Analysis of the mandibular canal course using unsupervised machine learning algorithm

Abstract

Objectives: Anatomical structure classification is necessary task in medical field, but the inevitable variability of interpretation among experts makes reliable classification difficult. This study aims to introduce cluster analysis, unsupervised machine learning method, for classification of three-dimensional (3D) mandibular canal (MC) courses, and to visualize standard MC courses derived from cluster analysis in the Korean population.

Materials and methods: A total of 429 cone-beam computed tomography images were used. Four sites in the mandible were selected for the measurement of the MC course and four parameters, two vertical and two horizontal parameters were measured per site. Cluster analysis was carried out as follows: parameter measurement, parameter normalization, cluster tendency evaluation, optimal number of clusters determination, and k-means cluster analysis. The 3D MC courses were classified into three types with statistically significant mean differences by cluster analysis.

Results: Cluster 1 showed a smooth line running towards the lingual side in the axial view and a steep slope in the sagittal view. Cluster 2 ran in an almost straight line closest to the lingual and inferior border of mandible. Cluster 3 showed the pathway with a bent buccally in the axial view and an increasing slope in the sagittal view in the posterior area. Cluster 2 showed the highest distribution (42.1%), and males were more widely distributed (57.1%) than the females (42.9%). Cluster 3 comprised similar ratio of male and female cases and accounted for 31.9% of the total distribution. Cluster 1 had the least distribution (26.0%) Distributions of the right and left sides did not show a statistically significant difference.

Conclusion: The MC courses were automatically classified as three types through cluster analysis. Cluster analysis enables the unbiased classification of the anatomical structures by reducing observer variability and can present representative standard information for each classified group.

Fig 1. The overall workflow of cluster analysis.

Fig 2. Two schematic diagrams illustrating the four selected sites and parameters.

(a) Selection of four sites in a CBCT image. S0 is the baseline that penetrates the center of mental foramen. Four cross-sectional images (S1, S2, S3 and S4) were selected at intervals of 10mm from S0. (b) Four parameters—upper height (UH), lower height (LH), lingual width (LW), and buccal width (BW)–used to assess the course of the mandibular canal. The mandibular canal is represented in gray.

Fig 3. Dissimilarity matrix visualizing the clustering tendency of the parameters.

Orange shows low dissimilarity level and purple shows high dissimilarity level.

Fig 4

Determination of the optimal number of clusters using dendrogram (a) and NbClust (b). (a) The vertical axis represents the distance between clusters and the horizontal axis represents individual variables. The dotted lines show an example of determining the optimal number of clusters. The clusters are classified into 2 and 5 groups at height 400 and 200 respectively. (b) Frequency distribution of NbClust indices for the number of clusters.

Fig 5

Illustrations of three types of the three-dimensional mandibular canal course in axial (a) and sagittal view (b). Cluster 1 shows traveling towards the lingual side with a steep vertical slope. Cluster 2 shows the closest to the lingual side and lowest vertical slope. Cluster 3 shows a buccal curvature with gradually increasing vertical slope in the posterior area.

Fig 6. Distribution of the three-dimensional mandibular canal course by cluster.

(a) Distributions of three clusters, (b) Distribution of three clusters for each age group, (c) Sex distribution of each cluster (P-value by Z-test at α = 0.05. *, P < .05.), and (d) Right and left distribution of each cluster.