Related Experiment Video
Updated: Jan 18, 2026
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
3.3K
MRI-based diffusion weighted imaging and diffusion kurtosis imaging grading of clear cell renal cell carcinoma using
Wenjing Zheng1,2, Xin Luo3, Yangyingqiu Liu3
1Department of Medical Imaging, Binzhou Medical University, Yantai, Shandong 264003, P.R. China.
Oncology Letters
|September 8, 2025
Summary
A deep learning (DL) model using MRI diffusion imaging accurately predicts clear cell renal cell carcinoma (ccRCC) grade. This non-invasive approach aids in personalized treatment decisions for ccRCC patients.
Area of Science:
- Oncology
- Radiology
- Artificial Intelligence
Background:
- Clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal cell carcinoma (RCC), accounting for approximately 85% of cases.
- Accurate preoperative pathological grading of ccRCC is crucial for guiding treatment strategies and predicting patient outcomes.
- Current grading methods often rely on invasive procedures or post-surgical analysis, highlighting the need for non-invasive predictive tools.
Purpose of the Study:
- To validate the efficacy of a deep learning (DL) model for the non-invasive, preoperative prediction of ccRCC pathological grading.
- To assess the performance of DL algorithms utilizing diffusion-weighted imaging (DWI) and diffusion kurtosis imaging (DKI) MRI sequences.
Main Methods:
- A DL algorithm was developed and trained using DWI and DKI MRI sequences from 79 ccRCC patients (40 low-grade, 39 high-grade).
- Image parameters including apparent diffusion coefficient (ADC), axial kurtosis (Ka), fractional anisotropy, radial kurtosis (Kr), and mean kurtosis (MK) were calculated.
- The VGG-16 model served as the backbone architecture for validating the DL model's predictive performance.
Main Results:
- The DL model demonstrated accurate prediction of ccRCC pathological grading.
- Mean MK achieved the highest accuracy (76.04%), precision (81.48%), F1-score (76.04%), and recall (74.08%) among tested parameters.
- Kr and Ka also showed promising predictive values, indicating the utility of DKI parameters.
Conclusions:
- The established DL model, leveraging MRI DWI and DKI sequences, can accurately predict ccRCC pathological grade non-invasively.
- This AI-driven approach shows significant potential for improving preoperative assessment and guiding individualized treatment decisions for ccRCC patients.
- Further validation and integration into clinical workflows could enhance patient management and outcomes in renal cell carcinoma.
Related Concept Videos
01:28Imaging Studies I: Kidney, Ureter, and Bladder Studies
288
Kidney, Ureter, and Bladder (KUB) StudiesKidney, Ureter, and Bladder (KUB) studies are standard diagnostic imaging procedures used to assess the anatomy of the urinary system. They are commonly utilized for patients experiencing abdominal pain or urinary symptoms. By using a simple X-ray of the abdomen, KUB studies can reveal structural and pathological abnormalities within the kidneys, ureters, and bladder. These studies are particularly valuable in diagnosing kidney stones, urinary...
288
01:27Imaging Studies IV: Magnetic Resonance Imaging
227
Introduction:Magnetic Resonance Imaging, or MRI, can include a specialized imaging technique of the urinary system known as Magnetic Resonance Urography (MRU). This radiation-free technique uses strong magnetic fields and radio waves to produce detailed images with the help of a computer. MRU is particularly effective for visualizing fluid-filled structures like the kidneys, ureters, and bladder.Applications of MRI in the Genitourinary SystemKidneys and Ureters: MRI detects tumors, cysts,...
227