Journal
UROLOGIC CLINICS OF NORTH AMERICA
Volume 51, Issue 1, Pages 35-45Publisher
W B SAUNDERS CO-ELSEVIER INC
DOI: 10.1016/j.ucl.2023.06.007
Keywords
Renal carcinoma; Imaging; Artificial intelligence; Radiomics; Kidney; Deep learning
Categories
Ask authors/readers for more resources
Radiomics and AI algorithms have great potential in improving the diagnosis and treatment of kidney cancer, enabling tumor segmentation, classification, and prediction of treatment outcomes.
Radiomics and AI algorithms have demonstrated significant potential in improving the diagnosis and treatment of kidney cancer. ML-based kidney organ and tumor segmentation, such as the nnUNet algorithm from the Kits19 and Kits21 challenges, has achieved high Dice scores, with further research needed to assess its portability and accuracy in real-world settings. Additionally, these algorithms have shown success in classifying kidney masses into malignant and benign classes, predicting oncologic and perioperative outcomes, and calculating scoring systems such as RENAL, PADUA, and C-index. With continued improvement in areas such as renal cancer subtyping, TNM staging, pathologic tumor grading, and developing easily explainable algorithms, radiomics holds promise as a noninvasive and robust method for enhancing patient treatment of RCC.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available