Search

Objectives: While chest radiograph (CXR) is the first-line imaging investigation in patients with respiratory symptoms, differentiating COVID-19 from other respiratory infections on CXR remains challenging. We developed and validated an AI system for COVID-19 detection on presenting CXR. Methods: A deep learning model (RadGenX), trained on 168,850 CXRs, was validated on a large international test set of presenting CXRs of symptomatic patients from 9 study sites (US, Italy, and Hong Kong SAR) and 2 public datasets from the US and Europe. Performance was measured by area under the receiver operator characteristic curve (AUC). Bootstrapped simulations were performed to assess performance across a range of potential COVID-19 disease prevalence values (3.33 to 33.3%). Comparison against international radiologists was performed on an independent test set of 852 cases. Results: RadGenX achieved an AUC of 0.89 on 4-fold cross-validation and an AUC of 0.79 (95%CI 0.78–0.80) on an independent test cohort of 5,894 patients. Delong's test showed statistical differences in model performance across patients from different regions (p < 0.01), disease severity (p < 0.001), gender (p < 0.001), and age (p = 0.03). Prevalence simulations showed the negative predictive value increases from 86.1% at 33.3% prevalence, to greater than 98.5% at any prevalence below 4.5%. Compared with radiologists, McNemar's test showed the model has higher sensitivity (p < 0.001) but lower specificity (p < 0.001). Conclusion: An AI model that predicts COVID-19 infection on CXR in symptomatic patients was validated on a large international cohort providing valuable context on testing and performance expectations for AI systems that perform COVID-19 prediction on CXR. Key Points: • An AI model developed using CXRs to detect COVID-19 was validated in a large multi-center cohort of 5,894 patients from 9 prospectively recruited sites and 2 public datasets. • Differences in AI model performance were seen across region, disease severity, gender, and age. • Prevalence simulations on the international test set demonstrate the model's NPV is greater than 98.5% at any prevalence below 4.5%. [ABSTRACT FROM AUTHOR]

Objectives: To investigate the predictive value of peritoneal carcinomatosis (PC) quantification by DWI in determining incomplete tumour debulking in ovarian carcinoma (OC). Methods: Prospective patients with suspected stage III–IV or recurrent OC were recruited for DWI before surgery. PC on DWI was segmented semi-automatically by k-means clustering, retaining voxels with intermediate apparent diffusion coefficient (ADC) to quantify PC burden. A scoring system, functional peritoneal cancer index (fPCI), was proposed based on the segmentation of tumour volume in 13 abdominopelvic regions with additional point given to involvement of critical sites. ADC of the largest PC was recorded. The surgical complexity and outcomes (complete vs. incomplete tumour debulking) were documented. fPCI was correlated with surgical PCI (sPCI), surgical complexity, and its ability to predict incomplete tumour debulking. Results: Fifty-three patients with stage III–IV or recurrent OC were included with a mean age of 56.1 ± 11.8 years old. Complete tumour debulking was achieved in 38/53 patients (71.7%). Significant correlation was found between fPCI and sPCI (r > 0.757, p < 0.001). Patients with high-fPCI (fPCI ≥ 6) had a high surgical complexity score (p = 0.043) with 84.2% received radical or supra-radical surgery. The mean fPCI was significantly higher in patients with incomplete tumour debulking than in those with complete debulking (10.27 vs. 4.71, p < 0.001). fPCI/ADC combined with The International Federation of Gynecology and Obstetrics stage achieved 92.5% accuracy in predicting incomplete tumour debulking (AUC 0.947). Conclusions: DWI-derived fPCI offered a semi-automated estimation of PC burden. fPCI/ADC could predict the likelihood of incomplete tumour debulking with high accuracy. Key Points: • Functional peritoneal cancer index (fPCI) derived from DWI offered a semi-automated estimation of tumour burden in ovarian carcinoma. • fPCI was highly correlated with surgical PCI (sPCI). • fPCI/ADC could predict the likelihood of incomplete tumour debulking with high accuracy. [ABSTRACT FROM AUTHOR]