| Autor: |
Murthy V; Lexington High School., Hou L; Stony Brook University., Samaras D; Stony Brook University, Ecole Centrale Paris., Kurc TM; Stony Brook University, Oak Ridge National Laboratory., Saltz JH; Stony Brook University, Stony Brook University Hospital. |
| Jazyk: |
angličtina |
| Zdroj: |
IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision [IEEE Winter Conf Appl Comput Vis] 2017 Mar; Vol. 2017, pp. 834-841. Date of Electronic Publication: 2017 May 15. |
| DOI: |
10.1109/WACV.2017.98 |
| Abstrakt: |
Classifying the various shapes and attributes of a glioma cell nucleus is crucial for diagnosis and understanding of the disease. We investigate the automated classification of the nuclear shapes and visual attributes of glioma cells, using Convolutional Neural Networks (CNNs) on pathology images of automatically segmented nuclei. We propose three methods that improve the performance of a previously-developed semi-supervised CNN. First, we propose a method that allows the CNN to focus on the most important part of an image-the image's center containing the nucleus. Second, we inject (concatenate) pre-extracted VGG features into an intermediate layer of our Semi-Supervised CNN so that during training, the CNN can learn a set of additional features. Third, we separate the losses of the two groups of target classes (nuclear shapes and attributes) into a single-label loss and a multi-label loss in order to incorporate prior knowledge of inter-label exclusiveness. On a dataset of 2078 images, the combination of the proposed methods reduces the error rate of attribute and shape classification by 21.54% and 15.07% respectively compared to the existing state-of-the-art method on the same dataset. |
| Databáze: |
MEDLINE |
| Externí odkaz: |
|
