Image quality improvement in cone-beam CT using the super-resolution technique

Abstract

This study was conducted to improve cone-beam computed tomography (CBCT) image quality using the super-resolution technique, a method of inferring a high-resolution image from a low-resolution image. This technique is used with two matrices, so-called dictionaries, constructed respectively from high-resolution and low-resolution image bases. For this study, a CBCT image, as a low-resolution image, is represented as a linear combination of atoms, the image bases in the low-resolution dictionary. The corresponding super-resolution image was inferred by multiplying the coefficients and the high-resolution dictionary atoms extracted from planning CT images. To evaluate the proposed method, we computed the root mean square error (RMSE) and structural similarity (SSIM). The resulting RMSE and SSIM between the super-resolution images and the planning CT images were, respectively, as much as 0.81 and 1.29 times better than those obtained without using the super-resolution technique. We used super-resolution technique to improve the CBCT image quality.

Visual enhancement of Cone‐beam CT by use of CycleGAN

“…Preserving anatomical structures is crucial for image-improvement methods using unpaired and unaligned CBCT and PlanCT datasets. In a previous work using PlanCT as prior information, high-frequency artifacts such as streaks, blurred edges, deformations, and missing anatomical structures were left as problems to be solved 15,16,17,18 . In this study, the image quality of CBCT improved while suppressing high-frequency artifacts and preserving the anatomical structures of CBCT.…”

“…On the other hand, a different approach has been proposed, which uses PlanCT as prior information to improve the quality of CBCT images. This approach is applicable to direct three‐dimensional (3D) image reconstruction with sparse sampling, histogram matching, super‐resolution, and a deep convolutional neural network . Although these do not require access to the raw projection data or a particular scanner manufacturer, they depend on accurate spatial alignment of CBCT and PlanCT volume pairs from the same patients.…”

Physiologically variable ventilation reduces regional lung inflammation in a pediatric model of acute respiratory distress syndrome

“…In this study we used a Cone Beam CT [ 43 ]. This device uses less radiation and creates higher resolution images than the regular fan beam CT; however, it produces more scatter artefacts, which can alter the measured values [ 44 , 45 ]. Due to technical limitations, breath gating was not performed in any of the acquisitions; therefore, basal lung areas had artefacts due to motion of the abdominal organs during breathing.…”

Postoperative Pain Control After Arthroscopic Rotator Cuff Repair: Arthroscopy-Guided Continuous Suprascapular Nerve Block Versus Ultrasound-Guided Continuous Interscalene Block

“…Patients were placed in upright sitting position and a 2-to-5-MHz curved probe was positioned under the lowest rib at the midaxillary or anterior plane to identify the liver or spleen, as an acoustic window. 24 After identifying the diaphragm using the 2-dimensional mode, patients were asked to inhale deeply during the measurement of diaphragmatic movement using the M-mode. The degree of diaphragmatic excursion was defined as follows: <25% of the preblock value (i.e., complete paresis) and 25% to 75% of the preblock value (i.e., partial paresis).…”