19 Harley St, London, W1G 9QJ, UK

A Neural Network Model For Detection And Classification Of Lumbar Spinal Stenosis On MRI London Spine Lumbar Stenosis

This article discusses the development of a three-stage convolutional neural network (CNN) approach to diagnose and classify lumbar spinal stenosis (LSS) using spine MRI images. The CNN was trained on annotated MRI studies and evaluated on an external validation set. The results showed that the CNN had comparable performance to radiologists in determining the presence/absence and severity of LSS for all three stenosis types: central, lateral recess, and foraminal. The study suggests that integrating neural network models in LSS diagnosis can improve accuracy, efficiency, consistency, and post-hoc interpretability in diagnostic practices. The keywords for this article are artificial intelligence, lumbar spinal stenosis, MRI, machine learning, and neural network

Summarised by Mr Mo Akmal – Lead Spinal Surgeon
The London Spine Unit : the highest rated spinal hospital in UK

Published article

CONCLUSIONS: The CNN showed comparable performance to radiologist subspecialists for the detection and classification of LSS. The integration of neural network models in the detection of LSS could bring higher accuracy, efficiency, consistency, and post-hoc interpretability in diagnostic practices.

Spine Lumbar Spinal Stenosis Expert. Best Spinal Surgeon UK
Abstract Objectives: To develop a three-stage convolutional neural network (CNN) approach to segment anatomical structures, classify the presence of lumbar spinal stenosis (LSS) for all 3 stenosis types: central, lateral recess and foraminal and assess its severity on spine MRI and to demonstrate its efficacy as an accurate and consistent diagnostic tool. Methods: The three-stage,

Abstract

Objectives: To develop a three-stage convolutional neural network (CNN) approach to segment anatomical structures, classify the presence of lumbar spinal stenosis (LSS) for all 3 stenosis types: central, lateral recess and foraminal and assess its severity on spine MRI and to demonstrate its efficacy as an accurate and consistent diagnostic tool.

Methods: The three-stage model was trained on 1635 annotated lumbar spine MRI studies consisting of T2-weighted sagittal and axial planes at each vertebral level. Accuracy of the model was evaluated on an external validation set of 150 MRI studies graded on a scale of absent, mild, moderate or severe by a panel of 7 radiologists. The reference standard for all types was determined by majority voting and in case of disagreement, adjudicated by an external radiologist. The radiologists’ diagnoses were then compared to the diagnoses of the model.

Results: The model showed comparable performance to the radiologist average both in terms of the determination of presence/absence of LSS as well as severity classification, for all 3 stenosis types. In the case of central canal stenosis, the sensitivity, specificity and AUROC of the CNN were (0.971, 0.864, 0.963) for binary (presence/absence) classification compared to the radiologist average of (0.786, 0.899, 0.842). For lateral recess stenosis, the sensitivity, specificity and AUROC of the CNN were (0.853, 0.787, 0.907) compared to the radiologist average of (0.713, 0.898, 805). For foraminal stenosis, the sensitivity, specificity and AUROC of the CNN were (0.942, 0.844, 0.950) compared to the radiologist average of (0.879, 0.877, 0.878). Multi-class severity classifications showed similarly comparable statistics.

Conclusions: The CNN showed comparable performance to radiologist subspecialists for the detection and classification of LSS. The integration of neural network models in the detection of LSS could bring higher accuracy, efficiency, consistency, and post-hoc interpretability in diagnostic practices.

Keywords: Artificial intelligence; Lumbar spinal stenosis; MRI; Machine learning; Neural network.

The London Spine Unit : the highest rated spinal hospital in UK

Read the original publication:

A neural network model for detection and classification of lumbar spinal stenosis on MRI

Related Posts

0/5 (0 Reviews)

Trusindex Reviews

London Spine Unit Harley Street Hospital

A Focus on High Quality Specialised Care

We are a specialist Private Hospital based on Harley Street, London UK The Harley Street Hospital, Day Surgery Hospital

We provide exclusive health services for individuals seeking Advanced medical, non-surgical or minimally invasive treatments. We are covered by All Insurance Companies apart from AXA PPP

Our Medical Director and Lead Spinal Surgeon Mr Mo Akmal MD is a world renowned Spine Specialist Consultant with over 20 years of experience. He and his team have developed revolutionary techniques to perform all types of Spinal Surgery as a Day Case procedure without traditional General Anaesthetic.

We are constantly improving our techniques for treatment and improving facilities for our patients.

Book your Appointment Now 
Check out our Reviews 
Check out our Patient Videos 
Check our Mr Akmal’s Profile

 

What our patients say ...

Abstract Objectives: To develop a three-stage convolutional neural network (CNN) approach to segment anatomical structures, classify the presence of lumbar spinal stenosis (LSS) for all 3 stenosis types: central, lateral recess and foraminal and assess its severity on spine MRI and to demonstrate its efficacy as an accurate and consistent diagnostic tool. Methods: The three-stage

Revolutionary Keyhole surgical technique to vaporise bulging discs

Dr Mo Akmal Medical Director
Dr Mo Akmal MD - Lead Spinal Surgeon

Laser Disc Surgery can be performed under local anaesthetic at The Harley Street Hospital.

Initial Consultation

with Consultant Spine Surgeon
£ 250
  • No Waiting Times
  • Top NHS affiliated Consultant
  • Includes Clinical Review and Report
  • Multidisciplinary discussion
  • Review of Previous Scans and Reports

Follow up Consultation

any appointment after initial consultation
£ 180
  • Top NHS affiliated Consultant
  • Includes Clinical Review and Report
  • Multidisciplinary discussion

High Resolution MRI Scan

any Single Region (3.0 Tesla)
£ 600
  • No waiting times
  • Includes Full Radiologist Report
  • Open or Closed MRI scan types
  • Copy of Scan on CD

Website Offer

Pre-Booked Online
£1130
£ 800
  • Initial Consultation
  • MRI Scan (Single Region)
  • Follow Up consultation
  • Same Day One Stop Visit
  • Full Medical and MRI scan Report
  • Copy of scan on CD
Popular

If you have any emergency Doctor’s need, simply call our 24 hour emergency

Your personal case manager will ensure that you receive the best possible care.

Call Now 

+44 844 589 2020
+44 203 973 8810