Literature DB >> 36236200

Automatic Segmentation of Periodontal Tissue Ultrasound Images with Artificial Intelligence: A Novel Method for Improving Dataset Quality.

Radu Chifor1,2, Mircea Hotoleanu3, Tiberiu Marita4, Tudor Arsenescu2, Mihai Adrian Socaciu5, Iulia Clara Badea1, Ioana Chifor1.   

Abstract

This research aimed to evaluate Mask R-CNN and U-Net convolutional neural network models for pixel-level classification in order to perform the automatic segmentation of bi-dimensional images of US dental arches, identifying anatomical elements required for periodontal diagnosis. A secondary aim was to evaluate the efficiency of a correction method of the ground truth masks segmented by an operator, for improving the quality of the datasets used for training the neural network models, by 3D ultrasound reconstructions of the examined periodontal tissue.
METHODS: Ultrasound periodontal investigations were performed for 52 teeth of 11 patients using a 3D ultrasound scanner prototype. The original ultrasound images were segmented by a low experienced operator using region growing-based segmentation algorithms. Three-dimensional ultrasound reconstructions were used for the quality check and correction of the segmentation. Mask R-CNN and U-NET were trained and used for prediction of periodontal tissue's elements identification.
RESULTS: The average Intersection over Union ranged between 10% for the periodontal pocket and 75.6% for gingiva. Even though the original dataset contained 3417 images from 11 patients, and the corrected dataset only 2135 images from 5 patients, the prediction's accuracy is significantly better for the models trained with the corrected dataset.
CONCLUSIONS: The proposed quality check and correction method by evaluating in the 3D space the operator's ground truth segmentation had a positive impact on the quality of the datasets demonstrated through higher IoU after retraining the models using the corrected dataset.

Entities:  

Keywords:  3D ultrasound reconstructions; artificial intelligence; automatic segmentation; dataset quality; periodontal tissue

Mesh:

Year:  2022        PMID: 36236200      PMCID: PMC9572264          DOI: 10.3390/s22197101

Source DB:  PubMed          Journal:  Sensors (Basel)        ISSN: 1424-8220            Impact factor:   3.847


  26 in total

Review 1.  From manual periodontal probing to digital 3-D imaging to endoscopic capillaroscopy: Recent advances in periodontal disease diagnosis.

Authors:  M Elashiry; M M Meghil; R M Arce; C W Cutler
Journal:  J Periodontal Res       Date:  2018-07-04       Impact factor: 4.419

2.  A noninvasive imaging and measurement using optical coherence tomography angiography for the assessment of gingiva: An in vivo study.

Authors:  Nhan M Le; Shaozhen Song; Hao Zhou; Jingjiang Xu; Yuandong Li; Cheng-En Sung; Alireza Sadr; Kwok-Hung Chung; Hrebesh M Subhash; Latonya Kilpatrick; Ruikang K Wang
Journal:  J Biophotonics       Date:  2018-09-05       Impact factor: 3.207

3.  Observation and determination of periodontal tissue profile using optical coherence tomography.

Authors:  S Kakizaki; A Aoki; M Tsubokawa; T Lin; K Mizutani; G Koshy; A Sadr; S Oda; Y Sumi; Y Izumi
Journal:  J Periodontal Res       Date:  2017-10-24       Impact factor: 4.419

4.  Alveolar Bone Segmentation in Intraoral Ultrasonographs with Machine Learning.

Authors:  K C T Nguyen; D Q Duong; F T Almeida; P W Major; N R Kaipatur; T T Pham; E H M Lou; M Noga; K Punithakumar; L H Le
Journal:  J Dent Res       Date:  2020-05-11       Impact factor: 6.116

5.  Microbiological analysis and the outcomes of periodontal treatment with or without adjunctive systemic antibiotics-a retrospective study.

Authors:  Sigrun Eick; Jasmin Nydegger; Walter Bürgin; Giovanni E Salvi; Anton Sculean; Christoph Ramseier
Journal:  Clin Oral Investig       Date:  2018-02-21       Impact factor: 3.573

6.  Signature of Microbial Dysbiosis in Periodontitis.

Authors:  Vincent Meuric; Sandrine Le Gall-David; Emile Boyer; Luis Acuña-Amador; Bénédicte Martin; Shao Bing Fong; Frederique Barloy-Hubler; Martine Bonnaure-Mallet
Journal:  Appl Environ Microbiol       Date:  2017-06-30       Impact factor: 4.792

7.  Comparative evaluation of accuracy of periodontal probing depth and attachment levels using a Florida probe versus traditional probes.

Authors:  Nitin Gupta; S K Rath; Parul Lohra
Journal:  Med J Armed Forces India       Date:  2012-10-23

Review 8.  Choice of diagnostic and therapeutic imaging in periodontics and implantology.

Authors:  Swarna Chakrapani; K Sirisha; Anumadi Srilalitha; Moogala Srinivas
Journal:  J Indian Soc Periodontol       Date:  2013-11

9.  Deep Learning Hybrid Method to Automatically Diagnose Periodontal Bone Loss and Stage Periodontitis.

Authors:  Hyuk-Joon Chang; Sang-Jeong Lee; Tae-Hoon Yong; Nan-Young Shin; Bong-Geun Jang; Jo-Eun Kim; Kyung-Hoe Huh; Sam-Sun Lee; Min-Suk Heo; Soon-Chul Choi; Tae-Il Kim; Won-Jin Yi
Journal:  Sci Rep       Date:  2020-05-05       Impact factor: 4.379

10.  Clinical Evaluation of a New Electronic Periodontal Probe: A Randomized Controlled Clinical Trial.

Authors:  Oliver Laugisch; Thorsten M Auschill; Christian Heumann; Anton Sculean; Nicole B Arweiler
Journal:  Diagnostics (Basel)       Date:  2021-12-25
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.