An Image Processing Method via OpenCL for Identification of Pulmonary Nodules

摘要

Lung cancer is one of the most diagnosable form of cancer worldwide. Recent researches have showed that the diagnoses of pulmonary nodules in Computed Tomography (CT) chest scans based on deep learning have made a significant progress for the medical diagnoses. However, the existence of many false positives or the high costs of processing time make it impossible to apply to clinical practice. Toward this purpose, this paper proposed a new image processing method to improve the performance by exploiting the power of acceleration technologies via OpenCL. We use parallel programming and pipeline models to parallelize the CT image preprocessing, and classify them by 3D CNNs according to the significant differences between nodules and non-nodules in 3D shapes. Extensive experimental results have shown that image processing can be accelerated significantly on GPU. In addition, the experiments on 500 patients indicate that our proposed method improved the performance by 12.5% and achieved 97.78% sensitivity rate for segmentation.