The influence of image reconstruction methods on the diagnosis of pulmonary emphysema with convolutional neural network.

This study investigated the influence of iterative reconstruction (IR) methods on computed tomography (CT) images when training convolutional neural network (CNN) models to diagnose pulmonary emphysema. To evaluate the influence of the IR algorithm on CNN, the present study comprised two steps: the comparison of noise reduction by IR algorithms using phantom examinations and the change in performance of CNN with IR algorithms using patient data. We retrospectively analyzed 97 patients. Raw CT data were reconstructed using the filtered back-projection (FBP) and adaptive statistical iterative reconstruction V (ASIR-V) algorithms with blending levels of 30%, 50%, and 70%. The models were trained using reconstructed CT images and were named the FBP, ASIR-V30, ASIR-V50, and ASIR-V70 models. The mean and the standard deviation of the CT values were 11.3 ± 21.2 at FBP, 11.0 ± 17.3 at ASIR-V30, 11.0 ± 14.4 at ASIR-V50, and 11.0 ± 11.8 at ASIR-V70. For all the evaluation metrics, the best values were obtained with the FBP model applied to the ASIR-V70 test images. The worst values were obtained with the ASIR-V70 model applied to the FBP test images. The model trained with FBP images exhibited significantly better performance than the models trained using IR images. The reduction in image noise with the IR algorithm on the test images contributed to improving the accuracy of the classification of emphysema subtypes using CNN.

Evaluation of a Monte Carlo-based algorithm for the influence of totally implantable venous access ports in external radiation therapy.

PURPOSE: This study aimed to assess whether a Monte Carlo (MC)-based algorithm reflects the influence of totally implantable venous access ports (TIVAPs) in external radiation therapy. MATERIALS AND METHODS: The present study comprised two steps: experimental measurements of depth doses and surface doses with and without TIVAPs and calculation with an MC-based algorithm. RESULTS: The TIVAP-associated maximum dose reduction compared with the dose at the same depths without TIVAPs was 7.8% at 4 MV, 6.9% at 6 MV, and 5.7% at 10 MV in measurement, and 7.4% at 4 MV, 6.6% at 6 MV, and 5.5% at 10 MV in calculation. Relative surface doses were higher with TIVAPs made of titanium, due to a higher fluence of backscattered electrons from the TIVAPs, than with plastic TIVAPs. There were no significant differences in the relative differences between the measured and calculated doses of the titanium TIVAP group and the plastic TIVAP group at 4 MV (p = 0.99), 6 MV (p = 0.67), and 10 MV (p = 0.54). CONCLUSION: TIVAPs caused target dose reductions and dose increase near the TIVAP, especially when made of titanium. The influences are reflected in the MC-based algorithm.

The edge artifact in the point-spread function-based PET reconstruction at different sphere-to-background ratios of radioactivity.

OBJECTIVE: The aim of this study was to quantitatively evaluate the edge artifacts in PET images reconstructed using the point-spread function (PSF) algorithm at different sphere-to-background ratios of radioactivity (SBRs). METHODS: We used a NEMA IEC body phantom consisting of six spheres with 37, 28, 22, 17, 13 and 10 mm in inner diameter. The background was filled with (18)F solution with a radioactivity concentration of 2.65 kBq/mL. We prepared three sets of phantoms with SBRs of 16, 8, 4 and 2. The PET data were acquired for 20 min using a Biograph mCT scanner. The images were reconstructed with the baseline ordered subsets expectation maximization (OSEM) algorithm, and with the OSEM + PSF correction model (PSF). For the image reconstruction, the number of iterations ranged from one to 10. The phantom PET image analyses were performed by a visual assessment of the PET images and profiles, a contrast recovery coefficient (CRC), which is the ratio of SBR in the images to the true SBR, and the percent change in the maximum count between the OSEM and PSF images (Δ % counts). RESULTS: In the PSF images, the spheres with a diameter of 17 mm or larger were surrounded by a dense edge in comparison with the OSEM images. In the spheres with a diameter of 22 mm or smaller, an overshoot appeared in the center of the spheres as a sharp peak in the PSF images in low SBR. These edge artifacts were clearly observed in relation to the increase of the SBR. The overestimation of the CRC was observed in 13 mm spheres in the PSF images. In the spheres with a diameter of 17 mm or smaller, the Δ % counts increased with an increasing SBR. The Δ % counts increased to 91 % in the 10-mm sphere at the SBR of 16. CONCLUSIONS: The edge artifacts in the PET images reconstructed using the PSF algorithm increased with an increasing SBR. In the small spheres, the edge artifact was observed as a sharp peak at the center of spheres and could result in overestimation.

The influence of respiratory motion on the cumulative SUV-volume histogram and fractal analyses of intratumoral heterogeneity in PET/CT imaging.

OBJECTIVE: The purpose of this study was to investigate the influence of respiratory motion on the evaluation of the intratumoral heterogeneity of FDG uptake using cumulative SUV-volume histogram (CSH) and fractal analyses. METHODS: We used an NEMA IEC body phantom with a homogeneous hot sphere phantom (HO) and two heterogeneous hot sphere phantoms (HE1 and HE2). The background radioactivity of (18)F in the NEMA phantom was 5.3 kBq/mL. The ratio of radioactivity was 4:2:1 for the HO and the outer rims of the HE1 and HE2 phantoms, the inner cores of the HE1 and HE2 phantoms, and background, respectively. Respiratory motion was simulated using a motion table with an amplitude of 2 cm. PET/CT data were acquired using Biograph mCT in motionless and moving conditions. The PET images were analyzed by both CSH and fractal analyses. The area under the CSH (AUC-CSH) and the fractal dimension (FD) was used as quantitative metrics. RESULTS: In motionless conditions, the AUC-CSHs of the HO (0.80), HE1 (0.75) and HE2 (0.65) phantoms were different. They did not differ in moving conditions (HO, 0.63; HE1, 0.65; HE2, 0.60). The FD of the HO phantom (0.77) was smaller than the FDs of the HE1 (1.71) and HE2 (1.98) phantoms in motionless conditions; however, the FDs of the HO (1.99) and HE1 (2.19) phantoms were not different from each other and were smaller than that of the HE2 (3.73) phantom in moving conditions. CONCLUSION: Respiratory motion affected the results of the CSH and fractal analyses for the evaluation of the heterogeneity of the PET/CT images. The influence of respiratory motion was considered to vary depending on the object size.