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.
Mammography Study: Can Stand-Alone AI Enhance Detection of Interval Breast Cancer?
August 28th 2024Identifying over 23 percent of interval breast cancers with a 96 percent sensitivity in mammography interpretation, an emerging AI software also facilitated correct localization in over 75 percent of cases involving interval breast cancer, according to new research.
Can AI Facilitate Effective Triage for Supplemental Breast MRI After Negative Mammography Screening?
July 10th 2024The AISmartDensity software facilitated a cancer detection rate (CDR) with breast MRI that was nearly four times higher than the CDR previously reported in trials involving traditional breast density assessment.