Nihon Hoshasen Gijutsu Gakkai zasshi最新文献

Purpose: The aim of this study was to validate the potential of substituting an observer in a paired comparison with a deep-learning observer.

Methods: Phantom images were obtained using computed tomography. Imaging conditions included a standard setting of 120 kVp and 200 mA, with tube current variations ranging from 160 mA, 120 mA, 80 mA, 40 mA, and 20 mA, resulting in six different imaging conditions. Fourteen radiologic technologists with >10 years of experience conducted pairwise comparisons using Ura's method. After training, VGG16 and VGG19 models were combined to form deep learning models, which were then evaluated for accuracy, recall, precision, specificity, and F₁value. The validation results were used as the standard, and the results of the average degree of preference and significance tests between images were compared to the standard if the results of deep learning were incorporated.

Results: The average accuracy of the deep learning model was 82%, with a maximum difference of 0.13 from the standard regarding the average degree of preference, a minimum difference of 0, and an average difference of 0.05. Significant differences were observed in the test results when replacing human observers with AI counterparts for image pairs with tube currents of 160 mA vs. 120 mA and 200 mA vs. 160 mA.

Conclusion: In paired comparisons with a limited phantom (7-point noise evaluation), the potential use of deep learning was suggested as one of the observers.

Purpose: In Japan, radiologists perform qualitative visual classification to define four categories of mammary gland density. However, an objective estimation of mammary gland density is necessary. To address this, we developed an automatic classification software using image similarity.

Methods: We prepared 741 cases of mediolateral oblique images (MLO) for evaluation, and they were diagnosed as normal among the mammography images taken at our hospital. Image matching was performed using the evaluation images and an image database for breast density determination. In this study, the image similarity used zero normalized cross-correlation (ZNCC) as an index. In addition, if the breast thickness is less than 30 mm and each breast density category ZNNC has the same value, the category is evaluated on the fat side. We compared the results of qualitative visual classification and automatic classification methods to assess consistency.

Results: The agreement with the subjective breast composition classification was 78.5%, and the weighted kappa coefficient was 0.98. One mismatched case was evaluated on the higher density side with the same ZNCC value between categories and a breast thickness greater than 30 mm.

Conclusion: Image similarity provides an excellent estimation of quantification of breast density. This system could contribute to improving the efficiency of the mammography screening system.

Purpose: To validate the effects of subject position on single energy metal artifact reduction (SEMAR) of a reverse shoulder prosthesis using computed tomography (CT).

Methods: A water phantom with a reverse shoulder prosthesis was scanned at four positions on the XY plane of the CT gantry (on-center, 50 mm, 100 mm, and 150 mm from on-center in the negative direction of the X axis, respectively). We obtained images with and without SEMAR. The artifact index (AI) was measured via physical assessment. Scheffé's (Ura) paired comparison methods were performed with the amount of metal artifact by ten radiological technologists via visual assessment.

Results: The AI was significantly reduced when using SEMAR. As the phantom moved away from the on-center position, the AI increased, and metal artifacts increased in Scheffé's methods.

Conclusion: SEMAR reduces metal artifacts of a reverse shoulder prosthesis, but metal artifacts may increase as the subject position moves away from the on-center position.

Purpose: To verify the optimal imaging conditions for coronary computed tomography angiography (CCTA) examinations when using high-definition (HD) mode and deep learning image reconstruction (DLIR) in combination.

Method: A chest phantom and an in-house phantom using 3D printer were scanned with a 256-row detector CT scanner. The scan parameters were as follows - acquisition mode: ON (HD mode) and OFF (normal resolution [NR] mode), rotation time: 0.28 s/rotation, beam coverage width: 160 mm, and the radiation dose was adjusted based on CT-AEC. Image reconstruction was performed using ASiR-V (Hybrid-IR), TrueFidelity Image (DLIR), and HD-Standard (HD mode) and Standard (NR mode) reconstruction kernels. The task-based transfer function (TTF) and noise power spectrum (NPS) were measured for image evaluation, and the detectability index (d') was calculated. Visual evaluation was also performed on an in-house coronary phantom.

Result: The in-plane TTF was better for the HD mode than for the NR mode, while the z-axis TTF was lower for DLIR than for Hybrid-IR. The NPS values in the high-frequency region were higher for the HD mode compared to those for the NR mode, and the NPS was lower for DLIR than for Hybrid-IR. The combination of HD mode and DLIR showed the best value for in-plane d', whereas the combination of NR mode and DLIR showed the best value for z-axis d'. In the visual evaluation, the combination of NR mode and DLIR showed the best values from a noise index of 45 HU.

Conclusion: The optimal combination of HD mode and DLIR depends on the image noise level, and the combination of NR mode and DLIR was the best imaging condition under noisy conditions.

Purpose: During computed tomography pulmonary angiography (CTPA), a decrease in the CT value of the pulmonary artery may be observed due to poor contrast enhancement, even though the imaging is performed at the optimum timing while continuously injecting a contrast medium. This study focused on the increase in blood flow in the superior and inferior vena cava during inspiration that affects the decrease in the CT value of the pulmonary artery and investigated a radiography method in which a delay time was set after inspiration in clinical cases.

Methods: A total of 50 patients who underwent CTPA for suspected pulmonary thromboembolism were included. Using the bolus tracking method, we monitored the pulmonary arteries before and after inspiration, and investigated the CT value changes.

Results: A decrease in the CT value of the pulmonary artery after inspiration was observed in approximately 30% of cases. By setting the delay time, the contrast enhancement effect before and after inspiration became equivalent.

Conclusion: As a result of this study, avoiding a decrease in the CT value of the pulmonary artery is possible by setting a delay time after inspiration, which is considered useful during CTPA.

Purpose: It is very difficult for a radiologist to correctly detect small lesions and lesions hidden on dense breast tissue on a mammogram. Therefore, recently, computer-aided detection (CAD) systems have been widely used to assist radiologists in interpreting images. Thus, in this study, we aimed to segment mass on the mammogram with high accuracy by using focus images obtained from an eye-tracking device.

Methods: We obtained focus images for two mammography expert radiologists and 19 mammography technologists on 8 abnormal and 8 normal mammograms published by the DDSM. Next, the auto-encoder, Pix2Pix, and UNIT learned the relationship between the actual mammogram and the focus image, and generated the focus image for the unknown mammogram. Finally, we segmented regions of mass on mammogram using the U-Net for each focus image generated by the auto-encoder, Pix2Pix, and UNIT.

Results: The dice coefficient in the UNIT was 0.64±0.14. The dice coefficient in the UNIT was higher than that in the auto-encoder and Pix2Pix, and there was a statistically significant difference (p<0.05). The dice coefficient of the proposed method, which combines the focus images generated by the UNIT and the original mammogram, was 0.66±0.15, which is equivalent to the method using the original mammogram.

Conclusion: In the future, it will be necessary to increase the number of cases and further improve the segmentation.

Purpose: In X-ray computed tomography (CT), noise distribution within images is nonuniform and thought to vary with imaging conditions. This study aimed to evaluate noise nonuniformity by altering specific imaging conditions, such as tube voltage, bow-tie filter (BTF), and phantom size.

Methods: Using four tube voltages (80, 100, 120, and 135 kV), two BTF types (L and M), and circular water phantoms with diameters of 240, 320, and 400 mm, we employed filtered back projection (FBP) for reconstruction. Noise nonuniformity was assessed by defining six regions of interest (ROI) from the image center to the periphery, and the noise nonuniformity index (NNI) was calculated based on the standard deviation (SD) values within these ROIs.

Results: Results showed consistently larger noise SD values in the central region compared to the peripheral region under all imaging conditions, with the maximum NNI reaching 32.1%. Variations in NNI were observed, reaching up to 5.5 points for tube voltage, 7.8 points for BTF, and 8.2 points for phantom size.

Conclusion: In conclusion, our quantitative assessment revealed moderate dependence of noise nonuniformity on imaging conditions in CT images.

Purpose: To investigate whether deep learning with high-pass filtering can be used to effectively reduce motion artifacts in magnetic resonance (MR) images of the liver.

Methods: The subjects were 69 patients who underwent liver MR examination at our hospital. Simulated motion artifact images (SMAIs) were created from non-artifact images (NAIs) and used for deep learning. Structural similarity index measure (SSIM) and contrast ratio (CR) were used to verify the effect of reducing motion artifacts in motion artifact reduction image (MARI) output from the obtained deep learning model. In the visual assessment, reduction of motion artifacts and image sharpness were evaluated between motion artifact images (MAIs) and MARIs.

Results: The SSIM values were 0.882 on the MARIs and 0.869 on the SMAIs. There was no statistically significant difference in CR between NAIs and MARIs. The visual assessment showed that MARIs had reduced motion artifacts and improved sharpness compared to MAIs.

Conclusion: The learning model in this study is indicated to be reduced motion artifacts without decreasing the sharpness of liver MR images.