naa a22 4500 510807976 CHVBK 20180411083427.0 cr unu---uuuuu 180411e20130701xx s 000 0 eng 10.1007/s11548-013-0813-y doi (NATIONALLICENCE)springer-10.1007/s11548-013-0813-y Multimodality GPU-based computer-assisted diagnosis of breast cancer using ultrasound and digital mammography images [Elektronische Daten] [Konstantinos Sidiropoulos, Spiros Kostopoulos, Dimitris Glotsos, Emmanouil Athanasiadis, Nikos Dimitropoulos, John Stonham, Dionisis Cavouras] Purpose To improve the computer-aided diagnosis of breast lesions, by designing a pattern recognition system (PR-system) on commercial graphics processing unit (GPU) cards using parallel programming and textural information from multimodality imaging. Material and methods Patients with histologically verified breast lesions underwent both ultrasound (US) and digital mammography (DM), lesions were outlined on the images by an experienced radiologist, and textural features were calculated. The PR-system was designed to provide highest possible precision by programming in parallel the multiprocessors of the NVIDIA's GPU cards, GeForce 8800GT or 580GTX, and using the CUDA programming framework and C++. The PR-system was built around the probabilistic neural network classifier, and its performance was evaluated by a re-substitution method, for estimating the system's highest accuracy, and by the external cross-validation method, for assessing the PR-system's unbiased accuracy to new, "unseen” by the system, data. Results Classification accuracies for discriminating malignant from benign lesions were as follows: 85.5% using US-features alone, 82.3% employing DM features alone, and 93.5% combining US and DM features. Mean accuracy to new "unseen” data for the combined US and DM features was 81%. Those classification accuracies were about 10% higher than accuracies achieved on a single CPU, using sequential programming methods, and 150-fold faster. Conclusion The proposed PR-system improves breast-lesion discrimination accuracy, it may be redesigned on site when new verified data are incorporated in its depository, and it may serve as a second opinion tool in a clinical environment. CARS, 2013 Breast cancer nationallicence Graphics Processing Units nationallicence Multimodality nationallicence Parallel processing nationallicence Pattern recognition nationallicence Sidiropoulos Konstantinos School of Engineering and Design, Brunel University West London, UB8 3PH, Uxbridge, Middlesex, UK aut Kostopoulos Spiros Medical Image and Signal Processing (medisp) Lab, Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos Street, Egaleo, 122 10, Athens, Greece aut Glotsos Dimitris Medical Image and Signal Processing (medisp) Lab, Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos Street, Egaleo, 122 10, Athens, Greece aut Athanasiadis Emmanouil Medical Image and Signal Processing (medisp) Lab, Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos Street, Egaleo, 122 10, Athens, Greece aut Dimitropoulos Nikos Delta Digital Diagnostic Center, Semitelou 6, 11528, Athens, Greece aut Stonham John School of Engineering and Design, Brunel University West London, UB8 3PH, Uxbridge, Middlesex, UK aut Cavouras Dionisis Medical Image and Signal Processing (medisp) Lab, Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos Street, Egaleo, 122 10, Athens, Greece aut International Journal of Computer Assisted Radiology and Surgery Springer Berlin Heidelberg 8/4(2013-07-01), 547-560 1861-6410 8:4<547 2013 8 11548 https://doi.org/10.1007/s11548-013-0813-y text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11548-013-0813-y text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Sidiropoulos Konstantinos School of Engineering and Design, Brunel University West London, UB8 3PH, Uxbridge, Middlesex, UK aut NATIONALLICENCE 700 1- Kostopoulos Spiros Medical Image and Signal Processing (medisp) Lab, Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos Street, Egaleo, 122 10, Athens, Greece aut NATIONALLICENCE 700 1- Glotsos Dimitris Medical Image and Signal Processing (medisp) Lab, Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos Street, Egaleo, 122 10, Athens, Greece aut NATIONALLICENCE 700 1- Athanasiadis Emmanouil Medical Image and Signal Processing (medisp) Lab, Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos Street, Egaleo, 122 10, Athens, Greece aut NATIONALLICENCE 700 1- Dimitropoulos Nikos Delta Digital Diagnostic Center, Semitelou 6, 11528, Athens, Greece aut NATIONALLICENCE 700 1- Stonham John School of Engineering and Design, Brunel University West London, UB8 3PH, Uxbridge, Middlesex, UK aut NATIONALLICENCE 700 1- Cavouras Dionisis Medical Image and Signal Processing (medisp) Lab, Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos Street, Egaleo, 122 10, Athens, Greece aut NATIONALLICENCE 773 0- International Journal of Computer Assisted Radiology and Surgery Springer Berlin Heidelberg 8/4(2013-07-01), 547-560 1861-6410 8:4<547 2013 8 11548 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer