Advertisement

Current imaging of PE and emerging techniques: is there a role for artificial intelligence?

      Highlights

      • Technical standards and interpretive guidelines facilitate accurate diagnosis and characterization of pulmonary embolism (PE).
      • Spectral CT and MRI are emerging technologies for PE evaluation.
      • Rationale of AI for PE is based on morbidity and mortality risk, in the setting of potentially constrained resources.
      • AI may play a role in CTPA exam decision support, triage and computer-aided detection, and reporting of associated findings.

      Abstract

      Acute pulmonary embolism (PE) is a critical, potentially life-threatening finding on contrast-enhanced cross-sectional chest imaging. Timely and accurate diagnosis of thrombus acuity and extent directly influences patient management, and outcomes. Technical and interpretive pitfalls may present challenges to the radiologist, and by extension, pose nuance in the development and integration of artificial intelligence support tools. This review delineates imaging considerations for diagnosis of acute PE, and rationale, hurdles and applications of artificial intelligence for the PE task.

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Clinical Imaging
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Goldhaber S.Z.
        • Bounameaux H.
        Pulmonary embolism and deep vein thrombosis.
        Lancet. 2012; 379: 1835-1846https://doi.org/10.1016/S0140-6736(11)61904-1
        • Wang R.C.
        • Miglioretti D.L.
        • Marlow E.C.
        • Kwan M.L.
        • Theis M.K.
        • Bowles E.J.A.
        • et al.
        Trends in imaging for suspected pulmonary embolism across US health care systems, 2004 to 2016.
        JAMA Netw Open. 2020; 3https://doi.org/10.1001/JAMANETWORKOPEN.2020.26930
        • Jiménez D.
        • Bikdeli B.
        • Quezada A.
        • Muriel A.
        • Lobo J.L.
        • De Miguel-Diez J.
        • et al.
        Hospital volume and outcomes for acute pulmonary embolism: multinational population based cohort study.
        BMJ. 2019; 366https://doi.org/10.1136/BMJ.L4416
        • Kraaijpoel N.
        • Bleker S.M.
        • Meyer G.
        • Mahé I.
        • Muñoz A.
        • Bertoletti L.
        • et al.
        Treatment and long-term clinical outcomes of incidental pulmonary embolism in patients with cancer: an international prospective cohort study.
        J Clin Oncol. 2019; 37: 1713-1720https://doi.org/10.1200/JCO.18.01977
        • Chen Z.
        • Deblois S.
        • Toporowicz K.
        • Boldeanu I.
        • Francoeur M.O.
        • Sadouni M.
        • et al.
        Yield of CT pulmonary angiography in the diagnosis of acute pulmonary embolism: short report.
        BMC Res Notes. 2019; 12: 1-4https://doi.org/10.1186/S13104-019-4076-8/TABLES/2
        • Hayes S.A.
        • Soff G.A.
        • Zabor E.C.
        • Moskowitz C.S.
        • Liu C.C.
        • Ginsberg M.S.
        Clinical consequences of an indeterminate CT pulmonary angiogram in cancer patients.
        Clin Imaging. 2014; 38: 637https://doi.org/10.1016/J.CLINIMAG.2014.04.015
        • Abujudeh H.H.
        • Kaewlai R.
        • Farsad K.
        • Orr E.
        • Gilman M.
        • Shepard J.A.O.
        Computed tomography pulmonary angiography: an assessment of the radiology report.
        Acad Radiol. 2009; 16: 1309-1315https://doi.org/10.1016/J.ACRA.2009.06.012
        • Jones S.E.
        • Wittram C.
        The indeterminate CT pulmonary angiogram: imaging characteristics and patient clinical outcome.
        Radiology. 2005; 237: 329-337https://doi.org/10.1148/RADIOL.2371041520
        • Wittram C.
        How I do it: CT pulmonary angiography.
        AJR Am J Roentgenol. 2007; 188: 1255-1261https://doi.org/10.2214/AJR.06.1104
        • Ramadan S.U.
        • Kosar P.
        • Sonmez I.
        • Karahan S.
        • Kosar U.
        Optimisation of contrast medium volume and injection-related factors in CT pulmonary angiography: 64-slice CT study.
        Eur Radiol. 2010; 20: 2100-2107https://doi.org/10.1007/S00330-010-1782-Y
        • Tan S.
        • Nance J.W.
        • Haramati L.B.
        • Rajiah P.
        • Sherk W.M.
        • Le Gal G.
        • et al.
        Pulmonary CTA reporting: AJR expert panel narrative review. 2021: 1-9https://doi.org/10.2214/AJR.21.26646
        • Kerl J.M.
        • Lehnert T.
        • Schell B.
        • Bodelle B.
        • Beeres M.
        • Jacobi V.
        • et al.
        Intravenous contrast material administration at high-pitch dual-source CT pulmonary angiography: test bolus versus bolus-tracking technique.
        Eur J Radiol. 2012; 81: 2887-2891https://doi.org/10.1016/J.EJRAD.2011.09.018
        • Henzler T.
        • Meyer M.
        • Reichert M.
        • Krissak R.
        • Nance J.W.
        • Haneder S.
        • et al.
        Dual-energy CT angiography of the lungs: comparison of test bolus and bolus tracking techniques for the determination of scan delay.
        Eur J Radiol. 2012; 81: 132-138https://doi.org/10.1016/J.EJRAD.2010.06.023
        • Rodrigues J.C.L.
        • Mathias H.
        • Negus I.S.
        • Manghat N.E.
        • Hamilton M.C.K.
        Intravenous contrast medium administration at 128 multidetector row CT pulmonary angiography: bolus tracking versus test bolus and the implications for diagnostic quality and effective dose.
        Clin Radiol. 2012; 67: 1053-1060https://doi.org/10.1016/J.CRAD.2012.02.010
        • Wittram C.
        • Yoo A.J.
        Transient interruption of contrast on CT pulmonary angiography: proof of mechanism.
        J Thorac Imaging. 2007; 22: 125-129https://doi.org/10.1097/01.RTI.0000213566.78785.26
        • Dane B.
        • Patel H.
        • O’Donnell T.
        • Girvin F.
        • Brusca-Augello G.
        • Alpert J.B.
        • et al.
        Image quality on dual-energy CTPA virtual monoenergetic images: quantitative and qualitative assessment.
        Acad Radiol. 2018; 25: 1075-1086https://doi.org/10.1016/j.acra.2017.12.012
        • Yuan R.
        • Shuman W.P.
        • Earls J.P.
        • Hague C.J.
        • Mumtaz H.A.
        • Scott-Moncrieff A.
        • et al.
        Reduced iodine load at CT pulmonary angiography with dual-energy monochromatic imaging: comparison with standard CT pulmonary angiography - a prospective randomized trial.
        Radiology. 2012; 262: 290-297https://doi.org/10.1148/RADIOL.11110648/ASSET/IMAGES/LARGE/110648FIG 02.JPEG
        • Seyal A.R.
        • Arslanoglu A.
        • Abboud S.F.
        • Sahin A.
        • Horowitz J.M.
        • Yaghmai V.
        CT of the abdomen with reduced tube voltage in adults: a practical approach.
        Radiographics. 2015; 35: 1922-1939https://doi.org/10.1148/RG.2015150048
        • Henry T.S.
        • Hammer M.M.
        • Little B.P.
        • Jensen L.E.
        • Kligerman S.J.
        • Kanne J.P.
        • et al.
        Smoke: how to differentiate flow-related artifacts from pathology on thoracic computed tomographic angiography.
        J Thorac Imaging. 2019; 34: W109-W120https://doi.org/10.1097/RTI.0000000000000429
        • Kirsch J.
        • Brown R.K.J.
        • Henry T.S.
        • Javidan-Nejad C.
        • Jokerst C.
        • Julsrud P.R.
        • et al.
        ACR appropriateness Criteria ® acute chest pain-suspected pulmonary embolism.
        J Am Coll Radiol. 2017; 14: S2-S12https://doi.org/10.1016/J.JACR.2017.02.027
        • McCabe B.E.
        • Veselis C.A.
        • Goykhman I.
        • Hochhold J.
        • Eisenberg D.
        • Son H.
        Beyond pulmonary embolism; nonthrombotic pulmonary embolism as diagnostic challenges.
        Curr Probl Diagn Radiol. 2019; 48: 387-392https://doi.org/10.1067/J.CPRADIOL.2018.07.007
        • Sodhi K.S.
        • Saxena A.K.
        • Chandrashekhar G.
        • Bhatia A.
        • Singhi S.
        • Agarwal R.
        • et al.
        Vascular air embolism after contrast administration on 64 row multiple detector computed tomography: a prospective analysis.
        Lung India. 2015; 32: 216-219https://doi.org/10.4103/0970-2113.156216
        • Imanaka H.
        • Takahara B.
        • Yamaguchi H.
        • Nakataki E.
        • Mano A.
        • Inui D.
        • et al.
        Chest computed tomography of a patient revealing severe hypoxia due to amniotic fluid embolism: a case report.
        J Med Case Rep. 2010; 4: 1-3https://doi.org/10.1186/1752-1947-4-55/FIGURES/2
        • So A.
        • Nicolaou S.
        Spectral computed tomography: fundamental principles and recent developments.
        Korean J Radiol. 2021; 22: 86https://doi.org/10.3348/KJR.2020.0144
        • Willemink M.J.
        • Persson M.
        • Pourmorteza A.
        • Pelc N.J.
        • Fleischmann D.
        Photon-counting CT: technical principles and clinical prospects.
        Radiology. 2018; 289: 293-312https://doi.org/10.1148/RADIOL.2018172656/ASSET/IMAGES/LARGE/RADIOL.2018172656.FIG 22.JPEG
        • Sauter A.P.
        • Shapira N.
        • Kopp F.K.
        • Aichele J.
        • Bodden J.
        • Knipfer A.
        • et al.
        CTPA with a conventional CT at 100 kVp vs. A spectral-detector CT at 120 kVp: comparison of radiation exposure, diagnostic performance and image quality.
        Eur J Radiol Open. 2020; 7100234https://doi.org/10.1016/J.EJRO.2020.100234
      1. RV G, MK K, A T, A O, MS G. Advanced CT techniques for decreasing radiation dose, reducing sedation requirements, and optimizing image quality in children.
        Radiographics. 2019; 39: 709-726https://doi.org/10.1148/RG.2019180082
      2. EK W, AJ P, DF H, SA H, R P-J, J Z, et al. Dual-energy CT angiography for detection of pulmonary emboli: incremental benefit of iodine maps.
        Radiology. 2018; 289: 546-553https://doi.org/10.1148/RADIOL.2018180594
        • Castañer E.
        • Gallardo X.
        • Ballesteros E.
        • Andreu M.
        • Pallardó Y.
        • Mata J.M.
        • et al.
        CT diagnosis of chronic pulmonary thromboembolism.
        Radiographics. 2009; 29: 31-50https://doi.org/10.1148/rg.291085061
        • Konstantinides S.V.
        • Meyer G.
        • Bueno H.
        • Galié N.
        • Gibbs J.S.R.
        • Ageno W.
        • et al.
        2019 ESC guidelines for the diagnosis and management of acute pulmonary embolism developed in collaboration with the European Respiratory Society (ERS)the Task Force for the diagnosis and management of acute pulmonary embolism of the European Society of Cardiology (ESC).
        Eur Heart J. 2020; 41: 543-603https://doi.org/10.1093/EURHEARTJ/EHZ405
        • Metter D.
        • Tulchinsky M.
        • Freeman L.M.
        Current status of ventilation-perfusion scintigraphy for suspected pulmonary embolism.
        . 2017; 208: 489-494https://doi.org/10.2214/AJR.16.17195
        • Hatabu H.
        • Ohno Y.
        • Gefter W.B.
        • Parraga G.
        • Madore B.
        • Lee K.S.
        • et al.
        Expanding applications of pulmonary MRI in the clinical evaluation of lung disorders: Fleischner Society Position Paper.
        Radiology. 2020; 201138https://doi.org/10.1148/radiol.2020201138
        • Repplinger M.D.
        • Nagle S.K.
        • Harringa J.B.
        • Broman A.T.
        • Lindholm C.R.
        • François C.J.
        • et al.
        Clinical outcomes after magnetic resonance angiography (MRA) versus computed tomographic angiography (CTA) for pulmonary embolism evaluation.
        Emerg Radiol. 2018; 25: 469-477https://doi.org/10.1007/S10140-018-1609-8
        • Dirk Sostman H.
        • Jablonski K.A.
        • Woodard P.K.
        • Stein P.D.
        • Naidich D.P.
        • Chenevert T.L.
        • et al.
        Factors in the technical quality of gadolinium enhanced magnetic resonance angiography for pulmonary embolism in PIOPED III.
        Int J Cardiovasc Imaging. 2012; 28: 303-312https://doi.org/10.1007/S10554-011-9820-7
        • Miró Ò.
        • Jiménez S.
        • Mebazaa A.
        • Freund Y.
        • Burillo-Putze G.
        • Martín A.
        • et al.
        Pulmonary embolism in patients with COVID-19: incidence, risk factors, clinical characteristics, and outcome.
        Eur Heart J. 2021; 42: 3127-3142https://doi.org/10.1093/EURHEARTJ/EHAB314
        • Pourvaziri A.
        • Narayan A.K.
        • Tso D.
        • Baliyan V.
        • Glover M.
        • Bizzo B.C.
        • et al.
        Imaging information overload: quantifying the burden of interpretive and non-interpretive tasks for CT angiography for aortic pathologies in emergency radiology.
        Curr Probl Diagn Radiol. 2022; https://doi.org/10.1067/J.CPRADIOL.2022.01.008
        • Bruls R.J.M.
        • Kwee R.M.
        Workload for radiologists during on-call hours: dramatic increase in the past 15 years.
        Insights Imaging. 2020; 11: 121https://doi.org/10.1186/S13244-020-00925-Z
        • Harolds J.A.
        • Parikh J.R.
        • Bluth E.I.
        • Dutton S.C.
        • Recht M.P.
        Burnout of radiologists: frequency, risk factors, and remedies: a report of the ACR Commission on Human Resources.
        J Am Coll Radiol. 2016; 13: 411-416https://doi.org/10.1016/J.JACR.2015.11.003
        • Hanna T.N.
        • Lamoureux C.
        • Krupinski E.A.
        • Weber S.
        • Johnson J.O.
        Effect of shift, schedule, and volume on interpretive accuracy: a retrospective analysis of 2.9 million radiologic examinations.
        Radiology. 2018; 287: 205-212https://doi.org/10.1148/RADIOL.2017170555/ASSET/IMAGES/LARGE/RADIOL.2017170555.FIG-4.JPEG
        • Rosenkrantz A.B.
        • Wang W.
        • Hughes D.R.
        • Duszak R.
        A county-level analysis of the US radiologist workforce: physician supply and subspecialty characteristics.
        J Am Coll Radiol. 2018; 15: 601-606https://doi.org/10.1016/J.JACR.2017.11.007
        • Kligerman S.J.
        • Mitchell J.W.
        • Sechrist J.W.
        • Meeks A.K.
        • Galvin J.R.
        • White C.S.
        Radiologist performance in the detection of pulmonary embolism: features that favor correct interpretation and risk factors for errors.
        J Thorac Imaging. 2018; 33: 350-357https://doi.org/10.1097/RTI.0000000000000361
        • Aamc
        The complexities of physician supply and demand: projections from 2019 to 2034.
        2021
        • Secemsky E.
        • Chang Y.
        • Jain C.C.
        • Beckman J.A.
        • Giri J.
        • Jaff M.R.
        • et al.
        Contemporary management and outcomes of patients with massive and submassive pulmonary embolism.
        Am J Med. 2018; 131: 1506-1514.e0https://doi.org/10.1016/J.AMJMED.2018.07.035
        • Rajpurkar P.
        • Chen E.
        • Banerjee O.
        • Banerjee O.
        • Topol E.J.
        AI in health and medicine.
        Nat Med. 2022; 281: 31-38https://doi.org/10.1038/s41591-021-01614-0
        • Colak E.
        • Kitamura F.C.
        • Hobbs S.B.
        • Wu C.C.
        • Lungren M.P.
        • Prevedello L.M.
        • et al.
        The RSNA pulmonary embolism CT dataset.
        Radiol Artif Intell. 2021; 3e200254https://doi.org/10.1148/RYAI.2021200254
        • Rajan D.
        • Beymer D.
        • Abedin S.
        • Dehghan E.
        Pi-PE: a pipeline for pulmonary embolism detection using sparsely annotated 3D CT images.
        Proc Mach Learn Res. 2019; XX: 1-13
      3. C Z, HP C, A C, S P, J K, LM H, et al. Variabilities in reference standard by radiologists and performance assessment in detection of pulmonary embolism in CT pulmonary angiography.
        J Digit Imaging. 2019; 32: 1089-1096https://doi.org/10.1007/S10278-019-00228-W
        • Casey A.
        • Davidson E.
        • Poon M.
        • Dong H.
        • Duma D.
        • Grivas A.
        • et al.
        A systematic review of natural language processing applied to radiology reports.
        BMC Med Inform Decis Mak. 2021; 21: 179https://doi.org/10.1186/S12911-021-01533-7
        • Olthof A.W.
        • van Ooijen P.M.A.
        • Cornelissen L.J.
        Deep learning-based natural language processing in radiology: the impact of report complexity, disease prevalence, dataset size, and algorithm type on model performance.
        J Med Syst. 2021; 45https://doi.org/10.1007/S10916-021-01761-4
        • Lu M.T.
        • Meyersohn N.M.
        • Mayrhofer T.
        • Bittner D.O.
        • Emami H.
        • Puchner S.B.
        • et al.
        Central core laboratory versus site interpretation of coronary CT angiography: agreement and association with cardiovascular events in the PROMISE trial.
        Radiology. 2018; 287: 87-95https://doi.org/10.1148/RADIOL.2017172181/ASSET/IMAGES/LARGE/RADIOL.2017172181.TBL3.JPEG
        • Kaushal A.
        • Altman R.
        • Langlotz C.
        Geographic distribution of US cohorts used to train deep learning algorithms.
        JAMA. 2020; 324: 1212-1213https://doi.org/10.1001/JAMA.2020.12067
        • Larrazabal A.J.
        • Nieto N.
        • Peterson V.
        • Milone D.H.
        • Ferrante E.
        Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis.
        Proc Natl Acad Sci U S A. 2020; 117: 12592-12594https://doi.org/10.1073/PNAS.1919012117
        • Yi P.H.
        • Kim T.K.
        • Siegel E.
        • Yahyavi-Firouz-Abadi N.
        Demographic reporting in publicly available chest radiograph data sets: opportunities for mitigating sex and racial disparities in deep learning models.
        J Am Coll Radiol. 2022; 19: 192-200https://doi.org/10.1016/J.JACR.2021.08.018
        • Huang S.-C.
        • Pareek A.
        • Zamanian R.
        • Banerjee I.
        • Lungren M.P.
        Multimodal fusion with deep neural networks for leveraging CT imaging and electronic health record: a case-study in pulmonary embolism detection.
        Sci Rep. 2020; 10https://doi.org/10.1038/S41598-020-78888-W
        • Wittenberg R.
        • Peters J.F.
        • Sonnemans J.J.
        • Bipat S.
        • Prokop M.
        • Schaefer-Prokop C.M.
        Impact of image quality on the performance of computer-aided detection of pulmonary embolism. 196. 2012: 95-101https://doi.org/10.2214/AJR.09.4165
        • Burrell J.
        How the machine ‘thinks’: understanding opacity in machine learning algorithms.
        3. 2016https://doi.org/10.1177/2053951715622512
        • Yan Z.
        • Ip I.K.
        • Raja A.S.
        • Gupta A.
        • Kosowsky J.M.
        • Khorasani R.
        Yield of CT pulmonary angiography in the emergency department when providers override evidence-based clinical decision support. 282. 2016: 717-725https://doi.org/10.1148/RADIOL.2016151985
        • Richardson S.
        • Cohen S.
        • Khan S.
        • Zhang M.
        • Qiu G.
        • Oppenheim M.I.
        • et al.
        Higher imaging yield when clinical decision support is used.
        J Am Coll Radiol. 2020; 17: 496-503https://doi.org/10.1016/J.JACR.2019.11.021
        • Banerjee I.
        • Sofela M.
        • Yang J.
        • Chen J.H.
        • Shah N.H.
        • Ball R.
        • et al.
        Development and performance of the pulmonary embolism result forecast model (PERFORM) for computed tomography clinical decision support.
        JAMA Netw Open. 2019; 2 (e198719-e198719)https://doi.org/10.1001/JAMANETWORKOPEN.2019.8719
      4. F D, W A, C B, L G, M G, N R, et al. Prevalence and clinical history of incidental, asymptomatic pulmonary embolism: a meta-analysis.
        Thromb Res. 2010; 125: 518-522https://doi.org/10.1016/J.THROMRES.2010.03.016
      5. AS Bader University Y I Tocino IA Khan . Use of a Machine Learning Algorithm to Detect Incidental Pulmonary Embolus n.d.

      6. T W, DJ W, J B, B S, V P, AW S, et al. Automated detection of pulmonary embolism in CT pulmonary angiograms using an AI-powered algorithm.
        Eur Radiol. 2020; 30: 6545-6553https://doi.org/10.1007/S00330-020-06998-0
        • Müller-Peltzer K.
        • Kretzschmar L.
        • Negrão De Figueiredo G.
        • Crispin A.
        • Stahl R.
        • Bamberg F.
        • et al.
        Present limitations of artificial intelligence in the emergency setting - performance study of a commercial, computer-aided detection algorithm for pulmonary embolism.
        Rofo. 2021; 193: 1436-1443https://doi.org/10.1055/A-1515-2923
        • Liang J.
        • Bi J.
        Computer aided detection of pulmonary embolism with tobogganing and multiple instance classification in CT pulmonary angiography.
        Inf Process Med Imaging. 2007; 20: 630-641https://doi.org/10.1007/978-3-540-73273-0_52
      7. L S, FC F, CH N, G M, R B, N S, et al. Deep learning-based automated detection of pulmonary embolism on CT pulmonary angiograms: no significant effects on report communication times and patient turnaround in the emergency department nine months after technical implementation.
        Eur J Radiol. 2021; 141https://doi.org/10.1016/J.EJRAD.2021.109816
        • Mastora I.
        • Remy-Jardin M.
        • Masson P.
        • Galland E.
        • Delannoy V.
        • Bauchart J.J.
        • et al.
        Severity of acute pulmonary embolism: evaluation of a new spiral CT angiographic score in correlation with echocardiographic data.
        Eur Radiol. 2003; 13: 29-35https://doi.org/10.1007/S00330-002-1515-Y
        • Qanadli S.D.
        • El Hajjam M.
        • Vieillard-Baron A.
        • Joseph T.
        • Mesurolle B.
        • Oliva V.L.
        • et al.
        New CT index to quantify arterial obstruction in pulmonary embolism. 176. 2012: 1415-1420https://doi.org/10.2214/Ajr17661761415
      8. W L, M L, X G, P Z, L Z, R Z, et al. Evaluation of acute pulmonary embolism and clot burden on CTPA with deep learning.
        Eur Radiol. 2020; 30: 3567-3575https://doi.org/10.1007/S00330-020-06699-8
        • Meinel F.G.
        • Nance J.W.
        • Joseph Schoepf U.
        • Hoffmann V.S.
        • Thierfelder K.M.
        • Costello P.
        • et al.
        Predictive value of computed tomography in acute pulmonary embolism: systematic review and meta-analysis.
        Am J Med. 2015; 128: 747-759.e2https://doi.org/10.1016/J.AMJMED.2015.01.023
        • Foley R.W.
        • Glenn-Cox S.
        • Rossdale J.
        • Mynott G.
        • Burnett T.A.
        • Brown W.J.H.
        • et al.
        Automated calculation of the right ventricle to left ventricle ratio on CT for the risk stratification of patients with acute pulmonary embolism.
        Eur Radiol. 2021; 31: 6013-6020https://doi.org/10.1007/S00330-020-07605-Y