Background Studies have rarely investigated stenosis detection from head and neck CT angiography scans because accurate interpretation is time consuming and labor intensive. Purpose To develop an automated convolutional neural network-based method for accurate stenosis detection and plaque classification in head and neck CT angiography images and compare its performance with that of radiologists. Materials and Methods A deep learning (DL) algorithm was constructed and trained with use of head and neck CT angiography images that were collected retrospectively from four tertiary hospitals between March 2020 and July 2021. CT scans were partitioned into training, validation, and independent test sets at a ratio of 7:2:1. An independent test set of CT angiography scans was collected prospectively between October 2021 and December 2021 in one of the four tertiary centers. Stenosis grade categories were as follows: mild stenosis (<50%), moderate stenosis (50%-69%), severe stenosis (70%-99%), and occlusion (100%). The stenosis diagnosis and plaque classification of the algorithm were compared with the ground truth of consensus by two radiologists (with more than 10 years of experience). The performance of the models was analyzed in terms of accuracy, sensitivity, specificity, and areas under the receiver operating characteristic curve. Results There were 3266 patients (mean age ± SD, 62 years ± 12; 2096 men) evaluated. The consistency between radiologists and the DL-assisted algorithm on plaque classification was 85.6% (320 of 374 cases [95% CI: 83.2, 88.6]) on a per-vessel basis. Moreover, the artificial intelligence model assisted in visual assessment, such as increasing confidence in the degree of stenosis. This reduced the time needed for diagnosis and report writing of radiologists from 28.8 minutes ± 5.6 to 12.4 minutes ± 2.0 (P < .001). Conclusion A deep learning algorithm for head and neck CT angiography interpretation accurately determined vessel stenosis and plaque classification and had equivalent diagnostic performance when compared with experienced radiologists. © RSNA, 2023 Supplemental material is available for this article.

Purpose: This study aimed to develop deep learning (DL) models based on multicentre biparametric magnetic resonance imaging (bpMRI) for the diagnosis of clinically significant prostate cancer (csPCa) and compare the performance of these models with that of the Prostate Imaging and Reporting and Data System (PI-RADS) assessment by expert radiologists based on multiparametric MRI (mpMRI). Methods: We included 1861 consecutive male patients who underwent radical prostatectomy or biopsy at seven hospitals with mpMRI. These patients were divided into the training (1216 patients in three hospitals) and external validation cohorts (645 patients in four hospitals). PI-RADS assessment was performed by expert radiologists. We developed DL models for the classification between benign and malignant lesions (DL-BM) and that between csPCa and non-csPCa (DL-CS). An integrated model combining PI-RADS and the DL-CS model, abbreviated as PIDL-CS, was developed. The performances of the DL models and PIDL-CS were compared with that of PI-RADS. Results: In each external validation cohort, the area under the receiver operating characteristic curve (AUC) values of the DL-BM and DL-CS models were not significantly different from that of PI-RADS (P > 0.05), whereas the AUC of PIDL-CS was superior to that of PI-RADS (P < 0.05), except for one external validation cohort (P > 0.05). The specificity of PIDL-CS for the detection of csPCa was much higher than that of PI-RADS (P < 0.05). Conclusion: Our proposed DL models can be a potential non-invasive auxiliary tool for predicting csPCa. Furthermore, PIDL-CS greatly increased the specificity of csPCa detection compared with PI-RADS assessment by expert radiologists, greatly reducing unnecessary biopsies and helping radiologists achieve a precise diagnosis of csPCa.

Under normal conditions, insulin promotes hepatic de novo lipogenesis (DNL). However, during insulin resistance (IR), when insulin signalling is blunted and accompanied by hyperinsulinaemia, the promotion of hepatic DNL continues unabated and hepatic steatosis increases. Here, we show that WD40 repeat-containing protein 6 (WDR6) promotes hepatic DNL during IR. Mechanistically, WDR6 interacts with the beta-type catalytic subunit of serine/threonine-protein phosphatase 1 (PPP1CB) to facilitate PPP1CB dephosphorylation at Thr316, which subsequently enhances fatty acid synthases transcription through DNA-dependent protein kinase and upstream stimulatory factor 1. Using molecular dynamics simulation analysis, we find a small natural compound, XLIX, that inhibits the interaction of WDR6 with PPP1CB, thus reducing DNL in IR states. Together, these results reveal WDR6 as a promising target for the treatment of hepatic steatosis.

Objective: To investigate the diagnostic performance of deep learning (DL)-based vascular extraction and stenosis detection technology in assessing coronary artery disease (CAD). Methods: The diagnostic performance of DL technology was evaluated by retrospective analysis of coronary computed tomography angiography in 124 suspected CAD patients, using invasive coronary angiography as reference standard. Lumen diameter stenosis ≥50% was considered obstructive, and the diagnostic performances were evaluated at per-patient, per-vessel and per-segment levels. The diagnostic performances between DL model and reader model were compared by the areas under the receiver operating characteristics curves (AUCs). Results: In patient-based analysis, AUC of 0.78 was obtained by DL model to detect obstructive CAD [sensitivity of 94%, specificity of 63%, positive predictive value of 94%, and negative predictive value of 59%], While AUC by reader model was 0.74 (sensitivity of 97%, specificity of 50%, positive predictive value of 93%, negative predictive value of 73%). In vessel-based analysis, the AUCs of DL model and reader model were 0.87 and 0.89 respectively. In segment-based analysis, the AUCs of 0.84 and 0.89 were obtained by DL model and reader model respectively. It took 0.47 min to analyze all segments per patient by DL model, which is significantly less than reader model (29.65 min) (p < 0.001). Conclusion: The DL technology can accurately and effectively identify obstructive CAD, with less time-consuming, and it could be a reliable diagnostic tool to detect CAD. Advances in knowledge: The DL technology has valuable prospect with the diagnostic ability to detect CAD.