WDRIV-Net: a weighted ensemble transfer learning to improve automatic type stratification of lumbar intervertebral disc bulge, prolapse, and herniation
Abstract The degeneration of the intervertebral discs in the lumbar spine is the common cause of neurological and physical dysfunctions and chronic disability of patients, which can be stratified into single—(e.g., disc herniation, prolapse, or bulge) and comorbidity-type degeneration (e.g., simulta...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | BioMedical Engineering OnLine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12938-025-01341-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861762355625984 |
|---|---|
| author | Ichiro Nakamoto Hua Chen Rui Wang Yan Guo Wei Chen Jie Feng Jianfeng Wu |
| author_facet | Ichiro Nakamoto Hua Chen Rui Wang Yan Guo Wei Chen Jie Feng Jianfeng Wu |
| author_sort | Ichiro Nakamoto |
| collection | DOAJ |
| description | Abstract The degeneration of the intervertebral discs in the lumbar spine is the common cause of neurological and physical dysfunctions and chronic disability of patients, which can be stratified into single—(e.g., disc herniation, prolapse, or bulge) and comorbidity-type degeneration (e.g., simultaneous presence of two or more conditions), respectively. A sample of lumbar magnetic resonance imaging (MRI) images from multiple clinical hospitals in China was collected and used in the proposal assessment. We devised a weighted transfer learning framework WDRIV-Net by ensembling four pre-trained models including Densenet169, ResNet101, InceptionV3, and VGG19. The proposed approach was applied to the clinical data and achieved 96.25% accuracy, surpassing the benchmark ResNet101 (87.5%), DenseNet169 (82.5%), VGG19 (88.75%), InceptionV3 (93.75%), and other state-of-the-art (SOTA) ensemble deep learning models. Furthermore, improved performance was observed as well for the metric of the area under the curve (AUC), producing a ≥ 7% increase versus other SOTA ensemble learning, a ≥ 6% increase versus most-studied models, and a ≥ 2% increase versus the baselines. WDRIV-Net can serve as a guide in the initial and efficient type screening of complex degeneration of lumbar intervertebral discs (LID) and assist in the early-stage selection of clinically differentiated treatment options. |
| format | Article |
| id | doaj-art-d4e7e650698b4d059963087b590b275d |
| institution | Kabale University |
| issn | 1475-925X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BioMedical Engineering OnLine |
| spelling | doaj-art-d4e7e650698b4d059963087b590b275d2025-02-09T12:47:30ZengBMCBioMedical Engineering OnLine1475-925X2025-02-0124112110.1186/s12938-025-01341-4WDRIV-Net: a weighted ensemble transfer learning to improve automatic type stratification of lumbar intervertebral disc bulge, prolapse, and herniationIchiro Nakamoto0Hua Chen1Rui Wang2Yan Guo3Wei Chen4Jie Feng5Jianfeng Wu6School of Internet Economics and Business, Fujian University of TechnologyDepartment of Radiology, Pingtan Comprehensive Experimentation Area HospitalDepartment of Neurosurgery, Pingtan Comprehensive Experimentation Area HospitalSchool of Internet Economics and Business, Fujian University of TechnologySchool of Internet Economics and Business, Fujian University of TechnologyDepartment of Radiology, Pingtan Comprehensive Experimentation Area HospitalDepartment of Neurosurgery, Pingtan Comprehensive Experimentation Area HospitalAbstract The degeneration of the intervertebral discs in the lumbar spine is the common cause of neurological and physical dysfunctions and chronic disability of patients, which can be stratified into single—(e.g., disc herniation, prolapse, or bulge) and comorbidity-type degeneration (e.g., simultaneous presence of two or more conditions), respectively. A sample of lumbar magnetic resonance imaging (MRI) images from multiple clinical hospitals in China was collected and used in the proposal assessment. We devised a weighted transfer learning framework WDRIV-Net by ensembling four pre-trained models including Densenet169, ResNet101, InceptionV3, and VGG19. The proposed approach was applied to the clinical data and achieved 96.25% accuracy, surpassing the benchmark ResNet101 (87.5%), DenseNet169 (82.5%), VGG19 (88.75%), InceptionV3 (93.75%), and other state-of-the-art (SOTA) ensemble deep learning models. Furthermore, improved performance was observed as well for the metric of the area under the curve (AUC), producing a ≥ 7% increase versus other SOTA ensemble learning, a ≥ 6% increase versus most-studied models, and a ≥ 2% increase versus the baselines. WDRIV-Net can serve as a guide in the initial and efficient type screening of complex degeneration of lumbar intervertebral discs (LID) and assist in the early-stage selection of clinically differentiated treatment options.https://doi.org/10.1186/s12938-025-01341-4Lumbar spine degenerationLumbar intervertebral discsTransfer learningDeep learningMagnetic resonance imagingWeighted ensemble learning |
| spellingShingle | Ichiro Nakamoto Hua Chen Rui Wang Yan Guo Wei Chen Jie Feng Jianfeng Wu WDRIV-Net: a weighted ensemble transfer learning to improve automatic type stratification of lumbar intervertebral disc bulge, prolapse, and herniation BioMedical Engineering OnLine Lumbar spine degeneration Lumbar intervertebral discs Transfer learning Deep learning Magnetic resonance imaging Weighted ensemble learning |
| title | WDRIV-Net: a weighted ensemble transfer learning to improve automatic type stratification of lumbar intervertebral disc bulge, prolapse, and herniation |
| title_full | WDRIV-Net: a weighted ensemble transfer learning to improve automatic type stratification of lumbar intervertebral disc bulge, prolapse, and herniation |
| title_fullStr | WDRIV-Net: a weighted ensemble transfer learning to improve automatic type stratification of lumbar intervertebral disc bulge, prolapse, and herniation |
| title_full_unstemmed | WDRIV-Net: a weighted ensemble transfer learning to improve automatic type stratification of lumbar intervertebral disc bulge, prolapse, and herniation |
| title_short | WDRIV-Net: a weighted ensemble transfer learning to improve automatic type stratification of lumbar intervertebral disc bulge, prolapse, and herniation |
| title_sort | wdriv net a weighted ensemble transfer learning to improve automatic type stratification of lumbar intervertebral disc bulge prolapse and herniation |
| topic | Lumbar spine degeneration Lumbar intervertebral discs Transfer learning Deep learning Magnetic resonance imaging Weighted ensemble learning |
| url | https://doi.org/10.1186/s12938-025-01341-4 |
| work_keys_str_mv | AT ichironakamoto wdrivnetaweightedensembletransferlearningtoimproveautomatictypestratificationoflumbarintervertebraldiscbulgeprolapseandherniation AT huachen wdrivnetaweightedensembletransferlearningtoimproveautomatictypestratificationoflumbarintervertebraldiscbulgeprolapseandherniation AT ruiwang wdrivnetaweightedensembletransferlearningtoimproveautomatictypestratificationoflumbarintervertebraldiscbulgeprolapseandherniation AT yanguo wdrivnetaweightedensembletransferlearningtoimproveautomatictypestratificationoflumbarintervertebraldiscbulgeprolapseandherniation AT weichen wdrivnetaweightedensembletransferlearningtoimproveautomatictypestratificationoflumbarintervertebraldiscbulgeprolapseandherniation AT jiefeng wdrivnetaweightedensembletransferlearningtoimproveautomatictypestratificationoflumbarintervertebraldiscbulgeprolapseandherniation AT jianfengwu wdrivnetaweightedensembletransferlearningtoimproveautomatictypestratificationoflumbarintervertebraldiscbulgeprolapseandherniation |