Artificial intelligence in medical imaging: implications for interventional therapy of heart valve diseases
-
摘要: 医学影像人工智能技术的研究与进展，将极大促进现代心脏瓣膜病介入诊疗的进步。超声心动图、心脏磁共振、CT与心血管造影等成像技术，在心脏瓣膜病介入治疗术前患者精准筛选、术中关键手术操作引导与监测、术后疗效评价与预后评估过程中，均发挥重要作用。不同成像技术依据其成像原理，在介入治疗围手术期各具独特优势。临床上，医学成像人工操作与解读方式，存在明显局限性。人工智能通过大数据分析，拥有智能解读医学影像的能力，在心脏瓣膜疾病的介入治疗中已显示出巨大的潜在应用前景。本文将对心脏瓣膜疾病介入诊疗领域中医学影像人工智能研究、进展与应用价值进行介绍。Abstract: The advances in artificial intelligence in medical imaging will have great potential to promote interventional therapy for heart valve disease. Imaging technologies such as echocardiography, magnetic resonance, CT and angiocardiography all have been playing an important role in the screening of patients before therapy, the guidance and monitoring of key intraoperative procedures, and the evaluation of the therapeutic outcomes and the prognosis. Different imaging techniques have unique advantages in the perioperative period of intervention. In clinical practice, there are many limitations to imaging by manual manipulation and interpretation. The ability of artificial intelligence to intelligently interpret medical images through big data analysis, has shown great potential for the interventional treatment of heart valve disease. We present the recent progress and applications of artificial intelligence in medical imaging in the field of interventional treatment of heart valve diseases.
-
Key words:
- heart valve disease /
- artificial intelligence /
- medical imaging /
- interventional therapy
-
-
图 1 基于AI自动定量心脏结构和功能参数
Figure 1. AI-based automatic quantification of cardiac structural and functional parameters
-
[1] Nkomo VT, Gardin JM, Skelton TN, et al. Burden of valvular heart diseases: a population-based study[J]. Lancet, 2006, 368(9540): 1005-1011. doi: 10.1016/S0140-6736(06)69208-8
[2] Coffey S, Roberts-Thomson R, Brown A, et al. Global epidemiology of valvular heart disease[J]. Nat Rev Cardiol, 2021, 18(12): 853-864. doi: 10.1038/s41569-021-00570-z
[3] Zhang J, Gajjala S, Agrawal P, et al. Fully Automated Echocardiogram Interpretation in Clinical Practice[J]. Circulation, 2018, 138(16): 1623-1635. doi: 10.1161/CIRCULATIONAHA.118.034338
[4] Ouyang D, He B, Ghorbani A, et al. Video-based AI for beat-to-beat assessment of cardiac function[J]. Nature, 2020, 580(7802): 252-256. doi: 10.1038/s41586-020-2145-8
[5] Kang NG, Suh YJ, Han K, et al. Performance of Prediction Models for Diagnosing Severe Aortic Stenosis Based on Aortic Valve Calcium on Cardiac Computed Tomography: Incorporation of Radiomics and Machine Learning[J]. Korean J Radiol, 2021, 22(3): 334-343. doi: 10.3348/kjr.2020.0099
[6] Kwak S, Lee Y, Ko T, et al. Unsupervised Cluster Analysis of Patients With Aortic Stenosis Reveals Distinct Population With Different Phenotypes and Outcomes[J]. Circ Cardiovasc Imaging, 2020, 13(5): e009707. doi: 10.1161/CIRCIMAGING.119.009707
[7] Lachmann M, Rippen E, Schuster T, et al. Subphenotyping of Patients With Aortic Stenosis by Unsupervised Agglomerative Clustering of Echocardiographic and Hemodynamic Data[J]. JACC Cardiovasc Interv, 2021, 14(19): 2127-2140. doi: 10.1016/j.jcin.2021.08.034
[8] Sengupta PP, Shrestha S, Kagiyama N, et al. A Machine-Learning Framework to Identify Distinct Phenotypes of Aortic Stenosis Severity[J]. JACC Cardiovasc Imaging, 2021, 14(9): 1707-1720. doi: 10.1016/j.jcmg.2021.03.020
[9] Moghaddasi H, Nourian S. Automatic assessment of mitral regurgitation severity based on extensive textural features on 2D echocardiography videos[J]. Comput Biol Med, 2016, 73: 47-55. doi: 10.1016/j.compbiomed.2016.03.026
[10] Pimor A, Galli E, Vitel E, et al. Predictors of post-operative cardiovascular events, focused on atrial fibrillation, after valve surgery for primary mitral regurgitation[J]. Eur Heart J Cardiovasc Imaging, 2019, 20(2): 177-184.
[11] Bartko PE, Heitzinger G, Spinka G, et al. Principal Morphomic and Functional Components of Secondary Mitral Regurgitation[J]. JACC Cardiovasc Imaging, 2021, 14(12): 2288-2300. doi: 10.1016/j.jcmg.2021.05.020
[12] Ouyang D, Thomas JD. Characterizing Mitral Regurgitation With Precision Phenotyping and Unsupervised Learning[J]. JACC Cardiovasc Imaging, 2021, 14(12): 2301-2302. doi: 10.1016/j.jcmg.2021.06.023
[13] Casaclang-Verzosa G, Shrestha S, Khalil MJ, et al. Network Tomography for Understanding Phenotypic Presentations in Aortic Stenosis[J]. JACC Cardiovasc Imaging, 2019, 12(2): 236-248. doi: 10.1016/j.jcmg.2018.11.025
[14] Playford D, Bordin E, Mohamad R, et al. Enhanced Diagnosis of Severe Aortic Stenosis Using Artificial Intelligence: A Proof-of-Concept Study of 530, 871 Echocardiograms[J]. JACC Cardiovasc Imaging, 2020, 13(4): 1087-1090. doi: 10.1016/j.jcmg.2019.10.013
[15] Thyregod HG, Steinbrüchel DA, Ihlemann N, et al. Transcatheter Versus Surgical Aortic Valve Replacement in Patients With Severe Aortic Valve Stenosis: 1-Year Results From the All-Comers NOTION Randomized Clinical Trial[J]. J Am Coll Cardiol, 2015, 65(20): 2184-2194. doi: 10.1016/j.jacc.2015.03.014
[16] Leon MB, Smith CR, Mack MJ, et al. Transcatheter or Surgical Aortic-Valve Replacement in Intermediate-Risk Patients[J]. N Engl J Med, 2016, 374(17): 1609-1620. doi: 10.1056/NEJMoa1514616
[17] Al WA, Jung HY, Yun ID, et al. Automatic aortic valve landmark localization in coronary CT angiography using colonial walk[J]. PLoS One, 2018, 13(7): e0200317. doi: 10.1371/journal.pone.0200317
[18] Theriault-Lauzier P, Alsosaimi H, Mousavi N, et al. Recursive multiresolution convolutional neural networks for 3D aortic valve annulus planimetry[J]. Int J Comput Assist Radiol Surg, 2020, 15(4): 577-588. doi: 10.1007/s11548-020-02131-0
[19] Astudillo P, De Beule M, Dambre J, et al. Towards safe and efficient preoperative planning of transcatheter mitral valve interventions[J]. Morphologie, 2019, 103(343): 139-147. doi: 10.1016/j.morpho.2019.09.002
[20] de Jaegere P, De Santis G, Rodriguez-Olivares R, et al. Patient-Specific Computer Modeling to Predict Aortic Regurgitation After Transcatheter Aortic Valve Replacement[J]. JACC Cardiovasc Interv, 2016, 9(5): 508-512. doi: 10.1016/j.jcin.2016.01.003
[21] Auricchio F, Conti M, Morganti S, et al. Simulation of transcatheter aortic valve implantation: a patient-specific finite element approach[J]. Comput MethodsBiomech Biomed Engin, 2014, 17(12): 1347-1357. doi: 10.1080/10255842.2012.746676
[22] Rocatello G, El Faquir N, de Backer O, et al. The Impact of Size and Position of a Mechanical Expandable Transcatheter Aortic Valve: Novel Insights Through Computational Modelling and Simulation[J]. J Cardiovasc Transl Res, 2019, 12(5): 435-446. doi: 10.1007/s12265-019-09877-2
[23] Astudillo P, Mortier P, Bosmans J, et al. Enabling Automated Device Size Selection for Transcatheter Aortic Valve Implantation[J]. J Interv Cardiol, 2019, 2019: 3591314.
[24] Mansi T, Voigt I, Georgescu B, et al. An integrated framework for finite-element modeling of mitral valve biomechanics from medical images: application to MitralClip intervention planning[J]. Med Image Anal, 2012, 16(7): 1330-1346. doi: 10.1016/j.media.2012.05.009
[25] Biaggi P, Sager DF, Külling J, et al. Potential Value of Fusion Imaging and Automated Three-Dimensional Heart Segmentation During Transcatheter Aortic Valve Replacement[J]. J Am Soc Echocardiogr, 2020, 33(4): 516-517. e1. doi: 10.1016/j.echo.2019.12.012
[26] Biaggi P, Nijhof N, Corti R. Automated anatomical intelligence: next-generation fusion imaging during structural heart interventions[J]. Eur Heart J, 2017, 38(18): 1412.
[27] Faletra FF, Pozzoli A, Agricola E, et al. Echocardiographic-fluoroscopic fusion imaging for transcatheter mitral valve repair guidance[J]. Eur Heart J Cardiovasc Imaging, 2018, 19(7): 715-726. doi: 10.1093/ehjci/jey067
[28] Luo Z, Cai J, Peters TM, et al. Intra-operative 2-D ultrasound and dynamic 3-D aortic model registration for magnetic navigation of transcatheter aortic valve implantation[J]. IEEE Trans Med Imaging, 2013, 32(11): 2152-2165. doi: 10.1109/TMI.2013.2275233
[29] Mazomenos EB, Chang PL, Rippel RA, et al. Catheter manipulation analysis for objective performance and technical skills assessment in transcatheter aortic valve implantation[J]. Int J Comput Assist Radiol Surg, 2016, 11(6): 1121-1131. doi: 10.1007/s11548-016-1391-6
[30] Schultz C, Rodriguez-Olivares R, Bosmans J, et al. Patient-specific image-based computer simulation for theprediction of valve morphology and calcium displacement after TAVI with the Medtronic CoreValve and the Edwards SAPIEN valve[J]. EuroIntervention, 2016, 11(9): 1044-1052. doi: 10.4244/EIJV11I9A212
[31] de Jaegere P, Rajani R, Prendergast B, et al. Patient-Specific Computer Modeling for the Planning of Transcatheter Mitral Valve Replacement[J]. J Am Coll Cardiol, 2018, 72(8): 956-958.
[32] Guerrero M, Urena M, Wang DD, et al. Reply: Patient-Specific Computer Modeling for the Planning of Transcatheter Mitral Valve Replacement[J]. J Am Coll Cardiol, 2018, 72(8): 958. doi: 10.1016/j.jacc.2018.06.020
[33] Wang DD, Eng MH, Greenbaum AB, et al. Validating a prediction modeling tool for left ventricular outflow tract(LVOT)obstruction after transcatheter mitral valve replacement(TMVR)[J]. Catheter Cardiovasc Interv, 2018, 92(2): 379-387. doi: 10.1002/ccd.27447
[34] Wang DD, Eng M, Greenbaum A, et al. Predicting LVOT Obstruction After TMVR[J]. JACC Cardiovasc Imaging, 2016, 9(11): 1349-1352. doi: 10.1016/j.jcmg.2016.01.017
[35] Karády J, Ntalas I, Prendergast B, et al. Transcatheter mitral valve replacement in mitral annulus calcification-"The art of computer simulation"[J]. J Cardiovasc Comput Tomogr, 2018, 12(2): 153-157. doi: 10.1016/j.jcct.2017.12.007
[36] Hernandez-Suarez DF, Kim Y, Villablanca P, et al. Machine Learning Prediction Models for In-Hospital Mortality After Transcatheter Aortic Valve Replacement[J]. JACC Cardiovasc Interv, 2019, 12(14): 1328-1338. doi: 10.1016/j.jcin.2019.06.013
[37] Navarese EP, Zhang Z, Kubica J, et al. Development and Validation of a Practical Model to Identify Patients at Risk of Bleeding After TAVR[J]. JACC Cardiovasc Interv, 2021, 14(11): 1196-1206. doi: 10.1016/j.jcin.2021.03.024
[38] Okuno T, Overtchouk P, Asami M, et al. Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement[J]. Sci Rep, 2021, 11(1): 18754. doi: 10.1038/s41598-021-98265-5
[39] Hernandez-Suarez DF, Ranka S, Kim Y, et al. Machine-Learning-Based In-Hospital Mortality Prediction for Transcatheter Mitral Valve Repair in the United States[J]. Cardiovasc Revasc Med, 2021, 22: 22-28. doi: 10.1016/j.carrev.2020.06.017
-
下载:
图(2)
计量
- 文章访问数: 3679
- PDF下载数: 3983
- 施引文献: 0