Binary Decision Trees for Preoperative Periapical Cyst Screening Using Cone-beam Computed Tomography

Brandon Pitcher, Ali Alaqla, Marcel Noujeim, James A. Wealleans, Georgios Kotsakis, Vanessa Chrepa

Research output: Contribution to journalArticle

Abstract

Introduction Cone-beam computed tomographic (CBCT) analysis allows for 3-dimensional assessment of periradicular lesions and may facilitate preoperative periapical cyst screening. The purpose of this study was to develop and assess the predictive validity of a cyst screening method based on CBCT volumetric analysis alone or combined with designated radiologic criteria. Methods Three independent examiners evaluated 118 presurgical CBCT scans from cases that underwent apicoectomies and had an accompanying gold standard histopathological diagnosis of either a cyst or granuloma. Lesion volume, density, and specific radiologic characteristics were assessed using specialized software. Logistic regression models with histopathological diagnosis as the dependent variable were constructed for cyst prediction, and receiver operating characteristic curves were used to assess the predictive validity of the models. A conditional inference binary decision tree based on a recursive partitioning algorithm was constructed to facilitate preoperative screening. Results Interobserver agreement was excellent for volume and density, but it varied from poor to good for the radiologic criteria. Volume and root displacement were strong predictors for cyst screening in all analyses. The binary decision tree classifier determined that if the volume of the lesion was >247 mm3, there was 80% probability of a cyst. If volume was <247 mm3 and root displacement was present, cyst probability was 60% (78% accuracy). Conclusions The good accuracy and high specificity of the decision tree classifier renders it a useful preoperative cyst screening tool that can aid in clinical decision making but not a substitute for definitive histopathological diagnosis after biopsy. Confirmatory studies are required to validate the present findings.

Original languageEnglish (US)
Pages (from-to)383-388
Number of pages6
JournalJournal of Endodontics
Volume43
Issue number3
DOIs
StatePublished - Mar 1 2017

Fingerprint

Radicular Cyst
Decision Trees
Cone-Beam Computed Tomography
Cysts
Logistic Models
Apicoectomy
Granuloma
ROC Curve
Decision Making
Software
Biopsy

Keywords

  • Binary decision tree
  • cone-beam computed tomography
  • cyst screening
  • differentiation between cysts and granulomas
  • volumetric analysis

ASJC Scopus subject areas

  • Dentistry(all)

Cite this

Binary Decision Trees for Preoperative Periapical Cyst Screening Using Cone-beam Computed Tomography. / Pitcher, Brandon; Alaqla, Ali; Noujeim, Marcel; Wealleans, James A.; Kotsakis, Georgios; Chrepa, Vanessa.

In: Journal of Endodontics, Vol. 43, No. 3, 01.03.2017, p. 383-388.

Research output: Contribution to journalArticle

Pitcher B, Alaqla A, Noujeim M, Wealleans JA, Kotsakis G, Chrepa V. Binary Decision Trees for Preoperative Periapical Cyst Screening Using Cone-beam Computed Tomography. Journal of Endodontics. 2017 Mar 1;43(3):383-388. Available from, DOI: 10.1016/j.joen.2016.10.046

Pitcher, Brandon; Alaqla, Ali; Noujeim, Marcel; Wealleans, James A.; Kotsakis, Georgios; Chrepa, Vanessa / Binary Decision Trees for Preoperative Periapical Cyst Screening Using Cone-beam Computed Tomography.

In: Journal of Endodontics, Vol. 43, No. 3, 01.03.2017, p. 383-388.

Research output: Contribution to journalArticle

@article{33911c535a7f40c5b06cca963476ac89,
title = "Binary Decision Trees for Preoperative Periapical Cyst Screening Using Cone-beam Computed Tomography",
abstract = "Introduction Cone-beam computed tomographic (CBCT) analysis allows for 3-dimensional assessment of periradicular lesions and may facilitate preoperative periapical cyst screening. The purpose of this study was to develop and assess the predictive validity of a cyst screening method based on CBCT volumetric analysis alone or combined with designated radiologic criteria. Methods Three independent examiners evaluated 118 presurgical CBCT scans from cases that underwent apicoectomies and had an accompanying gold standard histopathological diagnosis of either a cyst or granuloma. Lesion volume, density, and specific radiologic characteristics were assessed using specialized software. Logistic regression models with histopathological diagnosis as the dependent variable were constructed for cyst prediction, and receiver operating characteristic curves were used to assess the predictive validity of the models. A conditional inference binary decision tree based on a recursive partitioning algorithm was constructed to facilitate preoperative screening. Results Interobserver agreement was excellent for volume and density, but it varied from poor to good for the radiologic criteria. Volume and root displacement were strong predictors for cyst screening in all analyses. The binary decision tree classifier determined that if the volume of the lesion was >247 mm3, there was 80% probability of a cyst. If volume was <247 mm3 and root displacement was present, cyst probability was 60% (78% accuracy). Conclusions The good accuracy and high specificity of the decision tree classifier renders it a useful preoperative cyst screening tool that can aid in clinical decision making but not a substitute for definitive histopathological diagnosis after biopsy. Confirmatory studies are required to validate the present findings.",
keywords = "Binary decision tree, cone-beam computed tomography, cyst screening, differentiation between cysts and granulomas, volumetric analysis",
author = "Brandon Pitcher and Ali Alaqla and Marcel Noujeim and Wealleans, {James A.} and Georgios Kotsakis and Vanessa Chrepa",
year = "2017",
month = "3",
doi = "10.1016/j.joen.2016.10.046",
volume = "43",
pages = "383--388",
journal = "Journal of Endodontics",
issn = "0099-2399",
publisher = "Elsevier Inc.",
number = "3",

}

TY - JOUR

T1 - Binary Decision Trees for Preoperative Periapical Cyst Screening Using Cone-beam Computed Tomography

AU - Pitcher,Brandon

AU - Alaqla,Ali

AU - Noujeim,Marcel

AU - Wealleans,James A.

AU - Kotsakis,Georgios

AU - Chrepa,Vanessa

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Introduction Cone-beam computed tomographic (CBCT) analysis allows for 3-dimensional assessment of periradicular lesions and may facilitate preoperative periapical cyst screening. The purpose of this study was to develop and assess the predictive validity of a cyst screening method based on CBCT volumetric analysis alone or combined with designated radiologic criteria. Methods Three independent examiners evaluated 118 presurgical CBCT scans from cases that underwent apicoectomies and had an accompanying gold standard histopathological diagnosis of either a cyst or granuloma. Lesion volume, density, and specific radiologic characteristics were assessed using specialized software. Logistic regression models with histopathological diagnosis as the dependent variable were constructed for cyst prediction, and receiver operating characteristic curves were used to assess the predictive validity of the models. A conditional inference binary decision tree based on a recursive partitioning algorithm was constructed to facilitate preoperative screening. Results Interobserver agreement was excellent for volume and density, but it varied from poor to good for the radiologic criteria. Volume and root displacement were strong predictors for cyst screening in all analyses. The binary decision tree classifier determined that if the volume of the lesion was >247 mm3, there was 80% probability of a cyst. If volume was <247 mm3 and root displacement was present, cyst probability was 60% (78% accuracy). Conclusions The good accuracy and high specificity of the decision tree classifier renders it a useful preoperative cyst screening tool that can aid in clinical decision making but not a substitute for definitive histopathological diagnosis after biopsy. Confirmatory studies are required to validate the present findings.

AB - Introduction Cone-beam computed tomographic (CBCT) analysis allows for 3-dimensional assessment of periradicular lesions and may facilitate preoperative periapical cyst screening. The purpose of this study was to develop and assess the predictive validity of a cyst screening method based on CBCT volumetric analysis alone or combined with designated radiologic criteria. Methods Three independent examiners evaluated 118 presurgical CBCT scans from cases that underwent apicoectomies and had an accompanying gold standard histopathological diagnosis of either a cyst or granuloma. Lesion volume, density, and specific radiologic characteristics were assessed using specialized software. Logistic regression models with histopathological diagnosis as the dependent variable were constructed for cyst prediction, and receiver operating characteristic curves were used to assess the predictive validity of the models. A conditional inference binary decision tree based on a recursive partitioning algorithm was constructed to facilitate preoperative screening. Results Interobserver agreement was excellent for volume and density, but it varied from poor to good for the radiologic criteria. Volume and root displacement were strong predictors for cyst screening in all analyses. The binary decision tree classifier determined that if the volume of the lesion was >247 mm3, there was 80% probability of a cyst. If volume was <247 mm3 and root displacement was present, cyst probability was 60% (78% accuracy). Conclusions The good accuracy and high specificity of the decision tree classifier renders it a useful preoperative cyst screening tool that can aid in clinical decision making but not a substitute for definitive histopathological diagnosis after biopsy. Confirmatory studies are required to validate the present findings.

KW - Binary decision tree

KW - cone-beam computed tomography

KW - cyst screening

KW - differentiation between cysts and granulomas

KW - volumetric analysis

UR - http://www.scopus.com/inward/record.url?scp=85013269717&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013269717&partnerID=8YFLogxK

U2 - 10.1016/j.joen.2016.10.046

DO - 10.1016/j.joen.2016.10.046

M3 - Article

VL - 43

SP - 383

EP - 388

JO - Journal of Endodontics

T2 - Journal of Endodontics

JF - Journal of Endodontics

SN - 0099-2399

IS - 3

ER -