Impact of image quality on the performance of computer-aided detection of pulmonary embolism.

OBJECTIVE: The purpose of this article is to assess the relationship between CT image quality and the number and type of false-positive (FP) findings found by a prototype computer-aided detection (CAD) algorithm for automatic detection of pulmonary embolism (PE). MATERIALS AND METHODS: This retrospective study included 278 subjects (138 men and 140 women; mean age, 57 years; range, 18-88 years) who underwent consecutive CT pulmonary angiographies performed during off hours. Twenty-four percent (68/278) of studies were reported as positive for PE. CAD findings were classified as true-positive or FP by two independent readers and, in cases of discordance, by a third radiologist. Each FP result was classified according to underlying cause. The degree of vascular enhancement, image noise, motion artifacts, overall quality, and presence of underlying lung disease were rated on a 4- or 5-point scale. Chi-square tests and t tests were used to test significance of differences. RESULTS: The mean number of FP CAD findings was 4.7 (median, 2) per examination. Most were caused by veins (30% [389/1,298]) or airspace consolidations (22% [286/1,298]). There was a significant positive association between the number of FP findings and image noise, motion artifacts, low vascular enhancement, low overall quality, and the extent of underlying disease. On a per-embolism basis, sensitivity decreased from 70.6% (214/303) for scans with zero to five FP findings, to 62.3% (33/53) for scans with six to 10 FP findings, to 60% (12/20) for scans with more than 10 FP findings. CONCLUSION: There is a strong association between CT image quality and the number of FP findings indicated by a CAD algorithm for the detection of PE.

Computer-assisted detection of pulmonary embolism: evaluation of pulmonary CT angiograms performed in an on-call setting.

PURPOSE: The purpose of the study was to assess the stand-alone performance of computer-assisted detection (CAD) for evaluation of pulmonary CT angiograms (CTPA) performed in an on-call setting. METHODS: In this institutional review board-approved study, we retrospectively included 292 consecutive CTPA performed during night shifts and weekends over a period of 16 months. Original reports were compared with a dedicated CAD system for pulmonary emboli (PE). A reference standard for the presence of PE was established using independent evaluation by two readers and consultation of a third experienced radiologist in discordant cases. RESULTS: Original reports had described 225 negative studies and 67 positive studies for PE. CAD found PE in seven patients originally reported as negative but identified by independent evaluation: emboli were located in segmental (n = 2) and subsegmental arteries (n = 5). The negative predictive value (NPV) of the CAD algorithm was 92% (44/48). On average there were 4.7 false positives (FP) per examination (median 2, range 0-42). In 72% of studies or=10 FP. CONCLUSION: CAD identified small emboli originally missed under clinical conditions and found 93% of the isolated subsegmental emboli. On average there were 4.7 FP per examination.

Automatic detection of pulmonary embolism in CTA images.

Pulmonary embolism (PE) is a common life-threatening disorder for which an early diagnosis is desirable. We propose a new system for the automatic detection of PE in contrast-enhanced CT images. The system consists of candidate detection, feature computation and classification. Candidate detection focuses on the inclusion of PE--even complete occlusions--and the exclusion of false detections, such as tissue and parenchymal diseases. Feature computation does not only focus on the intensity, shape and size of an embolus, but also on locations and the shape of the pulmonary vascular tree. Several classifiers have been tested and the results show that the performance is optimized by using a bagged tree classifier with two features based on the shape of a blood vessel and the distance to the vessel boundary. The system was trained on 38 CT data sets. Evaluation on 19 other data sets showed that the system generalizes well. The sensitivity of our system on the evaluation data is 63% at 4.9 false positives per data set, which allowed the radiologist to improve the number of detected PE by 22%.