Dynamic computed tomography perfusion (CTP) imaging is a promising approach for acute ischemic stroke diagnosis and evaluation. Hemodynamic parametric maps of cerebral parenchyma are calculated from repeated CT scans of the first pass of iodinated contrast through the brain. It is necessary to reduce the dose of CTP for routine applications due to the high radiation exposure from the repeated scans, where image denoising is necessary to achieve a reliable diagnosis. In this article, we proposed a self-supervised deep learning method for CTP denoising, which did not require any high-dose reference images for training. The network was trained by mapping each frame of CTP to an estimation from its adjacent frames. Because the noise in the source and target was independent, this approach could effectively remove the noise. Being free from high-dose training images granted the proposed method easier adaptation to different scanning protocols. The method was validated on both simulation and a public real dataset. The proposed method achieved improved image quality compared to conventional denoising methods. On the real data, the proposed method also had improved spatial resolution and contrast-tonoise ratio compared to supervised learning which was trained on the simulation data.
Index Terms-Computed tomography, deep learning, dynamicCT perfusion, image denoising, self-supervised learning.
I. INTRODUCTIONS TROKE is the fifth cause of death and a leading cause of long term disability in the United States [1]. Stroke is caused by the interruption of blood supply to part of the cerebral tissue, which leads to a lack of oxygen in the tissue and permanent brain damage. Ischemic stroke which is caused by an obstructed blood supply, accounts for approximately 87% of all the strokes [1]. Mechanical thrombectomy has been proved to be an effective treatment for certain patients suffering from an ischemic stroke within 6 to 24 h from symptom onset [2]. Findings from imaging, such as the size of infarct cores, are important criteria to determine the patients' eligibility. Hence, imaging plays an important role in ischemic stroke Manuscript