GPU Accelerated Real Time Disease Detection
Keywords:
GPU Accelerated Computing, GPU, Convolutional Neural Networks.Abstract
Diagnosis of diseases with the help of computer aided systems is getting more prominence every day. It is like at someday in future, computer systems may take over this area reducing the workload of a doctor. Existing systems can process medical images and perform a diagnosis based on Image Processing technique and Artificial Intelligence. They are also able to perform video processing with the help of large hardware resources at the backend. This incurs significantly higher costs and space and are complex by both software and hardware. It is because video processing in real-time requires huge processing power. The system proposed here is also a real-time video processing system. But the difference with existing system is that, it works on the basis of a Graphical Processing Unit (GPU). Graphical Processing Units have high processing capabilities compared to a Central Processing Unit of a system. A GPU is composed of hundreds of cores that can handle thousands of threads simultaneously whereas a CPU can only handle a few of them at a time. Deep Learning on these images can be used to predict diseases. Use of Convolutional Neural Networks is proposed in this system. The proposed system will perform real-time analysis of medical video data and performs diagnosis. It will also suggest treatment plans based on its knowledge base, which is updated on the basis of each of its inputs. This project if implemented properly, will revolutionize the medical field. It will help the doctors to easily diagnose a patient and thus will help them to start the treatment as early as possible More specifically, for patients with cancer, this system will help the doctors to identify the growth instantaneously and thus go for the treatment. The real-time video processing will be performed with the help of a GPU which can execute thousands of threads simultaneously at a time and making the system more efficient than existing systems and it also has reduced latency. The system when tested with a lung cancer dataset, gave an accuracy of 80%.
References
- Smistad, T.L. Falch, M. Bozorgi, A.C. Elster, F. Lindseth "Medical Image Segmentation on GPUs - A Comprehensive Review",Journal of Medical Image Analysis, ELsevier, VOL. 20, 1-18, 2015
- G Yadav, "Detection of Lung Nodule using Content based Medical Image Retrieval", International Journal of Electrical, Electronics and Data Communication, 2320-2084, 2013.
- Birk, S. Koehler, M. Balzer, M. Huebner, N. V. Ruiter and J. Becker, "FPGA based Embedded Signal Processing for 3D Ultrasound Computer Tomography", Proceedings of 17th IEEE Real Time Conference (RT), 810-820, 2011.
- Sarraf, G. Tofighi, "Deep Learning-based Pipeline to Recognize Alzheimer’s Disease using fMRI Data" , Proceedings of IEEE Future Technologies Conference, 816-820, 2016.
- Pogorelov, M. Riegler, P. Halvorsen, P.T Schmidt, C. Griwodz, D. Johansen, S.L. Eskeland, T. de Lange, "GPU-accelerated Real-time Gastrointestinal Diseases Detection, Computer-Based Medical Systems (CBMS)" , Proceedings of IEEE 29th International Symposium, 251-265,2016.
- A. Elahi, A. Shahzad, M. Glavin, E. Jones, M. O’Halloran, "GPU Accelerated Confocal Microwave Imaging Algorithms for Breast Cancer Detection" , Proceedings of 9th European Conference on Antennas and Propagation (EuCAP),447-458, 2015.
- Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell, "Caffe: Convolutional architecture for fast feature embedding," in Proceedings of the ACM International Conference on Multimedia, pp. 675-678, ACM, 2014.
- Riegler, K. Pogorelov, P. Halvorsen, T. de Lange, C. Griwodz, P. T. Schmidt, S.L. Eskeland, and D, Johansen, "EIR - efcient computer aided diagnosis framework for gastrointestinal endoscopies," in Proc. of CBMI, 213-221,2016.
- Wang, W. Tavanapong, J. Wong, J. H. Oh, and P. C. de Groen, "Polypalert: Near real-time feedback during colonoscopy," Computer methods and programs in biomedicine, no. 3,415-422, 2015.
- Riegler, K. Pogorelov, J. Markussen, M. Lux, H. K. Stensland, T. de Lange, C. Griwodz, P. Halvorsen, D. Johansen, P. T. Schmidt, and S. L. Eskeland, "Computer aided disease detection system for gastrointestinal examinations," in Proc. Of MMSys,198-210, 2016.
- Pogorelov, M. Riegler, J. Markussen, H. Kvale Stensland, P. Halvorsen, C. Griwodz, S. L. Eskeland, and T. de Lange, "Efcient processing of videos in a multi auditory environment using device lending of gpus," in Proc. of MMSys, 351-360, 2016.
- Wang, W.Tavanapong, J.Wong, J.Oh and P.C.deGroen,"Near realtime retroexion detection in colonoscopy," IEEE Journal of Biomedical and Health Informatics, vol. 17, no. 1, pp. 143-152, 2013.
- Nawarathna, J. Oh, J. Muthukudage, W. Tavanapong, J. Wong, P. C. De Groen, and S. J. Tang, "Abnormal image detection in endoscopy videos using a lterbank and local binary patterns," NC,505-515, 2014.
- Wang, W. Tavanapong, J. Wong, J. Oh, and P. C. de Groen, "Computer-aided detection of retroexion in colonoscopy," in Proc. of IEEE International Symposium on Computer-Based Medical Systems (CBMS), 1-6, 2011.
- https://blogs.nvidia.com/blog/2016/09/19/deep-learning-breast-cancer-diagnosis/.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.