Impact of different reconstruction algorithms and setting parameters on radiomics features of PSMA PET images: A preliminary study.

PURPOSE: Radiomics analysis of oncologic positron emission tomography (PET) images is an area of significant activity and potential. The reproducibility of radiomics features is an important consideration for routine clinical use. This preliminary study investigates the robustness of radiomics features in PSMA-PET images across penalized-likelihood (Q.Clear) and standard ordered subset expectation maximization (OSEM) reconstruction algorithms and their setting parameters in phantom and prostate cancer (PCa) patients. METHOD: A NEMA image quality (IQ) phantom and 8 PCa patients were selected for phantom and patient analyses, respectively. PET images were reconstructed using Q.Clear (reconstruction ß-value: 100-700, at intervals of 100 for both NEMA IQ phantom and patients) and OSEM (duration: 15sec, 30sec, 1 min, 2 min, 3 min, 4 min and 5 min for NEMA phantom and duration: 30 s, 1 min and 2 min for patients) reconstruction methods. Subsequently, 129 radiomic features were extracted from the reconstructed images. The coefficient of variation (COV) of each feature across reconstruction methods and their parameters was calculated to determine feature robustness. RESULTS: The extracted radiomics features showed a different range of variability, depending on the reconstruction algorithms and setting parameters. Specifically, 23.0 % and 53.5 % of features were found as robust against ß-value variations in Q.Clear and different durations in OSEM reconstruction algorithms, respectively. Taking into account the two algorithms and their parameters, eleven features (8.5 %) showed COV ≤ 5 % and eighteen (14 %) showed 5 % 20 %. The mean COVs of the extracted radiomics features were significantly different between the two reconstruction methods (p < 0.05) except for the phantom morphological features. CONCLUSIONS: All radiomics features were affected by reconstruction methods and parameters, but features with small or very small variations are considered better candidates for reproducible quantification of either tumor or metastatic tissues in clinical trials. There is a need for standardization before the implementation of PET radiomics in clinical practice.

Generation of18F-FDG PET standard scan images from short scans using cycle-consistent generative adversarial network.

Objective.To improve positron emission tomography (PET) image quality, we aim to generate images of quality comparable to standard scan duration images using short scan duration (1/8 and 1/16 standard scan duration) inputs and assess the generated standard scan duration images quantitative and qualitatively. Also, the effect of training dataset properties (i.e. body mass index (BMI)) on the performance of the model(s) will be explored.Approach.Whole-body PET scans of 42 patients (4118F-FDG and one68Ga-PSMA) scanned with standard radiotracer dosage were included in this study. One18F-FDG patient data was set aside and the remaining 40 patients were split into four subsets of 10 patients with different mean patient BMI. Multiple copies of a developed cycle-GAN network were trained on each subset to predict standard scan images using 1/8 and 1/16 short duration scans. Also, the models' performance was tested on a patient scanned with the68Ga-PSMA radiotracer. Quantitative performance was tested using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and normalized root mean squared error (NRMSE) metrics, and two nuclear medicine specialists analyzed images qualitatively.Main results.The developed cycle-GAN model improved the PSNR, SSIM, and NRMSE of the 1/8 and 1/16 short scan duration inputs both18F-FDG and68Ga-PSMA radiotracers. Although, quantitatively PSNR, SSIM, and NRMSE of the 1/16 scan duration level were improved more than 1/8 counterparts, however, the later were qualitatively more appealing. SUVmeanand SUVmaxof the generated images were also indicative of the improvements. The cycle-GAN model was much more capable in terms of image quality improvements and speed than the NLM denoising method. All results proved statistically significant using the paired-sample T-Test statistical test (p-value < 0.05).Significance.Our suggested approach based on cycle-GAN could improve image quality of the 1/8 and 1/16 short scan-duration inputs through noise reduction both quantitively (PSNR, SSIM, NRMSE, SUVmean, and SUVmax) and qualitatively (contrast, noise, and diagnostic capability) to the level comparable to the standard scan-duration counterparts. The cycle-GAN model(s) had a similar performance on the68Ga-PSMA to the18F-FDG images and could improve the images qualitatively and quantitatively but requires more extensive study. Overall, images predicted from 1/8 short scan-duration inputs had the upper hand compared with 1/16 short scan-duration inputs.

Design and Evaluation of an Electronic Information Exchange System Connecting Laboratories and Physicians' Offices.

Laboratory services are a crucial part of medical care and contribute to physicians' treatment-related decision-making. However, paper-based information exchanges between physicians' offices and laboratories waste physicians' time and prevent them from using outpatient test results in a timely and effective manner. To solve this problem, improve the safety and quality of patient care, and save patients' time and energy, the present study developed a web-based system for electronic information exchange between laboratories and offices in Microsoft Visual Studio with the ASP.net technology and the Microsoft SQL Server database. The developed web-based software met the needs of the users and stakeholders (physicians, laboratory personnel, and patients) in the laboratory service cycle. To evaluate the software, user satisfaction was assessed in terms of user interface, operational functionality, and system performance, indicating the acceptability of all the criteria from the viewpoint of the stakeholders. The developed web-based software enables electronic communication between offices and laboratories (two important healthcare bases), establishes information exchange (sending requests and receiving laboratory results) between these two bases, and also notifies the patients. The software gained the overall satisfaction of the users, and this highlights the need for electronic communications in the healthcare domain.

Effectiveness of a smartphone-based educational intervention to improve breastfeeding.

BACKGROUND: Exclusive breastfeeding (EBF) is essential during the first six months of life and confers countless benefits to mothers and infants. This study aimed to assess the effectiveness of a smartphone-based educational intervention to improve new mothers' breastfeeding for infants younger than six months of age in Urmia, Iran. METHODS: A randomized controlled trial study was conducted from January to December 2019 with 40 new mothers and their first child aged < 3 months, assigned to the intervention (mobile app education + routine care) and control groups (routine care). The mean age of infants was 1.25 and 0.98 months for each group consequently. The designed app content categorized according to seven sections (the importance of breastfeeding, behavioral methods, complementary feeding and EBF, pumping and manual expression, managing common breast-related and breastfeeding problems, breastfeeding tips in special situations, and common queries) for educating the required knowledge to nursing mothers. RESULTS: Forty mothers were assessed for primary outcomes in each group. At three months, the mothers' knowledge, attitude, and practice (KAP) had meaningful differences in the intervention group compared to the control group. In the intervention group, the degree of changes in knowledge and attitude were 5.67 ± 0.94 and 8.75 ± 1.37 respectively more than the control group (p < 0.001, p < 0.001). However, this amount for the practice score was 0.8 ± 0.49 which is considered to be marginally significant (p = 0.063). During the study, the mothers' breastfeeding self-efficacy showed significant progress in favor of the intervention group. The score enhancement was 26.85 ± 7.13 for the intervention group and only 0.40 ± 5.17 for the control group that was confirmed to be significant (p < 0.001). CONCLUSION: The smartphone-based app for educating new mothers on breastfeeding had a significantly positive effect on breastfeeding self-efficacy and maternal KAP. In future studies, the intervention can be tested in both prenatal and postpartum periods.

The Effect of Information Technology on the Information Exchange between Laboratories and Ambulatory Care Centers: A Systematic Review.

Laboratory services form an integral part of medical care in the decision-making of physicians, including those working at ambulatory care centers. Information exchange is essential between ambulatory care centers and laboratories. Inevitable errors have always existed in the exchange of such information on paper, which can be to some extent avoided by developing appropriate computer-based interfaces. Therefore, this review aimed to examine studies conducted to determine the effect of electronic communication between ambulatory care centers and laboratories. This systematic review was conducted on the basis of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. Studies were searched in the PubMed, Embase, Cochrane, and Web of Science, and those written in English and published between 2000 and February 2019 with full texts available were selected. From a total of 3898 papers retrieved from the studied databases, 24 papers were eligible for entering this study after removing similar and nonrelated studies. Electronic exchanges between ambulatory care centers and laboratories can have numerous benefits in terms of financial, organizational, and quality. This evidence for the value of electronic communications is an important factor contributing to its local investment and adoption.