Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos, Egaleo, 12210 Athens, Greece.
Magn Reson Imaging. 2013 Jun;31(5):761-70. doi: 10.1016/j.mri.2012.10.029. Epub 2013 Jan 17.
The aim was to design a pattern-recognition (PR) system for discriminating between normal and pathological knee articular cartilage of the medial femoral (MFC) and tibial condyles (MTC). The data set comprised segmented regions of interest (ROIs) from coronal and sagittal 3-T magnetic resonance images of the MFC and MTC cartilage of young patients, 28 with abnormality-free knee and 16 with pathological findings. The PR system was designed employing the probabilistic neural network classifier, textural features from the segmented ROIs and the leave-one-out evaluation method, while the PR system's precision to "unseen" data was assessed by employing the external cross-validation method. Optimal system design was accomplished on a consumer graphics processing unit (GPU) using Compute Unified Device Architecture parallel programming. PR system design on the GPU required about 3.5 min against 15 h on a CPU-based system. Highest classification accuracies for the MFC and MTC cartilages were 93.2% and 95.5%, and accuracies to "unseen" data were 89% and 86%, respectively. The proposed PR system is housed in a PC, equipped with a consumer GPU, and it may be easily retrained when new verified data are incorporated in its repository and may be of value as a second-opinion tool in a clinical environment.
目的是设计一种模式识别（PR）系统，用于区分正常和病理膝关节内侧股骨（MFC）和胫骨髁（MTC）关节软骨。数据集包括来自年轻患者 MFC 和 MTC 软骨的冠状和矢状 3-T 磁共振图像的分割感兴趣区域（ROI），其中 28 例膝关节无异常，16 例存在病理发现。PR 系统采用概率神经网络分类器、分割 ROI 的纹理特征和留一法评估方法进行设计，而 PR 系统对“未见”数据的精度则采用外部交叉验证方法进行评估。最佳系统设计是在消费级图形处理单元（GPU）上使用计算统一设备架构并行编程完成的。GPU 上的 PR 系统设计大约需要 3.5 分钟，而基于 CPU 的系统则需要 15 小时。对于 MFC 和 MTC 软骨，分类准确率最高分别为 93.2%和 95.5%，对“未见”数据的准确率分别为 89%和 86%。所提出的 PR 系统安装在配备消费级 GPU 的 PC 上，当新的经过验证的数据被纳入其存储库中时，它可以很容易地进行重新训练，并且可能在临床环境中作为辅助诊断工具具有价值。
