Related Experiment Video
Updated: May 5, 2026
Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone
Published on: April 8, 2015
Automatic cell classification and quantification with machine learning in immunohistochemistry images
Pikting Cheung1, Wei Zhang2, Muhammad Shehzad Khan1,3
1Department of Physics, City University of Hong Kong, Hong Kong, SAR, China.
Insights
An innovative mathematical method precisely quantifies lymphoma cells in immunohistochemistry (IHC) images. This automated approach improves diagnostic accuracy for lymphoma classification, reducing human error.
Area of Science:
- Oncology
- Computational Pathology
- Medical Imaging Analysis
Background:
- Lymphoma incidence is increasing, necessitating accurate classification methods.
- Immunohistochemistry (IHC) is crucial for lymphoma classification.
- Manual cell counting in IHC images is time-consuming and prone to error.
Purpose of the Study:
- To develop an automated mathematical methodology for precise quantification and spatial analysis of immunopositive and immunonegative cells in CD3-stained lymphoma IHC images.
- To reduce human intervention and improve the accuracy of cell counting in lymphoma diagnosis.
Main Methods:
- Developed an algorithm using a mathematical color model for cell differentiation.
- Employed morphological erosion, algorithmic transformations, and customized histogram equalization for feature enhancement.
- Utilized refined local thresholding for improved classification precision.
- Applied a customized circular Hough transform for cell counting and spatial data assessment.
Main Results:
- Achieved an overall accuracy of 93.98% for automatic cell counts in IHC image samples.
- Automated counts and location information were cross-validated by three pathology specialists.
- Demonstrated effective and reliable performance of the automated approach.
Conclusions:
- The innovative framework enhances lymphoma cell counting accuracy in IHC images.
- Combines physics-based color understanding with machine learning for improved diagnosis.
- Reduces the risks of human error in lymphoma classification.
Abstract:
The incidence of lymphoma, a cancer that affects both humans and animals, has witnessed a significant increase. In response, immunohistochemistry (IHC) has become an essential tool for its classification. This prompted us to develop an innovative mathematical methodology for the precise quantification of immunopositive and immunonegative cells, along with their spatial analysis, in CD3-stained lymphoma IHC images. Our approach involves integrating an algorithm based on a mathematical color model for cell differentiation, employing the distinctive morphological erosion, algorithmic transformations, and customized histogram equalization to enhance features. Refined local thresholding enhances classification precision. Additionally, a customized circular Hough transform quantifies cell counts and assesses their spatial data. The algorithms accurately enumerate cell types, reducing human intervention and providing total numbers and spatial information on detected cells within tissue specimens. Evaluation of IHC image samples revealed an overall accuracy of 93.98% for automatic cell counts. The automatic counts and location information were cross-validated by three pathology specialists, highlighting the effectiveness and reliability of our automated approach. Our innovative framework enhances lymphoma cell counting accuracy in IHC images by combining physics-based color understanding with machine learning, thereby improving diagnosis and reducing the risks of human error.
