Periapical Lesions in Panoramic Radiography and CBCT Imaging—Assessment of AI’s Diagnostic Accuracy

Kazimierczak, Wojciech; Wajer, Róża; Wajer, Adrian; Kiian, Veronica; Kloska, Anna; Kazimierczak, Natalia; Janiszewska-Olszowska, Joanna; Serafin, Zbigniew

doi:10.3390/jcm13092709

Cited by 4 publications

(1 citation statement)

References 65 publications

(92 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Orhan et al (2020) reported that AI systems could effectively identify PLs in cone-beam computed tomography (CBCT) scans, highlighting the potential for AI to support clinical decision-making in endodontics [ 18 ]. Similar results were shown in our 2024 study on the diagnostic accuracy of Diagnocat for PL detection in the PAN and CBCT images of one patient cohort [ 19 ]. The sensitivity of the AI for PL detection via PAN was 33.33%, with significantly higher metrics for CBCT (77.78%).…”

Section: Discussionsupporting

confidence: 87%

Evaluating the Diagnostic Accuracy of an AI-Driven Platform for Assessing Endodontic Treatment Outcomes Using Panoramic Radiographs: A Preliminary Study

Kazimierczak,

Wajer,

Wajer

et al. 2024

JCM

Self Cite

View full text Add to dashboard Cite

Background/Objectives: The purpose of this preliminary study was to evaluate the diagnostic performance of an AI-driven platform, Diagnocat (Diagnocat Ltd., San Francisco, CA, USA), for assessing endodontic treatment outcomes using panoramic radiographs (PANs). Materials and Methods: The study included 55 PAN images of 55 patients (15 males and 40 females, aged 12–70) who underwent imaging at a private dental center. All images were acquired using a Hyperion X9 PRO digital cephalometer and were evaluated using Diagnocat, a cloud-based AI platform. The AI system assessed the following endodontic treatment features: filling probability, obturation adequacy, density, overfilling, voids in filling, and short filling. Two human observers independently evaluated the images, and their consensus served as the reference standard. The diagnostic accuracy metrics were calculated. Results: The AI system demonstrated high accuracy (90.72%) and a strong F1 score (95.12%) in detecting the probability of endodontic filling. However, the system showed variable performance in other categories, with lower accuracy metrics and unacceptable F1 scores for short filling and voids in filling assessments (8.33% and 14.29%, respectively). The accuracy for detecting adequate obturation and density was 55.81% and 62.79%, respectively. Conclusions: The AI-based system showed very high accuracy in identifying endodontically treated teeth but exhibited variable diagnostic accuracy for other qualitative features of endodontic treatment.

show abstract

Section: Discussionsupporting

confidence: 87%

Evaluating the Diagnostic Accuracy of an AI-Driven Platform for Assessing Endodontic Treatment Outcomes Using Panoramic Radiographs: A Preliminary Study

Kazimierczak,

Wajer,

Wajer

et al. 2024

JCM

Self Cite

View full text Add to dashboard Cite

show abstract

Endodontic Treatment Outcomes in Cone Beam Computed Tomography Images—Assessment of the Diagnostic Accuracy of AI

Kazimierczak,

Issa

et al. 2024

JCM

View full text Add to dashboard Cite

Background/Objectives: The aim of this study was to assess the diagnostic accuracy of the AI-driven platform Diagnocat for evaluating endodontic treatment outcomes using cone beam computed tomography (CBCT) images. Methods: A total of 55 consecutive patients (15 males and 40 females, aged 12–70 years) referred for CBCT imaging were included. CBCT images were analyzed using Diagnocat’s AI platform, which assessed parameters such as the probability of filling, adequate obturation, adequate density, overfilling, voids in filling, short filling, and root canal number. The images were also evaluated by two experienced human readers. Diagnostic accuracy metrics (accuracy, precision, recall, and F1 score) were assessed and compared to the readers’ consensus, which served as the reference standard. Results: The AI platform demonstrated high diagnostic accuracy for most parameters, with perfect scores for the probability of filling (accuracy, precision, recall, F1 = 100%). Adequate obturation showed moderate performance (accuracy = 84.1%, precision = 66.7%, recall = 92.3%, and F1 = 77.4%). Adequate density (accuracy = 95.5%, precision, recall, and F1 = 97.2%), overfilling (accuracy = 95.5%, precision = 86.7%, recall = 100%, and F1 = 92.9%), and short fillings (accuracy = 95.5%, precision = 100%, recall = 86.7%, and F1 = 92.9%) also exhibited strong performance. The performance of AI for voids in filling detection (accuracy = 88.6%, precision = 88.9%, recall = 66.7%, and F1 = 76.2%) highlighted areas for improvement. Conclusions: The AI platform Diagnocat showed high diagnostic accuracy in evaluating endodontic treatment outcomes using CBCT images, indicating its potential as a valuable tool in dental radiology.

show abstract

An Overview of Cone-Beam Computed Tomography and Dental Panoramic Radiography in Dentistry in the Community

MacDonald,

Telyakova

2024

Tomography

View full text Add to dashboard Cite

This study reviews the two most important and frequently used systems of tomography used in dentistry today. These are the dental panoramic radiograph (DPR) and cone-beam computed tomography (CBCT). The importance of the DPR has been accentuated by the recent COVID-19 pandemic, as it does not produce an aerosol. Its clinical importance is derived from its panoramic display of the jaws and associated structures and should be examined for incidental findings that may portend a potentially serious outcome. An important recent spin-off of the DPR is the extra-oral bitewing, which can replace its traditional, uncomfortable and aerosol-generating intra-oral counterpart. Although much has been written about them, this paper reviews their essential attributes and limitations in clinical dentistry. Although attempts have been made to reproduce some of the attributes of CT in CBCT such as Hounsfield Units (HU) and improve the contrast resolution of the soft tissues, these remain elusive. Nevertheless, CBCT’s dataset should be appropriately reconstructed to fully display the clinical feature prompting its prescription. In certain cases, more than one mode of reconstruction is required.

show abstract

Periapical Lesions in Panoramic Radiography and CBCT Imaging—Assessment of AI’s Diagnostic Accuracy

Cited by 4 publications

References 65 publications

Evaluating the Diagnostic Accuracy of an AI-Driven Platform for Assessing Endodontic Treatment Outcomes Using Panoramic Radiographs: A Preliminary Study

Evaluating the Diagnostic Accuracy of an AI-Driven Platform for Assessing Endodontic Treatment Outcomes Using Panoramic Radiographs: A Preliminary Study

Endodontic Treatment Outcomes in Cone Beam Computed Tomography Images—Assessment of the Diagnostic Accuracy of AI

An Overview of Cone-Beam Computed Tomography and Dental Panoramic Radiography in Dentistry in the Community

Contact Info

Product

Resources

About