Deep learning and radiomic feature-based blending ensemble classifier for malignancy risk prediction in cystic renal lesions

Abstract

Key points 1. Blending ensemble model achieved excellent diagnostic performance in the external validation dataset. 2. Blending ensemble model exceeded the management performance based on the Bosniak classification. 3. Histopathology criterion support ensured that blending ensemble model’s predictions were reliable.

Keywords

• Machine learning
• Bosniak-2019 classification
• Cystic renal lesions
• Radiomics