Caries Detection Using CNN
Caries, commonly referred to as tooth decay, is a prevalent dental issue. Detecting caries early is crucial for preventing further dental complications. In this report, we implement a Convolutional Neural Network (CNN) to classify dental images into two categories: Caries and no_Caries.
Dataset
The dataset consists of labeled dental X-ray images. Each image is classified into one of two categories: Caries: Images where dental caries are present. no_Caries: Images with no visible caries. The images are collected from various dental clinics and online repositories. The dataset includes images in .jpg format, with each image resized to 224x224 pixels for uniform input into the CNN model. The dataset was split into training, validation, and test sets as follows: Training Set: 80% of the data (4,000 images) Validation Set: 10% of the data (500 images) Test Set: 10% of the data (500 images)
Results
The CNN model achieved a high classification accuracy of 94% for detecting dental caries from X-ray images. By using data augmentation and dropout layers, overfitting was minimized, and the model generalized well to unseen test data. These results demonstrate that CNNs are a promising tool for automatic caries detection, which could potentially aid in clinical diagnostics.
