|
Current issue
Archive
Manuscripts accepted
About the journal
Editorial board
Reviewers
Abstracting and indexing
Subscription
Contact
Instructions for authors
Ethical standards and procedures
Editorial System
Submit your Manuscript
 
|
3/2024
vol. 77 abstract:
Original paper
Evaluation of effectiveness of a virtual AI-based dental assistant in recognizing mixed dentition on panoramic radiographs
Karolina Futyma-Gąbka
1
,
Magdalena Piskórz
1
,
Kamila Smala
2
,
Weronika Miazek
2
,
Maria Moskwa
2
,
Ingrid Różyło-Kalinowska
1
J Stoma 2024; 77, 3: 181-185
Online publish date: 2024/09/29
View
full text
Get citation
ENW EndNote
BIB JabRef, Mendeley
RIS Papers, Reference Manager, RefWorks, Zotero
AMA
APA
Chicago
Harvard
MLA
Vancouver
Introduction
Diagnocat Inc. software is an artificial intelligence (AI) program known as a virtual dental assistant that can be used to evaluate the anatomy of teeth using both 2D and 3D imaging. This tool intends to increase the effectiveness of diagnosis and treatment planning, while improving the efficiency of a doctor’s diagnosis. Objectives The objective of this study was to analyze panoramic radiographs of patients with mixed dentition using Diagnocat Inc. software, and to compare the results by a dentist. Material and methods Seventy-eight panoramic radiographs of patients with mixed dentition were evaluated for tooth numbering using Viohl system with Diagnocat Inc. software. Results were analyzed and compared by dentists. Descriptive statistics methods were employed. Results Diagnocat Inc. software correctly identified deciduous and permanent teeth in 58 patients (74.35%). In 20 cases (25.64%), the software incorrectly determined the order of teeth, doubled their number, or failed completely to identify them. The most significant issues occurred in cases involving deciduous teeth with advanced resorption. There were notably more errors in the assessment of anterior teeth compared with posterior region. However, AI was 100% effective in identifying the presence of third molars, even at very early stages of mineralization according to Demirjian’s classification. Conclusions The virtual dental assistant software demonstrates significant potential in identifying teeth in patients with mixed dentition. However, due to the lack of 100% accuracy in the assessment, it requires supervision of a dentist. The AI software’s effectiveness of nearly 75% in identifying teeth can be a useful aid for dentists in more effective analysis of radiographic images. keywords:
panoramic radiograph, mixed dentition, artificial intelligence |
