Related Experiment Video
Updated: May 10, 2026
07:52
Multiplexed Fluorescent Immunohistochemical Staining, Imaging, and Analysis in Histological Samples of Lymphoma
Published on: January 9, 2019
Image database analysis of Hodgkin lymphoma
Tim Schäfer1, Hendrik Schäfer, Alexander Schmitz
1Molecular Bioinformatics, Institute of Computer Science, Johann Wolfgang Goethe-University Frankfurt am Main, Frankfurt am Main, Germany.
Computational Biology and Chemistry
|June 15, 2013
Summary
This study introduces a novel image analysis pipeline for Hodgkin lymphoma (HL) digital pathology slides. The method accurately identifies malignant cells using CD30 immunostaining, aiding in HL diagnosis and research.
Area of Science:
- Digital pathology
- Computational analysis
- Oncology
Background:
- Hodgkin lymphoma (HL) diagnosis relies on morphological and immunohistochemical features.
- High-resolution digital imaging and large databases are emerging in pathology.
- Automated analysis of whole slide images presents computational challenges.
Purpose of the Study:
- To develop and implement an image analysis pipeline for high-resolution digital slides of Hodgkin lymphoma.
- To systematically analyze CD30 immunostained HL tissue images for improved pathological insights.
- To establish a novel computational approach for exploring large digital pathology image databases.
Main Methods:
- Developed a specialized image analysis pipeline for whole slide images of HL tissue.
- Utilized CD30 immunostaining to identify malignant Hodgkin lymphoma cells.
- Applied a supervised recognition method to classify pixels into predefined categories.
Main Results:
- The pipeline successfully preprocesses images, separating tissue from background.
- Pixels were classified into six categories, including CD30(+), to identify regions of interest.
- Increased CD30(+) pixels characterized nodular sclerosis HL, while non-lymphoma tissue showed low CD30(+) staining.
Conclusions:
- This is the first systematic application of image analysis to Hodgkin lymphoma tissue slides.
- The developed pipeline effectively identifies malignant cells and relevant regions in HL digital images.
- This approach offers a foundation for advanced computational exploration of HL pathology data.
