Image-based Mandibular and Maxillary Parcellation and Annotation using Computer Tomography (IMPACT): A Deep Learning-based Clinical Tool for Orodental Dose Estimation and Osteoradionecrosis Assessment
OPC-SURVIVOR Program and MD Anderson Head and Neck Cancer Symptom Working Group, ; Humbert-Vidan, L.; Castelo, A. H.; He, R.; van Dijk, L. V.; Rhee, D. J.; Wang, C.; Wang, H. C.; Wahid, K. A.; Joshi, S.; Gerafian, P.; West, N.; Kaffey, Z.; Mirbahaeddin, S.; Curiel, J.; Acharya, S.; Shekha, A.; Oderinde, P.; Ali, A. M. S.; Hope, A.; Watson, E.; Wesson-Aponte, R.; Frank, S. J.; Barbon, C. E. A.; Brock, K. K.; Chambers, M. S.; Walji, M.; Hutcheson, K. A.; Lai, S. Y.; Fuller, C. D.; Naser, M. A.; Moreno, A. C.
Show abstract
BackgroundAccurate delineation of orodental structures on radiotherapy CT images is essential for dosimetric assessments and dental decisions. We propose a deep-learning auto-segmentation framework for individual teeth and mandible/maxilla sub-volumes aligned with the ClinRad ORN staging system. MethodsMandible and maxilla sub-volumes were manually defined, differentiating between alveolar and basal regions, and teeth were labelled individually. For each task, a DL segmentation model was independently trained. A Swin UNETR-based model was used for the mandible sub-volumes. For the smaller structures (e.g., teeth and maxilla sub-volumes) a two-stage segmentation model first used the ResUNet to segment the entire teeth and maxilla regions as a single ROI that was then used to crop the image input of the Swin UNETR. In addition to segmentation accuracy and geometric precision, a dosimetric comparison was made between manual and model-predicted segmentations. ResultsSegmentation performance varied across sub-volumes - mean Dice values of 0.85 (mandible basal), 0.82 (mandible alveolar), 0.78 (maxilla alveolar), 0.80 (upper central teeth), 0.69 (upper premolars), 0.76 (upper molars), 0.76 (lower central teeth), 0.70 (lower premolars), 0.71 (lower molars) - and exhibited limited applicability in segmenting teeth and sub-volumes often absent in the data. Only the maxilla alveolar central sub-volume showed a statistically significant dosimetric difference (Bonferroni-adjusted p-value = 0.02). ConclusionWe present a novel DL-based auto-segmentation framework of orodental structures, enabling spatial localization of dose-related differences in the jaw. This tool enhances image-based bone injury detection, including ORN, and improves clinical decision-making in radiation oncology and dental care for head and neck cancer patients.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Comprehensive Quantitative Evaluation of Inter-observer Delineation Performance of MR-guided Delineation of Oropharyngeal Gross Tumor Volumes and High-risk Clinical Target Therapy: An R-IDEAL Stage 0 Prospective Study 96%
- Cluster-Based Toxicity Estimation of Osteoradionecrosis via Unsupervised Machine Learning: Moving Beyond Single Dose-Parameter Normal Tissue Complication Probability by Using Whole Dose-Volume Histograms for Cohort Risk Stratification 95%
- Normal Tissue Complication Probability (NTCP) prediction model for osteoradionecrosis of the mandible in head and neck cancer patients following radiotherapy: Large-scale observational cohort 95%
Similar papers in this journal
- Evaluation of indirect damage and damage saturation effects in dose-response curves of hypofractionated radiotherapy of early-stage NSCLC and brain metastases 95%
- LITE SABR M1: a Phase I Trial of Lattice Stereotactic Body Radiotherapy for Large Tumors 94%
- Artificial Intelligence Uncertainty Quantification in Radiotherapy Applications - A Scoping Review 94%
Similar papers in this journal
- Morphological changes after cranial fractionated photon radiotherapy: localized loss of white matter and grey matter volume with increasing dose 94%
- Auto-Detection and Segmentation of Involved Lymph Nodes in HPV-Associated Oropharyngeal Cancer Using a Convolutional Deep Learning Neural Network 94%
- Development of a High-Performance Multiparametric MRI Oropharyngeal Primary Tumor Auto-Segmentation Deep Learning Model and Investigation of Input Channel Effects: Results from a Prospective Imaging Registry 93%
Similar papers in this journal
- Quality Assurance Assessment of Intra-Acquisition Diffusion-Weighted and T2-Weighted Magnetic Resonance Imaging Registration and Contour Propagation for Head and Neck Cancer Radiotherapy 97%
- Cell lines of the same anatomic site and histologic type show large variability in intrinsic radiosensitivity and relative biological effectiveness to protons and carbon ions 94%
- Evaluation of inverse treatment planning for Gamma Knife radiosurgery using fMRI brain activation maps as organs at risk 94%
Similar papers in this journal
- Large language models to help appeal denied radiotherapy services 94%
- Histology-based Prediction of Therapy Response to Neoadjuvant Chemotherapy for Esophageal and Esophagogastric Junction Adenocarcinomas Using Deep Learning 89%
- Imaging-Genomics Study Of Head-Neck Squamous Cell Carcinoma: Associations Between Radiomic Phenotypes And Genomic Mechanisms Via Integration Of TCGA And TCIA 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.