Related Experiment Video
Updated: Oct 19, 2025
15:48
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
22.7K
Textural differences based on apparent diffusion coefficient maps for discriminating pT3 subclasses of rectal
Zhi-Hua Lu1, Kai-Jian Xia2, Heng Jiang3
1Department of Radiology, Changshu Hospital Affiliated to Soochow University, Changshu No. 1 People's Hospital, Changshu 215500, Jiangsu Province, China. luzhihua79@163.com.
World Journal of Clinical Cases
|September 20, 2021
Summary
Texture analysis of apparent diffusion coefficient (ADC) maps shows promise in distinguishing early-stage (pT3a) rectal cancer from advanced stages (pT3b-c). These findings could improve diagnostic accuracy in rectal cancer staging.
Area of Science:
- Radiology
- Oncology
- Medical Imaging
Background:
- Accurate discrimination between pT3a and pT3b-c rectal cancer using high-resolution MRI is challenging.
- Texture analysis (TA) offers potential to enhance diagnostic precision in rectal cancer staging.
Purpose of the Study:
- To evaluate the utility of TA on apparent diffusion coefficient (ADC) maps for differentiating pT3a rectal adenocarcinomas from pT3b-c tumors.
- To assess the diagnostic performance of specific TA features in rectal cancer staging.
Main Methods:
- A case-control study included 59 patients with pT3 rectal adenocarcinoma undergoing diffusion-weighted imaging (DWI).
- First-order (skewness, kurtosis, uniformity) and second-order (energy, entropy, inertia, correlation) texture features were extracted from whole-lesion ADC maps.
- Receiver operating characteristic (ROC) curve analysis was employed to determine diagnostic value.
Main Results:
- Skewness, energy, and entropy derived from ADC maps showed significant differences between pT3a and pT3b-c tumors.
- Individual AUCs for skewness, energy, and entropy were 0.686, 0.657, and 0.747, respectively.
- Logistic regression combining these features achieved an AUC of 0.775, with 69.0% sensitivity and 83.3% specificity for differentiating pT3a from pT3b-c tumors.
Conclusions:
- Texture analysis features derived from ADC maps demonstrate potential for differentiating pT3a rectal adenocarcinomas from pT3b-c tumors.
- ADC-based TA may serve as a valuable tool to improve the accuracy of rectal cancer staging.
