Related Experiment Video
Updated: Jun 10, 2026
15:48
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
Quantitative morphometry by image analysis of normal, hyperplastic and cancerous ductal breasts
Jie Gao1, Michael A McNutt, Weining Yi
1Department of Pathology, School of Basic Medical Science, Peking University Health Science Center, Beijing, China.
Analytical and Quantitative Cytology and Histology
|August 13, 2010
Summary
Quantitative image analysis of breast ductal proliferations revealed significant differences between normal tissue, hyperplasia, and carcinoma in situ. These findings support automated image recognition for improved breast cancer diagnosis.
Area of Science:
- Biomedical Engineering
- Pathology
- Computational Biology
Background:
- Accurate differentiation of breast ductal proliferations is crucial for patient management.
- Histologic and cytologic criteria are standard but can be subjective.
- Objective quantitative methods may enhance diagnostic accuracy.
Purpose of the Study:
- To identify quantitative variables useful in distinguishing between histologic diagnoses of breast ductal proliferations.
- To evaluate the potential of computer-aided image analysis for differential diagnosis.
Main Methods:
- A semiautomatic image analysis method was developed for quantitative assessment of breast ductal proliferations.
- Seventeen morphometric variables were calculated for 80 cases, including normal breast duct (DN), ductal hyperplasia (DH), ductal carcinoma in situ (DCIS), and invasive ductal carcinoma (INV).
Main Results:
- Fifteen of 17 variables showed statistically significant differences between ductal hyperplasia (DH) and ductal carcinoma in situ (DCIS) (p < 0.05).
- Seven variables demonstrated statistically significant differences between normal breast duct (DN) and ductal hyperplasia (DH) (p < 0.05).
Conclusions:
- Quantitative morphometric analysis of selected variables allows for significant statistical distinction between diagnostic groups.
- These findings support the development of automated computerized image recognition for differential diagnosis of breast lesions.
