Computer-Aided Detection of Acute Pulmonary Embolism With 64-Slice Multi-Detector Row Computed Tomography

2010 ◽  
Vol 34 (1) ◽  
pp. 23-30 ◽  
Author(s):  
Marion Dewailly ◽  
Martine Rémy-Jardin ◽  
Alain Duhamel ◽  
Jean-Baptiste Faivre ◽  
François Pontana ◽  
...  
Author(s):  
Katharina Müller-Peltzer ◽  
Lena Kretzschmar ◽  
Giovanna Negrão de Figueiredo ◽  
Alexander Crispin ◽  
Robert Stahl ◽  
...  

Purpose Since artificial intelligence is transitioning from an experimental stage to clinical implementation, the aim of our study was to evaluate the performance of a commercial, computer-aided detection algorithm of computed tomography pulmonary angiograms regarding the presence of pulmonary embolism in the emergency room. Materials and Methods This retrospective study includes all pulmonary computed tomography angiogram studies performed in a large emergency department over a period of 36 months that were analyzed by two radiologists experienced in emergency radiology to set a reference standard. Original reports and computer-aided detection results were compared regarding the detection of lobar, segmental, and subsegmental pulmonary embolism. All computer-aided detection findings were analyzed concerning the underlying pathology. False-positive findings were correlated to the contrast-to-noise ratio. Results Expert reading revealed pulmonary embolism in 182 of 1229 patients (49 % men, 10–97 years) with a total of 504 emboli. The computer-aided detection algorithm reported 3331 findings, including 258 (8 %) true-positive findings and 3073 (92 %) false-positive findings. Computer-aided detection analysis showed a sensitivity of 47 % (95 %CI: 33–61 %) on the lobar level and 50 % (95 %CI 43–56 %) on the subsegmental level. On average, there were 2.25 false-positive findings per study (median 2, range 0–25). There was no significant correlation between the number of false-positive findings and the contrast-to-noise ratio (Spearman’s Rank Correlation Coefficient = 0.09). Soft tissue (61.0 %) and pulmonary veins (24.1 %) were the most common underlying reasons for false-positive findings. Conclusion Applied to a population at a large emergency room, the tested commercial computer-aided detection algorithm faced relevant performance challenges that need to be addressed in future development projects. Key Points:  Citation Format


2018 ◽  
Vol 5 (1) ◽  
Author(s):  
Mojtaba Masoudi ◽  
Hamid-Reza Pourreza ◽  
Mahdi Saadatmand-Tarzjan ◽  
Noushin Eftekhari ◽  
Fateme Shafiee Zargar ◽  
...  

2007 ◽  
Vol 22 (4) ◽  
pp. 319-323 ◽  
Author(s):  
U. Joseph Schoepf ◽  
Alex C. Schneider ◽  
Marco Das ◽  
Susan A. Wood ◽  
Jugesh I. Cheema ◽  
...  

TH Open ◽  
2021 ◽  
Vol 05 (01) ◽  
pp. e66-e72
Author(s):  
Lisette F. van Dam ◽  
Lucia J. M. Kroft ◽  
Menno V. Huisman ◽  
Maarten K. Ninaber ◽  
Frederikus A. Klok

Abstract Background Computed tomography pulmonary angiography (CTPA) is the imaging modality of choice for the diagnosis of acute pulmonary embolism (PE). With computed tomography pulmonary perfusion (CTPP) additional information on lung perfusion can be assessed, but its value in PE risk stratification is unknown. We aimed to evaluate the correlation between CTPP-assessed perfusion defect score (PDS) and clinical presentation and its predictive value for adverse short-term outcome of acute PE. Patients and Methods This was an exploratory, observational study in 100 hemodynamically stable patients with CTPA-confirmed acute PE in whom CTPP was performed as part of routine clinical practice. We calculated the difference between the mean PDS in patients with versus without chest pain, dyspnea, and hemoptysis and 7-day adverse outcome. Multivariable logistic regression analysis and likelihood-ratio test were used to assess the added predictive value of PDS to CTPA parameters of right ventricle dysfunction and total thrombus load, for intensive care unit admission, reperfusion therapy and PE-related death. Results We found no correlation between PDS and clinical symptoms. PDS was correlated to reperfusion therapy (n = 4 with 16% higher PDS, 95% confidence interval [CI]: 3.5–28%) and PE-related mortality (n = 2 with 22% higher PDS, 95% CI: 4.9–38). Moreover, PDS had an added predictive value to CTPA assessment for PE-related mortality (from Chi-square 14 to 19, p = 0.02). Conclusion CTPP-assessed PDS was not correlated to clinical presentation of acute PE. However, PDS was correlated to reperfusion therapy and PE-related mortality and had an added predictive value to CTPA-reading for PE-related mortality; this added value needs to be demonstrated in larger studies.


Sign in / Sign up

Export Citation Format

Share Document