Deep learning using contrast-enhanced ultrasound images to predict the nuclear grade of clear cell renal cell carcinoma
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.A deep learning model effectively distinguishes high-grade from low-grade clear cell renal cell carcinoma (ccRCC) using contrast-enhanced ultrasound (CEUS) images. This non-invasive AI approach shows promise for accurate ccRCC grading.
Area Of Science
- Medical Imaging
- Artificial Intelligence in Oncology
- Renal Cell Carcinoma Research
Background
- Clear cell renal cell carcinoma (ccRCC) grading is crucial for treatment decisions.
- Distinguishing low-grade from high-grade ccRCC non-invasively remains a clinical challenge.
- Contrast-enhanced ultrasound (CEUS) offers a dynamic imaging modality for renal tumor assessment.
Purpose Of The Study
- To evaluate a deep learning (DL) model's efficacy in differentiating low-grade (I-II) from high-grade (III-IV) ccRCC.
- To assess the performance of CEUS-based AI in ccRCC classification.
- To validate the non-invasive grading capability of the proposed DL model.
Main Methods
- Retrospective analysis of 177 Fuhrman-graded ccRCC cases using CEUS images.
- Development of a RepVGG-based deep learning model for ccRCC grade classification.
- Performance evaluation using sensitivity, specificity, accuracy, and AUC; Class Activation Mapping (CAM) for interpretability.
Main Results
- The DL model achieved 74.8% sensitivity, 79.1% specificity, and 77.0% accuracy in the test set.
- Area Under the Curve (AUC) reached 0.852, indicating strong discriminative power.
- CAM visualization highlighted specific image regions contributing to the model's high-grade ccRCC predictions.
Conclusions
- Deep learning models utilizing CEUS images can accurately differentiate low-grade from high-grade ccRCC.
- The proposed AI approach offers a non-invasive method for ccRCC grading.
- CEUS combined with DL shows potential for improving ccRCC management and treatment planning.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
