Related Experiment Video
Updated: Sep 20, 2025
15:48
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
22.6K
Apparent Diffusion Coefficient-Based Radiomic Nomogram in Sinonasal Squamous Cell Carcinoma: A Preliminary Study on
Naier Lin1, Sihui Yu, Zhipeng Xia
1From the Department of Radiology, Eye & ENT Hospital, Fudan University, Shanghai Medical College, Shanghai, China.
Journal of Computer Assisted Tomography
|June 8, 2022
Summary
This study developed a radiomic nomogram using diffusion-weighted imaging to differentiate low- and high-grade sinonasal squamous cell carcinomas, achieving high accuracy in distinguishing tumor grades.
Area of Science:
- Radiology
- Oncology
- Medical Imaging
Background:
- Accurate preoperative grading of sinonasal squamous cell carcinomas is crucial for treatment planning.
- Differentiating between low- and high-grade tumors preoperatively remains a clinical challenge.
Purpose of the Study:
- To develop and validate a nomogram model for differentiating low- and high-grade sinonasal squamous cell carcinomas.
- To combine radiomic features and clinical characteristics for improved preoperative tumor grading.
Main Methods:
- 174 patients undergoing diffusion-weighted imaging were included, split into training (60%) and testing (40%) cohorts.
- Least Absolute Shrinkage and Selection Operator (LASSO) regression was used for feature selection and radiomic signature (radscore) construction.
- Model performance was assessed using AUC, calibration curves, and decision curve analysis.
Main Results:
- A radscore comprising 9 radiomic features was developed.
- Both radscore and clinical stage were identified as independent predictors.
- The nomogram demonstrated superior performance (AUC 0.92 training, 0.91 testing) compared to radscore or clinical stage alone, with good calibration and clinical utility.
Conclusions:
- An apparent diffusion coefficient-based radiomic nomogram effectively differentiates low- and high-grade sinonasal squamous cell carcinomas.
- This model shows potential as a non-invasive tool for preoperative tumor grading.
