Deep convolutional neural network algorithm for the automatic segmentation of oral potentially malignant disorders and oral cancers

Author:

Ünsal Gürkan1ORCID,Chaurasia Akhilanand2,Akkaya Nurullah3,Chen Nadler4,Abdalla-Aslan Ragda4,Koca Revan Birke5,Orhan Kaan6ORCID,Roganovic Jelena7,Reddy Prashanti8,Wahjuningrum Dian Agustin9

Affiliation:

1. Faculty of Dentistry, Department of Dentomaxillofacial Radiology, Near East University, Nicosia, Cyprus

2. Faculty of Dental Sciences, King George’s Medical University, Lucknow, Uttar Pradesh, India

3. Department of Computer Engineering, Artificial Intelligence Research Centre, Near East University, Nicosia, Cyprus

4. Department of Oral Medicine, Hadassah School of Dental Medicine, Hebrew University, Sedation and Maxillofacial Imaging, Hebrew, Israel

5. Faculty of Dentistry, Department of Periodontology, University of Kyrenia, Kyrenia, Cyprus

6. Faculty of Dentistry, Department of Dentomaxillofacial Radiology, Ankara University, Ankara, Turkey

7. Department of Pharmacology in Dentistry, School of Dental Medicine, University of Belgrade, Belgrade, Serbia

8. Department of Oral Medicine and Radiology, Government Dental College, Indore, Madhya Pradesh, India

9. Faculty of Dental Medicine, Dental Research Center, Airlangga University, Surabaya, Indonesia

Abstract

This study aimed to develop an algorithm to automatically segment the oral potentially malignant diseases (OPMDs) and oral cancers (OCs) of all oral subsites with various deep convolutional neural network applications. A total of 510 intraoral images of OPMDs and OCs were collected over 3 years (2006—2009). All images were confirmed both with patient records and histopathological reports. Following the labeling of the lesions the dataset was arbitrarily split, using random sampling in Python as the study dataset, validation dataset, and test dataset. Pixels were classified as the OPMDs and OCs with the OPMD/OC label and the rest as the background. U-Net architecture was used and the model with the best validation loss was chosen for the testing among the trained 500 epochs. Dice similarity coefficient (DSC) score was noted. The intra-observer ICC was found to be 0.994 while the inter-observer reliability was 0.989. The calculated DSC and validation accuracy across all clinical images were 0.697 and 0.805, respectively. Our algorithm did not maintain an excellent DSC due to multiple reasons for the detection of both OC and OPMDs in oral cavity sites. A better standardization for both 2D and 3D imaging (such as patient positioning) and a bigger dataset are required to improve the quality of such studies. This is the first study which aimed to segment OPMDs and OCs in all subsites of oral cavity which is crucial not only for the early diagnosis but also for higher survival rates.

Publisher

SAGE Publications

Subject

Mechanical Engineering,General Medicine

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3