A multiparametric MRI-based machine learning to distinguish between uterine sarcoma and benign leiomyoma: comparison with 18F-FDG PET/CT.

AIM: To compare the performance of machine learning using multiparametric magnetic resonance imaging (mp-MRI) and positron-emission tomography (PET) to distinguish between uterine sarcoma and leiomyoma. MATERIALS AND METHODS: This retrospective study was approved by the institutional review board and informed consent was waived. Sixty-seven consecutive patients with uterine sarcoma or leiomyoma who underwent pelvic 3 T MRI and PET were included. Of 67 patients, 11 had uterine sarcomas and 56 had leiomyomas. Seven different parameters were measured in the tumours, from T2-weighted, T1-weighted, contrast-enhanced, and diffusion-weighted MRI, and PET. The areas under the receiver operating characteristic curves (AUC) with a leave-one-out cross-validation were used to compare the diagnostic performances of the univariate and multivariate logistic regression (LR) model with those of two board-certified radiologists. RESULTS: The AUCs of the univariate models using MRI parameters (0.68-0.8) were inferior to that of the maximum standardised uptake value (SUVmax) of PET (0.85); however, the AUC of the multivariate LR model (0.92) was superior to that of SUVmax, and comparable to that of the board-certified radiologists (0.97 and 0.89). CONCLUSION: The diagnostic performance of the machine learning using mp-MRI was superior to PET and comparable to that of experienced radiologists.

Dual-layer detector CT of chest, abdomen, and pelvis with a one-third iodine dose: image quality, radiation dose, and optimal monoenergetic settings.

AIM: To compare the image quality and radiation dose of reduced iodine dose dual-layer detector (DL) computed tomography (CT) with those of a conventional 120 kVp protocol for chest-abdomen-pelvis CT (CAP-CT). MATERIALS AND METHODS: Forty patients with renal dysfunction (estimated glomerular filtrating ratio <45 ml/min/1.73 m2) underwent reduced iodine dose CAP-CT (120 kVp, 200 mg iodine/kg) on DLCT. Virtual monochromatic images (VMI) at 40-70 keV (5 keV interval) were reconstructed retrospectively. Forty matched patients who underwent conventional CAP-CT (120 kVp, 600 mg iodine/kg, iterative reconstruction) were included as controls. The size-specific dose estimate (SSDE), image noise, CT attenuation, and contrast-to-noise ratio (CNR) were compared between the protocols. Two radiologists rated image contrast, image noise, streak artefact, and diagnostic confidence on a five-point scale. RESULTS: The SSDE of the DLCT group was approximately 20% lower than that of the 120 kVp group (15.4±1.9 versus 19.4±2.3 mGy, p<0.01). DLCT-VMI provided almost constant image noise throughout the range of energies (differences of ≤13%), with the noise being equivalent or lower than 120 kVp in the abdomen. CT attenuation and CNR gradually increased as the energy decreased, with values comparable to 120 kVp being attained at around 45-50 keV. Although streak artefact was accentuated at 40-50 keV (p<0.01), the highest scores for diagnostic confidence were assigned at 40 and 45 keV, both of which were equivalent to 120 kVp (p=1.0). CONCLUSION: For CAP-CT with a one-third iodine dose, DLCT-VMI at 40-45 keV allows for a 20% reduction in radiation dose, while preserving image quality comparable to that of conventional 120 kVp protocol.

Reduction of dental metallic artefacts in CT: value of a newly developed algorithm for metal artefact reduction (O-MAR).

AIM: To evaluate the image quality of O-MAR (Metal Artifact Reduction for Orthopedic Implants) for dental metal artefact reduction. MATERIALS AND METHODS: This prospective study received institutional review board approval and written informed consent was obtained. Thirty patients who had dental implants or dental fillings were included in this study. Computed tomography (CT) images were obtained through the oral cavity and neck during the portal venous phase. The system reconstructed the O-MAR-processed images in addition to the uncorrected images. CT attenuation and image noise of the soft tissue of the oral cavity were compared between the O-MAR and the uncorrected images. Qualitative analysis was undertaken between the two image groups. RESULTS: The image noise of the O-MAR images was significantly lower than that of the uncorrected images (p < 0.01). O-MAR offered plausible attenuations of soft tissue compared with non-O-MAR. Better qualitative scores were obtained in the streaking artefacts and the degree of depiction of the oral cavity with O-MAR compared with non-O-MAR. CONCLUSION: O-MAR enables the depiction of structures in areas in which this was not previously possible due to dental metallic artefacts in qualitative image analysis. O-MAR images may have a supplementary role in addition to uncorrected images in oral diagnosis.

Low-dose abdominal CT protocols with a tube voltage setting of 100 kVp or 80 kVp: Performance of radiation dose reduction and influence on visual contrast.

AIM: To evaluate the radiation dose, image quality, and influence on visual contrast of low tube voltage abdominal computed tomography (CT) and the effects of display setting optimization. MATERIALS AND METHODS: One hundred and fifty-seven patients were randomly assigned to one of three protocols. Fifty-two patients underwent a 120 kVp protocol, and 53 and 52 patients underwent low-dose protocols with 100 and 80 kVp, respectively. The effective dose (ED), image noise, CT attenuation, and signal-to-noise ratio (SNR) of each organ of each protocol were compared using Dunnett's test. Qualitative analysis between the protocols was also performed. RESULTS: The ED of the 100 and 80 kVp protocols were 22% and 37% reduced, respectively. There were no significant differences in the SNR between the protocols (120 kVp: 13.8 ± 3.5; 100 kVp: 13.9 ± 3.3; 80 kVp: 13.5 ± 2.9; p > 0.05). However, there were significant differences in contrast familiarity between the 120 kVp images and all the other images, except 100 kVp images, with optimized display settings (p < 0.05). CONCLUSION: In abdominal CT, an 80 kVp setting offers greater radiation dose reduction than a 100 kVp setting without significant deterioration of the SNR; however, the visual contrast between the organs might be changed.

Low-dose abdominal CT: comparison of low tube voltage with moderate-level iterative reconstruction and standard tube voltage, low tube current with high-level iterative reconstruction.

AIM: To evaluate the quality of 100 kVp images with a hybrid iterative reconstruction algorithm level of 40% and 120 kVp (low-tube-current) images with a hybrid iterative reconstruction algorithm level of 60% in low-dose abdominal computed tomography (CT) using almost the same radiation dose. MATERIALS AND METHODS: This prospective study received institutional review board approval and written informed consent was obtained. One hundred and ten patients undergoing abdominal dynamic CT were randomly assigned to one of two protocols (100 and 120 kVp protocols). Radiation doses of the two protocols were almost identical. The 120 kVp images were post-processed with a hybrid iterative reconstruction algorithm level of 60% (i-120 kVp). The 100 kVp images were post-processed with a hybrid iterative reconstruction algorithm level of 40% (i-100 kVp). The effective dose (ED), image noise, CT attenuation, and signal-to-noise ratio (SNR) of the subcutaneous fat, muscle, liver, pancreas, and kidneys were compared between the protocols using Student's t-test. Qualitative analysis was also performed between the protocols. RESULTS: There were no significant differences in ED and SNR of any of the regions of interest (ROIs) between the protocols (p > 0.05). However, in the qualitative analysis, unnatural texture was significantly greater in the i-120 kVp than in the i-100 kVp protocol (p < 0.01). There were no other significant differences in the image quality between the protocols (p > 0.05). CONCLUSION: The combined use of low tube voltage and moderate-level iterative reconstruction techniques can be a more effective strategy for reducing patient radiation dose while attaining acceptable image quality than the use of standard tube voltage, low tube current with high-level iterative reconstruction.

Virtual magnetic resonance lumbar spine images generated from computed tomography images using conditional generative adversarial networks.

INTRODUCTION: The aim of this study was to generate virtual Magnetic resonance (MR) from computed tomography (CT) using conditional generative adversarial networks (cGAN). METHODS: We selected examinations from 22 adults who obtained their CT and MR lumbar spine examinations. Overall, 4 examinations were used as test data, and 18 examinations were used as training data. A cGAN was trained to generate virtual MR images from the CT images using the corresponding MR images as targets. After training, the generated virtual MR images from test data in epochs 1, 10, 50, 100, 500, and 1000 were compared with the original ones using the mean square error (MSE) and structural similarity index (SSIM). Additionally, two radiologists also performed qualitative assessments. RESULTS: The MSE of the virtual MR images decreased as the epoch of the cGANs increased from the original CT images: 8876.7 ± 1192.9 (original CT), 1567.5 ± 433.9 (Epoch 1), 1242.4 ± 442.0 (Epoch 10), 1065.8 ± 478.1 (Epoch 50), 1276.1 ± 718.9 (Epoch 100), 1046.7 ± 488.2 (Epoch 500), and 1031.7 ± 400.0 (Epoch 1000). No considerable differences were observed in the qualitative evaluation between the virtual MR images and the original ones, except in the structure of the spinal canal. CONCLUSION: Virtual MR lumbar spine images using cGANs could be a feasible technique to generate near-MR images from CT without MR examinations for evaluation of the vertebral body and intervertebral disc. IMPLICATIONS FOR PRACTICE: Virtual MR lumbar spine images using cGANs can offer virtual CT images with sufficient quality for attenuation correction for PET or dose planning in radiotherapy.

Metal Artifact Reduction in Head CT Performed for Patients with Deep Brain Stimulation Devices: Effectiveness of a Single-Energy Metal Artifact Reduction Algorithm.

BACKGROUND AND PURPOSE: Deep brain stimulation electrodes induce massive artifacts on CT images, deteriorating the diagnostic value of examinations. We aimed to investigate the usefulness and potential limitations of a single-energy metal artifact reduction algorithm in head CT performed in patients with implanted deep brain stimulation devices. MATERIALS AND METHODS: Thirty-four patients with deep brain stimulation (bilateral, n = 28) who underwent head CT on a 320-detector row scanner and whose images were reconstructed with and without single-energy metal artifact reduction at the examinations were retrospectively included. The severity of artifacts around electrodes was assessed objectively using SDs and an artifact index. Two radiologists subjectively evaluated the severity of artifacts from electrodes, the visibility of electrode localization and surrounding structures, and overall diagnostic confidence on 4-point scales. Background image quality (GM-WM contrast and image noise) was subjectively and objectively assessed. The presence and location of artifacts newly produced by single-energy metal artifact reduction were analyzed. RESULTS: Single-energy metal artifact reduction provided lower objective and subjective metal artifacts and improved visualization of electrode localization and surrounding structures and diagnostic confidence compared with non-single-energy metal artifact reduction images, with statistical significance (all, P < .01). No significant differences were observed in GM-WM contrast and image noise (all, P ≥ .11). The new artifacts from single-energy metal artifact reduction were prominently observed in patients with bilateral deep brain stimulation at high convexity, possibly induced by deep brain stimulation leads placed under the parietal scalp. CONCLUSIONS: Single-energy metal artifact reduction substantially reduces the metal artifacts from deep brain stimulation electrodes and improves the visibility of intracranial structures without affecting background image quality. However, non-single-energy metal artifact reduction images should be simultaneously reviewed to accurately assess the entire intracranial area, particularly in patients with bilateral deep brain stimulation.