Deep Learning-Based Automatic Segmentation of Mandible and Maxilla in Multi-Center CT Images

Abstract

Sophisticated segmentation of the craniomaxillofacial bones (the mandible and maxilla) in computed tomography (CT) is essential for diagnosis and treatment planning for craniomaxillofacial surgeries. Conventional manual segmentation is time-consuming and challenging due to intrinsic properties of craniomaxillofacial bones and head CT such as the variance in the anatomical structures, low contrast of soft tissue, and artifacts caused by metal implants. However, data-driven segmentation methods, including deep learning, require a large consistent dataset, which creates a bottleneck in their clinical applications due to limited datasets. In this study, we propose a deep learning approach for the automatic segmentation of the mandible and maxilla in CT images and enhanced the compatibility for multi-center datasets. Four multi-center datasets acquired by various conditions were applied to create a scenario where the model was trained with one dataset and evaluated with the other datasets. For the neural network, we designed a hierarchical, parallel and multi-scale residual block to the U-Net (HPMR-U-Net). To evaluate the performance, segmentation with in-house dataset and with external datasets from multi-center were conducted in comparison to three other neural networks: U-Net, Res-U-Net and mU-Net. The results suggest that the segmentation performance of HPMR-U-Net is comparable to that of other models, with superior data compatibility.

Diagnostic performance of artificial intelligence using cone-beam computed tomography imaging of the oral and maxillofacial region: A scoping review and meta-analysis

“… 29 31 32 Some studies have used deep learning and machine learning techniques to diagnose and classify temporomandibular joint diseases, perform maxillary and mandible segmentation, and guide oral and maxillofacial surgeons with acceptable diagnostic accuracy. 28 33 34 In the orthodontics field, some studies have proposed deep learning frameworks for cluster-based segmentation and automatic landmark detection in cephalometric analysis. 35 36 …”

RenseNet: A Deep Learning Network Incorporating Residual and Dense Blocks with Edge Conservative Module to Improve Small-Lesion Classification and Model Interpretation

“…The success of deep learning (DL) in computer vision has led to the increased application of artificial intelligence (AI) in medical image analysis [1,2]. DL-based AI models have been applied to clinical vision applications, such as lesion detection, classification, and segmentation, thereby outperforming conventional machine learning models [3][4][5][6]. Moreover, explainable AI (XAI) allows users to interpret and trust the results predicted by the AI model [7].…”

Impact of localized fine tuning in the performance of segmentation and classification of lung nodules from computed tomography scans using deep learning

“…It may halt the possible implementation of the general model into routine clinical care if it does not have a consistent accuracy for site-specific use. To obtain a comparable external test performance to the internal tests, reported studies involving training datasets from multicenter to develop the detection algorithm demonstrated that it can either underperform ( 10 – 12 ) or have a comparable performance to the internal test ( 11 , 13 ) without any unanimous conclusion reached, which may be explained by the differences of the datasets scale and the numbers of dataset origins ( 14 ). Using local images for model training seems to be another way to obtain a site-specific used tool for diagnosis.…”