Abstract | ||
---|---|---|
In this study, high-resolution detection was aimed with an approach based on the simultaneous consideration of spatial and spectral relationships in the detection of mitotic cells in digital multispectral histopathologic images. Thanks to these studies in computer-aided diagnosis (CAD), the detection of mitotic cells which are normally difficult to examine and detect by microscopes can be performed automatically by experts. In this context, multispectral histopathologic images of mitotic and non-mitotic cells were extracted in the first step. In this case, training and test samples with the same spatial and spectral dimensions are obtained. Subsequently, classifier models were developed for different sets of training clusters using support vector machines (SVM), random forests (RF), naive Bayes (NB), and k-Nearest Neighbor classification methods. For comparison purposes, the numerical results obtained by different methods are presented in the experiments and results section. |
Year | Venue | Keywords |
---|---|---|
2017 | Signal Processing and Communications Applications Conference | histopathological images,mitotic cells detection,multispectral imaging,spatial features,spectral features |
Field | DocType | ISSN |
CAD,Computer vision,Signal processing,Naive Bayes classifier,Pattern recognition,Medical imaging,Computer science,Multispectral image,Support vector machine,Artificial intelligence,Classifier (linguistics),Random forest | Conference | 2165-0608 |
Citations | PageRank | References |
0 | 0.34 | 4 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cukur, Huseyin | 1 | 2 | 1.06 |
Gökhan Bilgin | 2 | 62 | 13.18 |