The Artificial Intelligence and Computer Vision Lab of the Department of Computer Science, Cochin University of Science and Technology (Cusat), has developed a technology for the grading of breast cancer in association with the Intel Technology Pvt. Ltd.
A novel automated technique based on semi-supervised learning framework, combined with the deep neural network-based generative adversarial model, was developed by the researchers for discriminating the different cancer grades. The proposed work has been published in the IEEE Journal of Biomedical and Health Informatics , according to an official release.
The model is based on semi supervised learning (SSL) and it can considerably reduce the need of annotated data, besides reducing the time and cost. Intel has developed a hardware architecture with Intel Xeon scalable processors using distributed training to reduce the training time and to support the experimentation with multiple image resolutions without memory constraints. Four Intel Xeon scalable processors are used as a compute cluster without any deep learning accelerators for the model training, said the communication.
The work was carried out under the expertise of Dr. Madhu S. Nair, Associate Professor, Artificial Intelligence and Computer Vision Lab, and Dr. Asha Das, former Research Scholar, Department of Computer Science at Cusat and at present Assistant Professor, Department of Computer Science, Union Christian College, Aluva, with the technical support of Mr. Vinod Kumar Devarampati, Intel Technology Asia Pvt Ltd, Singapore, it said.