Learning Radiologist's Step-by-Step Skill for Cervical Spinal Injury Examination: Line Drawing, Prevertebral Soft Tissue Thickness Measurement, and Swelling Detection

Young Han Lee, Sewon Kim, Jin Suck Suh, Dosik Hwang

Research output: Contribution to journalArticle

Abstract

Radiologists examine lateral view radiographs of the cervical spine to determine the presence of cervical spinal injury. In this paper, we demonstrate that an artificial intelligence neural network can learn the steps employed by a radiologist when examining these radiographs for possible injury. We deconstructed the decision-making strategy into three steps: line drawing, prevertebral soft tissue thickness (PSTT) measurement, and swelling detection. After training neural networks to be guided by the radiologist's intermediate labels, the networks successfully performed comparable line drawings to those of the radiologists, and subsequent PSTT measurement and swelling detection were successful. Quantitative comparison of PSTT measurements between our proposed method and radiologists showed a high correlation (r = 0.8663, p < 0.05, and intraclass correlation coefficient = 0.9283 at the C2 level; r = 0.7720, p < 0.05, and intraclass correlation coefficient = 0.8667 at the C6 level). Using the radiologist's diagnosis as the reference point, the sensitivity, specificity, and accuracy of swelling detection by our proposed method were 100%, 98.37%, and 98.48, respectively. We conclude that our neural networks successfully learned the sequence of skills used by radiologists when interpreting radiographs for injury of the cervical spine.

Original languageEnglish
Article number8468966
Pages (from-to)55492-55500
Number of pages9
JournalIEEE Access
Volume6
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

Thickness measurement
Swelling
Tissue
Neural networks
Artificial intelligence
Labels
Decision making

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

@article{50365f27641749f886da43c6ee8d4da6,
title = "Learning Radiologist's Step-by-Step Skill for Cervical Spinal Injury Examination: Line Drawing, Prevertebral Soft Tissue Thickness Measurement, and Swelling Detection",
abstract = "Radiologists examine lateral view radiographs of the cervical spine to determine the presence of cervical spinal injury. In this paper, we demonstrate that an artificial intelligence neural network can learn the steps employed by a radiologist when examining these radiographs for possible injury. We deconstructed the decision-making strategy into three steps: line drawing, prevertebral soft tissue thickness (PSTT) measurement, and swelling detection. After training neural networks to be guided by the radiologist's intermediate labels, the networks successfully performed comparable line drawings to those of the radiologists, and subsequent PSTT measurement and swelling detection were successful. Quantitative comparison of PSTT measurements between our proposed method and radiologists showed a high correlation (r = 0.8663, p < 0.05, and intraclass correlation coefficient = 0.9283 at the C2 level; r = 0.7720, p < 0.05, and intraclass correlation coefficient = 0.8667 at the C6 level). Using the radiologist's diagnosis as the reference point, the sensitivity, specificity, and accuracy of swelling detection by our proposed method were 100{\%}, 98.37{\%}, and 98.48, respectively. We conclude that our neural networks successfully learned the sequence of skills used by radiologists when interpreting radiographs for injury of the cervical spine.",
author = "Lee, {Young Han} and Sewon Kim and Suh, {Jin Suck} and Dosik Hwang",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2018.2871502",
language = "English",
volume = "6",
pages = "55492--55500",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Learning Radiologist's Step-by-Step Skill for Cervical Spinal Injury Examination

T2 - Line Drawing, Prevertebral Soft Tissue Thickness Measurement, and Swelling Detection

AU - Lee, Young Han

AU - Kim, Sewon

AU - Suh, Jin Suck

AU - Hwang, Dosik

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Radiologists examine lateral view radiographs of the cervical spine to determine the presence of cervical spinal injury. In this paper, we demonstrate that an artificial intelligence neural network can learn the steps employed by a radiologist when examining these radiographs for possible injury. We deconstructed the decision-making strategy into three steps: line drawing, prevertebral soft tissue thickness (PSTT) measurement, and swelling detection. After training neural networks to be guided by the radiologist's intermediate labels, the networks successfully performed comparable line drawings to those of the radiologists, and subsequent PSTT measurement and swelling detection were successful. Quantitative comparison of PSTT measurements between our proposed method and radiologists showed a high correlation (r = 0.8663, p < 0.05, and intraclass correlation coefficient = 0.9283 at the C2 level; r = 0.7720, p < 0.05, and intraclass correlation coefficient = 0.8667 at the C6 level). Using the radiologist's diagnosis as the reference point, the sensitivity, specificity, and accuracy of swelling detection by our proposed method were 100%, 98.37%, and 98.48, respectively. We conclude that our neural networks successfully learned the sequence of skills used by radiologists when interpreting radiographs for injury of the cervical spine.

AB - Radiologists examine lateral view radiographs of the cervical spine to determine the presence of cervical spinal injury. In this paper, we demonstrate that an artificial intelligence neural network can learn the steps employed by a radiologist when examining these radiographs for possible injury. We deconstructed the decision-making strategy into three steps: line drawing, prevertebral soft tissue thickness (PSTT) measurement, and swelling detection. After training neural networks to be guided by the radiologist's intermediate labels, the networks successfully performed comparable line drawings to those of the radiologists, and subsequent PSTT measurement and swelling detection were successful. Quantitative comparison of PSTT measurements between our proposed method and radiologists showed a high correlation (r = 0.8663, p < 0.05, and intraclass correlation coefficient = 0.9283 at the C2 level; r = 0.7720, p < 0.05, and intraclass correlation coefficient = 0.8667 at the C6 level). Using the radiologist's diagnosis as the reference point, the sensitivity, specificity, and accuracy of swelling detection by our proposed method were 100%, 98.37%, and 98.48, respectively. We conclude that our neural networks successfully learned the sequence of skills used by radiologists when interpreting radiographs for injury of the cervical spine.

UR - http://www.scopus.com/inward/record.url?scp=85053594285&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053594285&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2871502

DO - 10.1109/ACCESS.2018.2871502

M3 - Article

AN - SCOPUS:85053594285

VL - 6

SP - 55492

EP - 55500

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8468966

ER -