Exploring the role of Convolutional Neural Networks (CNN) in dental radiography segmentation: A comprehensive Systematic Literature Review

计算机科学 卷积神经网络 分割 人工智能 系统回顾 模式识别(心理学) 梅德林 政治学 法学
作者
Walid Brahmi,Imen Jdey,Fadoua Drira
出处
期刊:Engineering Applications of Artificial Intelligence [Elsevier BV]
卷期号:133: 108510-108510 被引量:3
标识
DOI:10.1016/j.engappai.2024.108510
摘要

In dentistry, there is a growing need for accurate diagnostic tools, particularly advanced imaging techniques such as Computed Tomography (CT), Cone Beam Computed Tomography (CBCT), Magnetic Resonance Imaging (MRI), ultrasound, and traditional intraoral periapical X-rays. Deep Learning (DL) has emerged as a pivotal tool, facilitating automated segmentation that is crucial for extracting essential diagnostic data. This integration of cutting-edge technology addresses the urgent need for effective management of dental conditions. If left undetected, these conditions can significantly affect human health. Deep Learning (DL) has an impressive track record in various domains, including dentistry, underscoring its potential to revolutionize early detection and treatment of oral health issues. Convolutional Neural Networks (CNNs) have demonstrated significant results in diagnosis and prediction, representing an emerging field of multidisciplinary research. The goals of this study were to provide a concise overview of the state of the art, standardize ongoing debates, and establish baselines for future research. The methodology employed in this study involved a Systematic Literature Review (SLR) to identify and select relevant studies that specifically investigated deep learning techniques for dental imaging analysis. This study elucidates a methodological approach that includes systematic data collection, statistical analysis, and outcome dissemination. By incorporating 45 studies, we identified the selection criteria and research objectives, addressing significant gaps in the existing literature. These studies will assist clinicians in examining dental conditions and classifying dental structures, such as detecting cavities and identifying different types of teeth. The model performance was evaluated by addressing the identified gaps using a variety of metrics that were outlined and explained. This study demonstrated the effectiveness of using CNNs to analyze images and serves as an effective tool for detecting dental pathologies. Despite acknowledging some limitations, CNNs used for segmenting and categorizing teeth demonstrated their highest level of performance overall.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
上官若男应助无心的土豆采纳,获得10
2秒前
honeylaker发布了新的文献求助10
2秒前
3秒前
callmecjh发布了新的文献求助10
3秒前
9月有书读发布了新的文献求助10
4秒前
5秒前
英俊的铭应助忧虑的尔容采纳,获得10
6秒前
糖糖完成签到,获得积分10
6秒前
Enoch发布了新的文献求助10
7秒前
科目三应助等待八宝粥采纳,获得10
7秒前
7秒前
亨利公爵完成签到,获得积分10
8秒前
9秒前
krenc完成签到,获得积分10
9秒前
清脆谷槐发布了新的文献求助10
10秒前
J_C_Van发布了新的文献求助10
10秒前
10秒前
江南最后的深情完成签到,获得积分10
11秒前
hr完成签到 ,获得积分10
11秒前
cckk发布了新的文献求助10
11秒前
12秒前
ca发布了新的文献求助10
12秒前
13秒前
胡萝卜发布了新的文献求助10
14秒前
14秒前
亨利公爵发布了新的文献求助10
14秒前
lzcnextdoor发布了新的文献求助10
14秒前
打打应助xcx采纳,获得10
15秒前
16秒前
shinen发布了新的文献求助30
16秒前
Barry完成签到,获得积分10
16秒前
qixiaoqi完成签到,获得积分10
17秒前
贰鸟应助QPP采纳,获得20
18秒前
lzcnextdoor完成签到,获得积分10
18秒前
冉冉完成签到 ,获得积分0
18秒前
要减肥完成签到,获得积分10
19秒前
全麦面包完成签到,获得积分10
20秒前
爱学习发布了新的文献求助10
21秒前
清脆谷槐完成签到,获得积分10
21秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds第二卷 1200
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038657
求助须知:如何正确求助?哪些是违规求助? 3576306
关于积分的说明 11375198
捐赠科研通 3306108
什么是DOI,文献DOI怎么找? 1819379
邀请新用户注册赠送积分活动 892698
科研通“疑难数据库(出版商)”最低求助积分说明 815066