Abstract

A damage to the spinal cord can affect its natural functioning both temporarily or permanently resulting in loss of sensation and functioning of muscles. Spinal cord injury occurs due to vertebral fractures, especially in thoracolumbar junction. Early detection and treatment of spinal cord injury can help to improve the neurological status. Computed tomography (CT) is one of the effective imaging modalities to visualize the status of vertebrae and make necessary diagnosis. But, these imaging modalities involve both inter and intra observer variabilities which may result in identification of wrong level. Thus, an automated computer aided diagnosis (CAD) system is required to accurately identify the fracture and prescribe correct treatment at the earliest. It is very difficult to precisely segment the vertebra to detect spinal injuries using image processing techniques. Hence, in this paper, we are proposing an automated thoracolumbar fracture detection technique using convolutional neural networks (CNNs) without segmenting the vertebra. The proposed method can efficiently classify the normal and fractured subjects with an accuracy of 99.10%, sensitivity of 100% and specificity of 97.61% using our private dataset (Total image 1120). This novel CAD system can assist the orthopedists in their routine screening.

Original languageEnglish
Pages (from-to)184-189
Number of pages6
JournalFuture Generation Computer Systems
Volume85
DOIs
Publication statusPublished - 01-08-2018

Fingerprint

Network architecture
Computer aided diagnosis
Neural networks
Imaging techniques
Tomography
Muscle
Screening
Image processing

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

@article{cc783b7163304c07a1c165147a08bded,
title = "Automated system for the detection of thoracolumbar fractures using a CNN architecture",
abstract = "A damage to the spinal cord can affect its natural functioning both temporarily or permanently resulting in loss of sensation and functioning of muscles. Spinal cord injury occurs due to vertebral fractures, especially in thoracolumbar junction. Early detection and treatment of spinal cord injury can help to improve the neurological status. Computed tomography (CT) is one of the effective imaging modalities to visualize the status of vertebrae and make necessary diagnosis. But, these imaging modalities involve both inter and intra observer variabilities which may result in identification of wrong level. Thus, an automated computer aided diagnosis (CAD) system is required to accurately identify the fracture and prescribe correct treatment at the earliest. It is very difficult to precisely segment the vertebra to detect spinal injuries using image processing techniques. Hence, in this paper, we are proposing an automated thoracolumbar fracture detection technique using convolutional neural networks (CNNs) without segmenting the vertebra. The proposed method can efficiently classify the normal and fractured subjects with an accuracy of 99.10{\%}, sensitivity of 100{\%} and specificity of 97.61{\%} using our private dataset (Total image 1120). This novel CAD system can assist the orthopedists in their routine screening.",
author = "U. Raghavendra and Bhat, {N. Shyamasunder} and Anjan Gudigar and Acharya, {U. Rajendra}",
year = "2018",
month = "8",
day = "1",
doi = "10.1016/j.future.2018.03.023",
language = "English",
volume = "85",
pages = "184--189",
journal = "Future Generation Computer Systems",
issn = "0167-739X",
publisher = "Elsevier",

}

Automated system for the detection of thoracolumbar fractures using a CNN architecture. / Raghavendra, U.; Bhat, N. Shyamasunder; Gudigar, Anjan; Acharya, U. Rajendra.

In: Future Generation Computer Systems, Vol. 85, 01.08.2018, p. 184-189.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated system for the detection of thoracolumbar fractures using a CNN architecture

AU - Raghavendra, U.

AU - Bhat, N. Shyamasunder

AU - Gudigar, Anjan

AU - Acharya, U. Rajendra

PY - 2018/8/1

Y1 - 2018/8/1

N2 - A damage to the spinal cord can affect its natural functioning both temporarily or permanently resulting in loss of sensation and functioning of muscles. Spinal cord injury occurs due to vertebral fractures, especially in thoracolumbar junction. Early detection and treatment of spinal cord injury can help to improve the neurological status. Computed tomography (CT) is one of the effective imaging modalities to visualize the status of vertebrae and make necessary diagnosis. But, these imaging modalities involve both inter and intra observer variabilities which may result in identification of wrong level. Thus, an automated computer aided diagnosis (CAD) system is required to accurately identify the fracture and prescribe correct treatment at the earliest. It is very difficult to precisely segment the vertebra to detect spinal injuries using image processing techniques. Hence, in this paper, we are proposing an automated thoracolumbar fracture detection technique using convolutional neural networks (CNNs) without segmenting the vertebra. The proposed method can efficiently classify the normal and fractured subjects with an accuracy of 99.10%, sensitivity of 100% and specificity of 97.61% using our private dataset (Total image 1120). This novel CAD system can assist the orthopedists in their routine screening.

AB - A damage to the spinal cord can affect its natural functioning both temporarily or permanently resulting in loss of sensation and functioning of muscles. Spinal cord injury occurs due to vertebral fractures, especially in thoracolumbar junction. Early detection and treatment of spinal cord injury can help to improve the neurological status. Computed tomography (CT) is one of the effective imaging modalities to visualize the status of vertebrae and make necessary diagnosis. But, these imaging modalities involve both inter and intra observer variabilities which may result in identification of wrong level. Thus, an automated computer aided diagnosis (CAD) system is required to accurately identify the fracture and prescribe correct treatment at the earliest. It is very difficult to precisely segment the vertebra to detect spinal injuries using image processing techniques. Hence, in this paper, we are proposing an automated thoracolumbar fracture detection technique using convolutional neural networks (CNNs) without segmenting the vertebra. The proposed method can efficiently classify the normal and fractured subjects with an accuracy of 99.10%, sensitivity of 100% and specificity of 97.61% using our private dataset (Total image 1120). This novel CAD system can assist the orthopedists in their routine screening.

UR - http://www.scopus.com/inward/record.url?scp=85044523759&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044523759&partnerID=8YFLogxK

U2 - 10.1016/j.future.2018.03.023

DO - 10.1016/j.future.2018.03.023

M3 - Article

AN - SCOPUS:85044523759

VL - 85

SP - 184

EP - 189

JO - Future Generation Computer Systems

JF - Future Generation Computer Systems

SN - 0167-739X

ER -