BackgroundWe attempted to train and validate a model of deep learning for the preoperative prediction of the response of patients with intermediate-stage hepatocellular carcinoma (HCC) undergoing transarterial chemoembolization (TACE).MethodAll computed tomography (CT) images were acquired for 562 patients from the Nan Fang Hospital (NFH), 89 patients from Zhu Hai Hospital Affiliated with Jinan University (ZHHAJU), and 138 patients from the Sun Yat-sen University Cancer Center (SYUCC). We built a predictive model from the outputs using the transfer learning techniques of a residual convolutional neural network (ResNet50). The prediction accuracy for each patch was revaluated in two independent validation cohorts.ResultsIn the training set (NFH), the deep learning model had an accuracy of 84.3% and areas under curves (AUCs) of 0.97, 0.96, 0.95, and 0.96 for complete response (CR), partial response (PR), stable disease (SD), and progressive disease (PD), respectively. In the other two validation sets (ZHHAJU and SYUCC), the deep learning model had accuracies of 85.1% and 82.8% for CR, PR, SD, and PD. The ResNet50 model also had high AUCs for predicting the objective response of TACE therapy in patches and patients of three cohorts. Decision curve analysis (DCA) showed that the ResNet50 model had a high net benefit in the two validation cohorts.ConclusionThe deep learning model presented a good performance for predicting the response of TACE therapy and could help clinicians in better screening patients with HCC who can benefit from the interventional treatment.Key Points• Therapy response of TACE can be predicted by a deep learning model based on CT images. • The probability value from a trained or validation deep learning model showed significant correlation with different therapy responses. • Further improvement is necessary before clinical utilization. Electronic supplementary materialThe online version of this article (10.1007/s00330-019-06318-1) contains supplementary material, which is available to authorized users.
Objectives We aim to retrospectively analyze the diagnostic image quality of transvaginal 4‐dimensional hysterosalpingo‐contrast sonography from infertile patients and determine the significant influencing factors. Methods A total of 445 patients visiting infertility clinics were included in the study, of which 167 were primary infertile and 278 were secondary infertile. The factors were recorded, including age; examination time; infertility type; history of pelvic inflammatory disease, pelvic surgery, intrauterine surgery, and ectopic pregnancy; endometrial thickness; uterine position; ovarian position; 2‐dimensional image quality; intravasation quantity, position, and time; balloon volume; and the dosage of contrast agent or the sterile saline solution. All the factors were compared among different diagnostic image quality groups. The method of rank logistic regression analysis was adopted to analyze the risk factors affecting the diagnostic image quality. Results Among the 445 infertile patients, 124 (27.9%) patients had intravasation occur during transvaginal 4‐dimensional hysterosalpingo‐contrast sonography. The diagnostic image quality between the 2 sonographers was consistent (Cronbach's alpha, 0.993). Different intravasation quantities, positions, and times; increased of balloon volume; and history of pelvic surgery were substantial risk factors for the diagnostic image quality. The diagnostic image quality diminished with the increase of intravasation. In the patient with cornual intravasation, the diagnostic image quality was substantially worse than that with non–cornual intravasation. Moreover, early onset of intravasation seriously affected the diagnostic image quality. Conclusions In conclusion, intravasation affected the diagnostic image quality, especially early cornual massive intravasation.
2-(2'-Oxo-3'-oximidocyclododecyl) cyclododecanone (1) and 2-(1'-hydroxylcyclododecyl) cyclododecanone (2) were synthesized and characterized. The conformation analysis was carried out based on the NMR, molecular mechanics calculation and X-ray diffraction. The conformation of two cyclododecyl moieties of both 1 and 2 was found to be the [3333]-2-one or [3333] square conformation both in the crystal state and the solution. The dihedral angle between carbonyl and the oxime double bond of the ring B is 180° in the crystal of 1. The protons or hydroxyl group of carbon atoms to link the two cyclododecyl moieties of 1 and 2 constitute dihedral angles of 174° in the crystal, and 175° in the solution, and the C-C σ bond between two cyclododecyl moieties can not freely rotate in the solid state and the solution. In addition, compound 2 was the first example of α-corner-anti-monosubstituted cyclododecanone.
Personal privacy protection issues has gradually caused widespread concern in society which will lead to economic and reputation losses, hinder network and E-commerce innovation or some other consequences if not handled properly. In this paper, we make use of the de-centralization, permanent and audibility of the blockchain to propose a blockchain-based personal privacy protection mechanism, which uses Online taxi-hailing as the application scenario. We not only provide the details of the blockchain custom transaction domain used by the scene, but also expound the information exchanging and blockchain auditing between passengers, Online taxi-hailing platform and drivers in Online taxi-hailing scene, providing a case model for the blockchain solution to personal privacy protection and a technical mechanism solution for further study of personal privacy protection issues.
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.