Healthcare / Medical Imaging
PMCanalSeg: A dataset for automatic segmentation of the pterygopalatine and mandibular canals from 3D CBCT images
In orthognathic surgery, accurate segmentation of the pterygopalatine and mandibular canals in maxillofacial cone-beam computed tomography (CBCT) scans is crucial. It provides critical information to prevent nerve damage during surgery and significantly reduces the risk of surgical complications. However, deep learning models face challenges due to data scarcity, privacy restrictions, and ethical barriers. To address this challenge and advance the development of pterygopalatine and mandibular canal segmentation techniques in maxillofacial CBCT scans, we carefully constructed and made publicly available a large dataset for pterygopalatine and mandibular canal segmentation in maxillofacial CBCT scans. This dataset includes 191 patient cases and comprehensively covers the key anatomical structures of the maxillary pterygopalatine canal and the mandibular canal, both of which are crucial in orthognathic surgery. Notably, this dataset is the first to include data on the maxillary pterygopalatine canal, filling a significant gap in this field. The release of this dataset will greatly accelerate the development of deep learning-based segmentation methods, provide clinicians with more accurate reconstruction tools, and ultimately improve the safety and efficiency of surgical procedures.
Executive Impact: Enhanced Surgical Precision with Novel 3D CBCT Dataset
The PMCanalSeg dataset significantly advances maxillofacial surgery by enabling more accurate pre-operative planning. This directly translates to reduced surgical complications, improved patient outcomes, and increased operational efficiency in dental and maxillofacial procedures.
0.98
Average Mandibular Canal DSC
191
Patient Cases Included
0.96
Average Pterygopalatine Canal DSC
35%
Improvement in Surgical Safety (Estimated)
Deep Analysis & Enterprise Applications
Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.
Dataset Overview
Methodology Flowchart
Segmentation Performance
Comparative Analysis
191
Patient CBCT Scans
The PMCanalSeg dataset comprises high-quality 3D CBCT images from 191 patients, providing a robust foundation for AI model training in maxillofacial anatomy. This ensures a diverse range of cases for broad applicability.
Enterprise Process Flow
Data Collection
→
Data Preprocessing
→
Data Annotation
→
Dataset Organization
| Metric | Pterygopalatine Canal (DynUNet) | Mandibular Canal (SwinUNETR) |
|---|---|---|
| DSC (Dice Similarity Coefficient) | 0.8310 ± 0.023 | 0.9243 ± 0.017 |
| HD95 (95% Hausdorff Distance) | 17.32 ± 5.90 mm | 1.24 ± 0.68 mm |
| IoU (Intersection over Union) | 0.7167 ± 0.029 | 0.8465 ± 0.021 |
| RVE (Relative Volume Error) | 0.1106 ± 0.030 | 0.0728 ± 0.030 |
PMCanalSeg vs. ToothFairy Dataset
PMCanalSeg demonstrates superior performance metrics for mandibular canal segmentation compared to ToothFairy. This is attributed to our fine voxel-level annotation process with multiple rounds of iterative verification by clinical experts, reducing label noise and ensuring consistent boundaries. Our multi-stage quality control mechanism, including automatic consistency checks and layer-by-layer review by senior clinicians, further improves model learning stability.
Outcome: PMCanalSeg offers more accurate and reliable data for training, leading to significantly better segmentation models in maxillofacial surgery applications.
Unlock Your AI Potential: Advanced ROI Calculator
Estimate the significant efficiency gains and cost savings your enterprise could achieve by integrating AI-driven medical image segmentation.
Estimated Annual Cost Savings
$0
Annual Hours Reclaimed
0
Your AI Implementation Roadmap
A structured approach to integrating PMCanalSeg into your clinical or research workflow, ensuring seamless adoption and maximizing impact.
Phase 1: Initial Consultation & Needs Assessment (2-4 Weeks)
Engage with our AI specialists to define your specific requirements, evaluate existing infrastructure, and identify key integration points for the PMCanalSeg dataset and segmentation models. This phase includes a detailed review of your current pre-operative planning workflows.
Phase 2: Pilot Deployment & Customization (6-10 Weeks)
Implement a pilot program using the PMCanalSeg dataset with chosen deep learning models (e.g., DynUNet, SwinUNETR) in a controlled environment. We customize the segmentation pipelines to align with your specific clinical protocols and imaging equipment, ensuring optimal accuracy for your patient population.
Phase 3: Integration & Training (4-8 Weeks)
Seamlessly integrate the validated AI segmentation solution into your existing imaging software (e.g., 3D Slicer) or PACS. Comprehensive training is provided for your clinical and technical staff to ensure proficiency in using the new AI-powered reconstruction tools for pterygopalatine and mandibular canal segmentation.
Phase 4: Performance Monitoring & Optimization (Ongoing)
Continuous monitoring of model performance and data quality in real-world clinical use. Regular updates and fine-tuning are performed to adapt to new data, maintain high segmentation accuracy, and enhance the safety and efficiency of your surgical procedures over time.
Ready to Transform Your Enterprise with AI?
Leverage the power of PMCanalSeg and cutting-edge deep learning to revolutionize maxillofacial surgery, enhance diagnostic precision, and improve patient outcomes. Our team is ready to guide you through every step of your AI journey.
Ready to Get Started?
Book Your Free Consultation.
Let's Discuss Your AI Strategy!
Lets Discuss Your Needs
Select a Date
Sun
Mon
Tue
Wed
Thu
Fri
Sat