Clinical Research Directory
Browse clinical research sites, groups, and studies.
Artificial Intelligence-Guided Versus Manual CBCT Planning for Immediate Implant Placement
Sponsor: Shalash Dental education
Summary
This study evaluates whether artificial intelligence (AI)-based analysis of cone-beam computed tomography (CBCT) scans can support clinical decision-making for immediate dental implant placement in molar extraction sites. When a molar tooth is removed, placing a dental implant immediately may reduce treatment time and preserve surrounding bone. However, immediate implant placement is not always possible and depends on the anatomy of the extraction socket, particularly the interradicular septum (the bone between the roots). CBCT imaging is routinely used to assess this anatomy before surgery. Traditionally, radiologists manually evaluate these scans. Recently, AI-based tools have been developed to automatically analyze CBCT images. In this randomized controlled trial, patients requiring molar extraction and potential immediate implant placement will be assigned to one of two planning approaches: AI-guided CBCT assessment or conventional manual CBCT assessment. The operating surgeon will use the assigned planning report to guide treatment decisions. The primary outcome of the study is the feasibility of immediate implant placement, defined as successful implant placement with achievement of primary stability during surgery. Secondary outcomes include surgical time, need for changes to the treatment plan, and implant stability measurements. The goal of this study is to determine whether AI-assisted CBCT analysis performs similarly to, or improves upon, conventional manual radiologic assessment in supporting safe and effective immediate implant placement.
Official title: Artificial Intelligence-Guided Versus Manual CBCT Planning for Immediate Implant Placement in Molar Extraction Sites: A Randomized Controlled Trial
Key Details
Gender
All
Age Range
18 Years - 99 Years
Study Type
INTERVENTIONAL
Enrollment
80
Start Date
2026-03-03
Completion Date
2026-05-02
Last Updated
2026-03-09
Healthy Volunteers
Yes
Interventions
AI assisted CBCt
The intervention consists of a fully automated, deep learning-based CBCT analysis pipeline designed for extraction socket segmentation and quantitative interradicular septum assessment. The AI system utilizes a pre-trained convolutional neural network architecture to perform voxel-level segmentation of the extraction socket and surrounding alveolar structures on CBCT datasets. Following segmentation, the model automatically quantifies predefined anatomical parameters, including interradicular septum width at standardized reference levels and socket morphology classification. These measurements are generated using algorithmically defined geometric landmarks, ensuring consistent spatial reference across cases. Feasibility for immediate implant placement is determined using a prespecified, protocol-defined decision rule applied to AI-derived quantitative parameters.
Manual CBCT segmentation
The control intervention consists of conventional radiologic evaluation of CBCT datasets using manual segmentation and operator-driven anatomical assessment. CBCT scans will be reviewed by an experienced oral and maxillofacial radiologist using standard imaging software. Interradicular septum dimensions will be determined through manual identification of anatomical landmarks and measurement using software-based calipers at predefined reference levels. Socket morphology classification will be assigned based on visual interpretation and application of the same predefined anatomical criteria specified in the study protocol. Feasibility for immediate implant placement will be determined by applying the protocol-defined decision thresholds to manually obtained measurements. All measurements and classifications will be documented in a structured planning report provided to the operating surgeon. Unlike the AI-guided intervention, this workflow relies on manual landmark identification and ope
Locations (1)
Shalash Implant education
Cairo, Egypt