OBJECTIVE: To evaluate the performance of a computer-aided detection (CAD) system for diagnosis of pulmonary embolism on computed tomography (CT) pulmonary angiography. MATERIALS AND METHODS: One hundred and four pulmonary CT angiograms for pulmonary emboli (PE) were reviewed both by radiologists and a CAD detection system (ImageChecker CT V2.0, R2 Technology Inc, Sunnyvale, CA). CT scans, read and reported by radiologists in a routine daily clinical setting, were later processed by the CAD system. The performance of the CAD system was analyzed. RESULTS: Forty-five PE were identified by the radiologists in 15 patients. The CAD system revealed 123 findings, interpreted by the system as PE. Twenty-six of them, detected in 8 patients, represented true-positive results. Ninety-seven (78.9%) CAD findings were not true PE and were defined as false-positive. Nineteen true PE in 7 patients were missed by the CAD system constituting 42% false-negative rate. Sensitivity of the CAD system was 53.3% and the specificity was 77.5%. The positive predictive value of CAD system was 28.5% and the negative predictive value was 90.7%. CONCLUSIONS: With the evaluated CAD system, it is relatively simple and fast to check all detected findings and decide if they represent true PE. However, high false-negative results demand technologic improvement, to increase the sensitivity of the system. It is anticipated to become a promising supplement to the work and eyes of the radiologist in detecting PE on pulmonary CT angiography.
OBJECTIVE: To evaluate the performance of a computer-aided detection (CAD) system for diagnosis of pulmonary embolism on computed tomography (CT) pulmonary angiography. MATERIALS AND METHODS: One hundred and four pulmonary CT angiograms for pulmonary emboli (PE) were reviewed both by radiologists and a CAD detection system (ImageChecker CT V2.0, R2 Technology Inc, Sunnyvale, CA). CT scans, read and reported by radiologists in a routine daily clinical setting, were later processed by the CAD system. The performance of the CAD system was analyzed. RESULTS: Forty-five PE were identified by the radiologists in 15 patients. The CAD system revealed 123 findings, interpreted by the system as PE. Twenty-six of them, detected in 8 patients, represented true-positive results. Ninety-seven (78.9%) CAD findings were not true PE and were defined as false-positive. Nineteen true PE in 7 patients were missed by the CAD system constituting 42% false-negative rate. Sensitivity of the CAD system was 53.3% and the specificity was 77.5%. The positive predictive value of CAD system was 28.5% and the negative predictive value was 90.7%. CONCLUSIONS: With the evaluated CAD system, it is relatively simple and fast to check all detected findings and decide if they represent true PE. However, high false-negative results demand technologic improvement, to increase the sensitivity of the system. It is anticipated to become a promising supplement to the work and eyes of the radiologist in detecting PE on pulmonary CT angiography.
Authors: R Wittenberg; J F Peters; M Weber; R J Lely; L P J Cobben; M Prokop; C M Schaefer-Prokop Journal: Br J Radiol Date: 2011-12-13 Impact factor: 3.039
Authors: Kevin N Blackmon; Charles Florin; Luca Bogoni; Joshua W McCain; James D Koonce; Heon Lee; Gorka Bastarrika; Christian Thilo; Philip Costello; Marcos Salganicoff; U Joseph Schoepf Journal: Eur Radiol Date: 2011-01-13 Impact factor: 5.315
Authors: Christian Thilo; Mulugeta Gebregziabher; Felix G Meinel; Roman Goldenberg; John W Nance; Elisabeth M Arnoldi; Lashonda D Soma; Ullrich Ebersberger; Philip Blanke; Richard L Coursey; Michael A Rosenblum; Peter L Zwerner; U Joseph Schoepf Journal: Eur Radiol Date: 2014-10-15 Impact factor: 5.315
Authors: Chuan Zhou; Heang-Ping Chan; Berkman Sahiner; Lubomir M Hadjiiski; Aamer Chughtai; Smita Patel; Jun Wei; Philip N Cascade; Ella A Kazerooni Journal: Med Phys Date: 2009-08 Impact factor: 4.071
Authors: Yanhui Guo; Chuan Zhou; Heang-Ping Chan; Aamer Chughtai; Jun Wei; Lubomir M Hadjiiski; Ella A Kazerooni Journal: Med Phys Date: 2013-08 Impact factor: 4.071