Automatic Segmentation of Periodontal Tissue Ultrasound Images with Artificial Intelligence: A Novel Method for Improving Dataset Quality

Abstract

This research aimed to evaluate Mask R-CNN and U-Net convolutional neural network models for pixel-level classification in order to perform the automatic segmentation of bi-dimensional images of US dental arches, identifying anatomical elements required for periodontal diagnosis. A secondary aim was to evaluate the efficiency of a correction method of the ground truth masks segmented by an operator, for improving the quality of the datasets used for training the neural network models, by 3D ultrasound reconstructions of the examined periodontal tissue. Methods: Ultrasound periodontal investigations were performed for 52 teeth of 11 patients using a 3D ultrasound scanner prototype. The original ultrasound images were segmented by a low experienced operator using region growing-based segmentation algorithms. Three-dimensional ultrasound reconstructions were used for the quality check and correction of the segmentation. Mask R-CNN and U-NET were trained and used for prediction of periodontal tissue’s elements identification. Results: The average Intersection over Union ranged between 10% for the periodontal pocket and 75.6% for gingiva. Even though the original dataset contained 3417 images from 11 patients, and the corrected dataset only 2135 images from 5 patients, the prediction’s accuracy is significantly better for the models trained with the corrected dataset. Conclusions: The proposed quality check and correction method by evaluating in the 3D space the operator’s ground truth segmentation had a positive impact on the quality of the datasets demonstrated through higher IoU after retraining the models using the corrected dataset.

Automatic Segmentation of Teeth, Crown–Bridge Restorations, Dental Implants, Restorative Fillings, Dental Caries, Residual Roots, and Root Canal Fillings on Orthopantomographs: Convenience and Pitfalls

“…U-Net architecture was used to reveal this. U-Net is a convolutional neural network developed at the Freiburg University Computer Science Department for segmentation in image processing studies in biomedical fields [ 10 , 11 , 12 , 17 , 20 , 21 , 26 , 30 , 31 , 34 , 38 , 50 , 64 , 66 , 67 , 70 , 71 , 82 , 83 , 84 , 85 , 86 ].…”

“…Thus, by recognizing similar sequences, similar motifs, and similar pixels, the machine can detect, segment, and classify what those pictures are. The more data there are, the better artificial intelligence features will be revealed [ 1 , 11 , 12 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 ]. Deep neural networks have many hidden layers, with millions of interconnected artificial neurons.…”

“…Theoretically, deep neural networks can match any type of input to any type of output; however, they require much more training compared to other machine learning methods. They require millions of samples, compared to the hundreds or thousands of training data samples that a simpler network might need [ 1 , 2 , 11 , 12 , 17 , 18 , 19 , 20 , 21 , 30 , 33 , 34 , 35 , 36 , 37 , 38 , 39 ].…”

“…Common applications of AI in oral diagnosis and dentomaxillofacial radiology are as follows: Oral cancer prognosis and assessment of oral cancer risk [ 45 , 53 , 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 ]; Determination of temporomandibular joint disorder progression and temporomandibular internal derangements [ 27 , 30 , 34 , 38 , 63 ]; Interpretation of conventional 2D imaging [ 31 , 64 , 65 , 66 , 67 , 68 ]; Interpretation of cone beam computed tomography and other 3D imaging methods [ 1 , 10 , 12 , 17 , 18 , 19 , 21 , 23 , 27 , 69 , 70 , 71 ]. …”

“…Interpretation of cone beam computed tomography and other 3D imaging methods [ 1 , 10 , 12 , 17 , 18 , 19 , 21 , 23 , 27 , 69 , 70 , 71 ].…”