Pediatric evaluations for deep learning CT denoising.

BACKGROUND: Deep learning (DL) CT denoising models have the potential to improve image quality for lower radiation dose exams. These models are generally trained with large quantities of adult patient image data. However, CT, and increasingly DL denoising methods, are used in both adult and pediatric populations. Pediatric body habitus and size can differ significantly from adults and vary dramatically from newborns to adolescents. Ensuring that pediatric subgroups of different body sizes are not disadvantaged by DL methods requires evaluations capable of assessing performance in each subgroup. PURPOSE: To assess DL CT denoising in pediatric and adult-sized patients, we built a framework of computer simulated image quality (IQ) control phantoms and evaluation methodology. METHODS: The computer simulated IQ phantoms in the framework featured pediatric-sized versions of standard CatPhan 600 and MITA-LCD phantoms with a range of diameters matching the mean effective diameters of pediatric patients ranging from newborns to 18 years old. These phantoms were used in simulating CT images that were then inputs for a DL denoiser to evaluate performance in different sized patients. Adult CT test images were simulated using standard-sized phantoms scanned with adult scan protocols. Pediatric CT test images were simulated with pediatric-sized phantoms and adjusted pediatric protocols. The framework's evaluation methodology consisted of denoising both adult and pediatric test images then assessing changes in image quality, including noise, image sharpness, CT number accuracy, and low contrast detectability. To demonstrate the use of the framework, a REDCNN denoising model trained on adult patient images was evaluated. To validate that the DL model performance measured with the proposed pediatric IQ phantoms was representative of performance in more realistic patient anatomy, anthropomorphic pediatric XCAT phantoms of the same age range were also used to compare noise reduction performance. RESULTS: Using the proposed pediatric-sized IQ phantom framework, size differences between adult and pediatric-sized phantoms were observed to substantially influence the adult trained DL denoising model's performance. When applied to adult images, the DL model achieved a 60% reduction in noise standard deviation without substantial loss in sharpness in mid or high spatial frequencies. However, in smaller phantoms the denoising performance dropped due to different image noise textures resulting from the smaller field of view (FOV) between adult and pediatric protocols. In the validation study, noise reduction trends in the pediatric-sized IQ phantoms were found to be consistent with those found in anthropomorphic phantoms. CONCLUSION: We developed a framework of using pediatric-sized IQ phantoms for pediatric subgroup evaluation of DL denoising models. Using the framework, we found the performance of an adult trained DL denoiser did not generalize well in the smaller diameter phantoms corresponding to younger pediatric patient sizes. Our work suggests noise texture differences from FOV changes between adult and pediatric protocols can contribute to poor generalizability in DL denoising and that the proposed framework is an effective means to identify these performance disparities for a given model.

Report on the AAPM grand challenge on deep generative modeling for learning medical image statistics.

BACKGROUND: The findings of the 2023 AAPM Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics are reported in this Special Report. PURPOSE: The goal of this challenge was to promote the development of deep generative models for medical imaging and to emphasize the need for their domain-relevant assessments via the analysis of relevant image statistics. METHODS: As part of this Grand Challenge, a common training dataset and an evaluation procedure was developed for benchmarking deep generative models for medical image synthesis. To create the training dataset, an established 3D virtual breast phantom was adapted. The resulting dataset comprised about 108 000 images of size 512  × $\times$  512. For the evaluation of submissions to the Challenge, an ensemble of 10 000 DGM-generated images from each submission was employed. The evaluation procedure consisted of two stages. In the first stage, a preliminary check for memorization and image quality (via the Fréchet Inception Distance [FID]) was performed. Submissions that passed the first stage were then evaluated for the reproducibility of image statistics corresponding to several feature families including texture, morphology, image moments, fractal statistics, and skeleton statistics. A summary measure in this feature space was employed to rank the submissions. Additional analyses of submissions was performed to assess DGM performance specific to individual feature families, the four classes in the training data, and also to identify various artifacts. RESULTS: Fifty-eight submissions from 12 unique users were received for this Challenge. Out of these 12 submissions, 9 submissions passed the first stage of evaluation and were eligible for ranking. The top-ranked submission employed a conditional latent diffusion model, whereas the joint runners-up employed a generative adversarial network, followed by another network for image superresolution. In general, we observed that the overall ranking of the top 9 submissions according to our evaluation method (i) did not match the FID-based ranking, and (ii) differed with respect to individual feature families. Another important finding from our additional analyses was that different DGMs demonstrated similar kinds of artifacts. CONCLUSIONS: This Grand Challenge highlighted the need for domain-specific evaluation to further DGM design as well as deployment. It also demonstrated that the specification of a DGM may differ depending on its intended use.

Report on the AAPM Grand Challenge on deep generative modeling for learning medical image statistics.

Background: The findings of the 2023 AAPM Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics are reported in this Special Report. Purpose: The goal of this challenge was to promote the development of deep generative models for medical imaging and to emphasize the need for their domain-relevant assessments via the analysis of relevant image statistics. Methods: As part of this Grand Challenge, a common training dataset and an evaluation procedure was developed for benchmarking deep generative models for medical image synthesis. To create the training dataset, an established 3D virtual breast phantom was adapted. The resulting dataset comprised about 108,000 images of size 512×512. For the evaluation of submissions to the Challenge, an ensemble of 10,000 DGM-generated images from each submission was employed. The evaluation procedure consisted of two stages. In the first stage, a preliminary check for memorization and image quality (via the Fréchet Inception Distance (FID)) was performed. Submissions that passed the first stage were then evaluated for the reproducibility of image statistics corresponding to several feature families including texture, morphology, image moments, fractal statistics and skeleton statistics. A summary measure in this feature space was employed to rank the submissions. Additional analyses of submissions was performed to assess DGM performance specific to individual feature families, the four classes in the training data, and also to identify various artifacts. Results: Fifty-eight submissions from 12 unique users were received for this Challenge. Out of these 12 submissions, 9 submissions passed the first stage of evaluation and were eligible for ranking. The top-ranked submission employed a conditional latent diffusion model, whereas the joint runners-up employed a generative adversarial network, followed by another network for image superresolution. In general, we observed that the overall ranking of the top 9 submissions according to our evaluation method (i) did not match the FID-based ranking, and (ii) differed with respect to individual feature families. Another important finding from our additional analyses was that different DGMs demonstrated similar kinds of artifacts. Conclusions: This Grand Challenge highlighted the need for domain-specific evaluation to further DGM design as well as deployment. It also demonstrated that the specification of a DGM may differ depending on its intended use.

Assessing the Ability of Generative Adversarial Networks to Learn Canonical Medical Image Statistics.

In recent years, generative adversarial networks (GANs) have gained tremendous popularity for potential applications in medical imaging, such as medical image synthesis, restoration, reconstruction, translation, as well as objective image quality assessment. Despite the impressive progress in generating high-resolution, perceptually realistic images, it is not clear if modern GANs reliably learn the statistics that are meaningful to a downstream medical imaging application. In this work, the ability of a state-of-the-art GAN to learn the statistics of canonical stochastic image models (SIMs) that are relevant to objective assessment of image quality is investigated. It is shown that although the employed GAN successfully learned several basic first- and second-order statistics of the specific medical SIMs under consideration and generated images with high perceptual quality, it failed to correctly learn several per-image statistics pertinent to the these SIMs, highlighting the urgent need to assess medical image GANs in terms of objective measures of image quality.

Nuclear Medicine and Artificial Intelligence: Best Practices for Evaluation (the RELAINCE Guidelines).

An important need exists for strategies to perform rigorous objective clinical-task-based evaluation of artificial intelligence (AI) algorithms for nuclear medicine. To address this need, we propose a 4-class framework to evaluate AI algorithms for promise, technical task-specific efficacy, clinical decision making, and postdeployment efficacy. We provide best practices to evaluate AI algorithms for each of these classes. Each class of evaluation yields a claim that provides a descriptive performance of the AI algorithm. Key best practices are tabulated as the RELAINCE (Recommendations for EvaLuation of AI for NuClear medicinE) guidelines. The report was prepared by the Society of Nuclear Medicine and Molecular Imaging AI Task Force Evaluation team, which consisted of nuclear-medicine physicians, physicists, computational imaging scientists, and representatives from industry and regulatory agencies.

Fast X-ray Nanotomography with Sub-10 nm Resolution as a Powerful Imaging Tool for Nanotechnology and Energy Storage Applications.

In the last decade, transmission X-ray microscopes (TXMs) have come into operation in most of the synchrotrons worldwide. They have proven to be outstanding tools for non-invasive ex and in situ 3D characterization of materials at the nanoscale across varying range of scientific applications. However, their spatial resolution has not improved in many years, while newly developed functional materials and microdevices with enhanced performances exhibit nanostructures always finer. Here, optomechanical breakthroughs leading to fast 3D tomographic acquisitions (85 min) with sub-10 nm spatial resolution, narrowing the gap between X-ray and electron microscopy, are reported. These new achievements are first validated with 3D characterizations of nanolithography objects corresponding to ultrahigh-aspect-ratio hard X-ray zone plates. Then, this powerful technique is used to investigate the morphology and conformality of nanometer-thick film electrodes synthesized by atomic layer deposition and magnetron sputtering deposition methods on 3D silicon scaffolds for electrochemical energy storage applications.

Interpersonal Violence during the COVID-19 Lockdown Period in Nepal: A Descriptive Cross-sectional Study.

INTRODUCTION: The government issued a country-wide lockdown in Nepal as a measure to curb the spread of COVID-19 pandemic. This has resulted in various difficult experiences which includes financial loss, separation from loved ones, grief, uncertainty over disease status and loss of freedom. During these stressful situations, interpersonal violence is likely to be aggravated. To avoid the occurrence of adverse events such as impulsive acts, homicide, or suicide, it is important to identify high-risk individuals. METHODS: This is a descriptive cross-sectional, questionnaire-based, online survey by convenience sampling. The prevalence of different types of interpersonal violence with socio-demographic factors, substance use, and overall mental wellbeing was assessed by using descriptive statistical tests. RESULTS: Out of total 556 participants included in the analysis, 50.9% (283) were male and 48.7% (271) were female. There were 100 (18.0%) participants who reported being a victim of interpersonal violence and 101 (18.2%) participants who reported being a perpetrator during the lockdown. The victims of violence were more likely to be living with their spouse alone. The victims and perpetrators were also more likely to have increased alcohol and tobacco use. More number of victims and perpetrators had lower mental wellbeing scores on the WHO wellbeing index. CONCLUSIONS: There was prevalence of interpersonal violence during the COVID-19 lockdown. In addition to the fear regarding pandemic, victims have to face domestic violence placing them at a double injustice. Identification of vulnerable groups and proper management of survivors must be prioritized given the unanimous consensus on the rise of interpersonal violence during periods of heightened stress.

Mental Wellbeing during the Lockdown Period following the COVID-19 Pandemic in Nepal: A Descriptive Cross-sectional Study.

INTRODUCTION: COVID-19 pandemic has profoundly affected all aspects of society, including mental and physical health. Often missed is the fact that the pandemic is occurring against the backdrop of a very high prevalence of mental health issues. Protecting the mental health of people and healthcare workers is important for long-term positive health outcomes and proper control of the outbreak. METHODS: This is a descriptive cross-sectional, questionnaire-based, online survey by convenience sampling. Ethical approval was obtained from the institutional review committee of Nepal Health Research Council (reference no. 2467). Open access, pre-validated questionnaires were used. Participants with significantly poor Mental wellbeing were identified using the WHO well-being index threshold score. Descriptive statistical analysis was carried out. RESULTS: Five hundred and fifty-six participants were included in the analysis. Forty percent of the participants reported a WHO well-being index score of below 13, indicative of poor mental wellbeing and a need for further assessment for depression. Poor Mental wellbeing was more prevalent among participants less than 30 years of age, female gender, never married, diagnosed mental disorder, living alone and those using informal sources for COVID-19 related information. More participants with lower sleep quality score and higher perceived stress score reported poor Mental wellbeing. CONCLUSIONS: Combating this challenge requires integration across disciplines. One potential part of the solution is psychological intervention teams. An emerging positive connotation to the pandemic is that it needs to be harnessed as a tool for improving health facilities, community participation, and fighting misinformation.