Azzahara, Fahlin (2025) Deteksi Penyakit Gingivitis Pada Gigi Manusia Menggunakan Metode Convolutional Neural Network. Other thesis, Universitas Islam Riau.

Text skripsi_203510205_watermark.pdf - Submitted Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

Gingivitis is one of the common dental health problems caused by poor oral hygiene, which causes inflammation of the gums. Triggers for this disease include smoking, excessive alcohol consumption, unhealthy lifestyles, and fungal, bacterial, or viral infections. This condition not only affects the oral cavity, but also has the potential to affect other organs of the body. This study aims to develop a gingivitis detection system using the Convolutional Neural Network (CNN) model. The dataset used consists of images of normal teeth and images of teeth with gingivitis. To balance the amount of data, augmentation was performed on normal teeth images from 120 to 380 images. The augmentation process includes rotation up to 20 degrees, horizontal and vertical shifts of 20%, zoom in/out transformations of 20%, horizontal flips, and image cropping up to 20%. The results of the CNN model test showed good performance with an accuracy of 91%, a precision of 90%, a recall of 91.8%, and an F1-score of 90.6%. Meanwhile, two advanced models (CNN 1 Adam and CNN 2 Adam) successfully achieved 100% accuracy, precision, and recall. Thus, the developed system functions according to specifications and can be used as an early diagnostic tool to detect gingivitis effectively.

Actions (login required)

View Item