The global pandemic of coronavirus disease 2019 (COVID-19) has resulted in an increased demand for testing, diagnosis, and treatment. Reverse transcription polymerase chain reaction (RT-PCR) is the definitive test for the diagnosis of COVID-19; however, chest X-ray radiography (CXR) is a fast, effective, and affordable test that identifies the possible COVID-19-related pneumonia. This study investigates the feasibility of using a deep learning-based decision-tree classifier for detecting COVID-19 from CXR images. The proposed classifier comprises three binary decision trees, each trained by a deep learning model with convolution neural network based on the PyTorch frame. The first decision tree classifies the CXR images as normal or abnormal. The second tree identifies the abnormal images that contain signs of tuberculosis, whereas the third does the same for COVID-19. The accuracies of the first and second decision trees are 98 and 80%, respectively, whereas the average accuracy of the third decision tree is 95%. The proposed deep learning-based decision-tree classifier may be used in pre-screening patients to conduct triage and fast-track decision making before RT-PCR results are available.

Volumetric cone-beam CT (CBCT) images are acquired repeatedly during a course of radiation therapy and a natural question to ask is whether CBCT images obtained earlier in the process can be utilized as prior knowledge to reduce patient imaging dose in subsequent scans. The purpose of this work is to develop an adaptive prior image constrained compressed sensing (APICCS) method to solve this problem. Reconstructed images using full projections are taken on the first day of radiation therapy treatment and are used as prior images. The subsequent scans are acquired using a protocol of sparse projections. In the proposed APICCS algorithm, the prior images are utilized as an initial guess and are incorporated into the objective function in the compressed sensing (CS)-based iterative reconstruction process. Furthermore, the prior information is employed to detect any possible mismatched regions between the prior and current images for improved reconstruction. For this purpose, the prior images and the reconstructed images are classified into three anatomical regions: air, soft tissue and bone. Mismatched regions are identified by local differences of the corresponding groups in the two classified sets of images. A distance transformation is then introduced to convert the information into an adaptive voxel-dependent relaxation map. In constructing the relaxation map, the matched regions (unchanged anatomy) between the prior and current images are assigned with smaller weight values, which are translated into less influence on the CS iterative reconstruction process. On the other hand, the mismatched regions (changed anatomy) are associated with larger values and the regions are updated more by the new projection data, thus avoiding any possible adverse effects of prior images. The APICCS approach was systematically assessed by using patient data acquired under standard and low-dose protocols for qualitative and quantitative comparisons. The APICCS method provides an effective way for us to enhance the image quality at the matched regions between the prior and current images compared to the existing PICCS algorithm. Compared to the current CBCT imaging protocols, the APICCS algorithm allows an imaging dose reduction of 10-40 times due to the greatly reduced number of projections and lower x-ray tube current level coming from the low-dose protocol.

Background: While atlas segmentation (AS) has proven to be a time-saving and promising method for radiation therapy contouring, optimal methods for its use have not been well-established. Therefore, we investigated the relationship between the size of the atlas patient population and the atlas segmentation auto contouring (AC) performance. Methods: A total of 110 patients' head planning CT images were selected. The mandible and thyroid were selected for this study. The mandibles and thyroids of the patient population were carefully segmented by two skilled clinicians. Of the 110 patients, 100 random patients were registered to 5 different atlas libraries as atlas patients, in groups of 20 to 100, with increments of 20. AS was conducted for each of the remaining 10 patients, either by simultaneous atlas segmentation (SAS) or independent atlas segmentation (IAS). The AS duration of each target patient was recorded. To validate the accuracy of the generated contours, auto contours were compared to manually generated contours (MC) using a volume-overlap-dependent metric, Dice Similarity Coefficient (DSC), and a distance-dependent metric, Hausdorff Distance (HD). Results: In both organs, as the population increased from n = 20 to n = 60, the results showed better convergence. Generally, independent cases produced better performance than simultaneous cases. For the mandible, the best performance was achieved by n = 60 [DSC = 0.92 (0.01) and HD = 6.73 (1.31) mm] and the worst by n = 100 [DSC = 0.90 (0.03) and HD = 10.10 (6.52) mm] atlas libraries. Similar results were achieved with the thyroid; the best performance was achieved by n = 60 [DSC = 0.79 (0.06) and HD = 10.17 (2.89) mm] and the worst by n = 100 [DSC = 0.72 (0.13) and HD = 12.88 (3.94) mm] atlas libraries. Both IAS and SAS showed similar results. Manual contouring of the mandible and thyroid required an average of 1,044 (±170.15) seconds, while AS required an average of 46.4 (±2.8) seconds. Conclusions: The performance of AS AC generally increased as the population of the atlas library increased. However, the performance does not drastically vary in the larger atlas libraries in contrast to the logic that bigger atlas library should lead to better results. In fact, the results do not vary significantly toward the larger atlas library. It is necessary for the institutions to independently research the optimal number of subjects.

A ray-driven backprojector is based on ray-tracing, which computes the length of the intersection between the ray paths and each voxel to be reconstructed. To reduce the computational burden caused by these exhaustive intersection tests, we propose a fully graphics processing unit (GPU)-based ray-driven backprojector in conjunction with a ray-culling scheme that enables straightforward parallelization without compromising the high computing performance of a GPU. The purpose of the ray-culling scheme is to reduce the number of ray-voxel intersection tests by excluding rays irrelevant to a specific voxel computation. This rejection step is based on an axis-aligned bounding box (AABB) enclosing a region of voxel projection, where eight vertices of each voxel are projected onto the detector plane. The range of the rectangular-shaped AABB is determined by min/max operations on the coordinates in the region. Using the indices of pixels inside the AABB, the rays passing through the voxel can be identified and the voxel is weighted as the length of intersection between the voxel and the ray. This procedure makes it possible to reflect voxel-level parallelization, allowing an independent calculation at each voxel, which is feasible for a GPU implementation. To eliminate redundant calculations during ray-culling, a shared-memory optimization is applied to exploit the GPU memory hierarchy. In experimental results using real measurement data with phantoms, the proposed GPU-based ray-culling scheme reconstructed a volume of resolution 28032803176 in 77 seconds from 680 projections of resolution 10243768 , which is 26 times and 7.5 times faster than standard CPU-based and GPU-based ray-driven backprojectors, respectively. Qualitative and quantitative analyses showed that the ray-driven backprojector provides high-quality reconstruction images when compared with those generated by the Feldkamp-Davis-Kress algorithm using a pixel-driven backprojector, with an average of 2.5 times higher contrast-to-noise ratio, 1.04 times higher universal quality index, and 1.39 times higher normalized mutual information.

Most optical fibers are designed for forward firing i.e. the light is emitted at the distal end along the optical axis of the fiber. In some applications such as the laser surgery and laser scanners, side firing of the optical fiber is required. In this paper, we present the microstructuring of an optical fiber tip using the femtosecond laser and an arc discharging process for the multidirectional firing of the beam. The distal end of the optical fiber with diameter of 125 μm was machined into a conical structure using a femtosecond laser. The surface of the machined tip was exposed to the arc discharge using a fiber splicer. The arc discharge leads to the melting and re-solidification of the fiber tip. This results in a smoothing of laser-induced conical microstructure at the tip of the fiber. We were able to demonstrate the multidirectional (circumferential) emission of the light from the developed fiber tip.