Automatic detection, classification, and segmentation of sagittal MR images for diagnosing prolapsed lumbar intervertebral disc
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 com...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84301-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559585711718400 |
|---|---|
| author | Md. Abu Sayed G. M. Mahmudur Rahman Md. Sherajul Islam Md. Alimul Islam Jeongwon Park Hasan Ahmed Akram Hossain Rahat Shahrior |
| author_facet | Md. Abu Sayed G. M. Mahmudur Rahman Md. Sherajul Islam Md. Alimul Islam Jeongwon Park Hasan Ahmed Akram Hossain Rahat Shahrior |
| author_sort | Md. Abu Sayed |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-1cee73c7a5e341ebaac6cf315d435e80 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-1cee73c7a5e341ebaac6cf315d435e802025-01-05T12:22:41ZengNature PortfolioScientific Reports2045-23222025-01-0115111610.1038/s41598-024-84301-7Automatic detection, classification, and segmentation of sagittal MR images for diagnosing prolapsed lumbar intervertebral discMd. Abu Sayed0G. M. Mahmudur Rahman1Md. Sherajul Islam2Md. Alimul Islam3Jeongwon Park4Hasan Ahmed5Akram Hossain6Rahat Shahrior7Khulna University of Engineering and TechnologyKhulna University of Engineering and TechnologyKhulna University of Engineering and TechnologyKhulna University of Engineering and TechnologyDepartment of Electrical and Biomedical Engineering, University of NevadaKhulna University of Engineering and TechnologyKhulna University of Engineering and TechnologyKhulna University of Engineering and TechnologyAbstract 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.https://doi.org/10.1038/s41598-024-84301-7Magnetic resonance imagingProlapsed lumbar intervertebral discYOLOv8Weighted average ensembleROI |
| spellingShingle | Md. Abu Sayed G. M. Mahmudur Rahman Md. Sherajul Islam Md. Alimul Islam Jeongwon Park Hasan Ahmed Akram Hossain Rahat Shahrior Automatic detection, classification, and segmentation of sagittal MR images for diagnosing prolapsed lumbar intervertebral disc Scientific Reports Magnetic resonance imaging Prolapsed lumbar intervertebral disc YOLOv8 Weighted average ensemble ROI |
| title | Automatic detection, classification, and segmentation of sagittal MR images for diagnosing prolapsed lumbar intervertebral disc |
| title_full | Automatic detection, classification, and segmentation of sagittal MR images for diagnosing prolapsed lumbar intervertebral disc |
| title_fullStr | Automatic detection, classification, and segmentation of sagittal MR images for diagnosing prolapsed lumbar intervertebral disc |
| title_full_unstemmed | Automatic detection, classification, and segmentation of sagittal MR images for diagnosing prolapsed lumbar intervertebral disc |
| title_short | Automatic detection, classification, and segmentation of sagittal MR images for diagnosing prolapsed lumbar intervertebral disc |
| title_sort | automatic detection classification and segmentation of sagittal mr images for diagnosing prolapsed lumbar intervertebral disc |
| topic | Magnetic resonance imaging Prolapsed lumbar intervertebral disc YOLOv8 Weighted average ensemble ROI |
| url | https://doi.org/10.1038/s41598-024-84301-7 |
| work_keys_str_mv | AT mdabusayed automaticdetectionclassificationandsegmentationofsagittalmrimagesfordiagnosingprolapsedlumbarintervertebraldisc AT gmmahmudurrahman automaticdetectionclassificationandsegmentationofsagittalmrimagesfordiagnosingprolapsedlumbarintervertebraldisc AT mdsherajulislam automaticdetectionclassificationandsegmentationofsagittalmrimagesfordiagnosingprolapsedlumbarintervertebraldisc AT mdalimulislam automaticdetectionclassificationandsegmentationofsagittalmrimagesfordiagnosingprolapsedlumbarintervertebraldisc AT jeongwonpark automaticdetectionclassificationandsegmentationofsagittalmrimagesfordiagnosingprolapsedlumbarintervertebraldisc AT hasanahmed automaticdetectionclassificationandsegmentationofsagittalmrimagesfordiagnosingprolapsedlumbarintervertebraldisc AT akramhossain automaticdetectionclassificationandsegmentationofsagittalmrimagesfordiagnosingprolapsedlumbarintervertebraldisc AT rahatshahrior automaticdetectionclassificationandsegmentationofsagittalmrimagesfordiagnosingprolapsedlumbarintervertebraldisc |