A novel deep learning-based perspective for tooth numbering and caries detection

被引:8
作者
Ayhan, Baturalp [1 ]
Ayan, Enes [2 ]
Bayraktar, Yusuf [1 ]
机构
[1] Kirikkale Univ, Fac Dent, Dept Restorat Dent, Kirikkale, Turkiye
[2] Kirikkale Univ, Fac Engn & Architecture, Dept Comp Engn, Kirikkale, Turkiye
关键词
Artificial intelligence; Digital bitewing radiography; Deep learning; Detection; Numbering; Dental caries; CONVOLUTIONAL NEURAL-NETWORK; BITE-WING RADIOGRAPHY; PROXIMAL CARIES; DENTAL-CARIES; OCCLUSAL CARIES; TEETH; CLASSIFICATION; DIAGNOSIS; ACCURACY; FILM;
D O I
10.1007/s00784-024-05566-w
中图分类号
R78 [口腔科学];
学科分类号
1003 ;
摘要
ObjectivesThe aim of this study was automatically detecting and numbering teeth in digital bitewing radiographs obtained from patients, and evaluating the diagnostic efficiency of decayed teeth in real time, using deep learning algorithms.MethodsThe dataset consisted of 1170 anonymized digital bitewing radiographs randomly obtained from faculty archives. After image evaluation and labeling process, the dataset was split into training and test datasets. This study proposed an end-to-end pipeline architecture consisting of three stages for matching tooth numbers and caries lesions to enhance treatment outcomes and prevent potential issues. Initially, a pre-trained convolutional neural network (CNN) utilized to determine the side of the bitewing images. Then, an improved CNN model YOLOv7 was proposed for tooth numbering and caries detection. In the final stage, our developed algorithm assessed which teeth have caries by comparing the numbered teeth with the detected caries, using the intersection over union value for the matching process.ResultsAccording to test results, the recall, precision, and F1-score values were 0.994, 0.987 and 0.99 for teeth detection, 0.974, 0.985 and 0.979 for teeth numbering, and 0.833, 0.866 and 0.822 for caries detection, respectively. For teeth numbering and caries detection matching performance; the accuracy, recall, specificity, precision and F1-Score values were 0.934, 0.834, 0.961, 0.851 and 0.842, respectively.ConclusionsThe proposed model exhibited good achievement, highlighting the potential use of CNNs for tooth detection, numbering, and caries detection, concurrently.Clinical significanceCNNs can provide valuable support to clinicians by automating the detection and numbering of teeth, as well as the detection of caries on bitewing radiographs. By enhancing overall performance, these algorithms have the capacity to efficiently save time and play a significant role in the assessment process.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] Self-assessment and deep learning-based coronavirus detection and medical diagnosis systems for healthcare
    Qureshi, Kashif Naseer
    Alhudhaif, Adi
    Ali, Moazam
    Qureshi, Maria Ahmed
    Jeon, Gwanggil
    MULTIMEDIA SYSTEMS, 2022, 28 (04) : 1439 - 1448
  • [32] The Possibility of Deep Learning-Based, Computer-Aided Skin Tumor Classifiers
    Fujisawa, Yasuhiro
    Inoue, Sae
    Nakamura, Yoshiyuki
    FRONTIERS IN MEDICINE, 2019, 6
  • [33] Deep learning-based fabric defect detection: A review
    Kahraman, Yavuz
    Durmusoglu, Alptekin
    TEXTILE RESEARCH JOURNAL, 2023, 93 (5-6) : 1485 - 1503
  • [34] Deep learning-based small object detection: A survey
    Feng, Qihan
    Xu, Xinzheng
    Wang, Zhixiao
    MATHEMATICAL BIOSCIENCES AND ENGINEERING, 2023, 20 (04) : 6551 - 6590
  • [35] A novel end-to-end deep learning approach for cancer detection based on microscopic medical images
    Hammad, Mohamed
    Bakrey, Mohamed
    Bakhiet, Ali
    Tadeusiewicz, Ryszard
    Abd El-Latif, Ahmed A.
    Plawiak, Pawel
    BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, 2022, 42 (03) : 737 - 748
  • [36] Deep Learning-Based System for Automatic Melanoma Detection
    Adegun, Adekanmi A.
    Viriri, Serestina
    IEEE ACCESS, 2020, 8 : 7160 - 7172
  • [37] Review of Deep Learning-Based Video Anomaly Detection
    Ji G.
    Qi X.
    Wang J.
    Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2024, 37 (02): : 128 - 143
  • [38] A novel approach for detection of primary tooth caries based on the light influence foundation
    Anatoly A Kunin
    Natalia S Moiseeva
    EPMA Journal, 2014, 5 (Suppl 1)
  • [39] HSILDNet: A Novel Deep Learning-based Method for Cervical Lesions Detection
    Cao, Yuzhen
    Ma, Huizhan
    Fan, Yinuo
    Liu, Yuzhen
    Wang, Shuo
    Yu, Hui
    2022 9TH INTERNATIONAL CONFERENCE ON BIOMEDICAL AND BIOINFORMATICS ENGINEERING, ICBBE 2022, 2022, : 35 - 40
  • [40] Novel Deep Learning-Based Vocal Biomarkers for Stress Detection in Koreans
    Namkung, Junghyun
    Kim, Seok Min
    Cho, Won Ik
    Yoo, So Young
    Min, Beomjun
    Lee, Sang Yool
    Lee, Ji-Hye
    Park, Heyeon
    Baik, Soyoung
    Yun, Je-Yeon
    Kim, Nam Soo
    Kim, Jeong-Hyun
    PSYCHIATRY INVESTIGATION, 2024, 21 (11) : 1228 - 1237