Automated region of interest retrieval and classification using spectral analysis
2008
Automated Image Analysis in Pathology
Sample size: 73
publication
Evidence: moderate
Author Information
Author(s): Myriam Oger, Philippe Belhomme, Jacques Klossa, Jean-Jacques Michels, Abderrahim Elmoataz
Primary Institution: F. Baclesse Cancer Centre
Hypothesis
Can spectral analysis improve automated region of interest retrieval and classification in pathology?
Conclusion
Spectral Analysis is effective for automating the diagnosis of cancers and sorting isolated cells.
Supporting Evidence
- Spectral analysis was used to segment breast tumor tissue into stroma and epithelial zones.
- The method allowed for the selection of representative patches of each histological type.
- In blood smears, spectral analysis helped sort isolated blood cells into two classes.
Takeaway
This study shows that computers can help doctors find important parts of images of tumors and blood samples more easily.
Methodology
The study used spectral analysis for image segmentation and classification on whole slide images of breast tumors and blood smears.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website