Segmentation of Mental Foramen in Orthopantomographs: A Deep Learning Approach
Haider Raza, Mohsin Ali, Vishal Krishna Singh, Agustin Wahjuningrum, Rachel Sarig, Akhilanand Chaurasia
TL;DR
The study targets automatic segmentation of the mental foramen (MF) on 2D orthopantomographs (OPGs) using deep learning. It introduces a novel dual-ground-truth approach by employing both round- and square-shaped MF masks and evaluates nine segmentation architectures, with U-Net variants achieving the best performance. The dataset comprises 702 curated OPGs (from an initial 1000) and is assessed using 5-fold cross-validation and standard metrics such as Dice Similarity Coefficient and IoU; on the test set, U-Net yields DSCs of about 0.79 for round masks and 0.80 for square masks, with IoUs of about 0.68 and 0.77 respectively, while square masks show higher IoU. The findings demonstrate robust MF localization, suggesting practical value for accelerating dental procedures and improving patient outcomes through automated MF delineation.
Abstract
Precise identification and detection of the Mental Foramen are crucial in dentistry, impacting procedures such as impacted tooth removal, cyst surgeries, and implants. Accurately identifying this anatomical feature facilitates post-surgery issues and improves patient outcomes. Moreover, this study aims to accelerate dental procedures, elevating patient care and healthcare efficiency in dentistry. This research used Deep Learning methods to accurately detect and segment the Mental Foramen from panoramic radiograph images. Two mask types, circular and square, were used during model training. Multiple segmentation models were employed to identify and segment the Mental Foramen, and their effectiveness was evaluated using diverse metrics. An in-house dataset comprising 1000 panoramic radiographs was created for this study. Our experiments demonstrated that the Classical UNet model performed exceptionally well on the test data, achieving a Dice Coefficient of 0.79 and an Intersection over Union (IoU) of 0.67. Moreover, ResUNet++ and UNet Attention models showed competitive performance, with Dice scores of 0.675 and 0.676, and IoU values of 0.683 and 0.671, respectively. We also investigated transfer learning models with varied backbone architectures, finding LinkNet to produce the best outcomes. In conclusion, our research highlights the efficacy of the classical Unet model in accurately identifying and outlining the Mental Foramen in panoramic radiographs. While vital, this task is comparatively simpler than segmenting complex medical datasets such as brain tumours or skin cancer, given their diverse sizes and shapes. This research also holds value in optimizing dental practice, benefiting practitioners and patients.