Stand-alone Performance of a Computer-assisted Detection Prototype for Detection of Acute Pulmonary Embolism: a Multi-institutional Comparison

Overview

Journal Br J Radiol

Publisher Oxford University Press

Specialty Radiology

Date 2011 Dec 15

PMID 22167514

Citations 3

Authors

R Wittenberg

J F Peters

M Weber

R J Lely

L P J Cobben

M Prokop

C M Schaefer-Prokop

Affiliations

Soon will be listed here.

Abstract

Objective: To assess whether the performance of a computer-assisted detection (CAD) algorithm for acute pulmonary embolism (PE) differs in pulmonary CT angiographies acquired at various institutions.

Methods: In this retrospective study, we included 40 consecutive scans with and 40 without PE from 3 institutions (n = 240) using 64-slice scanners made by different manufacturers (General Electric; Philips; Siemens). CAD markers were classified as true or false positive (FP) using independent evaluation by two readers and consultation of a third chest radiologist in discordant cases. Image quality parameters were subjectively scored using 4/5-point scales. Image noise and vascular enhancement were measured. Statistical analysis was done to correlate image quality of the three institutions with CAD stand-alone performance.

Results: Patient groups were comparable with respect to age (p = 0.22), accompanying lung disease (p = 0.12) and inpatient/outpatient ratio (p = 0.67). The sensitivity was 100% (34/34), 97% (37/38) and 92% (33/36), and the specificity was 18% (8/44), 15% (6/41) and 13% (5/39). Neither significantly differed between the institutions (p = 0.21 and p = 0.820, respectively). The mean number of FP findings (4.5, 6.2 and 3.7) significantly varied (p = 0.02 and p = 0.03), but median numbers (2, 3 and 3) were comparable. Image quality parameters were significantly associated with the number of FP findings (p<0.05) but not with sensitivity. After correcting for noise and vascular enhancement, the number of FPs did not significantly differ between the three institutions (p = 0.43).

Conclusions: CAD stand-alone performance is independent of scanner type but strongly related to image quality and thus scanning protocols.

Citing Articles

Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis.

Soffer S, Klang E, Shimon O, Barash Y, Cahan N, Greenspana H Sci Rep. 2021; 11(1):15814.

PMID: 34349191 PMC: 8338977. DOI: 10.1038/s41598-021-95249-3.

Pathophysiology of COVID-19-associated acute respiratory distress syndrome: a multicentre prospective observational study.

Grasselli G, Tonetti T, Protti A, Langer T, Girardis M, Bellani G Lancet Respir Med. 2020; 8(12):1201-1208.

PMID: 32861276 PMC: 7834127. DOI: 10.1016/S2213-2600(20)30370-2.

Assessment of Acute Pulmonary Embolism by Computer-Aided Technique: A Reliability Study.

Sun Z, Hao F, Guo Y, Liu A, Zhao L Med Sci Monit. 2020; 26:e920239.

PMID: 32111815 PMC: 7063852. DOI: 10.12659/MSM.920239.

References

Wittenberg R, Peters J, Sonnemans J, Prokop M, Schaefer-Prokop C . Computer-assisted detection of pulmonary embolism: evaluation of pulmonary CT angiograms performed in an on-call setting. Eur Radiol. 2009; 20(4):801-6. PMC: 2835722. DOI: 10.1007/s00330-009-1628-7. View

Das M, Muhlenbruch G, Helm A, Bakai A, Salganicoff M, Stanzel S . Computer-aided detection of pulmonary embolism: influence on radiologists' detection performance with respect to vessel segments. Eur Radiol. 2008; 18(7):1350-5. DOI: 10.1007/s00330-008-0889-x. View

Walsham A, Roberts H, Kashani H, Mongiardi C, Ng Y, Patsios D . The use of computer-aided detection for the assessment of pulmonary arterial filling defects at computed tomographic angiography. J Comput Assist Tomogr. 2009; 32(6):913-8. DOI: 10.1097/RCT.0b013e31815b3ed0. View

Buhmann S, Herzog P, Liang J, Wolf M, Salganicoff M, Kirchhoff C . Clinical evaluation of a computer-aided diagnosis (CAD) prototype for the detection of pulmonary embolism. Acad Radiol. 2007; 14(6):651-8. DOI: 10.1016/j.acra.2007.02.007. View

Cronin P, Weg J, Kazerooni E . The role of multidetector computed tomography angiography for the diagnosis of pulmonary embolism. Semin Nucl Med. 2009; 38(6):418-31. DOI: 10.1053/j.semnuclmed.2008.07.002. View

. British Thoracic Society guidelines for the management of suspected acute pulmonary embolism. Thorax. 2003; 58(6):470-83. PMC: 1746692. DOI: 10.1136/thorax.58.6.470. View

Engelke C, Schmidt S, Auer F, Rummeny E, Marten K . Does computer-assisted detection of pulmonary emboli enhance severity assessment and risk stratification in acute pulmonary embolism?. Clin Radiol. 2010; 65(2):137-44. DOI: 10.1016/j.crad.2009.10.007. View

Schaefer-Prokop C, Prokop M . MDCT for the diagnosis of acute pulmonary embolism. Eur Radiol. 2006; 15 Suppl 4:D37-41. DOI: 10.1007/s10406-005-0144-3. View

Maizlin Z, Vos P, Godoy M, Godoy M, Cooperberg P . Computer-aided detection of pulmonary embolism on CT angiography: initial experience. J Thorac Imaging. 2007; 22(4):324-9. DOI: 10.1097/RTI.0b013e31815b89ca. View

10.

Schoepf U, Costello P . CT angiography for diagnosis of pulmonary embolism: state of the art. Radiology. 2004; 230(2):329-37. DOI: 10.1148/radiol.2302021489. View

11.

Schoepf U, Schneider A, Das M, Wood S, Cheema J, Costello P . Pulmonary embolism: computer-aided detection at multidetector row spiral computed tomography. J Thorac Imaging. 2007; 22(4):319-23. DOI: 10.1097/RTI.0b013e31815842a9. View

12.

Zhou C, Chan H, Patel S, Cascade P, Sahiner B, Hadjiiski L . Preliminary investigation of computer-aided detection of pulmonary embolism in three-dimensional computed tomography pulmonary angiography images. Acad Radiol. 2005; 12(6):782-92. PMC: 2784697. DOI: 10.1016/j.acra.2005.01.014. View

13.

Engelke C, Schmidt S, Bakai A, Auer F, Marten K . Computer-assisted detection of pulmonary embolism: performance evaluation in consensus with experienced and inexperienced chest radiologists. Eur Radiol. 2007; 18(2):298-307. DOI: 10.1007/s00330-007-0770-3. View

14.

Dewailly M, Remy-Jardin M, Duhamel A, Faivre J, Pontana F, Deken V . Computer-aided detection of acute pulmonary embolism with 64-slice multi-detector row computed tomography: impact of the scanning conditions and overall image quality in the detection of peripheral clots. J Comput Assist Tomogr. 2010; 34(1):23-30. DOI: 10.1097/RCT.0b013e3181b2e383. View

15.

Remy-Jardin M, Pistolesi M, Goodman L, Gefter W, Gottschalk A, Mayo J . Management of suspected acute pulmonary embolism in the era of CT angiography: a statement from the Fleischner Society. Radiology. 2007; 245(2):315-29. DOI: 10.1148/radiol.2452070397. View

16.

Masutani Y, MacMahon H, Doi K . Computerized detection of pulmonary embolism in spiral CT angiography based on volumetric image analysis. IEEE Trans Med Imaging. 2003; 21(12):1517-23. DOI: 10.1109/TMI.2002.806586. View

17.

Bouma H, Sonnemans J, Vilanova A, Gerritsen F . Automatic detection of pulmonary embolism in CTA images. IEEE Trans Med Imaging. 2009; 28(8):1223-30. DOI: 10.1109/TMI.2009.2013618. View

18.

Brunot S, Corneloup O, Latrabe V, Montaudon M, Laurent F . Reproducibility of multi-detector spiral computed tomography in detection of sub-segmental acute pulmonary embolism. Eur Radiol. 2005; 15(10):2057-63. DOI: 10.1007/s00330-005-2844-4. View