No abstract

Purpose: Despite the indispensable role of x-ray computed tomography (CT) in diagnostic medicine, the associated harmful ionizing radiation dose is a major concern, as it may cause genetic diseases and cancer. Decreasing patients' exposure can reduce the radiation dose and hence the related risks, but it would inevitably induce higher quantum noise. Supervised deep learning techniques have been used to train deep neural networks for denoising low-dose CT (LDCT) images, but the success of such strategies requires massive sets of pixel-level paired LDCT and normal-dose CT (NDCT) images, which are rarely available in real clinical practice. Our purpose is to mitigate the data scarcity problem for deep learning-based LDCT denoising. Methods: To solve this problem, we devised a shift-invariant property-based neural network that uses only the LDCT images to characterize both the inherent pixel correlations and the noise distribution, shaping into our probabilistic self-learning (PSL) framework. The AAPM Low-dose CT Challenge dataset was used to train the network. Both simulated datasets and real dataset were employed to test the denoising performance as well as the model generalizability. The performance was compared to a conventional method (total variation (TV)-based), a popular self-learning method (noise2void (N2V)), and a well-known unsupervised learning method (CycleGAN) by using both qualitative visual inspection and quantitative metrics including peak signal-noise-ratio (PSNR), structural similarity index (SSIM) and contrast-to-noise-ratio (CNR). The standard deviations (STD) of selected flat regions were also calculated for comparison. Results: The PSL method can improve the averaged PSNR/SSIM values from 27.61/0.5939 (LDCT) to 30.50/0.6797. By contrast, the averaged PSNR/SSIM values were 31.49/0.7284 (TV), 29.43/ 0.6699 (N2V), and 29.79/0.6992 (CycleGAN). The averaged STDs of selected flat regions were calculated to be 132.3 HU (LDCT), 25.77 HU (TV), 19.95 HU (N2V), 75.06 HU (CycleGAN), 60.62 HU (PSL) and 57.28 HU (NDCT). As for the low-contrast lesion detectability quantification, the CNR were calculated to be 0.202 (LDCT), 0.356 (TV), 0.372 (N2V), 0.383 (CycleGAN), 0.399 (PSL), and 0.359 (NDCT). By visual inspection, we observed that the proposed PSL method can deliver a noise-suppressed and detail-preserved image, while the TV-based method would lead to the blocky artifact, the N2V method would produce over-smoothed structures and CT value biased effect, and the CycleGAN method would generate slightly noisy results with inaccurate CT values. We also verified the generalizability of the PSL method, which exhibited superior denoising performance among various testing datasets with different data distribution shifts. Conclusions: A deep learning-based convolutional neural network can be trained without paired datasets. Qualitatively visual inspection showed the proposed PSL method can achieve superior denoising performance than all the competitors, despite that the employed quantitative metrics in terms of PS...

Monte Carlo (MC) simulation is considered the gold standard method for radiotherapy dose calculation. However, achieving high precision requires a large number of simulation histories, which is time-consuming. The use of computer graphics processing units (GPUs) has greatly accelerated MC simulation and allows dose calculation within a few minutes for a typical radiotherapy treatment plan. However, some clinical applications demand real-time efficiency for MC dose calculation. To tackle this problem, we have developed a real-time, deep learning (DL)-based dose denoiser that can be plugged into a current GPU-based MC dose engine to enable real-time MC dose calculation. We used two different acceleration strategies to achieve this goal: (1) we applied voxel unshuffle and voxel shuffle operators to decrease the input and output sizes without any information loss, and (2) we decoupled the 3D volumetric convolution into a 2D axial convolution and a 1D slice convolution. In addition, we used a weakly supervised learning framework to train the network, which greatly reduces the size of the required training dataset and thus enables fast fine-tuning-based adaptation of the trained model to different radiation beams. Experimental results show that the proposed denoiser can run in as little as 39 ms, which is 11.6 times faster than the baseline model. As a result, the whole MC dose calculation pipeline can be finished within ∼ 0.15 s, including both GPU MC dose calculation and DL-based denoising, achieving the real-time efficiency needed for some radiotherapy applications, such as online adaptive radiotherapy.

No abstract

Abrasive-free polishing (AFP) has been developed for processing of soft, hygroscopic KH2PO4 (KDP) crystal according to its deliquescence property. A new nonaqueous abrasive-free slurry, composed of water, dodecanol, and Triton X-100, is designed for the AFP process. In this slurry, the function of water, which is enveloped into surfactant micelles and has no direct contact with KDP crystal in the absence of polishing pressure, is to dissolve KDP surface material in the AFP. The experiments show that the material removal rate (MRR) is nonlinearly dependent on polishing pressure and platen speed; MRR as high as 700nmmin−1 at certain polishing condition and a scratch-free polished KDP surface with root-mean-square roughness lower than 2 nm are achieved by the AFP process. Moreover, the repeat utilization times of the slurry are experimentally determined in KDP AFP with a relatively high removal rate and a smooth surface.