Task-based assessment of resolution properties of CT images with a new index using deep convolutional neural network.

In this study, we propose a method for obtaining a new index to evaluate the resolution properties of computed tomography (CT) images in a task-based manner. This method applies a deep convolutional neural network (DCNN) machine learning system trained on CT images with known modulation transfer function (MTF) values to output an index representing the resolution properties of the input CT image [i.e., the resolution property index (RPI)]. Sample CT images were obtained for training and testing of the DCNN by scanning the American Radiological Society phantom. Subsequently, the images were reconstructed using a filtered back projection algorithm with different reconstruction kernels. The circular edge method was used to measure the MTF values, which were used as teacher information for the DCNN. The resolution properties of the sample CT images used to train the DCNN were created by intentionally varying the field of view (FOV). Four FOV settings were considered. The results of adapting this method to the filtered back projection (FBP) and hybrid iterative reconstruction (h-IR) images indicated highly correlated values with the MTF10% in both cases. Furthermore, we demonstrated that the RPIs could be estimated in the same manner under the same imaging conditions and reconstruction kernels, even for other CT systems, where the DCNN was trained on CT systems produced by the same manufacturer. In conclusion, the RPI, which is a new index that represents the resolution property using the proposed method, can be used to evaluate the resolution of a CT system in a task-based manner.

Pseudo-random Trajectory Scanning Suppresses Motion Artifacts on Gadoxetic Acid-enhanced Hepatobiliary-phase Magnetic Resonance Images.

PURPOSE: Hepatobiliary-phase (HBP) MRI with gadoxetic acid facilitates the differentiation between lesions with and without functional hepatocytes. Thus, high-quality HBP images are required for the detection and evaluation of hepatic lesions. However, the long scan time may increase artifacts due to intestinal peristalsis, resulting in the loss of diagnostic information. Pseudo-random acquisition order disperses artifacts into the background. The aim of this study was to investigate the clinical applicability of pseudo-random trajectory scanning for the suppression of motion artifacts on T1-weighted images including HBP. METHODS: Our investigation included computer simulation, phantom experiments, and a clinical study. For computer simulation and phantom experiments a region of interest (ROI) was placed on the area with motion artifact and the standard deviation inside the ROI was measured as image noise. For clinical study we subjected 62 patients to gadoxetic acid-enhanced hepatobiliary-phase imaging with a circular- and a pseudo-random trajectory (c-HBP and p-HBP); two radiologists graded the motion artifacts, sharpness of the liver edge, visibility of intrahepatic vessels, and overall image quality using a five-point scale where 1 = unacceptable and 5 = excellent. Differences in the qualitative scores were determined using the two-sided Wilcoxon signed-rank test. RESULTS: The image noise was higher on the circular image compared with pseudo-random image (101.0 vs 60.9 on computer simulation image, 91.2 vs 67.7 on axial, 95.5 vs 86.9 on reformatted sagittal image for phantom experiments). For clinical study the score for motion artifacts was significantly higher with p-HBP than c-HBP imaging (left lobe: mean 3.4 vs 3.2, P < 0.01; right lobe: mean 3.6 vs 3.4, P < 0.01) as was the qualitative score for the overall image quality (mean 3.6 vs 3.3, P < 0.01). CONCLUSION: At gadoxetic acid-enhanced hepatobiliary-phase imaging, p-HBP scanning suppressed motion artifacts and yielded better image quality than c-HBP scanning.

Demonstration of Human Fetal Bone Morphology with MR Imaging: A Preliminary Study.

PURPOSE: CT is a useful modality for the evaluation of fetal skeletal dysplasia but radiation exposure is unavoidable. The purpose of this study is to compare the usefulness of MRI and CT for evaluating the fetal skeletal shape. METHODS: This study was approved by our Institutional Review Board. Fetal specimens (n = 14) were scanned on a 3T MRI scanner using our newly-developed sequence. It is based on T2*-weighted imaging (TR, 12 ms; TE for opposed-phase imaging, 6.1 ms, for in-phase imaging, 7.3 ms; flip angle, 40°). The specimens were also scanned on a 320 detector-row CT scanner. Four radiologists visually graded and compared the visibility of the bone shape of eight regions on MRI- and CT-scans using a 5-point grading system. RESULTS: The diagnostic ability of MRI with respect to the 5th metacarpals, femur, fibula, and pelvis was superior to CT (all, P < 0.050); there was no significant difference in the evaluation results of observers with respect to the cervical and lumbar spine, and the 5th metatarsal (0.058 ≤ P ≤ 1.000). However, the diagnostic ability of MRI was significantly inferior to CT for the assessment of the bone shape of the thoracic spine (observers A and C: P = 0.002, observers B and D: P = 0.001). CONCLUSION: The MRI method we developed represents a potential alternative to CT imaging for the evaluation of the fetal bone structure.