Automated diagnosis and prognosis of COVID-19 pneumonia from initial ER chest X-rays using deep learning.

BACKGROUND: Airspace disease as seen on chest X-rays is an important point in triage for patients initially presenting to the emergency department with suspected COVID-19 infection. The purpose of this study is to evaluate a previously trained interpretable deep learning algorithm for the diagnosis and prognosis of COVID-19 pneumonia from chest X-rays obtained in the ED. METHODS: This retrospective study included 2456 (50% RT-PCR positive for COVID-19) adult patients who received both a chest X-ray and SARS-CoV-2 RT-PCR test from January 2020 to March of 2021 in the emergency department at a single U.S. INSTITUTION: A total of 2000 patients were included as an additional training cohort and 456 patients in the randomized internal holdout testing cohort for a previously trained Siemens AI-Radiology Companion deep learning convolutional neural network algorithm. Three cardiothoracic fellowship-trained radiologists systematically evaluated each chest X-ray and generated an airspace disease area-based severity score which was compared against the same score produced by artificial intelligence. The interobserver agreement, diagnostic accuracy, and predictive capability for inpatient outcomes were assessed. Principal statistical tests used in this study include both univariate and multivariate logistic regression. RESULTS: Overall ICC was 0.820 (95% CI 0.790-0.840). The diagnostic AUC for SARS-CoV-2 RT-PCR positivity was 0.890 (95% CI 0.861-0.920) for the neural network and 0.936 (95% CI 0.918-0.960) for radiologists. Airspace opacities score by AI alone predicted ICU admission (AUC = 0.870) and mortality (0.829) in all patients. Addition of age and BMI into a multivariate log model improved mortality prediction (AUC = 0.906). CONCLUSION: The deep learning algorithm provides an accurate and interpretable assessment of the disease burden in COVID-19 pneumonia on chest radiographs. The reported severity scores correlate with expert assessment and accurately predicts important clinical outcomes. The algorithm contributes additional prognostic information not currently incorporated into patient management.

Impact of Artificial Intelligence Assistance on Chest CT Interpretation Times: A Prospective Randomized Study.

BACKGROUND. Deep learning-based convolutional neural networks have enabled major advances in development of artificial intelligence (AI) software applications. Modern AI applications offer comprehensive multiorgan evaluation. OBJECTIVE. The purpose of this article was to evaluate the impact of an automated AI platform integrated into clinical workflow for chest CT interpretation on radiologists' interpretation times when evaluated in a real-world clinical setting. METHODS. In this prospective single-center study, a commercial AI software solution was integrated into clinical workflow for chest CT interpretation. The software provided automated analysis of cardiac, pulmonary, and musculoskeletal findings, including labeling, segmenting, and measuring normal structures as well as detecting, labeling, and measuring abnormalities. AI-annotated images and autogenerated summary results were stored in the PACS and available to interpreting radiologists. A total of 390 patients (204 women, 186 men; mean age, 62.8 ± 13.3 [SD] years) who underwent out-patient chest CT between January 19, 2021, and January 28, 2021, were included. Scans were randomized using 1:1 allocation between AI-assisted and non-AI-assisted arms and were clinically interpreted by one of three cardiothoracic radiologists (65 scans per arm per radiologist; total of 195 scans per arm) who recorded interpretation times using a stopwatch. Findings were categorized according to review of report impressions. Interpretation times were compared between arms. RESULTS. Mean interpretation times were significantly shorter in the AI-assisted than in the non-AI-assisted arm for all three readers (289 ± 89 vs 344 ± 129 seconds, p < .001; 449 ± 110 vs 649 ± 82 seconds, p < .001; 281 ± 114 vs 348 ± 93 seconds, p = .01) and for readers combined (328 ± 122 vs 421 ± 175 seconds, p < .001). For readers combined, the mean difference was 93 seconds (95% CI, 63-123 seconds), corresponding with a 22.1% reduction in the AI-assisted arm. Mean interpretation time was also shorter in the AI-assisted arm compared with the non-AI-assisted arm for contrast-enhanced scans (83 seconds), noncontrast scans (104 seconds), negative scans (84 seconds), positive scans without significant new findings (117 seconds), and positive scans with significant new findings (92 seconds). CONCLUSION. Cardiothoracic radiologists exhibited a 22.1% reduction in chest CT interpretations times when they had access to results from an automated AI support platform during real-world clinical practice. CLINICAL IMPACT. Integration of the AI support platform into clinical workflow improved radiologist efficiency.

Evaluating the Performance of a Convolutional Neural Network Algorithm for Measuring Thoracic Aortic Diameters in a Heterogeneous Population.

The purpose of this work was to assess the performance of a convolutional neural network (CNN) for automatic thoracic aortic measurements in a heterogeneous population. From June 2018 to May 2019, this study retrospectively analyzed 250 chest CT scans with or without contrast enhancement and electrocardiographic gating from a heterogeneous population with or without aortic pathologic findings. Aortic diameters at nine locations and maximum aortic diameter were measured manually and with an algorithm (Artificial Intelligence Rad Companion Chest CT prototype, Siemens Healthineers) by using a CNN. A total of 233 examinations performed with 15 scanners from three vendors in 233 patients (median age, 65 years [IQR, 54-72 years]; 144 men) were analyzed: 68 (29%) without pathologic findings, 72 (31%) with aneurysm, 51 (22%) with dissection, and 42 (18%) with repair. No evidence of a difference was observed in maximum aortic diameter between manual and automatic measurements (P = .48). Overall measurements displayed a bias of -1.5 mm and a coefficient of repeatability of 8.0 mm at Bland-Altman analyses. Contrast enhancement, location, pathologic finding, and positioning inaccuracy negatively influenced reproducibility (P < .003). Sites with dissection or repair showed lower agreement than did sites without. The CNN performed well in measuring thoracic aortic diameters in a heterogeneous multivendor CT dataset. Keywords: CT, Vascular, Aorta © RSNA, 2022.

Tumor burden of lung metastases at initial staging in breast cancer patients detected by artificial intelligence as a prognostic tool for precision medicine.

BACKGROUND: Determination of the total number and size of all pulmonary metastases on chest CT is time-consuming and as such has been understudied as an independent metric for disease assessment. A novel artificial intelligence (AI) model may allow for automated detection, size determination, and quantification of the number of pulmonary metastases on chest CT. OBJECTIVE: To investigate the utility of a novel AI program applied to initial staging chest CT in breast cancer patients in risk assessment of mortality and survival. METHODS: Retrospective imaging data from a cohort of 226 subjects with breast cancer was assessed by the novel AI program and the results validated by blinded readers. Mean clinical follow-up was 2.5 years for outcomes including cancer-related death and development of extrapulmonary metastatic disease. AI measurements including total number of pulmonary metastases and maximum nodule size were assessed by Cox-proportional hazard modeling and adjusted survival. RESULTS: 752 lung nodules were identified by the AI program, 689 of which were identified in 168 subjects having confirmed lung metastases (Lmet+) and 63 were identified in 58 subjects without confirmed lung metastases (Lmet-). When compared to the reader assessment, AI had a per-patient sensitivity, specificity, PPV and NPV of 0.952, 0.639, 0.878, and 0.830. Mortality in the Lmet + group was four times greater compared to the Lmet-group (p = 0.002). In a multivariate analysis, total lung nodule count by AI had a high correlation with overall mortality (OR 1.11 (range 1.07-1.15), p < 0.001) with an AUC of 0.811 (R2 = 0.226, p < 0.0001). When total lung nodule count and maximum nodule diameter were combined there was an AUC of 0.826 (R2 = 0.243, p < 0.001). CONCLUSION: Automated AI-based detection of lung metastases in breast cancer patients at initial staging chest CT performed well at identifying pulmonary metastases and demonstrated strong correlation between the total number and maximum size of lung metastases with future mortality. CLINICAL IMPACT: As a component of precision medicine, AI-based measurements at the time of initial staging may improve prediction of which breast cancer patients will have negative future outcomes.

Diagnostic Accuracy and Performance of Artificial Intelligence in Detecting Lung Nodules in Patients With Complex Lung Disease: A Noninferiority Study.

OBJECTIVES: The aim of the study is to investigate the performance of artificial intelligence (AI) convolutional neural networks (CNN) in detecting lung nodules on chest computed tomography of patients with complex lung disease, and demonstrate its noninferiority when compared against an experienced radiologist through clinically relevant assessments. METHODS: A CNN prototype was used to retrospectively evaluate 103 complex lung disease cases and 40 control cases without reported nodules. Computed tomography scans were blindly evaluated by an expert thoracic radiologist; a month after initial analyses, 20 positive cases were re-evaluated with the assistance of AI. For clinically relevant applications: (1) AI was asked to classify each patient into nodules present or absent and (2) AI results were compared against standard radiology reports. Standard statistics were performed to determine detection performance. RESULTS: AI was, on average, 27 seconds faster than the expert and detected 8.4% of nodules that would have been missed. AI had a sensitivity of 67.7%, similar to an accuracy reported for experienced radiologists. AI correctly classified each patient (nodules present/absent) with a sensitivity of 96.1%. When matched against radiology reports, AI performed with a sensitivity of 89.4%. Control group assessment demonstrated an overall specificity of 82.5%. When aided by AI, the expert decreased the average assessment time per case from 2:44 minutes to 35.7 seconds, while reporting an overall increase in confidence. CONCLUSION: In a group of patients with complex lung disease, the sensitivity of AI is similar to an experienced radiologist and the tool helps detect previously missed nodules. AI also helps experts analyze for lung nodules faster and more confidently, a feature that is beneficial to patients and favorable to hospitals due to increased patient load and need for shorter turnaround times.

Performance of an Artificial Intelligence-Based Platform Against Clinical Radiology Reports for the Evaluation of Noncontrast Chest CT.

RATIONALE AND OBJECTIVES: Research on implementation of artificial intelligence (AI) in radiology workflows and its impact on reports remains scarce. In this study, we aim to assess if an AI platform would perform better than clinical radiology reports in evaluating noncontrast chest computed tomography (CT) scans. MATERIALS AND METHODS: Consecutive patients who had undergone noncontrast chest CT were retrospectively identified. The radiology reports were reviewed in a binary fashion for reporting of pulmonary lesions, pulmonary emphysema, aortic dilatation, coronary artery calcifications (CAC), and vertebral compression fractures (VCF). CT scans were then processed using an AI platform. The reports' findings and the AI results were subsequently compared to a consensus read by two board-certificated radiologists as reference. RESULTS: A total of 100 patients (mean age: 64.2 ± 14.8 years; 57% males) were included in this study. Aortic segmentation and calcium quantification failed to be processed by AI in 2 and 3 cases, respectively. AI showed superior diagnostic performance in identifying aortic dilatation (AI: sensitivity: 96.3%, specificity: 81.4%, AUC: 0.89) vs (Reports: sensitivity: 25.9%, specificity: 100%, AUC: 0.63), p <0.001; and CAC (AI: sensitivity: 89.8%, specificity: 100, AUC: 0.95) vs (Reports: sensitivity: 75.4%, specificity: 94.9%, AUC: 0.85), p = 0.005. Reports had better performance than AI in identifying pulmonary lesions (Reports: sensitivity: 97.6%, specificity: 100%, AUC: 0.99) vs (AI: sensitivity: 92.8%, specificity: 82.4%, AUC: 0.88), p = 0.024; and VCF (Reports: sensitivity:100%, specificity: 100%, AUC: 1.0) vs (AI: sensitivity: 100%, specificity: 63.7%, AUC: 0.82), p <0.001. A comparable diagnostic performance was noted in identifying pulmonary emphysema on AI (sensitivity: 80.6%, specificity: 66.7%. AUC: 0.74) and reports (sensitivity: 74.2%, specificity: 97.1%, AUC: 0.86), p = 0.064. CONCLUSION: Our results demonstrate that incorporating AI support platforms into radiology workflows can provide significant added value to clinical radiology reporting.