Deep Learning Improves the Temporal Reproducibility of Aortic Measurement.

Imaging-based measurements form the basis of surgical decision making in patients with aortic aneurysm. Unfortunately, manual measurement suffer from suboptimal temporal reproducibility, which can lead to delayed or unnecessary intervention. We tested the hypothesis that deep learning could improve upon the temporal reproducibility of CT angiography-derived thoracic aortic measurements in the setting of imperfect ground-truth training data. To this end, we trained a standard deep learning segmentation model from which measurements of aortic volume and diameter could be extracted. First, three blinded cardiothoracic radiologists visually confirmed non-inferiority of deep learning segmentation maps with respect to manual segmentation on a 50-patient hold-out test cohort, demonstrating a slight preference for the deep learning method (p < 1e-5). Next, reproducibility was assessed by evaluating measured change (coefficient of reproducibility and standard deviation) in volume and diameter values extracted from segmentation maps in patients for whom multiple scans were available and whose aortas had been deemed stable over time by visual assessment (n = 57 patients, 206 scans). Deep learning temporal reproducibility was superior for measures of both volume (p < 0.008) and diameter (p < 1e-5) and reproducibility metrics compared favorably with previously reported values of manual inter-rater variability. Our work motivates future efforts to apply deep learning to aortic evaluation.

Technical Note: kV-independent coronary calcium scoring: A phantom evaluation of score accuracy and potential radiation dose reduction.

PURPOSE: To determine the accuracy of CT number and calcium score of a kV-independent technique based on an artificial 120 kV reconstruction, and its potential to reduce radiation dose. METHODS: Anthropomorphic chest phantoms were scanned on a third-generation dual-source CT system equipped with the artificial 120 kV reconstruction. First, a phantom module containing a 20-mm diameter hydroxyapatite (HA) insert was scanned inside the chest phantoms at different tube potentials (70-140 kV) to evaluate calcium CT number accuracy. Next, three small HA inserts (diameter/length = 5 mm) were inserted into a pork steak and scanned inside the phantoms to evaluate calcium score accuracy at different kVs. Finally, the same setup was scanned using automatic exposure control (AEC) at 120 kV, and then with automatic kV selection (auto-kV). Phantoms were also scanned at 120 kV using a size-dependent mA chart. CT numbers of soft tissue and calcium were measured from different kV images. Calcium score of each small HA insert was measured using commercial software. RESULTS: The CT number difference from 120 kV was small with tube potentials from 90 to 140 kV for both soft tissue and calcium (maximal difference of 4/5 HU, respectively). Consistent calcium scores were obtained from images of different kVs compared to 120 kV, with a relative difference <8%. Auto-kV provided a 25-34% dose reduction compared to AEC alone. CONCLUSION: A kV-independent calcium scoring technique can produce artificial 120 kV images with consistent soft tissue and calcium CT numbers compared to standard 120 kV examinations. When coupled with auto-kV, this technique can reduce radiation by 25-34% compared to that with AEC alone, while providing consistent calcium scores as that of standard 120 kV examinations.

Dynamic computed tomographic assessment of the mitral annulus in patients with and without mitral prolapse.

OBJECTIVES: To obtain 3D CT measurements of mitral annulus throughout cardiac cycle using prototype mitral modeling software, assess interobserver agreement, and compare among patients with mitral prolapse (MP) and control group. BACKGROUND: Pre-procedural imaging is critical for planning of transcatheter mitral valve (MV) replacement. However, there is limited data regarding reliable CT-based measurements to accurately characterize the dynamic geometry of the mitral annulus in patients with MV disease. METHODS: Patients with MP and control subjects without any MV disease who underwent ECG-gated cardiac CT were retrospectively identified. Multiphasic CT data was loaded into a prototype mitral modeling software. Multiple anatomical parameters in 3D space were recorded throughout the cardiac cycle (0-95%): annular circumference, planar-surface-area (PSA), anterior-posterior (A-P) distance, and anterolateral-posteromedial (AL-PM) distance. Comparisons were made among the two groups, with p < 0.05 considered statistically significant. Interobserver agreement was assessed on ten patients using intraclass correlation coefficient (ICC) among 4 experienced readers. RESULTS: A total of 100 subjects were included: 50 with MP and 50 control. Annular dimensions were significantly higher in the MP group than control group, with circumference (144 ± 11 vs. 117±8 mm), PSA (1533 ± 247 vs. 1005 ± 142 mm2), A-P distance (38 ± 4 vs. 32±2 mm), and AL-PM distance (47 ± 4 vs. 39±3 mm) (all p < 0.001). Substantial size changes were observed throughout the cardiac cycle, but with maximal and minimal sizes at different cardiac phases for the two groups. The interobserver agreement was excellent (ICC≥0.75) for annular circumference, PSA, A-P- and AL-PM distance. CONCLUSION: A significant variation in the mitral annular measures between different cardiac phases and two groups was observed with excellent interobserver agreement.

Technical Note: Display window setting: An important factor for detecting subtle but clinically relevant artifacts in daily CT quality control.

PURPOSE: This study aimed to investigate the influence of display window setting on technologist performance detecting subtle but clinically relevant artifacts in daily computed tomography (CT) quality control (dQC) images. METHODS: Fifty three sets of dQC images were retrospectively selected, including 30 sets without artifacts, and 23 with subtle but clinically relevant artifacts. They were randomized and shown to six CT technologists (two new and four experienced). Each technologist reviewed all images in each of two sessions, one with a display window width (WW) of 100 HU, which is currently recommended by the American College of Radiology, and the other with a narrow WW of 40 HU, both at a window level of 0 HU. For each case, technologists rated the presence of image artifacts based on a five point scale. The area under the receiver operating characteristic curve (AUC) was used to evaluate the artifact detection performance. RESULTS: At a WW of 100 HU, the AUC (95% confidence interval) was 0.658 (0.576, 0.740), 0.532 (0.429, 0.635), and 0.616 (0.543, 0.619) for the experienced, new, and all technologists, respectively. At a WW of 40 HU, the AUC was 0.768 (0.687, 0.850), 0.546 (0.433, 0.658), and 0.694 (0.619, 0.769), respectively. The performance significantly improved at WW of 40 HU for experienced technologists (p = 0.009) and for all technologists (p = 0.040). CONCLUSIONS: Use of a narrow display WW significantly improved technologists' performance in dQC for detecting subtle but clinically relevant artifacts as compared to that using a 100 HU display WW.