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.
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.
Authors: Antonio Ruiz; Olcay Sertel; Manuel Ujaldón; Umit Catalyurek; Joel Saltz; Metin N Gurcan Journal: Int J Data Min Bioinform Date: 2009 Impact factor: 0.667
Authors: Aneesa S Majid; Ellen Shaw de Paredes; Richard D Doherty; Neil R Sharma; Xavier Salvador Journal: Radiographics Date: 2003 Jul-Aug Impact factor: 5.333
Authors: A A Kolchev; D V Pasynkov; I A Egoshin; I V Kliouchkin; O O Pasynkova Journal: Int J Comput Assist Radiol Surg Date: 2021-11-02 Impact factor: 2.924
Authors: Shane M Summers; Eric J Chin; Brit J Long; Ronald D Grisell; John G Knight; Kurt W Grathwohl; John L Ritter; Jeffrey D Morgan; Jose Salinas; Lorne H Blackbourne Journal: West J Emerg Med Date: 2016-03-02