File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ISMICT51748.2021.9434936
- Scopus: eid_2-s2.0-85107298307
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Automatic Site-Specific Multiple Level Gum Disease Detection Based on Deep Neural Network
Title | Automatic Site-Specific Multiple Level Gum Disease Detection Based on Deep Neural Network |
---|---|
Authors | |
Keywords | gingivitis semantic segmentation deep learning network Dentistry |
Issue Date | 2021 |
Publisher | IEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome/1800343/all-proceedings |
Citation | 2021 15th International Symposium on Medical Information and Communication Technology (ISMICT), Xiamen, China, 14-16 April 2021, p. 201-205 How to Cite? |
Abstract | The Gum diseases (gingivitis and periodontitis) is one of the most prevalent dental diseases which are initiated by dental plaque (bacterial biofilm). It has been strongly linked to the systemic diseases including cardiovascular (atherosclerosis, hypertension, stroke), respiratory (aspiration pneumonia), adverse pregnancy outcomes and even cancer via systemic routes with significant health implications. As the inflammation of gum is manifested as increased in redness (colour), increase in volume (oedema), and loss of surface characteristics (stippling; gum fibre attachment). These diseased sites are site- specific (i.e. subject can have healthy and disease sites in a mouth) can be identified by visual examination of dentists. Moreover, these inflammatory changes of gum can also be recognized by intraoral photography which has been clinical practice of regular dental check-up. The aim of this study is to train the computer to identify the inflamed disease sites in pixel level by deep learning approach. We collected 337 and 110 images for training and validation respectively from 110 patients' standard intraoral photographs and randomly. They are labeled into four health status levels (healthy, questionable healthy, questionable diseased and diseased) and verified by a dental specialist with more than 15 years clinical experience. The proposed semantic segmentation architecture is based on the DeepLabv3+ network with Xception and MobileNetV2 as the backbone. Experimental results show the effectiveness of the proposed system, which shows possible application on dental self check-up using mobile app particularly during the disease pandemic where visit to dentists are difficult or even impossible. |
Persistent Identifier | http://hdl.handle.net/10722/308209 |
ISSN | 2020 SCImago Journal Rankings: 0.191 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, GH | - |
dc.contributor.author | Hsung, TC | - |
dc.contributor.author | Ling, WK | - |
dc.contributor.author | Lam, YHW | - |
dc.contributor.author | Pelekos, G | - |
dc.contributor.author | McGrath, C | - |
dc.date.accessioned | 2021-11-12T13:44:01Z | - |
dc.date.available | 2021-11-12T13:44:01Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | 2021 15th International Symposium on Medical Information and Communication Technology (ISMICT), Xiamen, China, 14-16 April 2021, p. 201-205 | - |
dc.identifier.issn | 2326-828X | - |
dc.identifier.uri | http://hdl.handle.net/10722/308209 | - |
dc.description.abstract | The Gum diseases (gingivitis and periodontitis) is one of the most prevalent dental diseases which are initiated by dental plaque (bacterial biofilm). It has been strongly linked to the systemic diseases including cardiovascular (atherosclerosis, hypertension, stroke), respiratory (aspiration pneumonia), adverse pregnancy outcomes and even cancer via systemic routes with significant health implications. As the inflammation of gum is manifested as increased in redness (colour), increase in volume (oedema), and loss of surface characteristics (stippling; gum fibre attachment). These diseased sites are site- specific (i.e. subject can have healthy and disease sites in a mouth) can be identified by visual examination of dentists. Moreover, these inflammatory changes of gum can also be recognized by intraoral photography which has been clinical practice of regular dental check-up. The aim of this study is to train the computer to identify the inflamed disease sites in pixel level by deep learning approach. We collected 337 and 110 images for training and validation respectively from 110 patients' standard intraoral photographs and randomly. They are labeled into four health status levels (healthy, questionable healthy, questionable diseased and diseased) and verified by a dental specialist with more than 15 years clinical experience. The proposed semantic segmentation architecture is based on the DeepLabv3+ network with Xception and MobileNetV2 as the backbone. Experimental results show the effectiveness of the proposed system, which shows possible application on dental self check-up using mobile app particularly during the disease pandemic where visit to dentists are difficult or even impossible. | - |
dc.language | eng | - |
dc.publisher | IEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome/1800343/all-proceedings | - |
dc.relation.ispartof | 2021 15th International Symposium on Medical Information and Communication Technology (ISMICT) | - |
dc.rights | International Symposium on Medical Information and Communication Technology (ISMICT). Copyright © IEEE. | - |
dc.rights | ©2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.subject | gingivitis | - |
dc.subject | semantic segmentation | - |
dc.subject | deep learning | - |
dc.subject | network | - |
dc.subject | Dentistry | - |
dc.title | Automatic Site-Specific Multiple Level Gum Disease Detection Based on Deep Neural Network | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Hsung, TC: tchsung@hku.hk | - |
dc.identifier.email | Lam, YHW: retlaw@hku.hk | - |
dc.identifier.email | Pelekos, G: george74@hku.hk | - |
dc.identifier.email | McGrath, C: mcgrathc@hkucc.hku.hk | - |
dc.identifier.authority | Lam, YHW=rp02183 | - |
dc.identifier.authority | Pelekos, G=rp01894 | - |
dc.identifier.authority | McGrath, C=rp00037 | - |
dc.description.nature | postprint | - |
dc.identifier.doi | 10.1109/ISMICT51748.2021.9434936 | - |
dc.identifier.scopus | eid_2-s2.0-85107298307 | - |
dc.identifier.hkuros | 329815 | - |
dc.identifier.spage | 201 | - |
dc.identifier.epage | 205 | - |
dc.publisher.place | United States | - |