Publication | Closed Access
Pulmonary nodules: computer-aided detection in digital chest images.
110
Citations
0
References
1990
Year
Possible Nodule LocationsDigital Chest ImagesEngineeringDiagnosisDiagnostic ImagingDigital RadiologyImage AnalysisPattern RecognitionBiostatisticsPulmonary NodulesLung NodulesRadiologyHealth SciencesMachine VisionMedical ImagingMedical Image ComputingComputer VisionRadiomicsMultiple Pulmonary NoduleComputer-aided DiagnosisMedical Image Analysis
Radiologists miss up to 30 % of pulmonary nodules, often because of background camouflage, subjective criteria, and clinical distractions. The study aimed to develop a computerized method to locate lung nodules in digital chest images. The method uses a difference‑image approach with growth, slope, and profile feature tests, and its results were used to alert 12 radiologists to potential nodule sites in 60 clinical cases. Preliminary results indicate that computer assistance can improve radiologists’ detection performance.
Currently, radiologists fail to detect pulmonary nodules in up to 30% of cases with actually positive findings. Diagnoses may be missed due to camouflaging effects of anatomic background, subjective and varying decision criteria, or distractions in clinical situations. We developed a computerized method to detect locations of lung nodules in digital chest images. The method is based on a difference-image approach and feature-extraction techniques, including growth, slope, and profile tests. Computer results were used to alert 12 radiologists to possible nodule locations in 60 clinical cases. Preliminary results suggest that computer aid can improve the detection performance of radiologists.