Deep Learning for Automatic Calcium Scoring in CT: Validation Using Multiple Cardiac CT and Chest CT Protocols

• Published in: Radiology Vol. 295; no. 1; pp. 66 - 79
• Main Authors: van Velzen, Sanne G. M., Lessmann, Nikolas, Velthuis, Birgitta K., Bank, Ingrid E. M., van den Bongard, Desiree H. J. G., Leiner, Tim, de Jong, Pim A., Veldhuis, Wouter B., Correa, Adolfo, Terry, James G., Carr, John Jeffrey, Viergever, Max A., Verkooijen, Helena M., Išgum, Ivana
• Format: Journal Article
• Language: English
• Published: United States Radiological Society of North America 01.04.2020
• Subjects: Aged; Clinical Protocols; Coronary Artery Disease - diagnostic imaging; Deep Learning; Female; Heart - diagnostic imaging; Humans; Male; Middle Aged; Original Research; Retrospective Studies; Thorax - diagnostic imaging; Tomography, X-Ray Computed - methods; Vascular Calcification - diagnostic imaging

Background Although several deep learning (DL) calcium scoring methods have achieved excellent performance for specific CT protocols, their performance in a range of CT examination types is unknown. Purpose To evaluate the performance of a DL method for automatic calcium scoring across a wide range...