PMID- 20426165
OWN - NLM
STAT- MEDLINE
DCOM- 20100607
LR  - 20190907
VI  - 12
IP  - Pt 2
DP  - 2009
TI  - Graph-based pancreatic islet segmentation for early type 2 diabetes mellitus on 
      histopathological tissue.
PG  - 633-40
AB  - It is estimated that in 2010 more than 220 million people will be affected by 
      type 2 diabetes mellitus (T2DM). Early evidence indicates that specific markers 
      for alpha and beta cells in pancreatic islets of Langerhans can be used for early 
      T2DM diagnosis. Currently, the analysis of such histological tissues is manually 
      performed by trained pathologists using a light microscope. To objectify 
      classification results and to reduce the processing time of histological tissues, 
      an automated computational pathology framework for segmentation of pancreatic 
      islets from histopathological fluorescence images is proposed. Due to high 
      variability in the staining intensities for alpha and beta cells, classical 
      medical imaging approaches fail in this scenario. The main contribution of this 
      paper consists of a novel graph-based segmentation approach based on cell nuclei 
      detection with randomized tree ensembles. The algorithm is trained via a cross 
      validation scheme on a ground truth set of islet images manually segmented by 4 
      expert pathologists. Test errors obtained from the cross validation procedure 
      demonstrate that the graph-based computational pathology analysis proposed is 
      performing competitively to the expert pathologists while outperforming a 
      baseline morphological approach.
FAU - Floros, Xenofon
AU  - Floros X
AD  - Department of Computer Science, ETH Zurich, Switzerland. 
      xenofon.floros@inf.ethz.ch
FAU - Fuchs, Thomas J
AU  - Fuchs TJ
FAU - Rechsteiner, Markus P
AU  - Rechsteiner MP
FAU - Spinas, Giatgen
AU  - Spinas G
FAU - Moch, Holger
AU  - Moch H
FAU - Buhmann, Joachim M
AU  - Buhmann JM
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
PL  - Germany
TA  - Med Image Comput Comput Assist Interv
JT  - Medical image computing and computer-assisted intervention : MICCAI ... 
      International Conference on Medical Image Computing and Computer-Assisted 
      Intervention
JID - 101249582
SB  - IM
MH  - *Algorithms
MH  - *Artificial Intelligence
MH  - Diabetes Mellitus, Type 2/*pathology
MH  - Humans
MH  - Image Enhancement/methods
MH  - Image Interpretation, Computer-Assisted/*methods
MH  - Islets of Langerhans/*pathology
MH  - Microscopy
MH  - Pattern Recognition, Automated/*methods
MH  - Reproducibility of Results
MH  - Sensitivity and Specificity
EDAT- 2009/01/01 00:00
MHDA- 2010/06/09 06:00
CRDT- 2010/04/30 06:00
PHST- 2010/04/30 06:00 [entrez]
PHST- 2009/01/01 00:00 [pubmed]
PHST- 2010/06/09 06:00 [medline]
AID - 10.1007/978-3-642-04271-3_77 [doi]
PST - ppublish
SO  - Med Image Comput Comput Assist Interv. 2009;12(Pt 2):633-40. doi: 
      10.1007/978-3-642-04271-3_77.