Related Experiment Video
Updated: May 9, 2025
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
MRI Features and Apparent Diffusion Coefficient Histogram-Based Nomogram for Classifying MRI-Only Suspicious Breast
Xue Li1, Lei Jiang1, Jiayin Gao1
1Department of Radiology, National Center of Gerontology, Beijing Hospital, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing 100730, China; Graduate School of Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China.
A new nomogram combining kinetic pattern and apparent diffusion coefficient (ADC) entropy effectively classifies MRI-only suspicious lesions. This noninvasive tool shows superior performance over mean ADC values for lesion characterization.
Area of Science:
- Radiology
- Medical Imaging
- Oncology
Background:
- Accurate classification of MRI-detected suspicious lesions is crucial for patient management.
- MRI-only workflows are increasingly adopted, necessitating robust diagnostic tools.
- Apparent diffusion coefficient (ADC) histogram analysis offers quantitative imaging biomarkers.
Purpose of the Study:
- To develop and validate a nomogram for classifying MRI-only suspicious lesions.
- To integrate clinicoradiologic features with ADC-based histogram parameters.
- To assess the diagnostic performance of the developed nomogram.
Main Methods:
- Retrospective analysis of 90 patients with suspicious breast lesions on MRI.
- Inclusion of clinical data and 17 ADC histogram parameters.
- Development of a nomogram using logistic regression, validated on separate cohorts.
Main Results:
- Kinetic pattern and ADC entropy were significant predictors of malignancy (P < .01).
- The nomogram achieved a C-index of 0.820 in the training cohort and 0.728 in the validation cohort.
- The nomogram demonstrated superior performance compared to mean ADC values.
Conclusions:
- A nomogram integrating kinetic pattern and ADC entropy is a valuable tool for MRI-only suspicious lesion classification.
- This noninvasive approach aids in differentiating benign from malignant lesions.
- The nomogram offers improved diagnostic accuracy over traditional ADC metrics.
