RT info:eu-repo/semantics/article
T1 Deep learning-based multiclass instance segmentation for dental lesion detection
A1 Fatima, Anum
A1 Shafi, Imran
A1 Afzal, Hammad
A1 Mahmood, Khawar
A1 Torre Díez, Isabel de la
A1 Lipari, Vivian
A1 Brito Ballester, Julien
A1 Ashraf, Imran
K1 Machine learning
K1 Aprendizaje automático
K1 Artificial intelligence - Medical applications
K1 Inteligencia artificial - Aplicaciones médicas
K1 Preventive dentistry
K1 Dental hygiene
K1 Higiene dental
K1 Mouth - Diseases - Diagnosis
K1 Boca - Enfermedades - Diagnóstico
K1 Image processing
K1 Imágenes, Tratamiento de las
K1 Health informatics
K1 Dentistry
K1 Odontología
K1 1203.04 Inteligencia Artificial
K1 1203.17 Informática
K1 3213.13 Ortodoncia-Estomatología
AB Automated dental imaging interpretation is one of the most prolific areas of research using artificial intelligence. X-ray imaging systems have enabled dental clinicians to identify dental diseases. However, the manual process of dental disease assessment is tedious and error-prone when diagnosed by inexperienced dentists. Thus, researchers have employed different advanced computer vision techniques, as well as machine and deep learning models for dental disease diagnoses using X-ray imagery. In this regard, a lightweight Mask-RCNN model is proposed for periapical disease detection. The proposed model is constructed in two parts: a lightweight modified MobileNet-v2 backbone and region-based network (RPN) are proposed for periapical disease localization on a small dataset. To measure the effectiveness of the proposed model, the lightweight Mask-RCNN is evaluated on a custom annotated dataset comprising images of five different types of periapical lesions. The results reveal that the model can detect and localize periapical lesions with an overall accuracy of 94%, a mean average precision of 85%, and a mean insection over a union of 71.0%. The proposed model improves the detection, classification, and localization accuracy significantly using a smaller number of images compared to existing methods and outperforms state-of-the-art approaches.
PB MDPI
SN 2227-9032
YR 2023
FD 2023
LK https://uvadoc.uva.es/handle/10324/63392
UL https://uvadoc.uva.es/handle/10324/63392
LA eng
NO Healthcare, 2023, Vol. 11, Nº. 3, 347
NO Producción Científica
DS UVaDOC
RD 28-nov-2024