Document Detail


Neural network-based segmentation and classification system for automated grading of histologic sections of bladder carcinoma.
MedLine Citation:
PMID:  12508689     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
OBJECTIVE: To develop an image analysis system for automated nuclear segmentation and classification of histologic bladder sections employing quantitative nuclear features.
STUDY DESIGN: Ninety-two cases were classified into three classes by experienced pathologists according to the WHO grading system: 18 cases as grade 1, 45 as grade 2, and 29 as grade 3. Nuclear segmentation was performed by means of an artificial neural network (ANN)-based pixel classification algorithm, and each case was represented by 36 nuclei features. Automated grading of bladder tumor histologic sections was performed by an ANN classifier implemented in a two-stage hierarchic tree.
RESULTS: On average, 95% of the nuclei were correctly detected. At the first stage of the hierarchic tree, classifier performance in discriminating between cases of grade 1 and 2 and cases of grade 3 was 89%. At the second stage, 79% of grade 1 cases were correctly distinguished from grade 2 cases.
CONCLUSION: The proposed image analysis system provides the means to reduce subjectivity in grading bladder tumors and may contribute to more accurate diagnosis and prognosis since it relies on nuclear features, the value of which has been confirmed.
Authors:
Panagiota Spyridonos; Dionisios Cavouras; Panagiota Ravazoula; George Nikiforidis
Related Documents :
16172339 - Hemangiomas of infancy: treatment of ulceration in the head and neck.
6615089 - Disopyramide-induced urinary retention. report of nine cases and review of the literature.
3191359 - Differing interpretations by pathologists of the pt category and grade of transitional ...
14732799 - Cavernous hemangiomas of lungs and liver in an asymptomatic girl.
9592899 - Surface-based hemangioma of bone: three case studies and a review of the literature.
12690339 - Dural cavernous hemangioma originating from superior petrosal sinus.
6644509 - Meconium thorax.
16149929 - Odontoma-like malformation in a permanent maxillary central incisor subsequent to traum...
4037549 - Stercoral perforation of the colon. concepts of operative management.
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Analytical and quantitative cytology and histology / the International Academy of Cytology [and] American Society of Cytology     Volume:  24     ISSN:  0884-6812     ISO Abbreviation:  Anal. Quant. Cytol. Histol.     Publication Date:  2002 Dec 
Date Detail:
Created Date:  2003-01-01     Completed Date:  2003-06-06     Revised Date:  2014-11-05    
Medline Journal Info:
Nlm Unique ID:  8506819     Medline TA:  Anal Quant Cytol Histol     Country:  United States    
Other Details:
Languages:  eng     Pagination:  317-24     Citation Subset:  IM    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Automation
Carcinoma / classification*,  pathology*,  ultrastructure
Cell Nucleus / ultrastructure
Diagnosis, Computer-Assisted / methods
Histological Techniques
Humans
Image Processing, Computer-Assisted / methods
Neural Networks (Computer)*
Tumor Markers, Biological / analysis
Urinary Bladder Neoplasms / classification*,  pathology*,  ultrastructure
Chemical
Reg. No./Substance:
0/Tumor Markers, Biological

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Discriminant analysis of image karyometric variables in benign and malignant melanocytic skin lesion...
Next Document:  DNA cytometry in pleomorphic adenomas with cytologic atypia.