EEG-VTTCNet: A loss joint training model based on the vision transformer and the temporal convolution network for EEG-based motor imagery classification.

Brain-computer interface (BCI) is a technology that directly connects signals between the human brain and a computer or other external device. Motor imagery electroencephalographic (MI-EEG) signals are considered a promising paradigm for BCI systems, with a wide range of potential applications in medical rehabilitation, human-computer interaction, and virtual reality. Accurate decoding of MI-EEG signals poses a significant challenge due to issues related to the quality of the collected EEG data and subject variability. Therefore, developing an efficient MI-EEG decoding network is crucial and warrants research. This paper proposes a loss joint training model based on the vision transformer (VIT) and the temporal convolutional network (EEG-VTTCNet) to classify MI-EEG signals. To take advantage of multiple modules together, the EEG-VTTCNet adopts a shared convolution strategy and a dual-branching strategy. The dual-branching modules perform complementary learning and jointly train shared convolutional modules with better performance. We conducted experiments on the BCI Competition IV-2a and IV-2b datasets, and the proposed network outperformed the current state-of-the-art techniques with an accuracy of 84.58% and 90.94%, respectively, for the subject-dependent mode. In addition, we used t-SNE to visualize the features extracted by the proposed network, further demonstrating the effectiveness of the feature extraction framework. We also conducted extensive ablation and hyperparameter tuning experiments to construct a robust network architecture that can be well generalized.

Long-Term Use of Nitrous Oxide Resulting in Vitamin B12 Deficiency Causing Cervical Myelopathy.

Nitrous oxide, commonly known as laughing gas, gained popularity in the medical field as an anesthetic. It also causes euphoria and acts as an anxiolytic in the human body. However, there is limited information available on its toxicity, particularly its neurotoxicity, which has been emerging in younger populations using it for recreational purposes. Here, we present a case of a young patient with subacute combined degeneration secondary to vitamin B12 deficiency from chronic use of nitrous oxide.

PLGA Nanoplatform for the Hypoxic Tumor Delivery: Folate Targeting, Therapy, and Ultrasound/Photoacoustic Imaging.

Effective targeting of breast tumors is critical for improving therapeutic outcomes in breast cancer treatment. Additionally, hypoxic breast cancers are difficult to treat due to resistance toward chemotherapeutics, poor vascularity, and enhanced angiogenesis, which complicate effective drug delivery and therapeutic response. Addressing this formidable challenge requires designing a drug delivery system capable of targeted delivery of the anticancer agent, inhibition of efflux pump, and suppression of the tumor angiogenesis. Here, we have introduced Palbociclib (PCB)-loaded PLGA nanoparticles (NPs) consisting of chitosan-folate (CS-FOL) for folate receptor-targeted breast cancer therapy. The developed NPs were below 219 nm with a smooth, spherical surface shape. The entrapment efficiencies of NPs were achieved up to 85.78 ± 1.8%. Targeted NPs demonstrated faster drug release at pH 5.5, which potentiated the therapeutic efficacy of NPs due to the acidic microenvironment of breast cancer. In vitro cellular uptake study in MCF-7 cells confirmed the receptor-mediated endocytosis of targeted NPs. In vivo ultrasound and photoacoustic imaging studies on rats with hypoxic breast cancer showed that targeted NPs significantly reduced tumor growth and hypoxic tumor volume, and suppressed angiogenesis.

Emission-based sensing of cobalt (II) and vitamin B12 via a bis-indole derivative.

In this study, a bis-indole compound was synthesized, characterized by 1H NMR, Fourier transform infrared, and mass spectroscopic measurements and used as a selective and efficient probe for the spectrofluorimetric analysis of Co (II). The cobalt-induced quenching in the emission maximum at 567 nm was considered as the analytical signal in calibration studies. When encapsulated in a polymethyl methacrylate (PMMA) matrix, the bis-indole compound exhibited a limit of detection (LOD) of 3.60 × 10-11 M for Co (II). Vitamin B12, which contains a cobalt ion in the center of a corrin ring in its structure, was also successfully quantified using the same probe. The bis-indole compound showed a linear response based on quenching for increasing concentrations of vitamin B12, partially mimicking the contracted tetrapyrrole ring found naturally in the center of vitamin B12. The LOD for vitamin B12 was found to be 76 nm. Promising photophysical properties of the proposed probe, including high molar extinction coefficient, considerable quantum yield (0.46 and 0.64 in tetrahydrofuran and PMMA, respectively), high Stoke's shift and satisfactory photostability, make it a good choice for fluorescence-based Co (II) determination. The ML3-type stoichiometry of the complex between the dye and cobalt was elucidated both by Job's method and by high-resolution mass spectrometry (HR-MS).

ViT-PSO-SVM: Cervical Cancer Predication Based on Integrating Vision Transformer with Particle Swarm Optimization and Support Vector Machine.

Cervical cancer (CCa) is the fourth most prevalent and common cancer affecting women worldwide, with increasing incidence and mortality rates. Hence, early detection of CCa plays a crucial role in improving outcomes. Non-invasive imaging procedures with good diagnostic performance are desirable and have the potential to lessen the degree of intervention associated with the gold standard, biopsy. Recently, artificial intelligence-based diagnostic models such as Vision Transformers (ViT) have shown promising performance in image classification tasks, rivaling or surpassing traditional convolutional neural networks (CNNs). This paper studies the effect of applying a ViT to predict CCa using different image benchmark datasets. A newly developed approach (ViT-PSO-SVM) was presented for boosting the results of the ViT based on integrating the ViT with particle swarm optimization (PSO), and support vector machine (SVM). First, the proposed framework extracts features from the Vision Transformer. Then, PSO is used to reduce the complexity of extracted features and optimize feature representation. Finally, a softmax classification layer is replaced with an SVM classification model to precisely predict CCa. The models are evaluated using two benchmark cervical cell image datasets, namely SipakMed and Herlev, with different classification scenarios: two, three, and five classes. The proposed approach achieved 99.112% accuracy and 99.113% F1-score for SipakMed with two classes and achieved 97.778% accuracy and 97.805% F1-score for Herlev with two classes outperforming other Vision Transformers, CNN models, and pre-trained models. Finally, GradCAM is used as an explainable artificial intelligence (XAI) tool to visualize and understand the regions of a given image that are important for a model's prediction. The obtained experimental results demonstrate the feasibility and efficacy of the developed ViT-PSO-SVM approach and hold the promise of providing a robust, reliable, accurate, and non-invasive diagnostic tool that will lead to improved healthcare outcomes worldwide.

Pseudomicroangiopathic Thrombotic Syndrome: Unveiling the Vitamin B12 Deficiency Connection.

Pernicious anemia, a manifestation of vitamin B12 deficiency, can present with a spectrum of hematological abnormalities, sometimes mimicking more severe conditions such as thrombotic microangiopathy (TMA). This case report details a 53-year-old female who presented with significant weight loss, watery diarrhea, and jaundice. Laboratory investigations revealed pancytopenia, hemolysis, and schistocytes, initially suggesting a diagnosis of microangiopathic hemolytic anemia (MAHA). However, significantly low vitamin B12 levels and subsequent bone marrow examination confirmed pernicious anemia with megaloblastic changes. This case underscores the importance of considering vitamin B12 deficiency in the differential diagnosis of patients presenting with TMA-like symptoms. Early recognition and treatment with vitamin B12 supplementation led to rapid clinical improvement and the resolution of symptoms. This report highlights the need for heightened clinical awareness of atypical presentations of pernicious anemia to prevent misdiagnosis and ensure timely, effective treatment.

Structural and Molecular Imaging-based Characterization of Soft Tissue and Vascular Calcification in Hyperphosphatemic Familial Tumoral Calcinosis.

Hyperphosphatemic Familial Tumoral Calcinosis (HFTC) is a rare disorder caused by deficient FGF23 signaling and resultant ectopic calcification. In this study, we systematically characterized and quantified macro- and micro-calcification in an HFTC cohort using computed tomography (CT) and 18F-sodium fluoride positron emission tomography/CT (18F-NaF PET/CT). Fourier-transform infrared (FTIR) spectroscopy was performed on four phenotypically different calcifications from a patient with HFTC, showing the dominant component to be hydroxyapatite. Eleven patients with HFTC were studied with CT and/or 18F-NaF PET/CT. Qualitative review was done to describe the spectrum of imaging findings on both modalities. CT-based measures of volume (e.g., total calcific burden and lesion volume) and density (Hounsfield units) were quantified and compared to PET-based measures of metabolic activity (e.g., mean standardized uptake values). Microcalcification scores (mCSs) were calculated for the vasculature of six patients using 18F-NaF PET/CT and visualized on a standardized vascular atlas. Ectopic calcifications were present in 82% of patients, predominantly near joints and the distal extremities. Considerable heterogeneity was observed in total calcific burden per patient (823.0 ± 670.1 cm3, n = 9) and lesion volume (282.5 ± 414.8 cm3, n = 27). The largest lesions were found at the hips and shoulders. 18F-NaF PET offered the ability to differentiate active vs. quiescent calcifications. Calcifications were also noted in multiple anatomic locations, including brain parenchyma (50%). Vascular calcification was seen in the distal aorta, carotid, and coronaries in 50%, 70%, 73%, and 50%, respectively. 18F-NaF-avid, but CT-negative calcification was seen in a 17-year-old patient, implicating early onset vascular calcification. This first systematic assessment of calcifications in a cohort of patients with HFTC has identified the early onset, prevalence, and extent of macro- and micro-calcification. It supports 18F-NaF PET/CT as a clinical tool for distinguishing between active and inactive calcification, informing disease progression, and quantification of ectopic and vascular disease burden.

Hyperphosphatemic familial tumoral calcinosis (HFTC) is a rare disorder in which patients develop sometimes large debilitating calcifications of soft tissues and blood vessels. It is caused by deficient fibroblast growth factor-23 that leads to high phosphate levels, which contributes to the calcifications. The calcifications and manifestations of this disorder have not been well characterized. We determined the mineral composition of the calcifications to be hydroxyapatite. Capitalizing on the fact fluoride can be integrated into hydroxyapatite, we used radiolabeled sodium fluoride positron emission tomography/computed tomography scans (18F-NaF PET/CT) to characterize and quantify the calcifications in 11 patients. 82% of the patients had calcifications, with the largest located at the hips and shoulders. Micro-calcifications were found in the blood vessels of most patients, including children. The technique also enabled us to differentiate between active versus stable calcifications. This first systematic assessment of calcifications in patients with HFTC showed the utility of 18F-NaF PET/CT as a tool to identify and quantify calcifications, as well as distinguish between active and stable calcifications. This approach will inform disease progression and may prove useful for measuring response to treatment.

A human activity recognition method based on Vision Transformer.

Human activity recognition has a wide range of applications in various fields, such as video surveillance, virtual reality and human-computer intelligent interaction. It has emerged as a significant research area in computer vision. GCN (Graph Convolutional networks) have recently been widely used in these fields and have made great performance. However, there are still some challenges including over-smoothing problem caused by stack graph convolutions and deficient semantics correlation to capture the large movements between time sequences. Vision Transformer (ViT) is utilized in many 2D and 3D image fields and has surprised results. In our work, we propose a novel human activity recognition method based on ViT (HAR-ViT). We integrate enhanced AGCL (eAGCL) in 2s-AGCN to ViT to make it process spatio-temporal data (3D skeleton) and make full use of spatial features. The position encoder module orders the non-sequenced information while the transformer encoder efficiently compresses sequence data features to enhance calculation speed. Human activity recognition is accomplished through multi-layer perceptron (MLP) classifier. Experimental results demonstrate that the proposed method achieves SOTA performance on three extensively used datasets, NTU RGB+D 60, NTU RGB+D 120 and Kinetics-Skeleton 400.

Hypophosphatemic rickets and short stature.

An 18-month-old male presented with gross motor delay and poor growth (weight z-score -2.21, length z-score -4.26). Radiographs showed metaphyseal irregularities suggesting metaphyseal dysplasia and sagittal craniosynostosis. Biochemical evaluation supported hypophosphatemic rickets [serum phosphorus 2.3 mg/dL (reference range (RR) 4.3-6.8), alkaline phosphatase 754 unit/L (RR 156-369)] due to renal phosphate wasting (TmP/GFR 4.3 mg/dL, normal for age 4.3-6.8), with C-terminal fibroblast growth factor 23 (FGF23) 125 RU/mL (>90 during hypophosphatemia suggests FGF23-mediated hypophosphatemia). Treatment was initiated with calcitriol and phosphate. Genetic analysis showed a pathogenic variant of FGF23: c.527G > A (p.Arg176Gln) indicative of autosomal dominant hypophosphatemic rickets (ADHR). Consistent with reports linking iron deficiency with the ADHR phenotype, low ferritin was detected. Following normalization of ferritin level (41 ng/mL) with oral ferrous sulfate replacement, biochemical improvement was demonstrated (FGF23 69 RU/mL, phosphorus 5.0 mg/dL and alkaline phosphatase 228 unit/L). Calcitriol and phosphate were discontinued. Three years later, the patient demonstrated improved developmental milestones, linear growth (length Z-score -2.01), radiographic normalization of metaphyses, and stabilization of craniosynostosis. While the most common cause of hypophosphatemic rickets is X-linked hypophosphatemia, other etiologies should be considered as treatment differs. In ADHR, normalization of iron leads to biochemical and clinical improvement.

Burosumab treatment of X-linked hypophosphatemia patients: interim analysis of the SUNFLOWER longitudinal, observational cohort study.

X-linked hypophosphatemia (XLH) is a genetic disease that results in excessive FGF23, chronic hypophosphatemia, and musculoskeletal abnormalities, with affected patients experiencing symptoms such as bone pain, bone deformity, fracture, and pseudofracture. Burosumab is a fully human monoclonal antibody that binds to FGF23, improving lowered serum 1,25(OH)2D and phosphate levels in patients with XLH. There are insufficient data on the use of burosumab, its safety, and the outcomes of treated patients in a real-world setting. The SUNFLOWER (Study of longitUdinal observatioN For patients with X-Linked hypOphosphatemic rickets/osteomalacia in collaboration With Asian partnERs) study is an ongoing longitudinal, observational cohort study of patients with XLH in Japan and South Korea. Enrollment occurred between April 2018 and December 2020. This interim analysis compared the background characteristics of patients who received burosumab with those who did not, and assessed improvements in biomarkers, physical and motor function, health-related quality-of-life (HRQOL) and other patient-reported outcome (PRO) measures, as well as the safety of burosumab treatment in 143 Japanese patients from 15 institutions over 6 mo. The patients had a median [interquartile range] age of 17.5 [11.0, 38.8] yr and 98 (68.5%) were female. Among patients aged <18 and ≥18 yr, 40/73 (54.8%) and 25/70 (35.7%) received burosumab, respectively. More patients aged ≥18 who received burosumab had bone pain at baseline vs those not treated with burosumab (6/25, 24.0% vs 2/45, 4.4%, p=.021). Patients treated with burosumab had improved serum phosphate and 1,25(OH)2D levels; moreover, rickets severity and HRQOL/PRO measures, such as pain, appeared to improve over 6 mo of burosumab treatment, and no new safety concerns were identified. This study identified trends in the background characteristics of patients with XLH who receive burosumab in real-world clinical practice. Furthermore, the results support the use of burosumab therapy in real-world settings.

Cycle contrastive adversarial learning with structural consistency for unsupervised high-quality image deraining transformer.

In overcoming the challenges faced in adapting to paired real-world data, recent unsupervised single image deraining (SID) methods have proven capable of accomplishing notably acceptable deraining performance. However, the previous methods usually fail to produce a high quality rain-free image due to neglecting sufficient attention to semantic representation and the image content, which results in the inability to completely separate the content from the rain layer. In this paper, we develop a novel cycle contrastive adversarial framework for unsupervised SID, which mainly consists of cycle contrastive learning (CCL) and location contrastive learning (LCL). Specifically, CCL achieves high-quality image reconstruction and rain-layer stripping by pulling similar features together while pushing dissimilar features further in both semantic and discriminant latent spaces. Meanwhile, LCL implicitly constrains the mutual information of the same location of different exemplars to maintain the content information. In addition, recently inspired by the powerful Segment Anything Model (SAM) that can effectively extract widely applicable semantic structural details, we formulate a structural-consistency regularization to fine-tune our network using SAM. Apart from this, we attempt to introduce vision transformer (VIT) into our network architecture to further improve the performance. In our designed transformer-based GAN, to obtain a stronger representation, we propose a multi-layer channel compression attention module (MCCAM) to extract a richer feature. Equipped with the above techniques, our proposed unsupervised SID algorithm, called CCLformer, can show advantageous image deraining performance. Extensive experiments demonstrate both the superiority of our method and the effectiveness of each module in CCLformer. The code is available at https://github.com/zhihefang/CCLGAN.

Severe B12 Deficiency Causing a Maturation Defect Mimicking Myelodysplastic Syndrome With Excess Blasts.

Vitamin B12 deficiency is a common condition that is often asymptomatic, though in severe cases may cause megaloblastic anemia and even neurologic symptoms. Occasionally, the clinical presentation can include pancytopenia and thus mimic a more concerning myelodysplastic syndrome (MDS) until corrected by B12 supplementation. In this unusual case, we present a patient with B12 deficiency who presents with severe macrocytic anemia, neutropenia, lymphocytosis, and a bone marrow morphology consistent with MDS.

Tumor-induced osteomalacia: A systematic literature review.

Introduction: Tumor-induced osteomalacia (TIO), is a rare acquired paraneoplastic syndrome characterized by defective bone mineralization, caused by the overproduction of fibroblast growth factor 23 (FGF23) by a tumor. Material and methods: We conducted a systematic review to identify all case reports of TIO, focusing on those associated with mesenchymal tumors. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) consensus, and we included patients with a diagnosis of TIO and histological confirmation of phosphaturic mesenchymal tumors or resolution of the condition after treatment of the tumor. Bibliographical searches were carried out until December 2023 in the Cochrane Library, Medline and Embase, as well as congress abstracts online. Results: We identified 769 articles with 1979 cases reported. Most patients were adults, with a higher incidence on men. Disease duration before diagnosis is a mean of 4.8 years. Most tumors were histologically classified as PMT. Lower limbs were the predominant location. Hypophosphatemia was present in 99.8 % of patients. The FGF23 was elevated at diagnosis in 95.5 %. Resection of the tumor was the treatment of choice in most of patients. After resection, there was a clinical improvement in 97.6 % of cases, and serum phosphorus and FGF23 levels returned to normal ranges in 91.5 % and 81.4 % of the patients, respectively. Conclusion: TIO is usually misdiagnosed with rheumatological or musculoskeletal disorders. The diagnosis should be suspected in patients with hypophosphatemic osteomalacia, and the measurement of serum FGF23 can be useful for diagnosis and management.

Apriori prediction of chemotherapy response in locally advanced breast cancer patients using CT imaging and deep learning: transformer versus transfer learning.

Objective: Neoadjuvant chemotherapy (NAC) is a key element of treatment for locally advanced breast cancer (LABC). Predicting the response to NAC for patients with Locally Advanced Breast Cancer (LABC) before treatment initiation could be beneficial to optimize therapy, ensuring the administration of effective treatments. The objective of the work here was to develop a predictive model to predict tumor response to NAC for LABC using deep learning networks and computed tomography (CT). Materials and methods: Several deep learning approaches were investigated including ViT transformer and VGG16, VGG19, ResNet-50, Res-Net-101, Res-Net-152, InceptionV3 and Xception transfer learning networks. These deep learning networks were applied on CT images to assess the response to NAC. Performance was evaluated based on balanced_accuracy, accuracy, sensitivity and specificity classification metrics. A ViT transformer was applied to utilize the attention mechanism in order to increase the weight of important part image which leads to better discrimination between classes. Results: Amongst the 117 LABC patients studied, 82 (70%) had clinical-pathological response and 35 (30%) had no response to NAC. The ViT transformer obtained the best performance range (accuracy = 71 ± 3% to accuracy = 77 ± 4%, specificity = 86 ± 6% to specificity = 76 ± 3%, sensitivity = 56 ± 4% to sensitivity = 52 ± 4%, and balanced_accuracy=69 ± 3% to balanced_accuracy=69 ± 3%) depending on the split ratio of train-data and test-data. Xception network obtained the second best results (accuracy = 72 ± 4% to accuracy = 65 ± 4, specificity = 81 ± 6% to specificity = 73 ± 3%, sensitivity = 55 ± 4% to sensitivity = 52 ± 5%, and balanced_accuracy = 66 ± 5% to balanced_accuracy = 60 ± 4%). The worst results were obtained using VGG-16 transfer learning network. Conclusion: Deep learning networks in conjunction with CT imaging are able to predict the tumor response to NAC for patients with LABC prior to start. A ViT transformer could obtain the best performance, which demonstrated the importance of attention mechanism.

Preclinical development of EXT608, an investigational parathyroid hormone derivative with extended half-life for the treatment of hypoparathyroidism.

Hypoparathyroidism, a deficiency of parathyroid hormone (PTH), results in hypocalcemia, hyperphosphatemia, and hypercalciuria. The disease is poorly controlled by calcium and vitamin D supplements or native PTH(1-84) replacement therapy. A version of PTH is being developed using D-VITylation technology, whereby vitamin D is conjugated to a therapeutic peptide, which confers a long plasma half-life by virtue of binding to the abundant vitamin D binding protein (DBP). D-VITylation of PTH caused no reduction in activity at the PTHR1 receptor, and resulted in a plasma elimination half-life of 7-15 h in rats and 24-32 h in cynomolgus monkeys. Analysis of steady-state pharmacokinetics as a function of dose showed flat profiles with smaller peak:trough ratios at low doses, indicative of slower subcutaneous absorption. In thyroparathyroidectomized (TPTx) rats, PTH(1-34)-vitamin D conjugates restored serum calcium and phosphate levels into the normal range over the 24 h dosing period, and increased bone turnover markers and reduced bone mineral density. Urinary calcium was initially elevated, but normalized by the end of treatment on day 27. In healthy monkeys, a single dose of PTH(1-34)-vitamin D conjugates elevated serum calcium levels above the normal range for a period of 24-48 h while simultaneously reducing urinary calcium. Therefore, the lead compound, EXT608, is a promising candidate as a therapeutic that can truly mimic the endogenous activity of PTH and warrants further study in patients with hypoparathyroidism.

Automated classification of choroidal neovascularization, diabetic macular edema, and drusen from retinal OCT images using vision transformers: a comparative study.

Classifying retinal diseases is a complex problem because the early problematic areas of retinal disorders are quite small and conservative. In recent years, Transformer architectures have been successfully applied to solve various retinal related health problems. Age-related macular degeneration (AMD) and diabetic macular edema (DME), two prevalent retinal diseases, can cause partial or total blindness. Diseases therefore require an early and accurate detection. In this study, we proposed Vision Transformer (ViT), Tokens-To-Token Vision Transformer (T2T-ViT) and Mobile Vision Transformer (Mobile-ViT) algorithms to detect choroidal neovascularization (CNV), drusen, and diabetic macular edema (DME), and normal using optical coherence tomography (OCT) images. The predictive accuracies of ViT, T2T-ViT and Mobile-ViT achieved on the dataset for the classification of OCT images are 95.14%, 96.07% and 99.17% respectively. Experimental results obtained from ViT approaches showed that Mobile-ViT have superior performance with regard to classification accuracy in comparison with the others. Overall, it has been observed that ViT architectures have the capacity to classify with high accuracy in the diagnosis of retinal diseases.

The Correlation between Maternal and Neonatal Vit D (25(OH)D) Levels in Greece: A Cross-Sectional Study.

BACKGROUND: Few studies have correlated maternal and neonatal Vit D (25(OH)D) levels at birth in Greece. We investigated this potential association, taking into account the administration or not of low doses (400-800 IU) of prenatal Vit D supplements. Our study contributes evidence not only to the small amount of existing literature regarding the above correlation, but also to the topic of maternal and neonatal vitamin D deficiency (VDD) during pregnancy in Mediterranean countries, such as Greece. METHODS: A cross-sectional study was conducted on 248 neonates and their mothers from September 2019 to January 2022. Blood samples of 25(OH)D were studied at the time of delivery. Frequency counts and percentages were registered, and logistic regression was used to investigate the independent factors associated with maternal Vit D status. The Chi-square test and the Pearson coefficient were used to demonstrate a possible association between maternal and neonatal 25(OH)D levels. RESULTS: Our findings show a high prevalence of VDD in Greek women and their newborns at birth. This was observed not only in women who did not receive Vit D supplements, but also in all the study groups, especially in the autumn and winter months. We observed that mothers who received low doses (400-800 IU) of prenatal Vit D supplements increased both their own 25(OH)D concentrations and those of their newborns; however, the latter did not seem to be completely covered by the prenatal administration of Vit D because, although their 25(OH)D concentrations increased, they never reached sufficient 25(OH)D levels, unlike their mothers who reached sufficient concentrations. CONCLUSIONS: Overall, this study highlights the strong association between maternal and neonatal 25(OH)D concentrations at the end of gestation. However, neonates tended to show even lower 25(OH)D concentrations relative to maternal 25(OH)D concentrations. The same phenomenon was observed irrespective of the administration of Vit D supplements during pregnancy. Moreover, this is what was observed concerning the administration of formulations with 400-800 IU of Vit D, which the doctors in our clinic used in the present study. In any case, more clinical studies related to the administration of higher doses of Vit D supplementation to pregnant women would lead to more reliable conclusions. Without a doubt, the measurement of maternal vitamin D status during pregnancy provides opportunities for preventive and therapeutic interventions in the mother-infant pair.

Lightweight Low-Rank Adaptation Vision Transformer Framework for Cervical Cancer Detection and Cervix Type Classification.

Cervical cancer is a major health concern worldwide, highlighting the urgent need for better early detection methods to improve outcomes for patients. In this study, we present a novel digital pathology classification approach that combines Low-Rank Adaptation (LoRA) with the Vision Transformer (ViT) model. This method is aimed at making cervix type classification more efficient through a deep learning classifier that does not require as much data. The key innovation is the use of LoRA, which allows for the effective training of the model with smaller datasets, making the most of the ability of ViT to represent visual information. This approach performs better than traditional Convolutional Neural Network (CNN) models, including Residual Networks (ResNets), especially when it comes to performance and the ability to generalize in situations where data are limited. Through thorough experiments and analysis on various dataset sizes, we found that our more streamlined classifier is highly accurate in spotting various cervical anomalies across several cases. This work advances the development of sophisticated computer-aided diagnostic systems, facilitating more rapid and accurate detection of cervical cancer, thereby significantly enhancing patient care outcomes.

A Multimodal Transformer Model for Recognition of Images from Complex Laparoscopic Surgical Videos.

The determination of the potential role and advantages of artificial intelligence-based models in the field of surgery remains uncertain. This research marks an initial stride towards creating a multimodal model, inspired by the Video-Audio-Text Transformer, that aims to reduce negative occurrences and enhance patient safety. The model employs text and image embedding state-of-the-art models (ViT and BERT) to assess their efficacy in extracting the hidden and distinct features from the surgery video frames. These features are then used as inputs for convolution-free Transformer architectures to extract comprehensive multidimensional representations. A joint space is then used to combine the text and image features extracted from both Transformer encoders. This joint space ensures that the relationships between the different modalities are preserved during the combination process. The entire model was trained and tested on laparoscopic cholecystectomy (LC) videos encompassing various levels of complexity. Experimentally, a mean accuracy of 91.0%, a precision of 81%, and a recall of 83% were reached by the model when tested on 30 videos out of 80 from the Cholec80 dataset.

Male Lrp5A214V mice maintain high bone mass during dietary calcium restriction by altering the vitamin D endocrine system.

Environmental factors and genetic variation individually impact bone. However, it is not clear how these factors interact to influence peak bone mass accrual. Here we tested whether genetically programmed high bone formation driven by missense mutations in the Lrp5 gene (Lrp5A214V) altered the sensitivity of mice to an environment of inadequate dietary calcium (Ca) intake. Weanling male Lrp5A214V mice and wildtype littermates (control) were fed AIN-93G diets with 0.125%, 0.25%, 0.5% (reference, basal), or 1% Ca from weaning until 12 weeks of age (ie, during bone growth). Urinary Ca, serum Ca, Ca regulatory hormones (PTH, 1,25 dihydroxyvitamin D3 (1,25(OH)2D3)), bone parameters (µCT, ash), and renal/intestinal gene expression were analyzed. As expected, low dietary Ca intake negatively impacted bones and Lrp5A214V mice had higher bone mass and ash content. Although bones of Lrp5A214V mice have more matrix to mineralize, their bones were not more susceptible to low dietary Ca intake. In control mice, low dietary Ca intake exerted expected effects on serum Ca (decreased), PTH (increased), and 1,25(OH)2D3 (increased) as well as their downstream actions (ie, reducing urinary Ca, increasing markers of intestinal Ca absorption). In contrast, Lrp5A214V mice had elevated serum Ca with a normal PTH response but a blunted 1,25(OH)2D3 response to low dietary Ca that was reflected in the renal 1,25(OH)2D3 producing/degrading enzymes, Cyp27b1 and Cyp24a1. Despite elevated serum Ca in Lrp5A214V mice, urinary Ca was not elevated. Despite an abnormal serum 1,25(OH)2D3 response to low dietary Ca, intestinal markers of Ca absorption (Trpv6, S100g mRNA) were elevated in Lrp5A214V mice and responded to low Ca intake. Collectively, our data indicate that the Lrp5A214V mutation induces changes in Ca homeostasis that permit mice to retain more Ca and support their high bone mass phenotype.

Optimizing peak bone mass (PBM) is critical for strong bones and osteoporosis prevention. Both genetics and dietary factors like calcium (Ca) contribute to PBM. The goal of this research study was to determine how dietary Ca intake and genetics interact with each other to impact bone mass. Lowering dietary Ca in control mice causes hormonal changes that increase intestinal Ca absorption and reduce urinary Ca loss to protect bone; but this process fails when dietary Ca becomes too low. However, mice with genetically programmed high bone mass could maintain high bone mass even when challenged with Ca deficient diets. This protection is because the high bone mass mice maintain higher serum Ca, have altered production and utilization of Ca-regulating hormones, and have increased molecular indicators of intestinal Ca absorption and kidney Ca retention. Our findings are important because they demonstrate how a genetic program that increases bone formation can drive improved efficiency of Ca utilization to accommodate the increased need for Ca deposition into bone. We believe that our preclinical study provides important proof-of-principle support for the concept of personalized recommendations for bone health management.