Evaluation of the Effectiveness of Artificial Intelligence in Determining the Accurate Working Length of Curved Root Canals in Endodontic Treatment
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 发起方
- 入组人数
- 200
- 主要终点
- Sensitivity of AI Model in Detecting Curved Root Canal Length
研究概览
简要总结
This study tests whether artificial intelligence (AI) can accurately measure the length of curved root canals from dental x-rays. Curved root canals are hard to measure correctly, and wrong measurements can lower the success of root canal treatment.
Adults over 18 years old who need root canal treatment can take part. Researchers will use x-rays taken during the patient's normal treatment. No extra x-rays, procedures, or visits are needed. An AI program will be trained to measure canal length automatically, and its measurements will be compared to measurements made by a human expert.
The results may show whether AI can measure root canal length faster and more consistently, which could help dentists plan treatment more accurately in the future.
详细描述
Working length determination is a critical step in root canal treatment, and inaccurate measurement can lead to under- or over-instrumentation, post-operative pain, and reduced treatment success. This is particularly challenging in curved root canals, where the apical foramen often deviates from the anatomical or radiographic apex, and where small endodontic files are difficult to visualize on periapical radiographs. Conventional methods for working length determination, including tactile sensation, electronic apex locators, and radiographic interpretation, are subject to observer variability and technical limitations, especially as canal curvature increases.
Recent advances in artificial intelligence, particularly deep learning-based image analysis, have shown promise in improving the objectivity and consistency of measurements derived from dental radiographs. This study aims to develop and evaluate deep learning models (including convolutional neural network architectures such as GoogleNet Inception V3, U-Net, Mask R-CNN, and YOLO-based networks) for the automatic detection and measurement of curved root canal length on periapical radiographs, and to compare the performance of these models with measurements made by a human observer.
Periapical radiographs will be obtained using the paralleling technique during the working length confirmation stage of routine root canal treatment, as part of the patient's standard clinical care. No additional radiographic exposure, procedure, or clinical visit will be performed solely for research purposes. Radiographic images will be anonymized and labeled using canal length segmentation, with pixel-based measurements calibrated to millimeters based on DICOM metadata.
The dataset will be divided into training, validation, and test subsets. Model performance will be evaluated using standard classification and segmentation metrics, including sensitivity, precision, F1 score, Intersection over Union (IoU), and Receiver Operating Characteristic (ROC) curve analysis with area under the curve (AUC).
研究设计
- 研究类型
- Observational
- 观察模型
- Other
- 时间视角
- Cross Sectional
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Eligibility Criteria
- •Age 18 years or older
- •Presenting for routine root canal treatment at Alanya Alaaddin Keykubat University Faculty of Dentistry
- •Radiographically identified curved root canal(s)
- •Periapical radiograph obtained using the paralleling technique during working length confirmation
- •Willing and able to provide informed consent
排除标准
- •Age under 18 years
- •Root canals without curvature
- •Periapical radiographs of insufficient diagnostic quality (e.g., distortion, poor image quality preventing accurate canal length assessment)
- •Unwillingness to provide informed consent
结局指标
主要结局
Sensitivity of AI Model in Detecting Curved Root Canal Length
时间窗: Measured once, at the time of model testing following completion of radiograph collection (estimated 12 months from study initiation)
Agreement between the AI-predicted root canal length and the length determined by a human observer on periapical radiographs, assessed by sensitivity, calculated as TP/(TP+FN), where TP (true positive) represents the overlapping region between the ground truth and predicted segmentation, and FN (false negative) represents the region present in the ground truth but not in the prediction.
Precision of AI Model in Detecting Curved Root Canal Length
时间窗: Measured once, at the time of model testing following completion of radiograph collection (estimated 12 months from study initiation)
Agreement between the AI-predicted root canal length and the length determined by a human observer on periapical radiographs, assessed by precision, calculated as TP/(TP+FP), where FP (false positive) represents the region present in the prediction but not in the ground truth.
F1 Score of AI Model in Detecting Curved Root Canal Length
时间窗: Measured once, at the time of model testing following completion of radiograph collection (estimated 12 months from study initiation)
F1 score of the AI-predicted root canal segmentation compared to ground truth on periapical radiographs, calculated as 2TP/(2TP+FP+FN), representing the harmonic mean of precision and sensitivity and interpreting the overlap between the ground truth and predicted pixels.
Intersection over Union (IoU) of AI Model in Detecting Curved Root Canal Length
时间窗: Measured once, at the time of model testing following completion of radiograph collection (estimated 12 months from study initiation)
Intersection over Union between the AI-predicted root canal segmentation and the ground truth segmentation on periapical radiographs, calculated as TP/(TP+FN+FP), representing the overlapping area between the predicted result and the ground truth segmentation area.
次要结局
未报告次要终点
研究者
Hatice BÜYÜKÖZER ÖZKAN
Associate Professor
Alanya Alaaddin Keykubat University