RESUMO
Purpose: To develop, train, and validate a multiview deep convolutional neural network (DeePSC) for the automated diagnosis of primary sclerosing cholangitis (PSC) on two-dimensional MR cholangiopancreatography (MRCP) images. Materials and Methods: This retrospective study included two-dimensional MRCP datasets of 342 patients (45 years ± 14 [SD]; 207 male patients) with confirmed diagnosis of PSC and 264 controls (51 years ± 16; 150 male patients). MRCP images were separated into 3-T (n = 361) and 1.5-T (n = 398) datasets, of which 39 samples each were randomly chosen as unseen test sets. Additionally, 37 MRCP images obtained with a 3-T MRI scanner from a different manufacturer were included for external testing. A multiview convolutional neural network was developed, specialized in simultaneously processing the seven images taken at different rotational angles per MRCP examination. The final model, DeePSC, derived its classification per patient from the instance expressing the highest confidence in an ensemble of 20 individually trained multiview convolutional neural networks. Predictive performance on both test sets was compared with that of four licensed radiologists using the Welch t test. Results: DeePSC achieved an accuracy of 80.5% ± 1.3 (sensitivity, 80.0% ± 1.9; specificity, 81.1% ± 2.7) on the 3-T and 82.6% ± 3.0 (sensitivity, 83.6% ± 1.8; specificity, 80.0% ± 8.9) on the 1.5-T test set and scored even higher on the external test set (accuracy, 92.4% ± 1.1; sensitivity, 100.0% ± 0.0; specificity, 83.5% ± 2.4). DeePSC outperformed radiologists in average prediction accuracy by 5.5 (P = .34, 3 T) and 10.1 (P = .13, 1.5 T) percentage points. Conclusion: Automated classification of PSC-compatible findings based on two-dimensional MRCP was achievable and demonstrated high accuracy on internal and external test sets.Keywords: Neural Networks, Deep Learning, Liver Disease, MRI, Primary Sclerosing Cholangitis, MR Cholangiopancreatography Supplemental material is available for this article. © RSNA, 2023.
RESUMO
Sarcoidosis is the most frequent immunologically related granulomatous disease and can serve as a model for understanding diseases within this category. The evidence on the diagnostics and treatment is so far limited. It is therefore all the more important that two new and significant guidelines on diagnosis and treatment of sarcoidosis were published during the last 2 years. Additionally, there were more new publications, which were considered for this review article. In this context, this review article provides a current update and overview of sarcoidosis. Pathophysiologically, there is an increasing understanding of the complex processes and interactions involved in the inflammatory processes and granuloma formation. The probability of a diagnosis of sarcoidosis is determined by compatible histology, the exclusion of differential diagnoses and if possible evidence of a multiorgan manifestation. The clinical course is variable and ranges from an asymptomatic manifestation to severe life-threatening organ failure. The most frequently affected organ are the lungs. Pulmonary fibrosis is the most severe form and is also decisive for mortality. An increasing focus is on the extrapulmonary organ manifestations, in particular, cardiac, hepatosplenic, gastrointestinal, renal, ocular and neurological involvement. Treatment, which consists primarily of immunosuppression, should be initiated in cases of organ-threatening or quality of life-impairing activity of the disease. Additional organ-specific management must also be evaluated. In cases of organ failure transplantation should be considered. Due to the limited evidence especially for the treatment of multiorgan sarcoidosis, when possible, patients with this disease should be included in clinical trials.
