TY - GEN
T1 - Pathological image analysis using the GPU
T2 - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007
AU - Ruiz, Antonio
AU - Sertel, Olcay
AU - Ujaldon, Manuel
AU - Catalyurek, Umit
AU - Saltz, Joel
AU - Gurcan, Metin
PY - 2007
Y1 - 2007
N2 - Neuroblastoma is one of the most malignant childhood cancers affecting infants mostly. The current prognosis is based on microscopic examination of slides by expert pathologists, a process that is error-prone, time consuming and may lead to inter- and intra-reader variations. Therefore, we are developing a Computer Aided Prognosis (CAP) system which provides computerized image analysis to assist pathologist in their prognosis. Since this system operates on relatively large-scale images and requires sophisticated algorithms, it takes a long time to process whole-slide images. In this paper, we propose a novel and efficient approach for the execution of a CAP system for neuroblastoma prognosis, using the graphics processing unit (GFU). By lever-aging high memory bandwidth and strong floating point operation capabilities of the GFU, our goal is to achieve order of magnitude reduction in the overall execution time as compared to that on a CPU alone. The proposed approach was tested on a set of testing images with a promising accuracy of 99.4% and an execution performance gain factor up to 45 times compared to C++ code running on the CPU.
AB - Neuroblastoma is one of the most malignant childhood cancers affecting infants mostly. The current prognosis is based on microscopic examination of slides by expert pathologists, a process that is error-prone, time consuming and may lead to inter- and intra-reader variations. Therefore, we are developing a Computer Aided Prognosis (CAP) system which provides computerized image analysis to assist pathologist in their prognosis. Since this system operates on relatively large-scale images and requires sophisticated algorithms, it takes a long time to process whole-slide images. In this paper, we propose a novel and efficient approach for the execution of a CAP system for neuroblastoma prognosis, using the graphics processing unit (GFU). By lever-aging high memory bandwidth and strong floating point operation capabilities of the GFU, our goal is to achieve order of magnitude reduction in the overall execution time as compared to that on a CPU alone. The proposed approach was tested on a set of testing images with a promising accuracy of 99.4% and an execution performance gain factor up to 45 times compared to C++ code running on the CPU.
UR - https://www.scopus.com/pages/publications/49049085035
U2 - 10.1109/BIBM.2007.15
DO - 10.1109/BIBM.2007.15
M3 - Conference contribution
AN - SCOPUS:49049085035
SN - 0769530311
SN - 9780769530314
T3 - Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007
SP - 78
EP - 85
BT - Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007
Y2 - 2 November 2007 through 4 November 2007
ER -