Please use this identifier to cite or link to this item:
|Title:||Automatic segmentation of routinely H&E stained microscopic images by combining support vector machine clustering and active contour models|
Σπυρίδωνος, Παναγιώτα Π.
Κάβουρας, Διονύσης Α.
|Contributors:||Νικηφορίδης, Γεώργιος Χ.|
|Item type:||Journal article|
|Publisher:||Journal of Reproductive Medicine|
|Abstract:||To develop a method for the automated segmentation of images of routinely hematoxylin-eosin (H-E)-stained microscopic sections to guarantee correct results in computer-assisted microscopy. Clinical material was composed 50 H-E-stained biopsies of astrocytomas and 50 H-E-stained biopsies of urinary bladder cancer. The basic idea was to use a support vector machine clustering (SVMC) algorithm to provide gross segmentation of regions holding nuclei and subsequently to refine nuclear boundary detection with active contours. The initialization coordinates of the active contour model were defined using a SVMC pixel-based classification algorithm that discriminated nuclear regions from the surrounding tissue. Starting from the boundaries of these regions, the snake fired and propagated until converging to nuclear boundaries. The method was validated for 2 different types of H-E-stained images. Results were evaluated by 2 histopathologists. On average, 94% of nuclei were correctly delineated. The proposed algorithm could be of value in computer-based systems for automated interpretation of microscopic images.|
|Citation:||Glotsos, D., Spyridonos, P., Cavouras, D., Ravazoula, I., Dadioti, P., et al. (December 2004). Automatic segmentation of routinely H&E stained microscopic images by combining support vector machine clustering and active contour models. Analytical and Quantitative Cytology and Histology. 26(6). pp. 331-341. Journal of Reproductive Medicine: 2004.|
|Journal:||Analytical and Quantitative Cytology and Histology|
|Type of Journal:||With a review process (peer review)|
|License:||Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες|
|Appears in Collections:||Δημοσιεύσεις|
Files in This Item:
There are no files associated with this item.
This item is licensed under a Creative Commons License