Machine learning-based computer-aided simple triage (CAST) for COVID-19 pneumonia as compared with triage by board-certified chest radiologists.

PURPOSE: Several reporting systems have been proposed for providing standardized language and diagnostic categories aiming for expressing the likelihood that lung abnormalities on CT images represent COVID-19. We developed a machine learning (ML)-based CT texture analysis software for simple triage based on the RSNA Expert Consensus Statement system. The purpose of this study was to conduct a multi-center and multi-reader study to determine the capability of ML-based computer-aided simple triage (CAST) software based on RSNA expert consensus statements for diagnosis of COVID-19 pneumonia. METHODS: For this multi-center study, 174 cases who had undergone CT and polymerase chain reaction (PCR) tests for COVID-19 were retrospectively included. Their CT data were then assessed by CAST and consensus from three board-certified chest radiologists, after which all cases were classified as either positive or negative. Diagnostic performance was then compared by McNemar's test. To determine radiological finding evaluation capability of CAST, three other board-certified chest radiologists assessed CAST results for radiological findings into five criteria. Finally, accuracies of all radiological evaluations were compared by McNemar's test. RESULTS: A comparison of diagnosis for COVID-19 pneumonia based on RT-PCR results for cases with COVID-19 pneumonia findings on CT showed no significant difference of diagnostic performance between ML-based CAST software and consensus evaluation (p > 0.05). Comparison of agreement on accuracy for all radiological finding evaluations showed that emphysema evaluation accuracy for investigator A (AC = 91.7%) was significantly lower than that for investigators B (100%, p = 0.0009) and C (100%, p = 0.0009). CONCLUSION: This multi-center study shows COVID-19 pneumonia triage by CAST can be considered at least as valid as that by chest expert radiologists and may be capable for playing as useful a complementary role for management of suspected COVID-19 pneumonia patients as well as the RT-PCR test in routine clinical practice.

Comparison of Xenon-Enhanced Area-Detector CT and Krypton Ventilation SPECT/CT for Assessment of Pulmonary Functional Loss and Disease Severity in Smokers.

OBJECTIVE: The objective of this study was to compare the capability of xenon-enhanced area-detector CT (ADCT) performed with a subtraction technique and coregistered 81mKr-ventilation SPECT/CT for the assessment of pulmonary functional loss and disease severity in smokers. SUBJECTS AND METHODS: Forty-six consecutive smokers (32 men and 14 women; mean age, 67.0 years) underwent prospective unenhanced and xenon-enhanced ADCT, 81mKr-ventilation SPECT/CT, and pulmonary function tests. Disease severity was evaluated according to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) classification. CT-based functional lung volume (FLV), the percentage of wall area to total airway area (WA%), and ventilated FLV on xenon-enhanced ADCT and SPECT/CT were calculated for each smoker. All indexes were correlated with percentage of forced expiratory volume in 1 second (%FEV1) using step-wise regression analyses, and univariate and multivariate logistic regression analyses were performed. In addition, the diagnostic accuracy of the proposed model was compared with that of each radiologic index by means of McNemar analysis. RESULTS: Multivariate logistic regression showed that %FEV1 was significantly affected (r = 0.77, r2 = 0.59) by two factors: the first factor, ventilated FLV on xenon-enhanced ADCT (p < 0.0001); and the second factor, WA% (p = 0.004). Univariate logistic regression analyses indicated that all indexes significantly affected GOLD classification (p < 0.05). Multivariate logistic regression analyses revealed that ventilated FLV on xenon-enhanced ADCT and CT-based FLV significantly influenced GOLD classification (p < 0.0001). The diagnostic accuracy of the proposed model was significantly higher than that of ventilated FLV on SPECT/CT (p = 0.03) and WA% (p = 0.008). CONCLUSION: Xenon-enhanced ADCT is more effective than 81mKr-ventilation SPECT/CT for the assessment of pulmonary functional loss and disease severity.

Diagnostic performance of different imaging modalities in the assessment of distant metastasis and local recurrence of tumor in patients with non-small cell lung cancer.

PURPOSE: To compare the diagnostic performance of positron emission tomography with [18F] fluoro-2-deoxy-glucose (FDG-PET) coregistered with magnetic resonance imaging (FDG-PET/MRI), MRI with and without diffusion-weighted imaging (DWI), FDG-PET fused with computed tomography (FDG-PET/CT) with brain contrast-enhanced (CE-) MRI, and routine radiological examination for assessment of postoperative recurrence in nonsmall-cell lung cancer (NSCLC) patients. MATERIALS AND METHODS: 96 consecutive postoperative NSCLC patients (52 men, 44 women; mean age 72 years) prospectively underwent whole-body 3T MRI with and without DWI; PET/CTs and routine radiological examinations consisted of CE-brain MRI, whole-body CE-CT, and bone scintigraphy. The patients were divided into a recurrence (n = 17) and a nonrecurrence (n = 79) group based on pathological and follow-up examinations. All coregistered PET/MRIs were generated by proprietary software. The probability of recurrence was visually assessed on a per-patient basis. Receiver operating characteristic analyses were used to compare the diagnostic performance of all methods. Finally, diagnostic capabilities were compared by means of McNemar's test. RESULTS: Areas under the curves (Azs) were significantly larger for PET/MRI and whole-body MRI with DWI (Az = 0.99) than for PET/CT (Az = 0.92, P < 0.05) and conventional radiological examination (Az = 0.91, P < 0.05). Specificity and accuracy of PET/MRI and MRI with and without DWI were significantly higher than those of PET/CT (P < 0.05) and routine radiological examination (P < 0.05). CONCLUSION: Whole-body FDG-PET/MRI and MRI with DWI were found to be more specific and accurate than FDG-PET/CT and routine radiological examinations for assessment of recurrence in NSCLC patients, although MRI with and without DWI demonstrated slightly lower sensitivity than PET/CT. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2017;46:1707-1717.