CardioVascular Systems Imaging and Artificial Intelligence (CVS.AI)

Background

The CVS.AI research core was developed in recognition of value of the superior and vast information available from cardiac imaging, and the power of Artificial Intelligence (AI) in harnessing this information to furthering clinically relevant research.

Expertise

Image analyses

1. CNN based approach for medical image segmentation
2. Machine learning for image analysis
3. Image processing and analysis (i.e. image extraction and quality metrics)
4. Small vessel disease identification on CTA, MRA and invasive angiography
5. Kinetic image feature dynamic tracking
   

Inferential and predictive machine intelligence for Image-based disease models and phenotyping

1. AI algorithm development, testing and validation using state-of-art platforms (e.g. Linux)
2. Development of imaging biomarkers for precision diagnosis and predictive modelling
3. Associative image-based learning between imaging characteristics and diseased phenotypes
4. Deriving machine intelligence-aided imaging signatures of various diseases and disorders

Research Area

1. AI driven national Platform for CT cOronary angiography for clinicaL and industriaL applicatiOns (APOLLO) is an AI-driven CT Coronary Angiography platform for automated anonymization, reporting, Agatston scoring and plaque quantification in CAD. It is a "one-stop" platform spanning diagnosis to clinical management and prognosis, and aid in predicting pharmacotherapy response. We aim to recruit 5000 subjects/CT scans across Singapore's 3 largest cardiac institutions.

2. Artificial Intelligence To Quantify Coronary Artery Disease from Lung Cancer Screening CT Scans aims to develop a rapid, fully automated high resolution AI model for the extraction and quantification of CAD using the coronary artery calcium score (CACS) for the identification and risk assessment of CAD from a lung CT scan. By doing so, this will allow the opportunistic and cost effective risk assessment of 2 diseases (lung cancer and CAD) from a single lung cancer screening CT scan, facilitating the large-scale improvement in preventative medicine of patients at risk of 2 diseases that pose the largest healthcare burden.

3. Artificial Intelligence in Medicine Transformation Program (AIMx) aims to create a joint strategic AI Health program in Singapore with SingHealth Health Service, Duke-NUS and A*STAR, including development of agnostic technical platforms for AI algorithms, novel clinical AI algorithms with technical capabilities for triaging and monitoring CVD with different clinical and imaging modalities (cardiac, radiological, retinal imaging with big data analytics with real-world clinical data). The eventual aim of this three year program is to commercialize and scale these AI algorithms in regional and international settings, offering low-cost and user-friendly digital solution for early diagnosis of CVD, more efficient delivery of care and improving patient outcomes.

Achievements

Grants

Relevant Publications

1. Zhang JM, Chandola G, Tan RS, et al, Zhong L. Quantification of effects of mean blood pressure and left ventricular mass on noninvasive fast fractional flow reserve. Am J Physiol Heart Circ Physiol 2020; 391(2):H360-H369

2. Wan M, Ma L, Zhao XD, Leng S, Zhang JM, Tan RS, Zhong L. Automatic segmentation of coronary artery lumen via anisotropic graph-cuts. Conf Proc IEEE Eng Med Biol Soc 2019;4871-4874.Cui HF, Xia Y, Zhang Y, Zhong L. Validation of right coronary artery lumen area from cardiac computed tomography against intravascular ultrasound. Machine Vision and Application 2018;29(8):1287-1298

3. Huang WM, Huang L, Lin Z, Huang S, Chi Y, Zhou J, Zhang JM, Tan RS, Zhong L. Coronary artery segmentation by deep learning neural networks on computed tomographic coronary angiographic images. Conf Proc IEEE Eng Med Biol Soc 2018;608-611.

4. Yang F, Yang XL, Teo SK, Lee G, Zhong L, Tan RS, Su Y. Multi-dimensional proprio-proximus machine learning for assessment of myocardial infarction. Comput Med Imaging Graph 2018;70:63-72.

5. Zhong L, Zhang JM, Su BY, Tan RS, Allen J, Kassab G. Application of patient-specific computational fluid dynamics in coronary and intra-cardiac flow simulations: challenges and opportunities. Front Physiol 2018;9:742

6. Zhang JM, Shuang D, Baskaran L, et al, Zhong L. Advanced analyses of computed tomography coronary angiography can help discriminate ischemic lesions. Int J Cardiol 2018:267:208-214

7. Tan XW, Zheng QS, Shi LM, et al, Zhong L. Combined diagnostic performance of coronary computed tomography angiography and computed derived fractional flow reserve for the evaluation of myocardial ischemia: A meta-analysis. Int J Cardiol 2017;236:100-106. 

8. Cui HF, Wang D, Wan M, et al, Zhong L. Fast marching and Rouge-Kutta based method for centerline extraction of right coronary artery in human patients. Cardiovasc Eng Tech 2016;7(2): 159-169.

9. Zhang JM, Zhong L, Luo T, Lomarda AM, Huo Y, Hap J, Lim ST, Tan RS, Wong ASL, Tan JWC, Yeo KK, Fam JM, Keng FYJ, Wan M, Su B, Zhao X, Allen JC, Kassab GS, Chua TSJ, Tan SY. Simplified models of non-invasive fractional flow reserve based on CT images. PLosOne 2016;11(5):e0153070.

10. Yoon YE, Baskaran L, Lee BC, Pandey MK, Goebel B, Lee S-E, Sung JM, Andreini D, Al-Mallah MH, Budoff MJ, Cademartiri F, Chinnaiyan K, Choi JH, Chun EJ, Conte E, Gottlieb I, Hadamitzky M, Kim YJ, Lee BK, Leipsic JA, Maffei E, Marques H, de Araújo Gonçalves P, Pontone G, Shin S, Narula J, Bax JJ, Lin FY-H, Shaw L, Chang H-J. Differential progression of coronary atherosclerosis according to plaque composition: a cluster analysis of PARADIGM registry data. Sci Rep 11:17121 . https://doi.org/10.1038/s41598-021-96616-w

11. Singh G, Al'Aref SJ, Lee BC, Lee JK, Tan SY, Lin FY, Chang HJ, Shaw LJ, Baskaran L. End-to-End, Pixel-Wise Vessel-Specific Coronary and Aortic Calcium Detection and Scoring Using Deep Learning. Diagnostics. 2021 Feb 2;11(2):215. doi: 10.3390/diagnostics11020215. PMID: 33540660.

12. Singh G, Hussain Y, Xu Z, Sholle E, Michalak K, Dolan K, Lee BC, van Rosendael AR, Fatima Z, Peña JM, Wilson PWF, Gotto AM, Shaw LJ, Baskaran L, Al'Aref SJ (2020) Comparing a novel machine learning method to the Friedewald formula and Martin-Hopkins equation for low-density lipoprotein estimation. PLOS ONE 15:e0239934 . https://doi.org/10.1371/journal.pone.0239934

13. Pandey, M., Xu, Z., Sholle, E., Maliakal, G., Singh, G., Fatima, Z., Larine, D., Lee, B. C., Wang, J., van Rosendael, A. R., Baskaran, L., Shaw, L. J., Min, J. K., & Al'Aref, S. J. (2020). Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing. PloS One, 15(7), e0236827. https://doi.org/10.1371/journal.pone.0236827

14. Al'Aref SJ, Singh G, Choi JW, Xu Z, Maliakal G, van Rosendael AR, Lee BC, Fatima Z, Andreini D, Bax JJ, Cademartiri F, Chinnaiyan K, Chow BJW, Conte E, Cury RC, Feuchtner G, Hadamitzky M, Kim YJ, Lee SE, Leipsic JA, Maffei E, Marques H, Plank F, Pontone G, Raff GL, Villines TC, Weirich HG, Cho I, Danad I, Han D, Heo R, Lee JH, Rizvi A, Stuijfzand WJ, Gransar H, Lu Y, Sung JM, Park HB, Berman DS, Budoff MJ, Samady H, Stone PH, Virmani R, Narula J, Chang HJ, Lin FY, Baskaran L, Shaw LJ, Min JK. A Boosted Ensemble Algorithm for Determination of Plaque Stability in High-Risk Patients on Coronary CTA. JACC Cardiovasc Imaging. 2020 Jul 9;(13):2162-2173. doi: 10.1016/j.jcmg.2020.03.025.

15. Baskaran L, Ying X, Xu Z, et al. Machine learning insight into the role of imaging and clinical variables for the prediction of obstructive coronary artery disease and revascularization: An exploratory analysis of the CONSERVE study. PLoS One. 2020;15(6):e0233791. doi: 10.1371/journal.pone.0233791

16. Baskaran L, Al'Aref SJ, Maliakal G, Lee BC, Xu Z, Choi JW. Automatic segmentation of multiple cardiovascular structures from cardiac computed tomography angiography images using deep learning. PLoS One. 2020;15(5): e0232573. doi: 10.1371/journal. pone.0232573

17. Han D, Kolli KK, Al'Aref SJ, Baskaran L, van Rosendael AR, Gransar H, Andreini D, Budoff MJ, Cademartiri F, Chinnaiyan K, Choi JH, Conte E, Marques H, de Araújo Gonçalves P, Gottlieb I, Hadamitzky M, Leipsic JA, Maffei E, Pontone G, Raff GL, Shin S, Kim YJ, Lee BK, Chun EJ, Sung JM, Lee SE, Virmani R, Samady H, Stone P, Narula J, Berman DS, Bax JJ, Shaw LJ, Lin FY, Min JK, Chang H. Machine Learning Framework to Identify Individuals at Risk of Rapid Progression of Coronary Atherosclerosis: From the PARADIGM Registry. Journal of the American Heart Association. 2020 Mar 3;(9):e013958. doi:10.1161/JAHA.119.013958

18. Baskaran L, Maliakal G, Al'Aref S, Singh G, Xu Z, Michalak K, Dolan K, Gianni U, van Rosendael A. van den Hoogen I, Han D, Stuijfzand W, Pandey M, Lee B, Lin FY, Pontone G, Knaapen P, Marques H, Bax J, Berman D, Chang HJ, Shaw LJ, Min JK. Identification and Quantification of Cardiovascular Structures from Coronary Computed Tomography Angiography: An End-to-End, Rapid, Pixel-wise Deep Learning Method. JACC Cardiovasc Imaging. 2019 Oct 11. 13:1163-1171. doi: 10.1016/j.jcmg.2019.08.025

19. Baskaran L, Ó Hartaigh B, Schulman-Marcus J, Gransar H, Lin F, Min JK. Dense calcium and lesion-specific ischemia: A comparison of CCTA with fractional flow reserve. Atherosclerosis. 2017 May;(260):163-168. doi: 10.1016/j.atherosclerosis.2017.02.017

20. Beecy AN, Chang Q, Anchouche K, Baskaran L, Elmore K, Kolli K, Wang H, Al'Aref S, Peña JM, Knight-Greenfield A, Patel P, Sun P, Zhang T, Kamel H, Gupta A, Min JK. A Novel Deep Learning Approach for Automated Diagnosis of Acute Ischemic Infarction on Computed Tomography. JACC Cardiovasc Imaging. 2018 May 11;(5):1-9. doi: 10.1016/j.jcmg.2018.03.012

21. Han D, Lee JH, Rizvi A, Gransar H, Baskaran L, Schulman-Marcus J, Ó Hartaigh B, Lin FY, Min JK. J Nucl Cardiol. Incremental role of resting myocardial computed tomography perfusion for predicting physiologically significant coronary artery disease: A machine learning approach.2018 Feb;25(1):223-233. doi: 10.1007/s12350-017-0834