Nasopharyngeal swabs (NPSs) are being widely used as specimens for multiplex real-time reverse transcription (RT)-PCR for respiratory virus detection. However, it remains unclear whether NPS specimens are optimal for all viruses targeted by multiplex RT-PCR. In addition, the procedure to obtain NPS specimens causes coughing in most patients, which possibly increases the risk of nosocomial spread of viruses. In this study, paired NPS and saliva specimens were collected from 236 adult male patients with suspected acute respiratory illnesses. Specimens were tested for 16 respiratory viruses by multiplex real-time RT-PCR. Among the specimens collected from the 236 patients, at least 1 respiratory virus was detected in 183 NPS specimens (77.5%) and 180 saliva specimens (76.3%). The rates of detection of respiratory viruses were comparable for NPS and saliva specimens ( P = 0.766). Nine virus species and 349 viruses were isolated, 256 from NPS specimens and 273 from saliva specimens ( P = 0.1574). Adenovirus was detected more frequently in saliva samples ( P < 0.0001), whereas influenza virus type A and human rhinovirus were detected more frequently in NPS specimens ( P = 0.0001 and P = 0.0289, respectively). The possibility of false-positive adenovirus detection from saliva samples was excluded by direct sequencing. In conclusion, neither of the sampling methods was consistently more sensitive than the other. We suggest that these cost-effective methods for detecting respiratory viruses in mixed NPS-saliva specimens might be valuable for future studies.

Background Patients have the highest risk of subsequent fractures in the first few years after an initial fracture, yet models to predict short-term subsequent risk have not been developed. Purpose To develop and validate a deep learning prediction model for subsequent fracture risk using digitally reconstructed radiographs from hip CT in patients with recent hip fractures. Materials and Methods This retrospective study included adult patients who underwent three-dimensional hip CT due to a fracture from January 2004 to December 2020. Two-dimensional frontal, lateral, and axial digitally reconstructed radiographs were generated and assembled to construct an ensemble model. DenseNet modules were used to calculate risk probability based on extracted image features and fracture-free probability plots were output. Model performance was assessed using the C index and area under the receiver operating characteristic curve (AUC) and compared with other models using the paired t test. Results The training and validation set included 1012 patients (mean age, 74.5 years ± 13.3 [SD]; 706 female, 113 subsequent fracture) and the test set included 468 patients (mean age, 75.9 years ± 14.0; 335 female, 22 subsequent fractures). In the test set, the ensemble model had a higher C index (0.73) for predicting subsequent fractures than that of other image-based models (C index range, 0.59-0.70 for five of six models; P value range, < .001 to < .05). The ensemble model achieved AUCs of 0.74, 0.74, and 0.73 at the 2-, 3-, and 5-year follow-ups, respectively; higher than that of most other image-based models at 2 years (AUC range, 0.57-0.71 for five of six models; P value range, < .001 to < .05) and 3 years (AUC range, 0.55-0.72 for four of six models; P value range, < .001 to < .05). Moreover, the AUCs achieved by the ensemble model were higher than that of a clinical model that included known risk factors (2-, 3-, and 5-year AUCs of 0.58, 0.64, and 0.70, respectively; P < .001 for all). Conclusion In patients with recent hip fractures, the ensemble deep learning model using digital reconstructed radiographs from hip CT showed good performance for predicting subsequent fractures in the short term. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Li and Jaremko in this issue.

Jee-Soo Lee, M.D., Eun Hye Cho, M.D., Boram Kim, M.D., Jinyoung Hong, M.D., Young-gon Kim, M.D., Yoonjung Kim, M.D., Ja-Hyun Jang, M.D., Seung-Tae Lee, M.D., Sun-Young Kong, M.D., Woochang Lee, M.D., Saeam Shin, M.D., and Eun Young Song, M.D., on behalf of the Clinical Practice Guidelines Committee of the Korean Society for Laboratory Medicine. Ann Lab Med 2024;44:195-209. https://doi.org/10.3343/alm.2023.0389

Background: To develop and test the performance of a fully automated system for classifying renal tumor subtypes via deep machine learning for automated segmentation and classification. Materials and methods: The model was developed using computed tomography (CT) images of pathologically proven renal tumors collected from a prospective cohort at a medical center between March 2016 and December 2020. A total of 561 renal tumors were included: 233 clear cell renal cell carcinomas (RCCs), 82 papillary RCCs, 74 chromophobe RCCs, and 172 angiomyolipomas. Renal tumor masks manually drawn on contrast-enhanced CT images were used to develop a 3D U-Net-based deep learning model for fully automated tumor segmentation. After segmentation, the entire classification pipeline, including feature extraction and subtype classification, was conducted without any manual intervention. Both conventional radiological features (Hounsfield units, HUs) and radiomic features extracted from areas predicted by the deep learning models were used to develop an algorithm for classifying renal tumor subtypes via a random forest classifier. The performance of the segmentation model was evaluated using the Dice similarity coefficient, while the classification model was assessed based on accuracy, sensitivity, and specificity. Results: For tumors larger than 4 cm, the Dice similarity coefficient (DSC) for automated segmentation was 0.83, while for tumors smaller than 4 cm, the DSC was 0.65. The classification accuracy (ACC) for distinguishing RCC subtypes was 0.77 for tumors larger than 4 cm and 0.68 for tumors smaller than 4 cm. Additionally, the accuracy for benign versus malignant classification was 0.85. Conclusions: Our automatic segmentation and classifier model showed promising results for renal tumor segmentation and classification.