Validation of nuclear texture, density, morphometry and tissue syntactic structure analysis as prognosticators of cervical carcinoma

Citation
B. Weyn et al., Validation of nuclear texture, density, morphometry and tissue syntactic structure analysis as prognosticators of cervical carcinoma, ANAL QUAN C, 22(5), 2000, pp. 373-382
Citations number
27
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Medical Research Diagnosis & Treatment
Journal title
ANALYTICAL AND QUANTITATIVE CYTOLOGY AND HISTOLOGY
ISSN journal
0884-6812 → ACNP
Volume
22
Issue
5
Year of publication
2000
Pages
373 - 382
Database
ISI
SICI code
0884-6812(200010)22:5<373:VONTDM>2.0.ZU;2-P
Abstract
OBJECTIVE: To evaluate the performance of karyometry and histometry in the prediction of survival, recurrence and response of early-stage invasive cer vical carcinoma. STUDY DESIGN: Nuclear morphometry, chromatin texture and tissue architectur e (characterized by syntactic structure analysis) were measured using a sem iautomated image analysis system on 46 cases of Feulgen-stained tissue sect ions. The performance of the features was compared to that of clinical feat ures, reported to be the best prognosticators until now, such as age, lymph o-vascular permeation, histologic type, stage and grade. A K nearest neighb or classifier was used for classification. RESULTS: In the prediction of three-year survival, recurrence and response, syntactic structure analysis proved to be the best performer. Classificati on rates were, respectively, 100%, 94.4% and 94.5%. In all classifications, karyometric and histometric features outperformed clinical features. In ge neral, the best performing features described differences in second-order p opulation statistics (standard deviations). CONCLUSION: The results show that a quantitative analysis based on nuclear morphology, chromatin texture and histology can be considered an excellent aid in the prognosis of invasive cervical carcinoma. The measurements are n ot hampered by the Meed to undertake complete resections and are suited to daily practice when implemented in a semiautomated image analysis system.