Contact us to get your publication featured here!
- Histological image classification using biologically interpretable shape-based features
, , and
Sonal is a PhD candidate at the Georgia Institute of Technology and is currently a graduate researcher in the BioMedical Informatics and Bio-Imaging Laboratory.
The paper discusses biologically interpretable shape-based features for automatic histological image classification.Notably,
The case examined renal tumor histological subtype (4 subtypes) classification. It was found that:
- Automatic color segmentation with color normalization, to overcome color variations in tissue samples
- Shape-based features using Fourier shape descriptors
To read the full publication go to http://www.biomedcentral.com/1471-2342/13/9/abstract
- Shape-based features complement or outperform other traditional features
- Emerging patterns are easily interpretable