Primary Methods and Algorithms in Artificial-Intelligence-Based Dental Image Analysis: A Systematic Review

Algorithms, Journal Year: 2024, Volume and Issue: 17(12), P. 567 - 567

Published: Dec. 11, 2024

Artificial intelligence (AI) has garnered significant attention in recent years for its potential to revolutionize healthcare, including dentistry. However, despite the growing body of literature on AI-based dental image analysis, challenges such as integration AI into clinical workflows, variability dataset quality, and lack standardized evaluation metrics remain largely underexplored. This systematic review aims address these gaps by assessing extent which technologies have been integrated specialties, with a specific focus their applications imaging. A comprehensive was conducted, selecting relevant studies through electronic searches from Scopus, Google Scholar, PubMed databases, covering publications 2018 2023. total 52 articles were systematically analyzed evaluate diverse approaches machine learning (ML) deep (DL) reveals that become increasingly prevalent, researchers predominantly employing convolutional neural networks (CNNs) detection diagnosis tasks. Pretrained demonstrate strong performance many scenarios, while ML techniques shown utility estimation classification. Key identified include need larger, annotated datasets translation research outcomes practice. The findings underscore AI’s significantly advance diagnostic support, particularly non-specialist dentists, improving patient care efficiency. AI-driven software can enhance accuracy, facilitate data sharing, support collaboration among professionals. Future developments are anticipated enable patient-specific optimization restoration designs implant placements, leveraging personalized history, tissue type, bone thickness achieve better outcomes.

Language: Английский

---

Detection and classification of Melanoma image of skin cancer based on Convolutional Neural Network and comparison with Coactive Neuro Fuzzy Inference System

2022 International Conference on Cyber Resilience (ICCR), Journal Year: 2022, Volume and Issue: unknown, P. 1 - 5

Published: Oct. 6, 2022

The main aim of the work is to improve accuracy for skin cancer detection that leads identification disease in a preclinical stage using Convolutional Neural Network algorithm comparison with Coactive Neuro Fuzzy Inference System. datas are collected from open access website uci machine learning repository datasets. In disease, 20 Melanoma images (MI) used (Group 1) and it compared System 2) 80 % pretest power maximum accepted error as 0.05. Proposed system CNN improves 98.31 CANFIS an 87.61%. Significance value 0.001 (p i 0.05, 2-tailed). this view better CANFIS.

Language: Английский

---

Prediction of Heart Disease Using Naive Bayes in Comparison with KNN Based on Accuracy

2022 International Conference on Cyber Resilience (ICCR), Journal Year: 2022, Volume and Issue: unknown, P. 1 - 4

Published: Oct. 6, 2022

The aim of the study is to predict heart disease by using naive bayes technique and increase accuracy in prediction machine learning classifiers comparing their performance. Two groups such as Naive Bayes K-Nearest Neighbour (KNN) are analysed this research. algorithms have been implemented tested over a dataset which consists 1700 records. Sample size found be 540 from clincalc.com with pretest power 80%. 20 samples for statistical analysis. After performing experiment mean 82.47% algorithm 79.64% k-nearest neighbour disease. There significant difference two p¡O.05 independent t-tests. This research improve algorithms. Performance carried out comparison results show that better performance compared KNN.

Language: Английский

---

A Survey on Dental Disease Detection Based on Deep Learning Algorithm Performance using Various Radiographs

Published: Dec. 2, 2022

Dental disease is a significant problem in humans and deep learning increasingly being used the field of dentistry. The purpose this literature review to identify dental problems such as tooth identification, caries, treated teeth, implants, endodontic treatment using approaches image analysis which help dentists their decision-making process. radiographs are essential for diagnosis detection issues. study focuses on development use several segmentation/ classification algorithms extraction regions interest from radiographs. To predict different forms impacted convolutional neural network trained, validated, tested images with labelled datasets. Our research suggests that Hybrid models CNN-SVM, CNN-KNN or CNN-LSTM K-mean can be trained over mixed data sets produce excellent results whereas compared other segmentation algorithms, UNet architecture performs better at segmenting Xray images.

Language: Английский

---

Güncel Pedodonti Çalışmaları IV

Published: April 19, 2024

Çocuk Diş Hekimliğinde Dental Adezyon Kadriye Görkem ULU GÜZEL Eda ODABAŞ Elektronik Çalışma Boyutu Tespiti (Apeks Bulucular) İsmail CİHANGİR Pulpanın Enflamasyonu ve Doğal İmmun Yanıt Aybüke BAHADIR SEZER Hüsniye GÜMÜŞ Minimal Girişimsel Hekimliği Ezgi TAŞPINAR Aşırı Madde Kayıplı Sut Dişlerinin Prefabrik Kronlar ile Restorasyonu Şerifenur YETİŞ Anterior Dişlerinde Restoratif Tedavi Seçenekleri Elif KILIÇ Sema AYDINOĞLU Çocuklarda Görülen Eti Hastalıkları Sena SAKIN ULUBAY Davranış Yönlendirme Teknikleri İrem İPEK Büşra KARAAĞAÇ ESKİBAĞLAR Genç Daimi Dişlerde Vital Pulpa Tedavileri Ecem CÖMERT Beyza ALKAÇ EKİCİ Yapay Zeka Yaşı Tahmin Yöntemleri Oğuzhan KARAYEL Halenur ALTAN

---

The Influence of Integrating Sex as a Feature in Deep Learning-Based Dental Age Estimation using Panoramic Radiographs

Published: Oct. 28, 2023

Forensic dental age estimation based on panoramic radiographs (orthopantomogram, OPG) is commonly used to assess the of children and young adolescents. Recent advances in deep learning techniques have shown that it possible accurately determine individual from these OPG images. Traditionally, sex has been considered a predictive parameter for estimation. Surprisingly, most studies not included as feature their models. This study aims investigate impact including models estimating age. Two learning-based methods were developed compared: first method only image input, while second integrated both information. Our dataset 1734 images Thai population aged between 8 23 years, along with corresponding chronological sex. A pretrained EfficientNet-B0, convolutional neural network model, was estimate results indicate there no statistical difference error groups 15 years when comparing two methods. However, individuals using information resulted statistically lower compared image. mean absolute (MAE) 11 days, which might be clinically insignificant. finding suggests development model could accomplished one input without significantly affecting accuracy.

Language: Английский

---

Optimizing Age Classification Using Hyperparameter Tuning and Handling Imbalanced Dataset: An Algorithm Decision Forest training Algorithms Approach

Published: Nov. 7, 2023

Age classification is a specialist field, and imbalanced datasets hyperparameter tuning are essential issues that can increase the superiority of models. This study proposes new method for age optimization using Decision Forest training technique, focusing on handling datasets. With substantial improvements in minority classes, this research aims to improve model's accuracy. A robust model shows resistance overfitting was created by utilizing capabilities algorithm model. The accuracy loss excellent; highest K-FOLD 5: Accuracy: 0.9512 Loss: 0.2172. innovative presents significant breakthroughs regarding categorization workable approach researchers perform appropriate adjustments when dealing with data. represents tremendous advance field an exciting path application

Language: Английский

---

Palm Print Identification and Classification in the field of Biometric in CNN using KNN

2022 14th International Conference on Mathematics, Actuarial Science, Computer Science and Statistics (MACS), Journal Year: 2022, Volume and Issue: unknown

Published: Nov. 12, 2022

To improve the efficiency in palm print identification based on CNN classifier and KNN classifier. Classification is performed by algorithm (N=25) over for identifying print. a Machine Learning which can take an input image, assign importance to various objects image be able differentiate one from other. The k- nearest neighbors (KNN) simple, supervised machine learning technique that used solve both problems are classification regression. obtained G-power test value 80%. By keeping alpha error-threshold 0.05, enrollment ratio as 0:1, 95% confidence interval, power terms of accuracy identified (95.8%) (94%). results were with significance 0.650 (P10.05). palmprint appears better than KNN.

Language: Английский

---