0001; multiple logistic regression: p = 0.0001) were significantly different. CONCLUSION AI-CADS has an ability to distinguish ≥ 50% coronary stenosis, but additional manual interpretation based on AI-CADS is necessary. The plaque length and CACs will affect the diagnostic performance of AI-CADS. KEY POINTS • AI-CADS can help radiologists quickly assess CCTA and improve diagnostic confidence. • Additional manual interpretation on the basis of AI-CADS is necessary. • The plaque length and CACs will affect the diagnostic performance of AI-CADS.
Collapse
Affiliation(s)
- Jie Xu
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Linli Chen
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Xiaojia Wu
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Chuanming Li
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Guangyong Ai
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Yuexi Liu
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Bitong Tian
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Dajing Guo
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China.
| | - Zheng Fang
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China.
| |
Collapse
|
4
|
Liu CY, Tang CX, Zhang XL, Chen S, Xie Y, Zhang XY, Qiao HY, Zhou CS, Xu PP, Lu MJ, Li JH, Lu GM, Zhang LJ. Deep learning powered coronary CT angiography for detecting obstructive coronary artery disease: The effect of reader experience, calcification and image quality. Eur J Radiol 2021; 142:109835. [PMID: 34237493 DOI: 10.1016/j.ejrad.2021.109835] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2021] [Revised: 05/28/2021] [Accepted: 06/23/2021] [Indexed: 02/06/2023]
Abstract
OBJECTIVES To investigate the effect of reader experience, calcification and image quality on the performance of deep learning (DL) powered coronary CT angiography (CCTA) in automatically detecting obstructive coronary artery disease (CAD) with invasive coronary angiography (ICA) as reference standard. METHODS A total of 165 patients (680 vessels and 1505 segments) were included in this study. Three sessions were performed in order: (1) The artificial intelligence (AI) software automatically processed CCTA images, stenosis degree and processing time were recorded for each case; (2) Six cardiovascular radiologists with different experiences (low/ intermediate/ high experience) independently performed image post-processing and interpretation of CCTA, (3) AI + human reading was performed. Luminal stenosis ≥50% was defined as obstructive CAD in ICA and CCTA. Diagnostic performances of AI, human reading and AI + human reading were evaluated and compared on a per-patient, per-vessel and per-segment basis with ICA as reference standard. The effects of calcification and image quality on the diagnostic performance were also studied. RESULTS The average post-processing and interpretation times of AI was 2.3 ± 0.6 min per case, reduced by 76%, 72%, 69% compared with low/ intermediate/ high experience readers (all P < 0.001), respectively. On a per-patient, per-vessel and per-segment basis, with ICA as reference method, the AI overall diagnostic sensitivity for detecting obstructive CAD were 90.5%, 81.4%, 72.9%, the specificity was 82.3%, 93.9%, 95.0%, with the corresponding areas under the curve (AUCs) of 0.90, 0.90, 0.87, respectively. Compared to human readers, the diagnostic performance of AI was higher than that of low experience readers (all P < 0.001). The diagnostic performance of AI + human reading was higher than human reading alone, and AI + human readers' ability to correctly reclassify obstructive CAD was also improved, especially for low experience readers (Per-patient, the net reclassification improvement (NRI) = 0.085; per-vessel, NRI = 0.070; and per-segment, NRI = 0.068, all P < 0.001). The diagnostic performance of AI was not significantly affected by calcification and image quality (all P > 0.05). CONCLUSIONS AI can substantially shorten the post-processing time, while AI + human reading model can significantly improve the diagnostic performance compared with human readers, especially for inexperienced readers, regardless of calcification severity and image quality.
Collapse
Affiliation(s)
- Chun Yu Liu
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Chun Xiang Tang
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Xiao Lei Zhang
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Sui Chen
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Yuan Xie
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Xin Yuan Zhang
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Hong Yan Qiao
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Chang Sheng Zhou
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Peng Peng Xu
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Meng Jie Lu
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Jian Hua Li
- Department of Cardiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Guang Ming Lu
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China
| | - Long Jiang Zhang
- Department of Diagnostic Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu 210002, PR China.
| |
Collapse
|
5
|
Yabushita H, Goto S, Nakamura S, Oka H, Nakayama M, Goto S. Development of Novel Artificial Intelligence to Detect the Presence of Clinically Meaningful Coronary Atherosclerotic Stenosis in Major Branch from Coronary Angiography Video. J Atheroscler Thromb 2020; 28:835-843. [PMID: 33012741 PMCID: PMC8326176 DOI: 10.5551/jat.59675] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/03/2022] Open
Abstract
Aim:
The clinically meaningful coronary stenosis is diagnosed by trained interventional cardiologists. Whether artificial intelligence (AI) could detect coronary stenosis from CAG video is unclear.
Methods:
The 199 consecutive patients who underwent coronary arteriography (CAG) with chest pain between December 2018 and May 2019 was enrolled. Each patient underwent CAG with multiple view resulting in total numbers of 1,838 videos. A multi-layer 3-dimensional convolution neural network (CNN) was trained as an AI to detect clinically meaningful coronary artery stenosis diagnosed by the expert interventional cardiologist, using data from 146 patients (resulted in 1,359 videos) randomly selected from the entire dataset (training dataset). This training dataset was further split into 109 patients (989 videos) for derivation and 37 patients (370 videos) for validation. The AI developed in derivation cohort was tuned in validation cohort to make final model.
Results:
The final model was selected as the model with best performance in validation dataset. Then, the predictive accuracy of final model was tested with the remaining 53 patients (479 videos) in test dataset. Our AI model showed a c-statistic of 0.61 in validation dataset and 0.61 in test dataset, respectively.
Conclusion:
An artificial intelligence applied to CAG videos could detect clinically meaningful coronary atherosclerotic stenosis diagnosed by expert cardiologists with modest predictive value. Further studies with improved AI at larger sample size is necessary.
Collapse
Affiliation(s)
- Hiroto Yabushita
- Department of Medicine (Cardiology), Tokai University School of Medicine.,Department of Cardiology, New-Tokyo Hospital
| | - Shinichi Goto
- Department of Medicine (Cardiology), Tokai University School of Medicine
| | | | - Hideki Oka
- Department of Medicine (Cardiology), Tokai University School of Medicine
| | - Masamitsu Nakayama
- Department of Medicine (Cardiology), Tokai University School of Medicine
| | - Shinya Goto
- Department of Medicine (Cardiology), Tokai University School of Medicine
| |
Collapse
|
6
|
Computer-aided detection in musculoskeletal projection radiography: A systematic review. Radiography (Lond) 2018; 24:165-174. [DOI: 10.1016/j.radi.2017.11.002] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/24/2017] [Revised: 10/31/2017] [Accepted: 11/16/2017] [Indexed: 11/17/2022]
|
7
|
Abd alamir M, Noack P, Jang KH, Moore JA, Goldberg R, Poon M. Computer-aided analysis of 64- and 320-slice coronary computed tomography angiography: a comparison with expert human interpretation. Int J Cardiovasc Imaging 2018; 34:1473-1483. [DOI: 10.1007/s10554-018-1361-x] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/12/2018] [Accepted: 04/20/2018] [Indexed: 10/17/2022]
|
8
|
Sun Y, Hua Y, Wang M, Mao D, Jin X, Li C, Shi K, Xu J. Evaluation of a High Concentrated Contrast Media Injection Protocol in Combination with Low Tube Current for Dose Reduction in Coronary Computed Tomography Angiography: A Randomized, Two-center Prospective Study. Acad Radiol 2017; 24:1482-1490. [PMID: 28800951 DOI: 10.1016/j.acra.2017.07.001] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2017] [Revised: 07/03/2017] [Accepted: 07/05/2017] [Indexed: 11/25/2022]
Abstract
RATIONALE AND OBJECTIVES The study aimed to prospectively evaluate the radiation dose reduction potential and image quality (IQ) of a high-concentration contrast media (HCCM) injection protocol in combination with a low tube current (mAs) in coronary computed tomography angiography. MATERIALS AND METHODS Eighty-one consecutive patients (mean age: 62 years; 34 females; body mass index: 18-31) were included and randomized-assigned into two groups. All computed tomography (CT) examinations were performed in two groups with the same tube voltage (100 kV), flow rate of contrast medium (5.0 mL/s), and iodine dose (22.8 g). An automatic mAs and low concentration contrast medium (300 mgI/mL) were used in group A, whereas effective mAs was reduced by a factor 0.6 along with HCCM (400 mgI/mL) in group B. Radiation dose was assessed (CT dose index [CTDIvol] and dose length product), and vessel-based objective IQ for various regions of interest (enhancement, noise, signal-to-noise ratio, and contrast-to-noise ratio), subjective IQ, noise, and motion artifacts were analyzed overall and vessel-based with a 5-point Likert scale. RESULTS The CT attenuation of coronary arteries and image noise in group B were significantly higher than those in group A (ranges: 507.5-548.1 Hounsfield units vs 407.5-444.5 Hounsfield units; and 20.3 ± 8.6 vs 17.7 ± 8.0) (P ≤ 0.0166). There was no significant difference between the two groups in signal-to-noise ratio, contrast-to-noise ratio, and subjective IQ of coronary arteries (29.4-31.7, 30.0-37.0, and medium score of 5 in group A vs 29.4-32.4, 27.7-36.3, and medium score of 5 in group B, respectively, P ≥ 0.1859). Both mean CTDIvol and dose length product in group B were 58% of those of group A. CONCLUSIONS HCCM combined with low tube current allows dose reduction in coronary computed tomography angiography and does not compromise IQ.
Collapse
|
9
|
Abstract
Coronary CT angiography (CTA) has emerged as a highly reliable and non-invasive modality for the exclusion of coronary artery disease. Recent technological advancements in coronary CTA imaging allow for robust qualitative and quantitative assessment of atherosclerotic plaques. Furthermore, CTA is a promising modality for functional evaluation of coronary lesions. Individual plaque features, the extent and severity of atherosclerotic plaque burden were proposed to improve cardiovascular risk stratification. It has been suggested that total atherosclerotic plaque burden is a stronger predictor of coronary events than total ischemia burden. The quest to noninvasively detect individual vulnerable plaques still remains. In the current review we sought to summarize state-of-the-art coronary artery plaque assessment by CTA.
Collapse
|
10
|
Cardiovascular imaging 2014 in the International Journal of Cardiovascular Imaging. Int J Cardiovasc Imaging 2015; 31:447-61. [DOI: 10.1007/s10554-015-0627-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|