Scholarlink

Objective <p>To evaluate a deep learning pipeline using YOLOv11 for segmentation and a custom CNN for classification to automatically detect and assess chondromalacia patella on axial knee MRI, aligning with expert clinical evaluation.</p> Materials and methods <p>A dataset of 650 axial knee MRIs was analyzed. YOLOv11 segmented the patellofemoral region, and a custom CNN classified chondromalacia. Performance was assessed using segmentation accuracy, classification accuracy, confidence scoring, and Grad-CAM-based visual explainability.</p> Results <p>The CNN achieved a test accuracy of 82.30% on 113 images, with an AUC of 0.87, indicating promising but preliminary discriminative ability. Grad-CAM maps showed reasonable agreement with expert interpretation.</p> Conclusion <p>The proposed YOLOv11-CNN pipeline demonstrated promising accuracy and may provide a potentially useful and interpretable solution for the detection and segmentation of chondromalacia patella on MRI, with the possibility of enhancing efficiency and consistency in orthopedic radiology workflows after further validation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automated detection and segmentation of chondromalacia patella on axial knee MRI using YOLOv11 and a custom CNN: a deep learning-based diagnostic model

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月13日

查看全文
  • Erdal Güngör,
  • Husam Vehbi,
  • Mehmet Batu Ertan,
  • Ahmetcan Cansın

摘要

Objective

To evaluate a deep learning pipeline using YOLOv11 for segmentation and a custom CNN for classification to automatically detect and assess chondromalacia patella on axial knee MRI, aligning with expert clinical evaluation.

Materials and methods

A dataset of 650 axial knee MRIs was analyzed. YOLOv11 segmented the patellofemoral region, and a custom CNN classified chondromalacia. Performance was assessed using segmentation accuracy, classification accuracy, confidence scoring, and Grad-CAM-based visual explainability.

Results

The CNN achieved a test accuracy of 82.30% on 113 images, with an AUC of 0.87, indicating promising but preliminary discriminative ability. Grad-CAM maps showed reasonable agreement with expert interpretation.

Conclusion

The proposed YOLOv11-CNN pipeline demonstrated promising accuracy and may provide a potentially useful and interpretable solution for the detection and segmentation of chondromalacia patella on MRI, with the possibility of enhancing efficiency and consistency in orthopedic radiology workflows after further validation.