Table 2 Summary of recent approaches for dental infection detection.
From: ACO-optimized MobileNetV2-ShuffleNet hybrid model for automated dental caries classification
Ref | Year | Objective | Dental infection type | Image type | Models used |
|---|---|---|---|---|---|
2024 | To improve deep learning-based recognition of dental diseases in X-ray images collected from hospitals. | Six major classes: healthy teeth, caries, impacted teeth, infections, fractured teeth, and broken-down crowns/roots (BDC/BDR). | Panoramic dental radiographs | Image enhancement-contrast-limited adaptive histogram equalization (CLAHE); identification-YOLOv7 | |
2024 | To propose effective methodology for segmentation and classification of tooth types in 3D dental models | – | Panoramic dental X-rays | Preprocessing-random number image conversion filter; segmentation-custom mask-CNN; classification-adaptive enhanced GoogLeNet (AEG) | |
2022 | To utilize the deep gradient-based LeNet classifier model for the diagnosis of caries lesions. | Caries | Bitewing radiographs | Preprocessing-Gaussian filter, gray scaling, thresholding; feature extraction-kernel-based non-linear fisher analysis; classification-DGLeNet | |
2022 | To enhance caries detection using FOC-KKC segmentation and metaheuristic-based ResNeXt-RNN. | Caries | Periodic dental X-ray images | Preprocessing-CLAHE, bilateral filtering; segmentation-FOC-KKC with hybrid sea lion–squirrel search optimization (HSLnSSO); detection-M-ResNeXt-RNN with HSLnSSO |
