International Journal of Computerized Dentistry, 3/2020
SciencePubMed ID (PMID): 32789308Pages 211-218, Language: German, English
Aim: To assess the accuracy of DigiBrain4, Inc (DB4) Dental Classifier and DB4 Smart Search Engine* in recognizing, categorizing, and classifying dental visual assets as compared with Google Search Engine, one of the largest publicly available search engines and the largest data repository.
Materials and methods: Dental visual assets were collected and labeled according to type, category, class, and modifiers. These dental visual assets contained radiographs and clinical images of patients' teeth and occlusion from different angles of view. A modified SqueezeNet architecture was implemented using the TensorFlow r1.10 framework. The model was trained using two NVIDIA Volta graphics processing units (GPUs). A program was built to search Google Images, using Chrome driver (Google web driver) and submit the returned images to the DB4 Dental Classifier and DB4 Smart Search Engine. The categorical accuracy of the DB4 Dental Classifier and DB4 Smart Search Engine in recognizing, categorizing, and classifying dental visual assets was then compared with that of Google Search Engine.
Results: The categorical accuracy achieved using the DB4 Smart Search Engine for searching dental visual assets was 0.93, whereas that achieved using Google Search Engine was 0.32.
Conclusion: The current DB4 Dental Classifier and DB4 Smart Search Engine application and add-on have proved to be accurate in recognizing, categorizing, and classifying dental visual assets. The search engine was able to label images and reject non-relevant results.
Keywords: dental visual assets, artificial intelligence, dental radiographs, dental clinical images, dental classifier, smart search engine, machine learning, deep learning, convolutional neural network
The International Journal of Oral & Maxillofacial Implants, 6/2017
DOI: 10.11607/jomi.5875, PubMed ID (PMID): 29140383Pages 1389-1398, Language: English
Purpose: Recent case reports suggest that amnion-chorion membranes (ACM) and dense polytetrafluoroethylene membranes (dPTFE) can be left exposed during ridge preservation. The aim of this study was to compare the effectiveness of these membranes in ridge preservation, particularly when they are intentionally left exposed.
Materials and Methods: A split-mouth, single-blind, randomized trial design was used to compare treatments with the two membranes in 22 nonmolar sites on the same arch. Ridge dimensions were recorded clinically and with cone beam computed tomography prior to and 3 months after ridge preservation. Postoperative discomfort was recorded with Visual Analog Scale (VAS) forms. Mixed‑model analysis of variance was used to test significance.
Results: Clinical and radiographic ridge dimensions were not significantly different between the two treatments. ACM sites had significantly more osteoid and higher bone volume density but significantly less graft particles and bone surface density compared with dPTFE. Mineralized bone area and soft tissue area were not significantly different between the two treatments. ACM sites had significantly lower postoperative VAS scores compared with dPTFE.
Conclusion: Intentionally exposed ACM is equally effective in ridge preservation compared with dPTFE. Additionally, ACM use may aid in reducing postoperative VAS scores, and potentially result in better quality of bone available for implant placement, as evidenced by improved histomorphometric measures.
Keywords: amnion-chorion membrane, cone beam computed tomography, dense PTFE, histomorphometry, microtomography, RCT, ridge preservation