Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Automated external cervical resorption segmentation in cone-beam CT using local texture features

Sadhana Ravikumar, Asma A. Khan, Matthew C. Davis, Beatriz Paniagua

TL;DR

This work addresses automated segmentation of external cervical resorption (ECR) in cone-beam CT by leveraging local texture features derived from GLCM and GLRLM, classified with a Linear SVM. The approach processes cropped tooth regions, uses percentile clipping and normalization, and applies post-processing to produce robust lesion masks. Evaluation on six CBCT scans from three patients shows that LGRE and HGRE features with a 5-voxel neighborhood yield moderate Dice scores (DSC ~0.59) and high precision, with longitudinal clustering revealing potential calcified subregions within lesions. The work advances prospective imaging biomarkers for ECR prognosis, enabling improved monitoring and treatment decisions, though it is limited by the small dataset.

Abstract

External cervical resorption (ECR) is a resorptive process affecting teeth. While in some patients, active resorption ceases and gets replaced by osseous tissue, in other cases, the resorption progresses and ultimately results in tooth loss. For proper ECR assessment, cone-beam computed tomography (CBCT) is the recommended imaging modality, enabling a 3-D characterization of these lesions. While it is possible to manually identify and measure ECR resorption in CBCT scans, this process can be time intensive and highly subject to human error. Therefore, there is an urgent need to develop an automated method to identify and quantify the severity of ECR resorption using CBCT. Here, we present a method for ECR lesion segmentation that is based on automatic, binary classification of locally extracted voxel-wise texture features. We evaluate our method on 6 longitudinal CBCT datasets and show that certain texture-features can be used to accurately detect subtle CBCT signal changes due to ECR. We also present preliminary analyses clustering texture features within a lesion to stratify the defects and identify patterns indicative of calcification. These methods are important steps in developing prognostic biomarkers to predict whether ECR will continue to progress or cease, ultimately informing treatment decisions.

Automated external cervical resorption segmentation in cone-beam CT using local texture features

TL;DR

This work addresses automated segmentation of external cervical resorption (ECR) in cone-beam CT by leveraging local texture features derived from GLCM and GLRLM, classified with a Linear SVM. The approach processes cropped tooth regions, uses percentile clipping and normalization, and applies post-processing to produce robust lesion masks. Evaluation on six CBCT scans from three patients shows that LGRE and HGRE features with a 5-voxel neighborhood yield moderate Dice scores (DSC ~0.59) and high precision, with longitudinal clustering revealing potential calcified subregions within lesions. The work advances prospective imaging biomarkers for ECR prognosis, enabling improved monitoring and treatment decisions, though it is limited by the small dataset.

Abstract

External cervical resorption (ECR) is a resorptive process affecting teeth. While in some patients, active resorption ceases and gets replaced by osseous tissue, in other cases, the resorption progresses and ultimately results in tooth loss. For proper ECR assessment, cone-beam computed tomography (CBCT) is the recommended imaging modality, enabling a 3-D characterization of these lesions. While it is possible to manually identify and measure ECR resorption in CBCT scans, this process can be time intensive and highly subject to human error. Therefore, there is an urgent need to develop an automated method to identify and quantify the severity of ECR resorption using CBCT. Here, we present a method for ECR lesion segmentation that is based on automatic, binary classification of locally extracted voxel-wise texture features. We evaluate our method on 6 longitudinal CBCT datasets and show that certain texture-features can be used to accurately detect subtle CBCT signal changes due to ECR. We also present preliminary analyses clustering texture features within a lesion to stratify the defects and identify patterns indicative of calcification. These methods are important steps in developing prognostic biomarkers to predict whether ECR will continue to progress or cease, ultimately informing treatment decisions.
Paper Structure (8 sections, 3 figures, 1 table)

This paper contains 8 sections, 3 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. Materials
  3. METHODS
  4. Dental segmentation
  5. Local texture feature extraction
  6. Support vector machine segmentation
  7. RESULTS
  8. CONCLUSION

Figures (3)

  • Figure 1: Schematic overview of the proposed ECR lesion segmentation and stratification approach.
  • Figure 2: Cross-sectional views of example predictions obtained for each patient overlaid on the corresponding CBCT scan. The ground truth ECR lesion is outlined in yellow, and the predicted segmentation is shown in red. The example scans shown for Case 1 and Case 2 achieved the best and worst Dice score coefficients (DSC) respectively.
  • Figure 3: Automated ECR lesion segmentations for Case 1 predicted at two time-points 1 year apart. Unsupervised k-means clustering identifies a distinct, darker inner cluster within the lesion that may correspond to calcified tissue.