Related Experiment Video For clear cell renal cell carcinoma
Updated: Feb 18, 2026
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
Weakly human-supervised deep learning for real-time detection of high-grade aggressive clear cell renal cell
Rui Zhi1, Qiao Li1, Shuai Shan1
1Department of Radiology, The First Affiliated Hospital with Nanjing Medical University, Nanjing, Jiangsu Province, P.R. China.
Background:
The performance of contrast-enhanced computed tomography (CECT) in staging clear cell renal cell carcinomas (ccRCCs) and assessing tumor aggressiveness remains limited by heterogeneous and poor sensitivity.
Purpose:
This study aims to design and validate a human-AI interactive network, Kidney Tumor Staging Network (KtSNet), which leverages weakly supervised learning for real-time, efficient detection of high-grade aggressive ccRCC (HGRCC) using CECT.
Materials And Methods:
A total of 1,092 patients with ccRCC were enrolled across five cohort datasets (training/internal testing/external testing, n = 611/153/328). To achieve precise pre-surgical detection of HGRCC on CT imaging, we pretrained a self-supervised foundation model (SSFM) using a large cross-modal dataset (n = 40 000) for image restoration-based transfer learning. To develop human-AI interactive capabilities, we trained KtSNet by integrating SSFM with weakly supervised learning, enabling real-time determination of HGRCC on CT imaging through human-AI interaction.
Results:
In the internal test cohort comprising 153 patients, KtSNet demonstrated significantly higher Area Under the Curve (AUC) values for both ROC and PR curves (ROC-AUC = 0.76; PR-AUC = 0.29, F1 max: 0.441) compared to B2Net (ROC-AUC = 0.68, p = 0.040; PR-AUC = 0.22, F1 max: 0.366), RML-XGB (ROC-AUC = 0.53, p < 0.001; PR-AUC = 0.14, F1 max: 0.264), and Likert scoring (ROC-AUC values of 0.57, 0.58, and 0.70 for the three readers) in staging HGRCC. In the external validation cohort, KtSNet maintained superior AUCs on both ROC and PR curves (ROC-AUC = 0.85; PR-AUC = 0.42, F1 max: 0.529) compared to B2Net (ROC-AUC = 0.74, p = 0.002; PR-AUC = 0.21, F1 max: 0.328) and exhibited significantly higher AUCs than RML-XGB (ROC-AUC = 0.63, p = 0.002; PR-AUC = 0.23, F1 max: 0.359).
Conclusions:
The weakly human-supervised KtSNet may serve as a promising opportunity for real-time determination of HGRCC using CT imaging.
