Intraoral radiograph anatomical region classification using neural networks

Purpose Dental radiography represents 13% of all radiological diagnostic imaging. Eliminating the need for manual classification of digital intraoral radiographs could be especially impactful in terms of time savings and metadata quality. However, automating the task can be challenging due to the li...

Full description

Saved in:
Bibliographic Details
Published in:International journal for computer assisted radiology and surgery 2021-03, Vol.16 (3), p.447-455
Main Authors: Kyventidis, Nikolaos, Angelopoulos, Christos
Format: Article
Language:English
Subjects:
Accuracy
Anatomy
Automation
Classification
Computer Imaging
Computer Science
Data augmentation
Datasets
Digital imaging
Health Informatics
Image classification
Imaging
Machine learning
Medical imaging
Medicine
Medicine & Public Health
Model accuracy
Neural networks
Original Article
Pattern Recognition and Graphics
Performance measurement
Radiographs
Radiography
Radiology
Surgery
Vision
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Purpose Dental radiography represents 13% of all radiological diagnostic imaging. Eliminating the need for manual classification of digital intraoral radiographs could be especially impactful in terms of time savings and metadata quality. However, automating the task can be challenging due to the limited variation and possible overlap of the depicted anatomy. This study attempted to use neural networks to automate the classification of anatomical regions in intraoral radiographs among 22 unique anatomical classes. Methods Thirty-six literature-based neural network models were systematically developed and trained with full supervision and three different data augmentation strategies. Only libre software and limited computational resources were utilized. The training and validation datasets consisted of 15,254 intraoral periapical and bite-wing radiographs, previously obtained for diagnostic purposes. All models were then comparatively evaluated on a separate dataset as regards their classification performance. Top-1 accuracy, area-under-the-curve and F 1-score were used as performance metrics. Pairwise comparisons were performed among all models with Mc Nemar’s test. Results Cochran's Q test indicated a statistically significant difference in classification performance across all models ( p  
ISSN:1861-6410
1861-6429
DOI:10.1007/s11548-021-02321-4