Lumbar spine discs classification based on deep convolutional neural networks using axial view MRI

In plain language

Recognising lumbar disc herniation from axial magnetic resonance imaging (MRI) is challenging due to image noise, blur, and complex backgrounds. An automated diagnostic system addresses this by employing deep convolutional neural networks. The method processes MRI scans across multiple scales of context and merges high-level features to identify discs along the lumbar spine. Architecture based on VGG16 is used to classify herniated discs, alongside a U-net deep neural network architecture to localise and detail the herniation site. Evaluations conducted on a clinical dataset from Sahloul University Hospital of Sousse demonstrate an overall classification accuracy of 94 percent. By utilising axial view MRI scans, the approach pinpoints normal and pathological intervertebral discs to assist radiologists in diagnosing and managing lumbar disc herniation.

Key takeaways

Identifying lumbar disc herniations in axial magnetic resonance imaging is difficult because of background complexity, blur, and noise.
A deep learning system using a VGG16 convolutional neural network architecture was developed to classify herniated lumbar discs.
The method integrates a U-net deep neural network architecture to localise the exact position of herniated and normal intervertebral discs.
Testing on a dataset from Sahloul University Hospital of Sousse achieved a classification accuracy of 94 percent.

Why it matters

Lumbar disc herniation can be difficult to interpret on magnetic resonance imaging due to poor image clarity and complex anatomy. Developing reliable automated detection tools assists clinical radiologists by accurately locating diseased discs across the spine. Such computer-aided diagnostic systems can support more consistent clinical decisions and streamline treatment planning for spinal conditions.

Commercialisation angle

The system serves as a computer-aided diagnostic tool aimed directly at hospital radiologists evaluating spinal scans. Tested on an institutional dataset with 94 percent accuracy, the technology demonstrates applied research ready for further validation, but the abstract does not indicate whether it has been integrated into commercial radiology software or deployed in live clinical workflows.

AI-generated from the published abstract. Always read the original work before citing.

Abstract

Axial Lumbar disc herniation recognition is a difficult task to achieve, due to many challenges such as complex background, noise, blurry image. Lumbar discs are small joints that lie between each two vertebrae (L1-L2, L2-L3, L3-L4, L4-L5 and L5-S1). The segmentation and localization of the different discs are the most important tasks in Computer aided diagnosing of herniation. During the last five years, deep learning based methods have set new standards for many computer vision and pattern recognition research. In this work, our objective is to develop an automatic system based on deep convolutional neural network. This Network processes the input MRI (Magnetic Resonance Imaging) in multiple scales of context and then merges the high-level features to enhance the capability of the network to detect discs from lumbar spine. In this study, we are particularly interested in convolutional neural networks (CNN); it was characterized by a topology similar to a visual cortex of mammals. In fact, these kind of techniques has been applied successfully in many classification problems. In order to recognize herniated lumbar disc in Magnetic Resonance Imaging (MRI), we have chosen to use Convolutional neural networks based on VGG16 architecture. Experiments were carried on our own dataset from Sahloul University Hospital of Sousse. The accuracy achieved of the trained model was 94% which represents a high-performance results by providing state of the art. Our system is very efficient and effective for detecting and diagnosing herniated lumbar disc. Therefore, The contribution of this study includes in: Firstly, the using of the U-net deep neural network architecture to localize and to detail the location of the herniation. Secondly, the using of the axial view MRI in order to locate exactly the pathological and the normal intervertebral discs.The main objective of this paper is to help radiologists in the diagnosing and treating lumbar herniated disc disease.

Research topics

Medical Imaging and Analysis
Spine and Intervertebral Disc Pathology
Spinal Fractures and Fixation Techniques

Discussion

Discuss this research

Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.

No discussion yet. Open the first thread.

New to MARATTO™? Create a free account.