AAPM task group report 273: Recommendations on best practices for AI and machine learning for computer-aided diagnosis in medical imaging.

Rapid advances in artificial intelligence (AI) and machine learning, and specifically in deep learning (DL) techniques, have enabled broad application of these methods in health care. The promise of the DL approach has spurred further interest in computer-aided diagnosis (CAD) development and applications using both "traditional" machine learning methods and newer DL-based methods. We use the term CAD-AI to refer to this expanded clinical decision support environment that uses traditional and DL-based AI methods. Numerous studies have been published to date on the development of machine learning tools for computer-aided, or AI-assisted, clinical tasks. However, most of these machine learning models are not ready for clinical deployment. It is of paramount importance to ensure that a clinical decision support tool undergoes proper training and rigorous validation of its generalizability and robustness before adoption for patient care in the clinic. To address these important issues, the American Association of Physicists in Medicine (AAPM) Computer-Aided Image Analysis Subcommittee (CADSC) is charged, in part, to develop recommendations on practices and standards for the development and performance assessment of computer-aided decision support systems. The committee has previously published two opinion papers on the evaluation of CAD systems and issues associated with user training and quality assurance of these systems in the clinic. With machine learning techniques continuing to evolve and CAD applications expanding to new stages of the patient care process, the current task group report considers the broader issues common to the development of most, if not all, CAD-AI applications and their translation from the bench to the clinic. The goal is to bring attention to the proper training and validation of machine learning algorithms that may improve their generalizability and reliability and accelerate the adoption of CAD-AI systems for clinical decision support.

Inactivation of SARS-CoV-2 and photocatalytic degradation by TiO2 photocatalyst coatings.

The novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causative agent of the COVID-19, which is a global pandemic, has infected more than 552 million people, and killed more than 6.3 million people. SARS-CoV-2 can be transmitted through airborne route in addition to direct contact and droplet modes, the development of disinfectants that can be applied in working spaces without evacuating people is urgently needed. TiO2 is well known with some features of the purification, antibacterial/sterilization, making it could be developed disinfectants that can be applied in working spaces without evacuating people. Facing the severe epidemic, we expect to fully expand the application of our proposed effective approach of mechanical coating technique (MCT), which can be prepared on a large-scale fabrication of an easy-to-use TiO2/Ti photocatalyst coating, with hope to curb the epidemic. The photocatalytic inactivation of SARS-CoV-2 and influenza virus, and the photocatalytic degradation of acetaldehyde (C2H4O) and formaldehyde (CH2O) has been investigated. XRD and SEM results show that anatase TiO2 successfully coats on the surface of Ti coatings, while the crystal structure of anatase TiO2 can be increased during the following oxidation in air. The catalytic activity towards methylene blue of TiO2/Ti coating balls has been significantly enhanced by the followed oxidation in air, showing a very satisfying photocatalytic degradation of C2H4O and CH2O. Notably, the TiO2/Ti photocatalyst coating balls demonstrate a significant antiviral activity, with a decrease rate of virus reached 99.96% for influenza virus and 99.99% for SARS-CoV-2.

[Investigation of Foreign Particles in Moderna COVID-19 Vaccine].

Particular batches of Moderna mRNA Coronavirus Disease 2019 (COVID-19) vaccine were recalled after foreign particles were found in some vaccine vials at the vaccination site in Japan in August 2021. We investigated the foreign particles at the request of the Ministry of Health, Labour and Welfare. Energy dispersive X-ray spectroscopy analysis suggested that the foreign particles found in the vials recalled from the vaccination sites were from stainless steel SUS 316L, which was in line with the findings of the root cause investigation by the manufacturer. The sizes of the observed particles ranged from <50 µm to 548 µm in the major axis. Similar foreign particles were also detected in 2 of the 5 vaccine vials of the same lot stored by the manufacturer, indicating that the foreign particles have already been administered to some people via vaccine. Observation of the vials of the same lot by digital microscope found smaller particles those were not detected by visual inspection, suggesting that more vials were affected. Contrarily, visual inspection and subvisible particulate matter test indicated no foreign particles in the vials of normal lots. Possible root cause and strategies to prevent such a deviation were discussed from technical and regulatory aspects.

Season- and facial site-specific skin changes due to long-term mask wearing during the COVID-19 pandemic.

BACKGROUND: As people have regularly worn facial masks due to the coronavirus disease 2019 (COVID-19) pandemic, mask-wear-related adverse effects on the skin have been recognized. The aim of this study was to explore skin changes, their seasonal variations in the general population caused by commonly used masks and a possible mechanism underlying negative effects of mask-wearing. MATERIALS AND METHODS: Eighteen Japanese females participated in the study during summer and winter in Japan. Skin characteristics were measured in the non-mask-wearing preauricular area and the mask-wearing cheek and perioral areas. RESULTS: Trans-epidermal water loss (TEWL) on the cheek area tended to be increased in winter, which was positively correlated with skin scaliness on the same area. Ceramide (CER) content and composition in the mask-covered stratum corneum (SC) were slightly changed between summer and winter, and CER [NP]/[NS] ratio was negatively correlated with the TEWL on the perioral skin in winter. Skin hydration and sebum secretion were higher on the cheek compared to the perioral area in summer. Skin redness was particularly high on the cheek in winter. CONCLUSION: Mask-wear-related skin changes were season- and facial site-specific, and alterations in SC CER may play a role in barrier-related skin problems caused by mask use.

Weakly unsupervised conditional generative adversarial network for image-based prognostic prediction for COVID-19 patients based on chest CT.

Because of the rapid spread and wide range of the clinical manifestations of the coronavirus disease 2019 (COVID-19), fast and accurate estimation of the disease progression and mortality is vital for the management of the patients. Currently available image-based prognostic predictors for patients with COVID-19 are largely limited to semi-automated schemes with manually designed features and supervised learning, and the survival analysis is largely limited to logistic regression. We developed a weakly unsupervised conditional generative adversarial network, called pix2surv, which can be trained to estimate the time-to-event information for survival analysis directly from the chest computed tomography (CT) images of a patient. We show that the performance of pix2surv based on CT images significantly outperforms those of existing laboratory tests and image-based visual and quantitative predictors in estimating the disease progression and mortality of COVID-19 patients. Thus, pix2surv is a promising approach for performing image-based prognostic predictions.

[Evaluation of Valved Holding Chambers Simulating Repurposing Use of Ciclesonide Metered-dose Inhaler by Patients with Pneumonia].

Achieving appropriate inhalation in patients with coronavirus disease 2019 (COVID-19) is a common challenge in the use of repurposed metered-dose inhaler (MDI) formulations. The purpose of this study was to evaluate the effect of five valved holding chambers (VHCs) on the inhalation of ciclesonide from Alvesco MDI. The aerodynamic particle size distribution of ciclesonide discharged from Alvesco MDI was evaluated using a Next Generation Impactor in the presence and absence of VHCs. The use of VHCs retained or slightly increased the amount of ciclesonide in the fine particle diameter range (aerodynamic particle size below 3 µm) (FPD) and reduced the amount at the induction port after coordinated inhalation. However, the use of VHC reduced the FPD of the formulation by increasing the time between the MDI discharge and the pump suction by various degrees among the five VHCs. These results indicated that use of the VHCs and minimizing the inhalation delay time should ensure sufficient inhalation of ciclesonide particles.