WDRIV-Net: a weighted ensemble transfer learning to improve automatic type stratification of lumbar intervertebral disc bulge, prolapse, and herniation

• Published in: Biomedical engineering online Vol. 24; no. 1; pp. 11 - 21
• Main Authors: Nakamoto, Ichiro, Chen, Hua, Wang, Rui, Guo, Yan, Chen, Wei, Feng, Jie, Wu, Jianfeng
• Format: Journal Article
• Language: English
• Published: London BioMed Central 06.02.2025; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Accuracy; Adult; Algorithms; Automation; Biomaterials; Biomedical Engineering and Bioengineering; Biomedical Engineering/Biotechnology; Biotechnology; Classification; Comorbidity; Deep Learning; Degeneration; Degeneration (Pathology); Diagnosis; Disease; Engineering; Ensemble learning; Female; Humans; Image processing; Image Processing, Computer-Assisted - methods; Intervertebral Disc - diagnostic imaging; Intervertebral Disc Degeneration - diagnostic imaging; Intervertebral Disc Displacement - diagnostic imaging; Intervertebral discs; Intervertebral disk; Literature reviews; Lumbar intervertebral discs; Lumbar spine degeneration; Lumbar Vertebrae - diagnostic imaging; Machine Learning; Magnetic Resonance Imaging; Male; Medical examination; Medical imaging equipment; Methods; Middle Aged; Neural networks; Neurological diseases; Observational learning; Performance evaluation; Prolapse; Spinal diseases; Spine; Spine (lumbar); Transfer learning; Trends; Vertebrae, Lumbar; Weighted ensemble learning; China; Deep learning; Lumbar spine degeneration; Weighted ensemble learning; Magnetic resonance imaging; Transfer learning; Lumbar intervertebral discs
• ISSN: 1475-925X; 1475-925X
• DOI: 10.1186/s12938-025-01341-4

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.