Related Experiment Video
Updated: Jul 20, 2026
Ovine Lumbar Intervertebral Disc Degeneration Model Utilizing a Lateral Retroperitoneal Drill Bit Injury
Published on: May 25, 2017
Automatic detection, classification, and segmentation of sagittal MR images for diagnosing prolapsed lumbar
Md Abu Sayed1, G M Mahmudur Rahman2, Md Sherajul Islam3
1Khulna University of Engineering and Technology, Khulna, 9203, Bangladesh.
Abstract:
Magnetic resonance (MR) images are commonly used to diagnose prolapsed lumbar intervertebral disc (PLID). However, for a computer-aided diagnostic (CAD) system, distinguishing between pathological abnormalities of PLID in MR images is a challenging and intricate task. Here, we propose a comprehensive model for the automatic detection and cropping of regions of interest (ROI) from sagittal MR images using the YOLOv8 framework to solve this challenge. We also propose weighted average ensemble (WAE) classification and segmentation models for the classification and the segmentation, respectively. YOLOv8 has good detection accuracy for both the lumbar region (mAP50 = 99.50%) and the vertebral disc (mAP50 = 99.40%). The use of ROI approaches enhances the accuracy of individual models. Specifically, the classification accuracy of the WAE classification model reaches 97.64%, while the segmentation model achieves a Dice value of 95.72%. This automatic technique would improve the diagnostic process by offering enhanced accuracy and efficiency in the assessment of PLID.
Insights
This study introduces an automated system using YOLOv8 and weighted average ensemble models for diagnosing prolapsed lumbar intervertebral discs (PLID) from MR images, enhancing diagnostic accuracy and efficiency.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Healthcare
- Radiology
Background:
- Magnetic resonance (MR) imaging is crucial for diagnosing prolapsed lumbar intervertebral disc (PLID).
- Automating the detection and analysis of PLID in MR images presents significant challenges for computer-aided diagnostic (CAD) systems.
- Accurate identification of pathological abnormalities is essential for effective patient treatment.
Purpose of the Study:
- To develop a comprehensive model for automatic detection and cropping of regions of interest (ROI) in sagittal MR images for PLID diagnosis.
- To implement weighted average ensemble (WAE) classification and segmentation models to improve diagnostic accuracy.
- To enhance the efficiency and precision of PLID assessment using advanced AI techniques.
Main Methods:
- Utilized the YOLOv8 framework for accurate detection and cropping of lumbar regions and vertebral discs from MR images.
- Developed and applied weighted average ensemble (WAE) models for both classification and segmentation tasks.
- Integrated ROI-based approaches to refine the performance of individual diagnostic models.
Main Results:
- YOLOv8 achieved high detection accuracy for the lumbar region (mAP50 = 99.50%) and vertebral discs (mAP50 = 99.40%).
- The WAE classification model demonstrated a classification accuracy of 97.64%.
- The WAE segmentation model achieved a Dice score of 95.72%, indicating precise delineation of abnormalities.
Conclusions:
- The proposed comprehensive model effectively automates the detection, classification, and segmentation of PLID in MR images.
- The integration of YOLOv8 and WAE models significantly improves diagnostic accuracy and efficiency.
- This automated technique offers a promising advancement for clinical assessment of PLID.
Related Concept Videos
01:29Herniated Intervertebral Disc l: Introduction
01:27Degenerative Disc Disease I: Introduction