Table 2.
Characteristic table for the selected studies.
| S. no. | Author, year of publication, country | Objective | Algorithm | Language | Dataset size | Accuracy |
|---|---|---|---|---|---|---|
| 1 | (1) Devito | To diagnose proximal dental caries | Hidden-layer perceptron with backpropagation | English | 160 X-dental radiograph | 88.4% |
| (2) de Souza Barbosa | ||||||
| (3) Filho (2008, Brazil) | ||||||
| 2 | (1) Mayank | To detect tooth caries in bitewing radiographs | F-CNN | English | 3000 | 70% |
| (2) Pratyush Kumar | ||||||
| (3) Lalit Pradhan | ||||||
| (4) Srikrishna Varadarajan (2017, USA) | ||||||
| 3 | (1) Casalegno | To predict occlusal and proximal caries | CNN | English | 217 dental images | (1) Occlusal = 83.6% |
| (2) Newton | ||||||
| (3) Daher | (2) Proximal = 85.6% | |||||
| (4) Abdelaziz A. Lodi-Rizzini | ||||||
| (5) F. Schürmann | ||||||
| (6) I. Krejci | ||||||
| (7) H. Markram (2018, Switzerland) | ||||||
| 4 | (1) Jae-Hong Leea | To evaluate the efficacy of deep CNN algorithms for detection and diagnosis of dental caries on periapical radiographs | CNN | English | 3000 X-dental images | (1) Molar = 89% |
| (2) Do-Hyung Kima | ||||||
| (3) Seong-Nyum Jeonga | (1) Molar | (2) Premolar = 88% | ||||
| (4) Seong-Ho Choib(2018, Korea) | (2) Premolar | |||||
| (3) Both molar and premolar | ||||||
| (3) Both molar and premolar = 82% | ||||||
| 5 | (1) Laura A. Zanella-Calzada | To diagnose caries using socioeconomic and nutritional features as determinants | ANN | English | 189 images | 69% |
| (2) Carlos E. Galván-Tejada | ||||||
| (3) Nubia M. Chávez-Lamas | ||||||
| (4) Jesús Rivas-Gutierre | ||||||
| (5) Rafael Magallanes-Quintanar | ||||||
| (6) Jose M. Celaya-Padilla | ||||||
| (7) Jorge I. Galván-Tejada | ||||||
| (8) Hamurabi Gamboa-Rosales (2018, Mexico) | ||||||
| 6 | (1) K. Moutselos | To determine occlusal caries in dental intraoral images | MASK | English | 88 | (1) MC = most common = 88.9% |
| (2) E. Berdouses | (R-CNN) | In-vitro dental images | (2) CPC = center pixel class = 77.8% | |||
| (3) C. Oulis | ||||||
| (4) I. Maglogiannis (2019, Greece) | (3) WC = worst class = 66.7% | |||||
| 7 | (1) Shashi Kant Patil | To evaluate accurate detection of caries using feature extraction and classification of the dental images along with amalgamation-adaptive dragonfly algorithm (DA) algorithm and neural network (NN) classifier | (1) Adaptive dragonfly algorithm (ADA-NN) | English | 120 dental images | Summarizes the performance analysis of proposed ADA-NN classifier over the other conventional classifiers. |
| (2) Vaishali Kulkarni | Test case 1. Here, the accuracy of the proposed model is 5.55% better than KNN, SVM, NB and LM-NN. | |||||
| (3) Archana Bhise (2019, India) | (2) K-nearest neighbors (KNN) | 40 for each test case | Test case 2. ADA model is 11.76% and 52% superior to the existing models like KNN and SVM in terms of accuracy. | |||
| Test case 3. The accuracy of the proposed model is 6.30% better than SVM and NB classifier | ||||||
| (3) Support vector machine (SVM) | ||||||
| (4) Naive Bayes (NB) | ||||||
| (5) LM-NN | ||||||
| 8 | (1) Syed Javed | To predict of post- Streptococcus mutans in dental caries | Feedforward backpropagation | English | 45 premolar teeth images | 99% |
| (2) M. Zakirulla | ANN | |||||
| (3) Rahmath Ulla Baig | (as it causes the dental caries) | |||||
| (4) S.M. Asif | ||||||
| (5) Allah Baksh Meer (2019, Saudi Arabia) | ||||||
| 9 | (1) Man Hung | Application of machine learning for diagnostic prediction of root caries | Support vector machine (SVM) | English | 5,135 | From all the machine learning algorithms developed, support vector machine (SVM) demonstrated the best performance with an accuracy of 97.1% |
| (2) Maren W. Voss | ||||||
| (3) Megan N. Rosales | Random forest regression (RF) | |||||
| (4) Wei Li | ||||||
| (5) Weicong Su | k-nearest neighbors (k-NN) | |||||
| (6) Julie Xu | ||||||
| (7) Jerry Bounsanga, | Logistic regression | |||||
| (8) Bianca Ruiz-Negrón Evelyn Lauren | ||||||
| (9) Frank W. Licari | ||||||
| (2019, Jordan) | ||||||
| 10 | (1) Geetha K. | To diagnose dental caries | Backpropagation | English | 105 | 97.1% |
| (2) S. Aprameya | ||||||
| (3) Dharam | ||||||
| (4) M. Hinduja (2020, India) | ||||||
| 11 | (1) Duc Long Duong | Automated caries detection with smartphone color photography using machine learning | Support vector machine (SVM) | English | 620 unrestored molars/premolars | 92.37% |
| (2) Malitha Humayun Kabir | ||||||
| (3) Rong fu Kuo (2021, Taiwan) | ||||||
| 12 | (1) J. Kühnisch | Caries detection on intraoral images using artificial intelligence | Convolutional neural networks (CNNs) | English | 2,417 peranent teeth | 93.3% |
| (2) O. Meyer | (1,317 occlusal and 1,100 smooth surfaces) | |||||
| (3) M. Hesenius | ||||||
| (4) R. Hickel1 | ||||||
| (5) V. Gruhn (2022, Germany) |