In quantitative histology several image analysis software are avaible with good results in detecting objects both on morphometrical side (perimeter, diameter, area, shape factor) and densitometrical features (RGB or gray density). Classification usually is performed by estracting overall information y low-level features (relationships between pixels and objects) and high level features (histological textures/structures). In thi communication we ficus the possibility to exploit random effects approach in histopathological analisys.
Statistics and histopathology: a mixed-effects model approach to digital image analysis
BORELLI, MASSIMO;ZANCONATI, FABRIZIO;BORTOLUSSI, LUCA;GIUDICI, FABIOLA;BARBATI, GIULIA;TORELLI, LUCIO
2012-01-01
Abstract
In quantitative histology several image analysis software are avaible with good results in detecting objects both on morphometrical side (perimeter, diameter, area, shape factor) and densitometrical features (RGB or gray density). Classification usually is performed by estracting overall information y low-level features (relationships between pixels and objects) and high level features (histological textures/structures). In thi communication we ficus the possibility to exploit random effects approach in histopathological analisys.File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.