Automated lumbar intervertebral disc identification and herniation detection in MR images using cascade CNN architecture
Objective: Identifying herniated discs in MRI scans is inherently challenging due to the small size, irregular shape, and complex appearance of the affected regions. Conventional approaches typically rely on semi-automated region-of-interest (ROI) selection and single-model classification using eith...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S235291482500036X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850033130549805056 |
|---|---|
| author | Md Abu Sayed Ashiqur Rahman Sadman Mohammad Nasif Sudipto Halder Akram Hossain Hasan Ahmed Muhammad Abdul Kadir |
| author_facet | Md Abu Sayed Ashiqur Rahman Sadman Mohammad Nasif Sudipto Halder Akram Hossain Hasan Ahmed Muhammad Abdul Kadir |
| author_sort | Md Abu Sayed |
| collection | DOAJ |
| description | Objective: Identifying herniated discs in MRI scans is inherently challenging due to the small size, irregular shape, and complex appearance of the affected regions. Conventional approaches typically rely on semi-automated region-of-interest (ROI) selection and single-model classification using either axial or sagittal views, limiting diagnostic performance. This study aims to develop an automated, accurate, and efficient system for the detection and classification of lumbar intervertebral disc herniation using deep learning models applied to axial and sagittal MR images. Methods: A YOLO-based framework was developed to automatically identify lumbar intervertebral discs (IVD1-5) and extract ROIs from MR images. Attention-enhanced and fine-tuned VGG19 and ResNet50 models were employed to analyze axial and sagittal images for herniation detection. A decision fusion strategy was used to combine the classification probabilities from both models to further enhance accuracy. The dataset underwent extensive preprocessing and augmentation to improve model robustness and generalization. Results: The proposed approach demonstrated exceptional performance in detection and classification tasks. For detection, the model achieved mAP50 scores of 95.18 % (axial IVD1-5), 99.50 % (lumbar regions), and 94.87 % (sagittal IVD1-5). Classification accuracy reached 97.05 % for axial images and 97.45 % for sagittal images, increasing to 98.09 % with decision fusion. Conclusion: Designed to assist physicians, especially during high-demand periods such as pandemics, this approach has the potential to improve diagnostic efficiency and reduce clinical workload. |
| format | Article |
| id | doaj-art-a7ad7e360e4c40daa7b4a767acb269e1 |
| institution | DOAJ |
| issn | 2352-9148 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj-art-a7ad7e360e4c40daa7b4a767acb269e12025-08-20T02:58:19ZengElsevierInformatics in Medicine Unlocked2352-91482025-01-015510164810.1016/j.imu.2025.101648Automated lumbar intervertebral disc identification and herniation detection in MR images using cascade CNN architectureMd Abu Sayed0Ashiqur Rahman1Sadman Mohammad Nasif2Sudipto Halder3Akram Hossain4Hasan Ahmed5Muhammad Abdul Kadir6Department of Biomedical Physics and Technology, University of Dhaka, Dhaka, 1000, BangladeshDepartment of Biomedical Physics and Technology, University of Dhaka, Dhaka, 1000, BangladeshDepartment of Computer Science Engineering, Khulna University of Engineering & Technology, Khulna, 9203, BangladeshDepartment of Mechatronics Engineering, Khulna University of Engineering & Technology, Khulna, 9203, BangladeshDepartment of Biomedical Physics and Technology, University of Dhaka, Dhaka, 1000, BangladeshTechnical Technical Expert-Environment, UNOPS South Asia Multi-Country Office, Dhaka, 1212, BangladeshDepartment of Biomedical Physics and Technology, University of Dhaka, Dhaka, 1000, Bangladesh; Corresponding author.Objective: Identifying herniated discs in MRI scans is inherently challenging due to the small size, irregular shape, and complex appearance of the affected regions. Conventional approaches typically rely on semi-automated region-of-interest (ROI) selection and single-model classification using either axial or sagittal views, limiting diagnostic performance. This study aims to develop an automated, accurate, and efficient system for the detection and classification of lumbar intervertebral disc herniation using deep learning models applied to axial and sagittal MR images. Methods: A YOLO-based framework was developed to automatically identify lumbar intervertebral discs (IVD1-5) and extract ROIs from MR images. Attention-enhanced and fine-tuned VGG19 and ResNet50 models were employed to analyze axial and sagittal images for herniation detection. A decision fusion strategy was used to combine the classification probabilities from both models to further enhance accuracy. The dataset underwent extensive preprocessing and augmentation to improve model robustness and generalization. Results: The proposed approach demonstrated exceptional performance in detection and classification tasks. For detection, the model achieved mAP50 scores of 95.18 % (axial IVD1-5), 99.50 % (lumbar regions), and 94.87 % (sagittal IVD1-5). Classification accuracy reached 97.05 % for axial images and 97.45 % for sagittal images, increasing to 98.09 % with decision fusion. Conclusion: Designed to assist physicians, especially during high-demand periods such as pandemics, this approach has the potential to improve diagnostic efficiency and reduce clinical workload.http://www.sciencedirect.com/science/article/pii/S235291482500036XDisc herniationLumbar intervertebral discIVDYOLOv11ROI detectionAttention module |
| spellingShingle | Md Abu Sayed Ashiqur Rahman Sadman Mohammad Nasif Sudipto Halder Akram Hossain Hasan Ahmed Muhammad Abdul Kadir Automated lumbar intervertebral disc identification and herniation detection in MR images using cascade CNN architecture Informatics in Medicine Unlocked Disc herniation Lumbar intervertebral disc IVD YOLOv11 ROI detection Attention module |
| title | Automated lumbar intervertebral disc identification and herniation detection in MR images using cascade CNN architecture |
| title_full | Automated lumbar intervertebral disc identification and herniation detection in MR images using cascade CNN architecture |
| title_fullStr | Automated lumbar intervertebral disc identification and herniation detection in MR images using cascade CNN architecture |
| title_full_unstemmed | Automated lumbar intervertebral disc identification and herniation detection in MR images using cascade CNN architecture |
| title_short | Automated lumbar intervertebral disc identification and herniation detection in MR images using cascade CNN architecture |
| title_sort | automated lumbar intervertebral disc identification and herniation detection in mr images using cascade cnn architecture |
| topic | Disc herniation Lumbar intervertebral disc IVD YOLOv11 ROI detection Attention module |
| url | http://www.sciencedirect.com/science/article/pii/S235291482500036X |
| work_keys_str_mv | AT mdabusayed automatedlumbarintervertebraldiscidentificationandherniationdetectioninmrimagesusingcascadecnnarchitecture AT ashiqurrahman automatedlumbarintervertebraldiscidentificationandherniationdetectioninmrimagesusingcascadecnnarchitecture AT sadmanmohammadnasif automatedlumbarintervertebraldiscidentificationandherniationdetectioninmrimagesusingcascadecnnarchitecture AT sudiptohalder automatedlumbarintervertebraldiscidentificationandherniationdetectioninmrimagesusingcascadecnnarchitecture AT akramhossain automatedlumbarintervertebraldiscidentificationandherniationdetectioninmrimagesusingcascadecnnarchitecture AT hasanahmed automatedlumbarintervertebraldiscidentificationandherniationdetectioninmrimagesusingcascadecnnarchitecture AT muhammadabdulkadir automatedlumbarintervertebraldiscidentificationandherniationdetectioninmrimagesusingcascadecnnarchitecture |