SpineScan: Model Weights and Training Configuration for Lumbar Spine MRI Annotation and Pfirrmann Grading

<p dir="ltr">This repository includes two key files associated with the study <i>“SpineScan: A Deep Learning Model for Lumbar Spine MRI Annotation and Pfirrmann Grading Assessment.”</i></p><ul><li><b>args.yaml</b> — provides the complete trai...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Aleksandr Minin (21545072) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
الوصف
الملخص:<p dir="ltr">This repository includes two key files associated with the study <i>“SpineScan: A Deep Learning Model for Lumbar Spine MRI Annotation and Pfirrmann Grading Assessment.”</i></p><ul><li><b>args.yaml</b> — provides the complete training configuration used in the study. It defines the YOLOv8x model architecture, data preprocessing and augmentation pipeline, optimization hyperparameters, and inference thresholds, ensuring full reproducibility of the experimental setup.</li><li><b>spine_scan_yolov8x.pt</b> — contains the final trained model weights fine-tuned for automatic intervertebral disc detection and Pfirrmann grade classification on lumbar spine MRI scans.</li></ul><p dir="ltr">These files can be used together with the official YOLOv8 (Ultralytics) framework to reproduce the SpineScan model behavior or adapt it for related medical imaging tasks, such as spine segmentation or disc degeneration assessment.<br><br><b>License and Usage Notice</b></p><p dir="ltr">This item is distributed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.<br>However, the author does not permit commercial use of this content. The model and accompanying files are provided for research and educational purposes only. For any other type of use, please contact the author for permission.</p>