Improving traumatic fracture detection on radiographs with artificial intelligence support: a multi-reader study.

Objectives: The aim of this study was to evaluate the diagnostic performance of nonspecialist readers with and without the use of an artificial intelligence (AI) support tool to detect traumatic fractures on radiographs of the appendicular skeleton. Methods: The design was a retrospective, fully crossed multi-reader, multi-case study on a balanced dataset of patients (≥2 years of age) with an AI tool as a diagnostic intervention. Fifteen readers assessed 340 radiographic exams, with and without the AI tool in 2 different sessions and the time spent was automatically recorded. Reference standard was established by 3 consultant radiologists. Sensitivity, specificity, and false positives per patient were calculated. Results: Patient-wise sensitivity increased from 72% to 80% (P < .05) and patient-wise specificity increased from 81% to 85% (P < .05) in exams aided by the AI tool compared to the unaided exams. The increase in sensitivity resulted in a relative reduction of missed fractures of 29%. The average rate of false positives per patient decreased from 0.16 to 0.14, corresponding to a relative reduction of 21%. There was no significant difference in average reading time spent per exam. The largest gain in fracture detection performance, with AI support, across all readers, was on nonobvious fractures with a significant increase in sensitivity of 11 percentage points (pp) (60%-71%). Conclusions: The diagnostic performance for detection of traumatic fractures on radiographs of the appendicular skeleton improved among nonspecialist readers tested AI fracture detection support tool showed an overall reader improvement in sensitivity and specificity when supported by an AI tool. Improvement was seen in both sensitivity and specificity without negatively affecting the interpretation time. Advances in knowledge: The division and analysis of obvious and nonobvious fractures are novel in AI reader comparison studies like this.

Detection of Critical Spinal Epidural Lesions on CT Using Machine Learning.

BACKGROUND: Critical spinal epidural pathologies can cause paralysis or death if untreated. Although magnetic resonance imaging is the preferred modality for visualizing these pathologies, computed tomography (CT) occurs far more commonly than magnetic resonance imaging in the clinical setting. OBJECTIVE: A machine learning model was developed to screen for critical epidural lesions on CT images at a large-scale teleradiology practice. This model has utility for both worklist prioritization of emergent studies and identifying missed findings. MATERIALS AND METHODS: There were 153 studies with epidural lesions available for training. These lesions were segmented and used to train a machine learning model. A test data set was also created using previously missed epidural lesions. The trained model was then integrated into a teleradiology workflow for 90 days. Studies were sent to secondary manual review if the model detected an epidural lesion but none was mentioned in the clinical report. RESULTS: The model correctly identified 50.0% of epidural lesions in the test data set with 99.0% specificity. For prospective data, the model correctly prioritized 66.7% of the 18 epidural lesions diagnosed on the initial read with 98.9% specificity. There were 2.0 studies flagged for potential missed findings per day, and 17 missed epidural lesions were found during a 90-day time period. These results suggest almost half of critical spinal epidural lesions visible on CT imaging are being missed on initial diagnosis. CONCLUSION: A machine learning model for identifying spinal epidural hematomas and abscesses on CT can be implemented in a clinical workflow.

Measurement of Endotracheal Tube Positioning on Chest X-Ray Using Object Detection.

Patients who are intubated with endotracheal tubes often receive chest x-ray (CXR) imaging to determine whether the tube is correctly positioned. When these CXRs are interpreted by a radiologist, they evaluate whether the tube needs to be repositioned and typically provide a measurement in centimeters between the endotracheal tube tip and carina. In this project, a large dataset of endotracheal tube and carina bounding boxes was annotated on CXRs, and a machine-learning model was trained to generate these boxes on new CXRs and to calculate a distance measurement between the tube and carina. This model was applied to a gold standard annotated dataset, as well as to all prospective data passing through our radiology system for two weeks. Inter-radiologist variability was also measured on a test dataset. The distance measurements for both the gold standard dataset (mean error = 0.70 cm) and prospective dataset (mean error = 0.68 cm) were noninferior to inter-radiologist variability (mean error = 0.70 cm) within an equivalence bound of 0.1 cm. This suggests that this model performs at an accuracy similar to human measurements, and these distance calculations can be used for clinical report auto-population and/or worklist prioritization of severely malpositioned tubes.

Automated quantification and evaluation of motion artifact on coronary CT angiography images.

PURPOSE: This study developed and validated a Motion Artifact Quantification algorithm to automatically quantify the severity of motion artifacts on coronary computed tomography angiography (CCTA) images. The algorithm was then used to develop a Motion IQ Decision method to automatically identify whether a CCTA dataset is of sufficient diagnostic image quality or requires further correction. METHOD: The developed Motion Artifact Quantification algorithm includes steps to identify the right coronary artery (RCA) regions of interest (ROIs), segment vessel and shading artifacts, and to calculate the motion artifact score (MAS) metric. The segmentation algorithms were verified against ground-truth manual segmentations. The segmentation algorithms were also verified by comparing and analyzing the MAS calculated from ground-truth segmentations and the algorithm-generated segmentations. The Motion IQ Decision algorithm first identifies slices with unsatisfactory image quality using a MAS threshold. The algorithm then uses an artifact-length threshold to determine whether the degraded vessel segment is large enough to cause the dataset to be nondiagnostic. An observer study on 30 clinical CCTA datasets was performed to obtain the ground-truth decisions of whether the datasets were of sufficient image quality. A five-fold cross-validation was used to identify the thresholds and to evaluate the Motion IQ Decision algorithm. RESULTS: The automated segmentation algorithms in the Motion Artifact Quantification algorithm resulted in Dice coefficients of 0.84 for the segmented vessel regions and 0.75 for the segmented shading artifact regions. The MAS calculated using the automated algorithm was within 10% of the values obtained using ground-truth segmentations. The MAS threshold and artifact-length thresholds were determined by the ROC analysis to be 0.6 and 6.25 mm by all folds. The Motion IQ Decision algorithm demonstrated 100% sensitivity, 66.7% ± 27.9% specificity, and a total accuracy of 86.7% ± 12.5% for identifying datasets in which the RCA required correction. The Motion IQ Decision algorithm demonstrated 91.3% sensitivity, 71.4% specificity, and a total accuracy of 86.7% for identifying CCTA datasets that need correction for any of the three main vessels. CONCLUSION: The Motion Artifact Quantification algorithm calculated accurate (<10% error) motion artifact scores using the automated segmentation methods. The developed algorithms demonstrated high sensitivity (91.3%) and specificity (71.4%) in identifying datasets of insufficient image quality. The developed algorithms for automatically quantifying motion artifact severity may be useful for comparing acquisition techniques, improving best-phase selection algorithms, and evaluating motion compensation techniques.

Evaluation of motion artifact metrics for coronary CT angiography.

PURPOSE: This study quantified the performance of coronary artery motion artifact metrics relative to human observer ratings. Motion artifact metrics have been used as part of motion correction and best-phase selection algorithms for Coronary Computed Tomography Angiography (CCTA). However, the lack of ground truth makes it difficult to validate how well the metrics quantify the level of motion artifact. This study investigated five motion artifact metrics, including two novel metrics, using a dynamic phantom, clinical CCTA images, and an observer study that provided ground-truth motion artifact scores from a series of pairwise comparisons. METHOD: Five motion artifact metrics were calculated for the coronary artery regions on both phantom and clinical CCTA images: positivity, entropy, normalized circularity, Fold Overlap Ratio (FOR), and Low-Intensity Region Score (LIRS). CT images were acquired of a dynamic cardiac phantom that simulated cardiac motion and contained six iodine-filled vessels of varying diameter and with regions of soft plaque and calcifications. Scans were repeated with different gantry start angles. Images were reconstructed at five phases of the motion cycle. Clinical images were acquired from 14 CCTA exams with patient heart rates ranging from 52 to 82 bpm. The vessel and shading artifacts were manually segmented by three readers and combined to create ground-truth artifact regions. Motion artifact levels were also assessed by readers using a pairwise comparison method to establish a ground-truth reader score. The Kendall's Tau coefficients were calculated to evaluate the statistical agreement in ranking between the motion artifacts metrics and reader scores. Linear regression between the reader scores and the metrics was also performed. RESULTS: On phantom images, the Kendall's Tau coefficients of the five motion artifact metrics were 0.50 (normalized circularity), 0.35 (entropy), 0.82 (positivity), 0.77 (FOR), 0.77(LIRS), where higher Kendall's Tau signifies higher agreement. The FOR, LIRS, and transformed positivity (the fourth root of the positivity) were further evaluated in the study of clinical images. The Kendall's Tau coefficients of the selected metrics were 0.59 (FOR), 0.53 (LIRS), and 0.21 (Transformed positivity). In the study of clinical data, a Motion Artifact Score, defined as the product of FOR and LIRS metrics, further improved agreement with reader scores, with a Kendall's Tau coefficient of 0.65. CONCLUSION: The metrics of FOR, LIRS, and the product of the two metrics provided the highest agreement in motion artifact ranking when compared to the readers, and the highest linear correlation to the reader scores. The validated motion artifact metrics may be useful for developing and evaluating methods to reduce motion in Coronary Computed Tomography Angiography (CCTA) images.

Huge traumatic pulmonary artery pseudoaneurysm.

Pulmonary artery pseudoaneurysm is a very rare complication of penetrating thoracic trauma. We present a case of a 27-year-old woman who developed a 6.5-cm traumatic pulmonary artery pseudoaneurysm after suffering multiple stab wounds to the chest and the abdomen. The pseudoaneurysm was successfully treated endovascularly with vascular plug occlusion and coil embolization.

Association of Coronary Artery Calcification and Mortality in the National Lung Screening Trial: A Comparison of Three Scoring Methods.

PURPOSE: To evaluate three coronary artery calcification (CAC) scoring methods to assess risk of coronary heart disease (CHD) death and all-cause mortality in National Lung Screening Trial (NLST) participants across levels of CAC scores. MATERIALS AND METHODS: The NLST was approved by the institutional review board at each participating institution, and informed consent was obtained from all participants. Image review was HIPAA compliant. Five cardiothoracic radiologists evaluated 1575 low-dose computed tomographic (CT) scans from three groups: 210 CHD deaths, 315 deaths not from CHD, and 1050 participants who were alive at conclusion of the trial. Radiologists used three scoring methods: overall visual assessment, segmented vessel-specific scoring, and Agatston scoring. Weighted Cox proportional hazards models were fit to evaluate the association between scoring methods and outcomes. RESULTS: In multivariate analysis of time to CHD death, Agatston scores of 1-100, 101-1000, and greater than 1000 (reference category 0) were associated with hazard ratios of 1.27 (95% confidence interval: 0.69, 2.53), 3.57 (95% confidence interval: 2.14, 7.48), and 6.63 (95% confidence interval: 3.57, 14.97), respectively; hazard ratios for summed segmented vessel-specific scores of 1-5, 6-11, and 12-30 (reference category 0) were 1.72 (95% confidence interval: 1.05, 3.34), 5.11 (95% confidence interval: 2.92, 10.94), and 6.10 (95% confidence interval: 3.19, 14.05), respectively; and hazard ratios for overall visual assessment of mild, moderate, or heavy (reference category none) were 2.09 (95% confidence interval: 1.30, 4.16), 3.86 (95% confidence interval: 2.02, 8.20), and 6.95 (95% confidence interval: 3.73, 15.67), respectively. CONCLUSION: By using low-dose CT performed for lung cancer screening in older, heavy smokers, a simple visual assessment of CAC can be generated for risk assessment of CHD death and all-cause mortality, which is comparable to Agatston scoring and strongly associated with outcome.

Computed tomography pulmonary findings in healthy older adult aspirators versus nonaspirators.

OBJECTIVES/HYPOTHESIS: In previous studies, we consistently found that approximately 30% of asymptomatic healthy older adults silently aspirated liquids during a flexible endoscopic evaluation of swallowing (FEES) and that their aspiration status was stable for the following year. However, no studies have systematically evaluated effects of silent aspiration on lung parenchyma and airways. We used computed tomography (CT) to compare lungs of healthy older adult aspirators versus nonaspirators. We hypothesized that CT images would show pulmonary differences in healthy older adult aspirators versus nonaspirators. STUDY DESIGN: Prospective study. METHODS: Fifty healthy older adults (25 aspirators and 25 nonaspirators) who participated in a previous FEES were randomly selected. CT scans were performed; on inspiration, lung views were taken at 1.25 mm and 2.5 mm windows, and on expiration, lung views were taken at 2.5 mm. CT scans were reviewed by radiologists blinded to group assignment. Outcomes included bronchiectasis, bronchiolectasis, bronchial wall thickening, parenchymal band, fibrosis, air trapping, intraluminal airway debris, and tree-in-bud pattern. RESULTS: χ(2) analyses between aspirators and nonaspirators found no statistically significant differences between aspirators and nonaspirators for any outcomes (P > .05). Logistic regression analyses adjusted for smoking did not change the results. CONCLUSIONS: There were no differences in pulmonary CT findings between healthy older adult aspirators and nonaspirators. This study adds to the evidence that some aspiration may be within the range of normal for older adults, or at least does not contribute to a change in pulmonary appearance on CT images. LEVEL OF EVIDENCE: 3b.

ACR Appropriateness Criteria® acute chest pain--suspected pulmonary embolism.

Pulmonary embolism (PE) remains a common and important clinical condition that cannot be accurately diagnosed on the basis of signs, symptoms, and history alone. In the absence of high pretest probability and with a negative high-sensitivity D-dimer test, PE can be effectively excluded; in other situations, diagnostic imaging is necessary. The diagnosis of PE has been facilitated by technical advancements and multidetector computed tomography pulmonary angiography, which is the major diagnostic modality currently used. Ventilation and perfusion (V/Q) scans remain largely accurate and useful in certain settings. Lower-extremity ultrasound can substitute by demonstrating deep vein thrombosis; however, if negative, further studies to exclude PE are indicated. In all cases, correlation with the clinical status, particularly with risk factors, improves not only the accuracy of diagnostic imaging but also overall utilization. Other diagnostic tests have limited roles. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed every 2 years by a multidisciplinary expert panel. The development and review of the guidelines include an extensive analysis of current medical literature from peer-reviewed journals and the application of a well-established consensus methodology (modified Delphi) to rate the appropriateness of imaging and treatment procedures by the panel. In those instances in which evidence is lacking or not definitive, expert opinion may be used to recommend imaging or treatment.

Complete pancreatic encasement of the portal vein (circumportal pancreas): imaging findings and implications of a rare pancreatic anomaly.

Computed tomography and magnetic resonance imaging findings in 4 patients with complete pancreatic encasement of the portal vein are presented, with emphasis on the use of multiplanar reconstructions in demonstrating this anomaly.