Search

BackgroundRecent advancements in generative artificial intelligence (AI) for image generation have presented significant opportunities for medical imaging, offering a promising way to generate realistic virtual medical images while ensuring patient privacy. The generation of a large number of virtual medical images through AI has the potential to augment training datasets for discriminative AI models, particularly in fields with limited data availability, such as neuroimaging. Current studies on generative AI in neuroimaging have mainly focused on disease discrimination; however, its potential for simulating complex phenomena in psychiatric disorders remains unknown. In this study, as examples of a simulation, we aimed to present a novel generative AI model that transforms magnetic resonance imaging (MRI) images of healthy individuals into images that resemble those of patients with schizophrenia (SZ) and explore its application.MethodsWe used anonymized public datasets from the Center for Biomedical Research Excellence (SZ, 71 patients; healthy subjects [HSs], 71 patients) and the Autism Brain Imaging Data Exchange (autism spectrum disorder [ASD], 79 subjects; HSs, 105 subjects). We developed a model to transform MRI images of HSs into MRI images of SZ using cycle generative adversarial networks. The efficacy of the transformation was evaluated using voxel-based morphometry to assess the differences in brain region volumes and the accuracy of age prediction pre- and post-transformation. In addition, the model was examined for its applicability in simulating disease comorbidities and disease progression.ResultsThe model successfully transformed HS images into SZ images and identified brain volume changes consistent with existing case-control studies. We also applied this model to ASD MRI images, where simulations comparing SZ with and without ASD backgrounds highlighted the differences in brain structures due to comorbidities. Furthermore, simulating disease progression while preserving individual characteristics showcased the model’s ability to reflect realistic disease trajectories.DiscussionThe results suggest that our generative AI model can capture subtle changes in brain structures associated with SZ, providing a novel tool for visualizing brain changes in different diseases. The potential of this model extends beyond clinical diagnosis to advances in the simulation of disease mechanisms, which may ultimately contribute to the refinement of therapeutic strategies.

Abstract Alzheimer’s disease is one of the most important health-care challenges in the world. For decades, numerous efforts have been made to develop therapeutics for Alzheimer’s disease, but most clinical trials have failed to show significant treatment effects on slowing or halting cognitive decline. Among several challenges in such trials, one recently noticed but unsolved is biased allocation of fast and slow cognitive decliners to treatment and placebo groups during randomization caused by the large individual variation in the speed of cognitive decline. This allocation bias directly results in either over- or underestimation of the treatment effect from the outcome of the trial. In this study, we propose a stratified randomization method using the degree of cognitive decline predicted by an artificial intelligence model as a stratification index to suppress the allocation bias in randomization and evaluate its effectiveness by simulation using ADNI data set.

We previously reported that variations in the number and type of bacteria found in public spaces are influenced by environmental factors. However, based on field survey data alone, whether the dynamics of bacteria in the air change as a result of a single environmental factor or multiple factors working together remains unclear. To address this, mathematical modeling may be applied. We therefore conducted a reanalysis of the previously acquired data using principal component analysis (PCA) in conjunction with a generalized linear model (Glm2) and a statistical analysis of variance (ANOVA) test employing the χ2 distribution. The data used for the analysis were reused from a previous public environmental survey conducted at 8:00-20:00 on May 2, June 1, and July 5, 2016 (regular sampling) and at 5:50-7:50 and 20:15-24:15 on July 17, 2017 (baseline sampling) in the Sapporo underground walking space, a 520-meter-long underground walkway. The dataset consisted of 60 samples (22 samples for "bacterial flora"), including variables such as "temperature (T)," "humidity (H)," "atmospheric pressure (A)," "traffic pedestrians (TP)," "number of inorganic particles (Δ5: 1-5 μm)," "number of live airborne bacteria," and "bacterial flora." Our PCA with these environmental factors (T, H, A, and TP) revealed that the 60 samples could be categorized into four groups (G1 to G4), primarily based on variations in PC1 [Loadings: T(-0.62), H(-0.647), TP(0.399), A(0.196)] and PC2 [Loadings: A(-0.825), TP(0.501), H(0.209), T(-0.155)]. Notably, the number of inorganic particles significantly increased from G4 to G1, but the count of live bacteria was highest in G2, with no other clear pattern. Further analysis with Glm2 indicated that changes in inorganic particles could largely be explained by two variables (H/TP), while live bacteria levels were influenced by all explanatory variables (TP/A/H/T). ANOVA tests confirmed that inorganic particles and live bacteria were influenced by different factors. Moreover, there were minimal changes in bacterial flora observed among the groups (G1-G4). In conclusion, our findings suggest that the dynamics of live bacteria in the underground walkway differ from those of inorganic particles and are regulated in a complex manner by multiple environmental factors. This discovery may contribute to improving public health in urban settings.

BACKGROUND: Cerebral vasospasm (CVS) is one of the most critical factors associated with clinical outcomes of patients with subarachnoid hemorrhage (SAH). Clazosentan has been investigated worldwide as a prophylactic agent to prevent CVS. We evaluated a new CVS management protocol which included clazosentan. METHODS: Consecutive 138 patients with SAH, hospitalized in our institution between January 2017 and December 2022, were included in this study. Baseline characteristics, clinical findings, and operative records were analyzed retrospectively. From May 2022, 10 mg/h clazosentan was co-administered with fasudil to all patients according to the indication in the Japanese label. Patients admitted before this date received the conventional combined protocol using the fasudil hydrochloride, nicardipine, and ozagrel. RESULTS: Eighteen (13.0%) patients received the new protocol during the CVS period (defined as day 1 up to day 14 after SAH onset). There were 54 (39.1%) elderly patients aged 75 years or older. Seventy-two (52.2%) patients underwent neurosurgical clipping, whereas 55 (39.9%) patients received endovascular coiling. Among the patients with new protocol, only one patient (5.6%) had symptomatic CVS, compared with 18 patients (15.0%) in those with conventional protocol. More patients who received the new protocol had fluid retention compared with control group (38.9% [7/18] vs. 8.3% [10/120]). Other results did not differ between the two groups. CONCLUSIONS: Clinical outcomes of the new protocol were comparable to those of conventional protocol. Clazosentan may simplify anti-vasospasm treatment. Fluid retention was a specific side-effect of clazosentan, which requires attention especially in the first half of the CVS period.

Orthodontic space closure following tooth extraction is often hindered by alveolar bone deficiency. This study investigates the therapeutic use of nuclear factor-kappa B (NF-κB) decoy oligodeoxynucleotides loaded with polylactic-co-glycolic acid nanospheres (PLGA-NfDs) to mitigate alveolar bone loss during orthodontic tooth movement (OTM) following the bilateral extraction of maxillary first molars in a controlled experiment involving forty rats of OTM model with ethics approved. The decreased tendency of the OTM distance and inclination angle with increased bone volume and improved trabecular bone structure indicated minimized alveolar bone destruction. Reverse transcription-quantitative polymerase chain reaction and histomorphometric analysis demonstrated the suppression of inflammation and bone resorption by downregulating the expression of tartrate-resistant acid phosphatase, tumor necrosis factor-α, interleukin-1β, cathepsin K, NF-κB p65, and receptor activator of NF-κB ligand while provoking periodontal regeneration by upregulating the expression of alkaline phosphatase, transforming growth factor-β1, osteopontin, and fibroblast growth factor-2. Importantly, relative gene expression over the maxillary second molar compression side in proximity to the alveolus highlighted the pharmacological effect of intra-socket PLGA-NfD administration, as evidenced by elevated osteocalcin expression, indicative of enhanced osteocytogenesis. These findings emphasize that locally administered PLGA-NfD serves as an effective inflammatory suppressor and yields periodontal regenerative responses following tooth extraction.