Title | ||
---|---|---|
Classification of tumor regions in histopathological images using convolutional neural networks. |
Abstract | ||
---|---|---|
In recent years, the number of deaths caused by cancer diseases are quite high when compared to other diseases. Early diagnosis of cancer and its associated diseases is crucial in terms of treating the disease. With the development of imaging devices, it has become possible to image, track, and treat patients with the computer assisted diagnosis (CAD) systems. Especially with high-resolution scanners, it is possible to detect automatically the tumoral regions in tissues and organs by CAD based systems. In this study, convolutional neural networks (CNN), one of the deep learning methods, were applied to the data set consists of images for the detection of the metastasis regions in sentinel lymph nodes prepared by Radboud University Medical Center and University Medical Center Utrecht. According to the result, it was observed that the applied CNN model had 99.15% accuracy in detection of tumor regions. In addition, the classification performance of the proposed CNN model in 2000 images which were included in the training data set was 95%. When the proposed CNN model is analyzed in terms of time, it can be seen that the training phase is very slow. However, the prediction of the proposed model is very fast after the model is created. |
Year | Venue | Keywords |
---|---|---|
2018 | Signal Processing and Communications Applications Conference | Histopathological images,deep learning,convolutional neural networks,classification |
Field | DocType | ISSN |
CAD,Metastasis,Training set,Pattern recognition,Computer science,Convolutional neural network,Computer-aided diagnosis,Solid modeling,Artificial intelligence,Deep learning | Conference | 2165-0608 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Koray Gunduz | 1 | 0 | 0.34 |
Abdulkadir Albayrak | 2 | 6 | 2.86 |
Gökhan Bilgin | 3 | 62 | 13.18 |
M. Elif Karsligil | 4 | 73 | 13.69 |