Pulmonary emboli missed by CT angiography may be detected by computer aided detection programs.
Pulmonary embolism-computer aided detection (PE-CADx) was able to correctly identify 77.4 percent of cases of acute PE that were previously missed in clinical practice, according to a study published in the American Journal of Roentgenology.
Researchers from the University of Maryland School of Medicine in Baltimore undertook a retrospective study to assess the use of a PE-CADx program in the detection of pulmonary emboli that may have been missed in clinical practice.
A total of 6,769 pulmonary CT angiography (CTA) studies performed between January 2009 and July 2012 were identified for the study and assessed by a thoracic radiologist. When studies positive for PE were identified, all prior contrast-enhanced CTA studies were reviewed. Three thoracic radiologists assessed the presence, proximal extent, and number of PEs.
Studies with missed acute PE and available slice thickness of 2 mm or less were assessed with a prototype PE-CADx program. False-positive PE-CADx marks were analyzed. Outcomes of missed acute PEs were assessed in patients with both follow-up imaging and clinical data.
The researchers found that 53 studies with overlooked PE fit the inclusion criteria for PE-CADx assessment. The program then found at least one PE in 41 of the 53 cases (77.4 percent). Using PE-CADx, the radiologists correctly marked at least one PE all cases where there were multiple PEs (23 of 23) and 18 of 30 (60 percent) cases with a solitary PE.
The PE-CADx per-study sensitivity was significantly higher for segmental (65.5 percent) than for subsegmental (91.7 percent) PEs. PE-CADx averaged 3.8 false-positive marks per case (range, 0–23 marks). Fourteen patients with missed PE who were not receiving anticoagulation therapy developed new PEs, including nine with an isolated subsegmental PE on the initial CT scan.
FDA Clears Updated AI Platform for Digital Breast Tomosynthesis
November 12th 2024Employing advanced deep learning convolutional neural networks, ProFound Detection Version 4.0 reportedly offers a 50 percent improvement in detecting cancer in dense breasts in comparison to the previous version of the software.
Is the Kaiser Score More Effective than BI-RADS for Assessing Contrast-Enhanced Mammography and MRI?
October 14th 2024For women with breast-enhanced masses, Kaiser scoring (KS) demonstrated a 20 percent higher AUC than BI-RADS classification for contrast-enhanced mammography (CEM) and was comparable to KS for breast MRI.
FDA Clears New Features in AI-Powered Mammography Software Suite
October 11th 2024Therapixel’s MammoScreen suite has received 510(k) FDA clearances for a breast density assessment feature and updated software that includes automated pre-reporting, which reportedly expedites reporting of mammography findings.