Distinguishing benign renal masses from malignant renal tumours, and further differentiating indolent from aggressive renal cancers, on computed tomography (CT) scans remains challenging. Here, the authors develop deep learning models for distinguishing benign from malignant renal masses, and differentiating indolent from aggressive renal tumours in a large cohort of preoperative CT scans, obtaining high accuracy and a strong association with clinical outcomes.
- Ying Xiong
- Linpeng Yao
- Shuo Wang