nach oben

Erschienen in:

03.08.2023 | Imaging Informatics and Artificial Intelligence

Added value of an artificial intelligence algorithm in reducing the number of missed incidental acute pulmonary embolism in routine portal venous phase chest CT

verfasst von: Eline Langius-Wiffen, Pim A. de Jong, Firdaus A. Mohamed Hoesein, Lisette Dekker, Andor F. van den Hoven, Ingrid M. Nijholt, Martijn F. Boomsma, Wouter B. Veldhuis

Erschienen in: European Radiology | Ausgabe 1/2024

Einloggen, um Zugang zu erhalten

Abstract

Objectives

The purpose of this study was to evaluate the incremental value of artificial intelligence (AI) compared to the diagnostic accuracy of radiologists alone in detecting incidental acute pulmonary embolism (PE) on routine portal venous contrast-enhanced chest computed tomography (CT).

Methods

CTs of 3089 consecutive patients referred to the radiology department for a routine contrast-enhanced chest CT between 27–5-2020 and 31–12-2020, were retrospectively analysed by a CE-certified and FDA-approved AI algorithm. The diagnostic performance of the AI was compared to the initial report. To determine the reference standard, discordant findings were independently evaluated by two readers. In case of disagreement, another experienced cardiothoracic radiologist with knowledge of the initial report and the AI output adjudicated.

Results

The prevalence of acute incidental PE in the reference standard was 2.2% (67 of 3089 patients). In 25 cases, AI detected initially unreported PE. This included three cases concerning central/lobar PE. Sensitivity of the AI algorithm was significantly higher than the outcome of the initial report (respectively 95.5% vs. 62.7%, p < 0.001), whereas specificity was very high for both (respectively 99.6% vs 99.9%, p = 0.012). The AI algorithm only showed a slightly higher amount of false-positive findings (11 vs. 2), resulting in a significantly lower PPV (85.3% vs. 95.5%, p = 0.047).

Conclusion

The AI algorithm showed high diagnostic accuracy in diagnosing incidental PE, detecting an additional 25 cases of initially unreported PE, accounting for 37.3% of all positive cases.

Clinical relevance statement

Radiologist support from AI algorithms in daily practice can prevent missed incidental acute PE on routine chest CT, without a high burden of false-positive cases.

Key Points

• Incidental pulmonary embolism is often missed by radiologists in non-diagnostic scans with suboptimal contrast opacification within the pulmonary trunk.

• An artificial intelligence algorithm showed higher sensitivity detecting incidental pulmonary embolism on routine portal venous chest CT compared to the initial report.

• Implementation of artificial intelligence support in routine daily practice will reduce the number of missed incidental pulmonary embolism.

Deniz MA, Deniz ZT, Adin ME et al (2017) Detection of incidental pulmonary embolism with multi-slice computed tomography in cancer patients. Clin Imaging 41:106–111 (S0899-7071(16)30160-7)CrossRefPubMed

Nishikawa T, Fujita T, Morishima T et al (2021) Prognostic effect of incidental pulmonary embolism on long-term mortality in cancer patients. Circ J. https://doi.org/10.1253/circj.CJ-20-1160CrossRefPubMed

Meyer HJ, Wienke A, Surov A (2021) Incidental pulmonary embolism in oncologic patients-a systematic review and meta-analysis. Support Care Cancer 29:1293–1302. https://doi.org/10.1007/s00520-020-05601-yCrossRefPubMed

Abdel-Razeq HN, Mansour AH, Ismael YM (2011) Incidental pulmonary embolism in cancer patients: clinical characteristics and outcome–a comprehensive cancer center experience. Vasc Health Risk Manag 7:153–158. https://doi.org/10.2147/VHRM.S17947CrossRefPubMedPubMedCentral

Font C, Cooksley T, Ahn S, Rapoport B, Escalante C (2022) Emergency management of incidental pulmonary embolism (IPE). Emerg Cancer Care 1:7–7. https://doi.org/10.1186/s44201-022-00004-7CrossRefPubMedPubMedCentral

Bach AG, Beckel C, Schurig N et al (2015) Imaging characteristics and embolus burden of unreported pulmonary embolism in oncologic patients. Clin Imaging 39:237–242 (S0899-7071(14)00246-0)CrossRefPubMed

Soffer S, Klang E, Shimon O et al (2021) Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis. Sci Rep 11:15814–15823. https://doi.org/10.1038/s41598-021-95249-3CrossRefPubMedPubMedCentral

Wiklund P, Medson K, Elf J (2022) Incidental pulmonary embolism in patients with cancer: prevalence, underdiagnosis and evaluation of an AI algorithm for automatic detection of pulmonary embolism. Eur Radiol. https://doi.org/10.1007/s00330-022-09071-0CrossRefPubMedPubMedCentral

Batra K, Xi Y, Al-Hreish K et al (2022) Detection of incidental pulmonary embolism on conventional contrast-enhanced chest CT: comparison of an artificial intelligence algorithm and clinical reports. Am J Roentgenol:1–8. https://doi.org/10.2214/AJR.22.27895

10.

Wildman-Tobriner B, Ngo L, Mammarappallil JG, Konkel B, Johnson JM, Bashir MR (2021) Missed incidental pulmonary embolism: Harnessing artificial intelligence to assess prevalence and improve quality improvement opportunities. J Am Coll Radiol 18:992–999. https://doi.org/10.1016/j.jacr.2021.01.014CrossRefPubMed

11.

Strohm L, Hehakaya C, Ranschaert ER, Boon WPC, Moors EHM (2020) Implementation of artificial intelligence (AI) applications in radiology: hindering and facilitating factors. Eur Radiol 30:5525–5532. https://doi.org/10.1007/s00330-020-06946-yCrossRefPubMedPubMedCentral

12.

He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp 770–778. https://doi.org/10.1109/CVPR.2016.90CrossRef

13.

Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3431–3440). https://doi.org/10.48550/arXiv.1411.4038

14.

Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint. https://doi.org/10.48550/arXiv.1412.6980

15.

Lee CH, Goo JM, Lee HJ, Kim KG, Im J, Bae KT (2007) Determination of optimal timing window for pulmonary artery MDCT angiography. Am J Roentgenol 188:313–317. https://doi.org/10.2214/AJR.06.0078CrossRef

16.

Cheikh AB, Gorincour G, Nivet H et al (2022) How artificial intelligence improves radiological interpretation in suspected pulmonary embolism. Eur Radiol 32:5831–5842. https://doi.org/10.1007/s00330-022-08645-2CrossRefPubMedPubMedCentral

17.

Weikert T, Winkel DJ, Bremerich J et al (2020) Automated detection of pulmonary embolism in CT pulmonary angiograms using an AI-powered algorithm. Eur Radiol 30:6545–6553. https://doi.org/10.1007/s00330-020-06998-0CrossRefPubMed

18.

Schmuelling L, Franzeck FC, Nickel CH et al (2021) 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 141:109816. https://doi.org/10.1016/j.ejrad.2021.109816CrossRefPubMed

19.

Yu AC, Mohajer B, Eng J (2022) External validation of deep learning algorithms for radiologic diagnosis: a systematic review. Radiol: Artif Intell 4:e210064. https://doi.org/10.1148/ryai.210064CrossRefPubMed

20.

Daye D, Wiggins WF, Lungren MP et al (2022) Implementation of clinical artificial intelligence in radiology: who decides and how? Radiology 305:555–563. https://doi.org/10.1148/radiol.212151CrossRefPubMed

21.

Jacobson FL, Krupinski EA (2021) Clinical validation is the key to adopting AI in clinical practice. Radiol Artif Intell 3:e210104. https://doi.org/10.1148/ryai.2021210104CrossRefPubMedPubMedCentral

22.

Kwok CS, Wong CW, Lovatt S, Myint PK, Loke YK (2022) Misdiagnosis of pulmonary embolism and missed pulmonary embolism: a systematic review of the literature. Health Sciences Review 3:100022. https://doi.org/10.1016/j.hsr.2022.100022CrossRef

23.

Park SH, Han K, Jang HY et al (2022) Methods for clinical evaluation of artificial intelligence algorithms for medical diagnosis. Radiology:220182. https://doi.org/10.1148/radiol.220182

24.

Mohan CS (2018) Artificial intelligence in radiology - are we treating the image or the patient? Indian J Radiol Imaging 28:137–139. https://doi.org/10.4103/ijri.IJRI_256_18CrossRefPubMed

25.

Castañer E, Gonzalez A, Andreu M, Lozano C, Gallardo X (2022) Influence of using recommended radiological criteria on MDCT-angiography diagnosis of single isolated subsegmental pulmonary embolism. Eur Radiol 32:4284–4291. https://doi.org/10.1007/s00330-021-08480-xCrossRefPubMed

26.

Baumgartner C, Klok FA, Carrier M et al (2020) Clinical Surveillance vs. Anticoagulation For low-risk patiEnts with isolated SubSegmental Pulmonary Embolism: protocol for a multicentre randomised placebo-controlled non-inferiority trial (SAFE-SSPE). BMJ Open 10:e040151. https://doi.org/10.1136/bmjopen-2020-040151CrossRefPubMedPubMedCentral

27.

Wichmann JL, Willemink MJ, De Cecco CN (2020) Artificial intelligence and machine learning in radiology: current state and considerations for routine clinical implementation. Invest Radiol 55:619–627. https://doi.org/10.1097/RLI.0000000000000673CrossRefPubMed

28.

Katzman BD, van der Pol CB, Soyer P, Patlas MN (2022) Artificial intelligence in emergency radiology: a review of applications and possibilities. Diagn Interv Imaging. https://doi.org/10.1016/j.diii.2022.07.005CrossRefPubMed

29.

Grutters JPC, Govers T, Nijboer J, Tummers M, van der Wilt GJ, Rovers MM (2019) Problems and promises of health technologies: the role of early health economic modeling. IJHPM 8:575–582. https://doi.org/10.15171/ijhpm.2019.36CrossRefPubMedPubMedCentral

30.

Wolff J, Pauling J, Keck A, Baumbach J (2020) The economic impact of artificial intelligence in health care: systematic review. J Med Internet Res 22:e16866. https://doi.org/10.2196/16866CrossRefPubMedPubMedCentral

Titel: Added value of an artificial intelligence algorithm in reducing the number of missed incidental acute pulmonary embolism in routine portal venous phase chest CT
verfasst von: Eline Langius-Wiffen
Pim A. de Jong
Firdaus A. Mohamed Hoesein
Lisette Dekker
Andor F. van den Hoven
Ingrid M. Nijholt
Martijn F. Boomsma
Wouter B. Veldhuis
Publikationsdatum: 03.08.2023
Verlag: Springer Berlin Heidelberg
Erschienen in: European Radiology / Ausgabe 1/2024
Print ISSN: 0938-7994
Elektronische ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-023-10029-z

Feasibility of spectral CT–derived extracellular volume fraction for differentiating aldosterone-producing from nonfunctioning adrenal nodules

Computed Tomography

Characterization of the CT-based risk factors for concomitant patellofemoral instability in patients with anterior cruciate ligament injury

Musculoskeletal

Voxel-wise mapping of DCE-MRI time-intensity-curve profiles enables visualizing and quantifying hemodynamic heterogeneity in breast lesions

Breast

Assessment of whole-body MRI including diffusion-weighted sequences in the initial staging of breast cancer patients at high risk of metastases in comparison with PET-CT: a prospective cohort study

Breast

Information extraction from weakly structured radiological reports with natural language queries

Open Access
Original Article

Deep learning–based assessment of CT markers of sarcopenia and myosteatosis for outcome assessment in patients with advanced pancreatic cancer after high-intensity focused ultrasound treatment

Open Access
Musculoskeletal

Neu im Fachgebiet Radiologie

Abdominale CT bei Kindern: 40% mit Zufallsbefunden

09.02.2025
Stumpfes Abdominaltrauma
Nachrichten

Wird bei Kindern mit stumpfem Trauma eine CT des Bauchraums veranlasst, sind in rund 40% der Fälle Auffälligkeiten zu sehen, die nichts mit dem Trauma zu tun haben. Die allerwenigsten davon sind klinisch relevant.

Genügt die biparametrische MRT für die Prostatadiagnostik?

08.02.2025
Uroradiologie
Nachrichten

Die multiparametrische Magnetresonanztomografie hat einen festen Platz im Screening auf klinisch signifikante Prostatakarzinome. Ob auch ein biparametrisches Vorgehen ausreicht, ist in einer Metaanalyse untersucht worden.

Höhere Trefferquoten bei Brustkrebsscreening dank KI?

06.02.2025
Mammografie
Nachrichten

Künstliche Intelligenz unterstützt bei der Auswertung von Mammografie-Screenings und senkt somit den Arbeitsaufwand für Radiologen. Wie wirken sich diese Technologien auf die Trefferquote und die Falsch-positiv-Rate aus? Das hat jetzt eine Studie aus Schweden untersucht.

KI-gestütztes Mammografiescreening überzeugt im Praxistest

16.01.2025
Künstliche Intelligenz im Gesundheitswesen
Nachrichten

Mit dem Einsatz künstlicher Intelligenz lässt sich die Detektionsrate im Mammografiescreening offenbar deutlich steigern. Mehr unnötige Zusatzuntersuchungen sind laut der Studie aus Deutschland nicht zu befürchten.

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Springer Medizin

Added value of an artificial intelligence algorithm in reducing the number of missed incidental acute pulmonary embolism in routine portal venous phase chest CT