Diagnostic Performance of Cone-Beam Computed Tomography to Diagnose in Vivo/in Vitro Root Resorption: A Systematic Review and Meta-Analysis

Iglesia, T. Baena-de la; Yáñez-Vico, Rosa-María; Iglesias-Linares, Alejandro

doi:10.1016/j.jebdp.2022.101803

Cited by 6 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These ndings suggest that our proposed approaches are effective in improving the accuracy of the classi cation task. The diagnostic performance of clinicians in detecting external root resorption in CBCT images ranges from a sensitivity of 42-98% and a speci city of 49.3-96.3% (23). Our outcomes showed that the performance of the hierarchical deep learning approaches was comparable to the range of performances reported for clinicians in regard to the diagnosis of external root resorption in CBCT images.…”

Section: Discussionsupporting

confidence: 54%

A Data-Efficient Hierarchical Deep Learning Approach for Diagnosing Impacted Canine-Induced Root Resorption via Cone-beam Computed Tomography

Pirayesh,

Mohammad-Rahimi,

Motamedian

et al. 2024

Preprint

View full text Add to dashboard Cite

Objectives: Impacted canines can cause canine-induced root resorption (CIRR), potentially leading to root resorption and even incisor loss. The aim of this study was to usedeep learning to automatically evaluate the diagnosis of CIRR in maxillary incisors more accurately using CBCT images. Methods: A total of 50 CBCT images and 176 incisors were selected for the present study. The maxillary incisors were manually segmented from the CBCT images and labeled by two independent radiologists as either healthy or having root resorption induced by the impacted canines. We used five different strategies for training the model: A) classification using 3D ResNet50 (Baseline), B) classification of the segmented masks using the outcome of a 3D U-Net pretrained on the 3D MNIST, C) training a 3D U-Net for the segmentation task and use its outputs for classification, D) pretraining a 3D U-Net for the segmentation and transfer of the model, and E) pretraining a 3D U-Net for the segmentation and fine-tuning the model with only the model encoder. The segmentation models were evaluated using the mean intersection over union (mIoU) and Dice coefficient. The classification models were evaluated in terms of classification accuracy, precision, recall, and F1 score. Results: The segmentation model achieved a mean intersection over union (mIoU) of 0.641 and a Dice coefficient of 0.901, indicating good performance in segmenting the tooth structures from the CBCT images. For the main classification task of detecting canine-induced root resorption (CIRR), Model C (classification of the segmented masks using 3D ResNet) and Model E (pretraining on segmentation followed by fine-tuning for classification) performed the best, both achieving 82% classification accuracy and 0.62 F1-scores on the test set. These results demonstrate the effectiveness of the proposed hierarchical, data-efficient deep learning approaches in improving the accuracy of automated CIRR diagnosis from limited CBCT data compared to the 3D ResNet baseline model. Conclusion: The proposed approaches are effective at improving the accuracy of classification tasks and are helpful when the diagnosis is based on the volume and boundaries of an object. The study demonstrated that the proposed approaches improve the accuracy of medical image classification tasks.

show abstract

Section: Discussionsupporting

confidence: 54%

A Data-Efficient Hierarchical Deep Learning Approach for Diagnosing Impacted Canine-Induced Root Resorption via Cone-beam Computed Tomography

Pirayesh,

Mohammad-Rahimi,

Motamedian

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Baena de la Iglesia T, 2023 [25] Revisión sistemática Cráter en la raíz: cambios en volumen, área, pérdida mineral total o parcial. describen como tratamiento una variedad de opciones que van desde el control hasta la exodoncia [11].…”

Section: Autor Y Año Tipo De Estudio Características Radiográficas Co...unclassified

“…Yi [37], sugiere que esta herramienta tiene mayor eficacia diagnóstica que la radiografía periapical [20,22,26]. El estudio más reciente concluye que el uso de la tomografía computarizada de haz cónico tiene una sensibilidad de 60,8% y una especificidad de 60% [25].…”

Section: Tomografía Computarizada De Haz Cónico Versus Radiografía Co...unclassified

Clinical and radiographic characterization of external root resorption

Buchi-Velazquez,

Escobar-Torres,

Veloso

et al. 2024

Medwave

View full text Add to dashboard Cite

Introduction The following bibliographic review was carried out with the purpose of recognizing the clinical and radiographic characteristics that must be considered in the diagnosis of external root resorption, including treatments. Methods A bibliographic search was carried out in PubMed/Medline, Cochrane Library and Google Scholar databases under the term "external root resorption", from 2010 to 2022 in Spanish and English. Experimental studies and bibliographic reviews were selected, and finally 17 articles were included. Results The results obtained indicated that each type of resorption presents specific clinical characteristics that differentiate them, these are: for external inflammatory resorption a negative pulp vitality; for replacement external resorption the absence of mobility and metallic percussion; for cervical external resorption a pink coloration of the crown; superficial external resorption does not present any type of clinical symptoms and transient apical collapse presents a transient change in color. Conclusion External root resorptions require accurate and early diagnosis. A clinical examination should be performed with emphasis on the following: probing, coloration, mobility, and vitality tests.

show abstract

“…(4) Core algorithm: describe the calculation formula and specific calculation steps used in the core algorithm. (5) The process logic, in the form of the process flow diagram, shows the logical flow of the realization program. (6) Operating environment: specify the hardware configuration, software environment and network conditions required for software operation, including hardware configuration (including processor, memory and peripheral devices), software environment (including system software, support software and security software), and network conditions (including network architecture, network type (WAN, LAN, personal domain network) and bandwidth).…”

Section: Software System Detailed Design and Evaluationmentioning

confidence: 99%

“…In vitro diagnostics can be divided into biochemical diagnostics, immunodiagnostics, molecular diagnostics, microbiological diagnostics, blood diagnostics, point of care testing (POCT), etc. [5,6]. The related technologies involved include electrochemical technology, spectroscopic technology, chromatographic technology, mass spectrometry, electrophoresis, flow cytometry, labeled immunology, molecular biology, biosensing technology, etc.…”

Section: Introductionmentioning

confidence: 99%

Methods and Advances in the Design, Testing and Development of In Vitro Diagnostic Instruments

Wang

et al. 2023

Processes

View full text Add to dashboard Cite

With the continuous improvement of medical testing and instrumentation engineering technologies, the design, testing and development methods of in vitro diagnostic instruments are developing rapidly. In vitro diagnostic instruments are also gradually developing into a class of typical high-end medical equipment. The design of in vitro diagnostic instruments involves a variety of medical diagnostic methods and biochemical, physical and other related technologies, and its development process involves complex system engineering. This paper systematically organizes and summarizes the design, testing and development methods of in vitro diagnostic instruments and their development in recent years, focusing on summarizing the related technologies and core aspects of the R&D process, and analyzes the development trend of the in vitro diagnostic instrument market.

show abstract

Diagnostic Performance of Cone-Beam Computed Tomography to Diagnose in Vivo/in Vitro Root Resorption: A Systematic Review and Meta-Analysis

Cited by 6 publications

References 41 publications

A Data-Efficient Hierarchical Deep Learning Approach for Diagnosing Impacted Canine-Induced Root Resorption via Cone-beam Computed Tomography

A Data-Efficient Hierarchical Deep Learning Approach for Diagnosing Impacted Canine-Induced Root Resorption via Cone-beam Computed Tomography

Clinical and radiographic characterization of external root resorption

Methods and Advances in the Design, Testing and Development of In Vitro Diagnostic Instruments

Contact Info

Product

Resources

About