Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: Fuhrman grading

Sortuj według:

Ogranicz wyniki do:

Ensemble of classifiers and wavelet transformation for improved recognition of Fuhrman grading in clear-cell renal carcinoma

Kruk M., Kurek J., Osowski S., Koktysz R., Swiderski B., Markiewicz T.

Biocybernetics and Biomedical Engineering

2017

Vol. 37, no. 3

357--364

The paper presents an improved system to recognition of Fuhrman grading in clear-cell renal carcinoma using an ensemble of classifiers. The novelty of solution includes the segmentation applying wavelet transformation in preprocessing stage, application of few selection methods for feature generation and using the ensemble of classifiers in final recognition step. The wavelet transformation is a very efficient tool for image de-noising and enhancing the edges of cell nuclei. The important distinction to other approaches is that diagnostic features of nuclei, based on the texture, geometry, color and histogram, are selected by using few methods, each relying on different mechanism of selection. These different sets of features have enabled creating the ensemble of classifiers based on the support vector machine and random forest, both cooperating with them. Such approach has led to the significant increase of the quality factors in comparison to the best existing results: sensitivity (the average of this solution 94.3% compared to 91.5%) and specificity (the average 98.6% compared to 97.5%.

Computer-assisted Fuhrman grading system for the analysis of clear-cell renal carcinoma: a pilot study

Kruk M., Osowski S., Kozłowski W., Koktysz R., Słodkowska J., Markiewicz T.

Przegląd Elektrotechniczny

2013

R. 89, nr 3a

268--270

The paper presents an automatic computer system for evaluation of the Fuhrman degree in renal carcinoma, of the accuracy comparable to the human expert. The solution uses the combined methods of mathematical morphology, Hough transform and neural networks for the estimation of Fuhrman degree of the carcinoma clarocellular cells, based on the microscopic kidney image. The results of numerical experiments have shown that the average discrepancy rate between the score of our system and the human expert results estimated on the basis of almost 300 cells is below 10% and this accuracy is acceptable in the medical practice.

Praca przedstawia podejście komputerowe do automatycznej oceny stopnia skali Fuhrmana w przypadku raka nerki. Ocena dotyczy mikroskopowego obrazu nerek. Proponowane rozwiązanie stosuje zespół metod obejmujących morfologię matematyczną, transformację Hougha, sieci neuronowe oraz grupowanie danych wielowymiarowych. Proponowane rozwiązanie zostało sprawdzone na zbiorze prawie 300 obrazów nerek z różnym stopniem zaawansowania choroby nowotworowej.