Simultaneous detection of dental caries and fissure sealant in intraoral photos by deep learning: a pilot study.

BACKGROUND: Deep learning, as an artificial intelligence method has been proved to be powerful in analyzing images. The purpose of this study is to construct a deep learning-based model (ToothNet) for the simultaneous detection of dental caries and fissure sealants in intraoral photos. METHODS: A total of 1020 intraoral photos were collected from 762 volunteers. Teeth, caries and sealants were annotated by two endodontists using the LabelMe tool. ToothNet was developed by modifying the YOLOX framework for simultaneous detection of caries and fissure sealants. The area under curve (AUC) in the receiver operating characteristic curve (ROC) and free-response ROC (FROC) curves were used to evaluate model performance in the following aspects: (i) classification accuracy of detecting dental caries and fissure sealants from a photograph (image-level); and (ii) localization accuracy of the locations of predicted dental caries and fissure sealants (tooth-level). The performance of ToothNet and dentist with 1year of experience (1-year dentist) were compared at tooth-level and image-level using Wilcoxon test and DeLong test. RESULTS: At the image level, ToothNet achieved an AUC of 0.925 (95% CI, 0.880-0.958) for caries detection and 0.902 (95% CI, 0.853-0.940) for sealant detection. At the tooth level, with a confidence threshold of 0.5, the sensitivity, precision, and F1-score for caries detection were 0.807, 0.814, and 0.810, respectively. For fissure sealant detection, the values were 0.714, 0.750, and 0.731. Compared with ToothNet, the 1-year dentist had a lower F1 value (0.599, p < 0.0001) and AUC (0.749, p < 0.0001) in caries detection, and a lower F1 value (0.727, p = 0.023) and similar AUC (0.829, p = 0.154) in sealant detection. CONCLUSIONS: The proposed deep learning model achieved multi-task simultaneous detection in intraoral photos and showed good performance in the detection of dental caries and fissure sealants. Compared with 1-year dentist, the model has advantages in caries detection and is equivalent in fissure sealants detection.

TPGS functionalized mesoporous silica nanoparticles for anticancer drug delivery to overcome multidrug resistance.

Multidrug resistance (MDR) has become a very serious problem in cancer therapy. To effectively reverse MDR in tumor treatments, a new pH-sensitive nano drug delivery system (NDDS) composed of mesoporous silica nanoparticles (MSNs) and d-a-tocopheryl poly-ethylene glycol 1000 succinate (TPGS) copolymers was synthesized to deliver doxorubicin (DOX) into drug-resistant breast cancer cell line (MCF-7/ADR). DOX@MSNs-TPGS were characterized to have a single peak size distribution, high DOX loading efficiency and a pH-dependent drug release profile. MSNs-TPGS were internalized via caveolae, clathrin-mediated endocytosis and energy-dependent cellular uptake. The DOX@MSNs-TPGS exhibited 10-fold enhanced cell killing potency compared to free DOX and DOX@MSNs. The enhanced MDR reversal effect was ascribed to the higher amount of cellular uptake of DOX@MSNs-TPGS in MCF-7/ADR cells than that of free DOX and DOX@MSNs, as a result of the inhibition of P-gp mediated drug efflux by TPGS. In vivo studies of NDDS in tumor-bearing mice showed that DOX@MSNs-TPGS displayed better efficacy against MDR tumors in mice and reached the tumor site more effectively than DOX and DOX@MSNs, with minimal toxicity. These results suggest DOX@MSNs-TPGS developed in this study have promising applications to overcome drug resistance in tumor treatments.

Evaluation of toxicity and single-dose pharmacokinetics of intravenous ursolic acid liposomes in healthy adult volunteers and patients with advanced solid tumors.

OBJECTIVE: The purpose of this study was to investigate the maximum tolerated dose (MTD), dose-limiting toxicity (DLT), and pharmacokinetics of ursolic acid liposomes (UAL), as a new drug, in healthy adult volunteers and patients with advanced solid tumors. METHODS: All subjects received a single-dose of UAL (11, 22, 37, 56, 74, 98, and 130 mg/m(2)) administered as a 4-h intravenous infusion. Toxicity was assessed and plasma samples were analyzed using validated ultra-performance liquid chromatograph/tandem mass spectroscopy method. RESULTS: A total of 63 subjects including 4 patients and 35 healthy adult volunteers for toxicity study and 24 healthy adult volunteers for pharmacokinetic study were enrolled in this trial. The DLT was encountered at 74, 98, and 130 mg/m(2), and consisted of hepatotoxicity and diarrhea. Other adverse events included grade 1 nausea, grade 2 abdominal distention, grade 1 microscopic hematuria, grade 2 elevated serum sodium, grade 1 vascular stimulation, and grade 1 skin rash. The MTD was 98 mg/m(2). The single-dose pharmacokinetic parameters revealed a linear relationship between C(max), AUC(0→24 h), or AUC(0→∞) and escalated doses. CONCLUSIONS: The clinical data reported for the first time that UAL had manageable toxicities with MTD of 98 mg/m(2). The DLT were hepatotoxicity and diarrhea. Meanwhile, UAL had a linear pharmacokinetic profile. The registration number of this trial is ChiCTR-ONC-12002385.