RESUMO
Purpose@#Periodontitis, the most prevalent chronic inflammatory condition affecting teeth-supporting tissues, is diagnosed and classified through clinical and radiographic examinations. The staging of periodontitis using panoramic radiographs provides information for designing computer-assisted diagnostic systems. Performing image segmentation in periodontitis is required for image processing in diagnostic applications. This study evaluated image segmentation for periodontitis staging based on deep learning approaches. @*Materials and Methods@#Multi-Label U-Net and Mask R-CNN models were compared for image segmentation to detect periodontitis using 100 digital panoramic radiographs. Normal conditions and 4 stages of periodontitis were annotated on these panoramic radiographs. A total of 1100 original and augmented images were then randomly divided into a training (75%) dataset to produce segmentation models and a testing (25%) dataset to determine the evaluation metrics of the segmentation models. @*Results@#The performance of the segmentation models against the radiographic diagnosis of periodontitis conducted by a dentist was described by evaluation metrics (i.e., dice coefficient and intersection-over-union [IoU] score). Multi-Label U-Net achieved a dice coefficient of 0.96 and an IoU score of 0.97. Meanwhile, Mask R-CNN attained a dice coefficient of 0.87 and an IoU score of 0.74. U-Net showed the characteristic of semantic segmentation, and Mask R-CNN performed instance segmentation with accuracy, precision, recall, and F1-score values of 95%, 85.6%, 88.2%, and 86.6%, respectively. @*Conclusion@#Multi-Label U-Net produced superior image segmentation to that of Mask R-CNN. The authors recommend integrating it with other techniques to develop hybrid models for automatic periodontitis detection.
RESUMO
OBJECTIVES: The aim of this study is to propose a method that automatically select the trabecular bone area in digital periapical radiographic images using a sequence of morphological operations. METHODS: The study involved 50 digital periapical radiographic images of women aged from 36 to 58 years old. The proposed method consists of three stages: teeth detection, trabecular identification, and validation. A series of morphological operations-top-hat and bottom-hat filtering, automatic thresholding, closing, labeling, global thresholding, and image subtraction-are performed to automatically obtain the trabecular bone area in images. For validation, the results of the proposed method were compared with those of two dentists pixel by pixel. Three parameters were used in the validation: trabecular area, percentage of agreed area, and percentage of disagreed area. RESULTS: The proposed method obtains the trabecular bone area in a polygon. The obtained trabecular bone area is usually larger than that of previous studies, but is usually smaller than the dentists'. On average over all images, the trabecular area produced by the proposed method is 5.83% smaller than that identified by dentists. Furthermore, the average percentage of agreed area and the average percentage of disagreed area of the proposed method against the dentists' results were 75.22% and 8.75%, respectively. CONCLUSIONS: The shape of the trabecular bone area produced by the proposed method is similar and closer to that identified by dentists. The method, which consists of only simple morphological operations on digital periapical radiographic images, can be considered for selecting the trabecular bone area automatically.