AI-Enabled Diagnosis of Lumbar Spinal Stenosis from Axial MR Images Using Convolutional Neural Network and Image Explainer

Uthman O.  Oyebanji; Ala S. Al Kafri; Hiba Alsmadi; Mohammad  Alkasasbeh; Wasiq  Khan

doi:10.1109/DeSE63988.2024.10911920

AI-Enabled Diagnosis of Lumbar Spinal Stenosis from Axial MR Images Using Convolutional Neural Network and Image Explainer

Uthman O. Oyebanji
, Ala S. Al Kafri
, Hiba Alsmadi
, Mohammad Alkasasbeh
, Wasiq Khan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Lower back pain (LBP) is a global medical condition
that affects more than 80% of people at least once in their
lifetime. Various abnormal conditions could cause LBP. One of
these conditions is Lumbar Spinal Stenosis (LSS), which is
usually a serious condition, hence the need for its prompt
diagnosis. The visual assessment process of magnetic resonance
imaging (MRI) is expensive in terms of time and effort and prone
to delays. The integration of an AI-enabled system to help
clinicians in diagnosing patients with LBP is expected to alleviate
the burden on radiologists and foster a less time-consuming and
cost-efficient diagnostic process. In this paper, a convolutional
neural network (CNN) model has been built to diagnose T2-
weighted (T2W) axial MRI scans. The model detects LSS in these
scans and has achieved remarkable accuracy and recall of 91%
and 96%, respectively. Explainable AI (XAI) using LIME's
ImageExplainer was also implemented to ensure the model offers
explainable insights. This is to ensure the model is not only
accurate but also reliable.

Original language	English
Title of host publication	2024 17th International Conference on Development in eSystem Engineering (DeSE)
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	9798350368697, 9798350368703
DOIs	https://doi.org/10.1109/DeSE63988.2024.10911920
Publication status	Published - 11 Mar 2025
Event	17th International Conference on Development in eSystem Engineering (DeSE) - University of Sharjah, Dubai, United Arab Emirates Duration: 6 Nov 2024 → 8 Nov 2024 https://dese.ai/dese-2024/

Conference

Conference	17th International Conference on Development in eSystem Engineering (DeSE)
Country/Territory	United Arab Emirates
City	Dubai
Period	6/11/24 → 8/11/24
Internet address	https://dese.ai/dese-2024/

Access to Document

10.1109/DeSE63988.2024.10911920

Cite this

@inproceedings{131b436ff80247d0b12f4c3be229e517,

title = "AI-Enabled Diagnosis of Lumbar Spinal Stenosis from Axial MR Images Using Convolutional Neural Network and Image Explainer",

abstract = "Lower back pain (LBP) is a global medical condition that affects more than 80\% of people at least once in their lifetime. Various abnormal conditions could cause LBP. One of these conditions is Lumbar Spinal Stenosis (LSS), which is usually a serious condition, hence the need for its prompt diagnosis. The visual assessment process of magnetic resonance imaging (MRI) is expensive in terms of time and effort and prone to delays. The integration of an AI-enabled system to help clinicians in diagnosing patients with LBP is expected to alleviate the burden on radiologists and foster a less time-consuming and cost-efficient diagnostic process. In this paper, a convolutional neural network (CNN) model has been built to diagnose T2- weighted (T2W) axial MRI scans. The model detects LSS in these scans and has achieved remarkable accuracy and recall of 91\% and 96\%, respectively. Explainable AI (XAI) using LIME's ImageExplainer was also implemented to ensure the model offers explainable insights. This is to ensure the model is not only accurate but also reliable.",

author = "Oyebanji, \{Uthman O.\} and \{Al Kafri\}, \{Ala S.\} and Hiba Alsmadi and Mohammad Alkasasbeh and Wasiq Khan",

year = "2025",

month = mar,

day = "11",

doi = "10.1109/DeSE63988.2024.10911920",

language = "English",

booktitle = "2024 17th International Conference on Development in eSystem Engineering (DeSE)",

publisher = "IEEE",

note = "17th International Conference on Development in eSystem Engineering (DeSE) ; Conference date: 06-11-2024 Through 08-11-2024",

url = "https://dese.ai/dese-2024/",

}

Oyebanji, UO, Al Kafri, AS , Alsmadi, H, Alkasasbeh, M & Khan, W 2025, AI-Enabled Diagnosis of Lumbar Spinal Stenosis from Axial MR Images Using Convolutional Neural Network and Image Explainer. in 2024 17th International Conference on Development in eSystem Engineering (DeSE). IEEE, 17th International Conference on Development in eSystem Engineering (DeSE), Dubai, United Arab Emirates, 6/11/24. https://doi.org/10.1109/DeSE63988.2024.10911920

TY - GEN

T1 - AI-Enabled Diagnosis of Lumbar Spinal Stenosis from Axial MR Images Using Convolutional Neural Network and Image Explainer

AU - Oyebanji, Uthman O.

AU - Al Kafri, Ala S.

AU - Alsmadi, Hiba

AU - Alkasasbeh, Mohammad

AU - Khan, Wasiq

PY - 2025/3/11

Y1 - 2025/3/11

N2 - Lower back pain (LBP) is a global medical condition that affects more than 80% of people at least once in their lifetime. Various abnormal conditions could cause LBP. One of these conditions is Lumbar Spinal Stenosis (LSS), which is usually a serious condition, hence the need for its prompt diagnosis. The visual assessment process of magnetic resonance imaging (MRI) is expensive in terms of time and effort and prone to delays. The integration of an AI-enabled system to help clinicians in diagnosing patients with LBP is expected to alleviate the burden on radiologists and foster a less time-consuming and cost-efficient diagnostic process. In this paper, a convolutional neural network (CNN) model has been built to diagnose T2- weighted (T2W) axial MRI scans. The model detects LSS in these scans and has achieved remarkable accuracy and recall of 91% and 96%, respectively. Explainable AI (XAI) using LIME's ImageExplainer was also implemented to ensure the model offers explainable insights. This is to ensure the model is not only accurate but also reliable.

AB - Lower back pain (LBP) is a global medical condition that affects more than 80% of people at least once in their lifetime. Various abnormal conditions could cause LBP. One of these conditions is Lumbar Spinal Stenosis (LSS), which is usually a serious condition, hence the need for its prompt diagnosis. The visual assessment process of magnetic resonance imaging (MRI) is expensive in terms of time and effort and prone to delays. The integration of an AI-enabled system to help clinicians in diagnosing patients with LBP is expected to alleviate the burden on radiologists and foster a less time-consuming and cost-efficient diagnostic process. In this paper, a convolutional neural network (CNN) model has been built to diagnose T2- weighted (T2W) axial MRI scans. The model detects LSS in these scans and has achieved remarkable accuracy and recall of 91% and 96%, respectively. Explainable AI (XAI) using LIME's ImageExplainer was also implemented to ensure the model offers explainable insights. This is to ensure the model is not only accurate but also reliable.

U2 - 10.1109/DeSE63988.2024.10911920

DO - 10.1109/DeSE63988.2024.10911920

M3 - Conference contribution

BT - 2024 17th International Conference on Development in eSystem Engineering (DeSE)

PB - IEEE

T2 - 17th International Conference on Development in eSystem Engineering (DeSE)

Y2 - 6 November 2024 through 8 November 2024

ER -

AI-Enabled Diagnosis of Lumbar Spinal Stenosis from Axial MR Images Using Convolutional Neural Network and Image Explainer

Abstract

Conference

Access to Document

Fingerprint

Cite this