Background: Preoperative evaluation of the number of lymph node metastasis (LNM) is the basis of individual treatment of locally advanced gastric cancer (LAGC). However, the routinely used preoperative determination method is not accurate enough. Patients and methods: We enrolled 730 LAGC patients from five centers in China and one center in Italy, and divided them into one primary cohort, three external validation cohorts, and one international validation cohort. A deep learning radiomic nomogram (DLRN) was built based on the images from multiphase computed tomography (CT) for preoperatively determining the number of LNM in LAGC. We comprehensively tested the DLRN and compared it with three state-of-the-art methods. Moreover, we investigated the value of the DLRN in survival analysis. Results: The DLRN showed good discrimination of the number of LNM on all cohorts [overall C-indexes (95% confidence interval): 0.821 (0.785e0.858) in the primary cohort, 0.797 (0.771e0.823) in the external validation cohorts, and 0.822 (0.756e0.887) in the international validation cohort]. The nomogram performed significantly better than the routinely used clinical N stages, tumor size, and clinical model (P < 0.05). Besides, DLRN was significantly associated with the overall survival of LAGC patients (n ¼ 271). Conclusion: A deep learning-based radiomic nomogram had good predictive value for LNM in LAGC. In staging-oriented treatment of gastric cancer, this preoperative nomogram could provide baseline information for individual treatment of LAGC.
Objective Little information is available about deep learning methods used in ultrasound images of salivary gland tumors. We aimed to compare the accuracy of the ultrasound‐trained model to computed tomography or magnetic resonance imaging trained model. Materials and methods Six hundred and thirty‐eight patients were included in this retrospective study. There were 558 benign and 80 malignant salivary gland tumors. A total of 500 images (250 benign and 250 malignant) were acquired in the training and validation set, then 62 images (31 benign and 31 malignant) in the test set. Both machine learning and deep learning were used in our model. Results The test accuracy, sensitivity, and specificity of our final model were 93.5%, 100%, and 87%, respectively. There were no over fitting in our model as the validation accuracy was similar with the test accuracy. Conclusions The sensitivity and specificity were comparable with current MRI and CT images using artificial intelligence.
BACKGROUNDAn enteric-coated levonorgestrel emergency contraceptive pill (E-LNG-ECP) is an improved formulation, in terms of side effects, which both dissolves and is absorbed in the intestine. Our aim was to evaluate the efficacy and safety of E-LNG-ECP as an over-the-counter (OTC) drug for emergency contraception (EC) in Chinese women.METHODSA Phase IV clinical trial was conducted in five family planning clinics in China. Women seeking EC within 72 h after unprotected sexual intercourse or contraceptive failure who met the inclusion criteria were recruited. The efficacy of contraception (primary end-point was pregnancy rate), side effects (i.e. safety) and the value of E-LNG-ECP for EC were investigated.RESULTSOf 2445 women (aged 15–48 years) who took E-LNG-ECP with follow-up to determine pregnancy, only five pregnancies (0.2%) occurred. The efficacy of contraception was 95.3%. In total, 6.5% of women reported at least one adverse event after taking E-LNG-ECP, and no serious adverse events were reported. Only four subjects (0.16%) reported vomiting. The incidence of menstrual cycle disturbance was 20.1% after taking E-LNG-ECP. Subjects who had previously taken ECPs (54.4% of these women) rated the acceptability of E-LNG-ECP at 9.36 (on a 10-point scale) higher (P<0.05) than the rating of other LNG-EC pills taken previously.CONCLUSIONSThe study found that E-LNG-ECP was effective, safe and well tolerated as an OTC drug. However, an randomized controlled trial should be performed to compare standard LNG tablets with E-LNG-ECP.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.