-
Scientific Reports Jul 2024Blinding eye diseases are often related to changes in retinal structure, which can be detected by analysing retinal blood vessels in fundus images. However, existing...
Blinding eye diseases are often related to changes in retinal structure, which can be detected by analysing retinal blood vessels in fundus images. However, existing techniques struggle to accurately segment these delicate vessels. Although deep learning has shown promise in medical image segmentation, its reliance on specific operations can limit its ability to capture crucial details such as the edges of the vessel. This paper introduces LMBiS-Net, a lightweight convolutional neural network designed for the segmentation of retinal vessels. LMBiS-Net achieves exceptional performance with a remarkably low number of learnable parameters (only 0.172 million). The network used multipath feature extraction blocks and incorporates bidirectional skip connections for the information flow between the encoder and decoder. In addition, we have optimised the efficiency of the model by carefully selecting the number of filters to avoid filter overlap. This optimisation significantly reduces training time and improves computational efficiency. To assess LMBiS-Net's robustness and ability to generalise to unseen data, we conducted comprehensive evaluations on four publicly available datasets: DRIVE, STARE, CHASE_DB1, and HRF The proposed LMBiS-Net achieves significant performance metrics in various datasets. It obtains sensitivity values of 83.60%, 84.37%, 86.05%, and 83.48%, specificity values of 98.83%, 98.77%, 98.96%, and 98.77%, accuracy (acc) scores of 97.08%, 97.69%, 97.75%, and 96.90%, and AUC values of 98.80%, 98.82%, 98.71%, and 88.77% on the DRIVE, STARE, CHEASE_DB, and HRF datasets, respectively. In addition, it records F1 scores of 83.43%, 84.44%, 83.54%, and 78.73% on the same datasets. Our evaluations demonstrate that LMBiS-Net achieves high segmentation accuracy (acc) while exhibiting both robustness and generalisability across various retinal image datasets. This combination of qualities makes LMBiS-Net a promising tool for various clinical applications.
Topics: Retinal Vessels; Humans; Neural Networks, Computer; Deep Learning; Image Processing, Computer-Assisted; Algorithms
PubMed: 38956117
DOI: 10.1038/s41598-024-63496-9 -
Scientific Reports Jul 2024In our study, blood concentrations of lead (Pb), arsenic (As), and cadmium (Cd) and urine concentrations of thallium (Tl) were measured together with related symptoms of...
In our study, blood concentrations of lead (Pb), arsenic (As), and cadmium (Cd) and urine concentrations of thallium (Tl) were measured together with related symptoms of heavy metal poisoning in cigarette smoking volunteers diagnosed with schizophrenia, in cigarette smokers not diagnosed with schizophrenia, and in the control group of non-smokers and not diagnosed with schizophrenia volunteers. Our study was performed on 171 volunteers divided into the following subgroups: patients diagnosed with schizophrenia with at least 1 year of continuous cigarette smoking experience (56 participants), cigarette smokers not diagnosed with schizophrenia with at least one year of continuous smoking experience (58), and control group (not diagnosed with schizophrenia and non-smoking volunteers) (57). Smoking durations of cigarette smokers diagnosed with schizophrenia and cigarette smokers not diagnosed with schizophrenia are not similar (p = 0.431). Blood Pb, As, and Cd concentrations and urine Tl concentrations were the highest in the subgroup of cigarette smokers not diagnosed with schizophrenia, followed by the subgroup of cigarette smokers diagnosed with schizophrenia, and the control group. Only blood Pb concentrations were significantly higher (probability value p < 0.05) in the group of cigarette smokers not diagnosed with schizophrenia (5.16 μg/dL), comparing to the group of cigarette smokers diagnosed with schizophrenia (3.83 μg/dL) and to the control group (3.43 μg/dL). Blood Cd and As concentrations and urine Tl concentrations were significantly higher (p < 0.05) in cigarette smokers not diagnosed with schizophrenia than in the control group. The results revealed a statistically significant positive correlation (p < 0.001) in the cigarette smokers in the schizophrenia diagnosed group between blood Pb, blood As, and urine Tl concentrations and the duration of cigarette smoking.
Topics: Humans; Schizophrenia; Male; Adult; Female; Cigarette Smoking; Lead; Cadmium; Middle Aged; Metals, Heavy; Arsenic; Thallium; Case-Control Studies
PubMed: 38956098
DOI: 10.1038/s41598-024-64333-9 -
Scientific Reports Jul 2024With the increasing prevalence of obesity in India, body mass index (BMI) has garnered importance as a disease predictor. The current World Health Organization (WHO)...
With the increasing prevalence of obesity in India, body mass index (BMI) has garnered importance as a disease predictor. The current World Health Organization (WHO) body mass index (BMI) cut-offs may not accurately portray these health risks in older adults aged 60 years and above. This study aims to define age-appropriate cut-offs for older adults (60-74 years and 75 years and above) and compare the performance of these cut-offs with the WHO BMI cut-offs using cardio-metabolic conditions as outcomes. Using baseline data from the Longitudinal Ageing Study in India (LASI), classification and regression tree (CART) cross-sectional analysis was conducted to obtain age-appropriate BMI cut-offs based on cardio-metabolic conditions as outcomes. Logistic regression models were estimated to compare the association of the two sets of cut-offs with cardio-metabolic outcomes. The area under the receiver operating characteristic curve (AUC), sensitivity and specificity were estimated. Agreement with waist circumference, an alternate measure of adiposity, was conducted. For older adults aged 60-74 years and 75 years and above, the cut-off for underweight reduced from < 18.5 to < 17.4 and < 13.3 respectively. The thresholds for overweight and obese increased for older adults aged 60-74 years old from > = 25 to > 28.8 and > = 30 to > 33.7 respectively. For older adults aged 75 years and above, the thresholds decreased for both categories. The largest improvement in AUC was observed in older adults aged 75 years and above. The newly derived cut-offs also demonstrated higher sensitivity and specificity among all age-sex stratifications. There is a need to adopt greater rigidity in defining overweight/obesity among older adults aged 75 years and above, as opposed to older adults aged 60-74 years old among whom the thresholds need to be less conservative. Further stratification in the low risk category could also improve BMI classification among older adults. These age-specific thresholds may act as improved alternatives of the current WHO BMI thresholds and improve classification among older adults in India.
Topics: Humans; Aged; Body Mass Index; India; Male; Female; Middle Aged; Malnutrition; Cross-Sectional Studies; Obesity; Age Factors; ROC Curve; Aged, 80 and over; Longitudinal Studies; Overweight; Waist Circumference; Thinness
PubMed: 38956083
DOI: 10.1038/s41598-024-63421-0 -
Scientific Reports Jul 2024Biological agents are getting a noticeable concern as efficient eco-friendly method for nanoparticle fabrication, from which fungi considered promising agents in this...
Biological agents are getting a noticeable concern as efficient eco-friendly method for nanoparticle fabrication, from which fungi considered promising agents in this field. In the current study, two fungal species (Embellisia spp. and Gymnoascus spp.) were isolated from the desert soil in Saudi Arabia and identified using 18S rRNA gene sequencing then used as bio-mediator for the fabrication of silver nanoparticles (AgNPs). Myco-synthesized AgNPs were characterized using UV-visible spectrometry, transmission electron microscopy, Fourier transform infrared spectroscopy and dynamic light scattering techniques. Their antibacterial activity against Escherichia coli, Pseudomonas aeruginosa, Staphylococcus aureus, and Klebsiella pneumoniae were investigated. In atrial to detect their possible antibacterial mechanism, Sodium dodecyl sulfate (SDS-PAGE) and TEM analysis were performed for Klebsiella pneumoniae treated by the myco-synthesized AgNPs. Detected properties of the fabricated materials indicated the ability of both tested fungal strains in successful fabrication of AgNPs having same range of mean size diameters and varied PDI. The efficiency of Embellisia spp. in providing AgNPs with higher antibacterial activity compared to Gymnoascus spp. was reported however, both indicated antibacterial efficacy. Variations in the protein profile of K. pneumoniae after treatments and ultrastructural changes were observed. Current outcomes suggested applying of fungi as direct, simple and sustainable approach in providing efficient AgNPs.
Topics: Silver; Saudi Arabia; Metal Nanoparticles; Soil Microbiology; Microbial Sensitivity Tests; Anti-Bacterial Agents; Desert Climate; Fungi; Klebsiella pneumoniae; Pseudomonas aeruginosa; Anti-Infective Agents
PubMed: 38956076
DOI: 10.1038/s41598-024-63117-5 -
Scientific Reports Jul 2024Celiac Disease (CD) is a primary malabsorption syndrome resulting from the interplay of genetic, immune, and dietary factors. CD negatively impacts daily activities and...
Celiac Disease (CD) is a primary malabsorption syndrome resulting from the interplay of genetic, immune, and dietary factors. CD negatively impacts daily activities and may lead to conditions such as osteoporosis, malignancies in the small intestine, ulcerative jejunitis, and enteritis, ultimately causing severe malnutrition. Therefore, an effective and rapid differentiation between healthy individuals and those with celiac disease is crucial for early diagnosis and treatment. This study utilizes Raman spectroscopy combined with deep learning models to achieve a non-invasive, rapid, and accurate diagnostic method for celiac disease and healthy controls. A total of 59 plasma samples, comprising 29 celiac disease cases and 30 healthy controls, were collected for experimental purposes. Convolutional Neural Network (CNN), Multi-Scale Convolutional Neural Network (MCNN), Residual Network (ResNet), and Deep Residual Shrinkage Network (DRSN) classification models were employed. The accuracy rates for these models were found to be 86.67%, 90.76%, 86.67% and 95.00%, respectively. Comparative validation results revealed that the DRSN model exhibited the best performance, with an AUC value and accuracy of 97.60% and 95%, respectively. This confirms the superiority of Raman spectroscopy combined with deep learning in the diagnosis of celiac disease.
Topics: Celiac Disease; Humans; Spectrum Analysis, Raman; Deep Learning; Female; Male; Adult; Neural Networks, Computer; Case-Control Studies; Middle Aged
PubMed: 38956075
DOI: 10.1038/s41598-024-64621-4 -
Nature Communications Jul 2024The primary obstacle to curing HIV-1 is a reservoir of CD4+ cells that contain stably integrated provirus. Previous studies characterizing the proviral landscape, which...
The primary obstacle to curing HIV-1 is a reservoir of CD4+ cells that contain stably integrated provirus. Previous studies characterizing the proviral landscape, which have been predominantly conducted in males in the United States and Europe living with HIV-1 subtype B, have revealed that most proviruses that persist during antiretroviral therapy (ART) are defective. In contrast, less is known about proviral landscapes in females with non-B subtypes, which represents the largest group of individuals living with HIV-1. Here, we analyze genomic DNA from resting CD4+ T-cells from 16 female and seven male Ugandans with HIV-1 receiving suppressive ART (n = 23). We perform near-full-length proviral sequencing at limiting dilution to examine the proviral genetic landscape, yielding 607 HIV-1 subtype A1, D, and recombinant proviral sequences (mean 26/person). We observe that intact genomes are relatively rare and clonal expansion occurs in both intact and defective genomes. Our modification of the primers and probes of the Intact Proviral DNA Assay (IPDA), developed for subtype B, rescues intact provirus detection in Ugandan samples for which the original IPDA fails. This work will facilitate research on HIV-1 persistence and cure strategies in Africa, where the burden of HIV-1 is heaviest.
Topics: Humans; HIV-1; Proviruses; HIV Infections; Male; Female; Genome, Viral; CD4-Positive T-Lymphocytes; Adult; DNA, Viral; Uganda; Viral Load; Anti-HIV Agents
PubMed: 38956017
DOI: 10.1038/s41467-024-48985-9 -
Journal of Imaging Informatics in... Jul 2024This study aimed to investigate the performance of a fine-tuned large language model (LLM) in extracting patients on pretreatment for lung cancer from picture archiving...
This study aimed to investigate the performance of a fine-tuned large language model (LLM) in extracting patients on pretreatment for lung cancer from picture archiving and communication systems (PACS) and comparing it with that of radiologists. Patients whose radiological reports contained the term lung cancer (3111 for training, 124 for validation, and 288 for test) were included in this retrospective study. Based on clinical indication and diagnosis sections of the radiological report (used as input data), they were classified into four groups (used as reference data): group 0 (no lung cancer), group 1 (pretreatment lung cancer present), group 2 (after treatment for lung cancer), and group 3 (planning radiation therapy). Using the training and validation datasets, fine-tuning of the pretrained LLM was conducted ten times. Due to group imbalance, group 2 data were undersampled in the training. The performance of the best-performing model in the validation dataset was assessed in the independent test dataset. For testing purposes, two other radiologists (readers 1 and 2) were also involved in classifying radiological reports. The overall accuracy of the fine-tuned LLM, reader 1, and reader 2 was 0.983, 0.969, and 0.969, respectively. The sensitivity for differentiating group 0/1/2/3 by LLM, reader 1, and reader 2 was 1.000/0.948/0.991/1.000, 0.750/0.879/0.996/1.000, and 1.000/0.931/0.978/1.000, respectively. The time required for classification by LLM, reader 1, and reader 2 was 46s/2539s/1538s, respectively. Fine-tuned LLM effectively extracted patients on pretreatment for lung cancer from PACS with comparable performance to radiologists in a shorter time.
PubMed: 38955964
DOI: 10.1007/s10278-024-01186-8 -
Updates in Surgery Jul 2024The Nurse Navigator is a highly specialized nurse with technical and non-technical skills that offers individualized assistance to cancer patients, their family and...
The Nurse Navigator is a highly specialized nurse with technical and non-technical skills that offers individualized assistance to cancer patients, their family and caregivers to overcome health system barriers and facilitate access to care. This role was introduced in the General Surgery Unit of the Madonna del Soccorso Hospital in San Benedetto del Tronto from 1st January 2023. The primary endpoint is to compare the times taken for each step of the diagnostic-therapeutic pathway comparing the study group followed by Oncology Nurse Navigator (ONN) and the group not followed by this role. The secondary endpoints, only for the study group, were the number of patient contacts with the ONN and the time slots; the number of examinations and consultations organized by ONN; the evaluation of patient satisfaction at discharge; the number and type of problems noted during follow-up contact at 7 and 30 days after discharge. A prospective court study with historical control was conducted from 1st January 2023 in Madonna del Soccorso Hospital, Italy. The study group consists of all cancer patients cared for by ONN. The control group was created by selecting the same number of patients as the study group but taken care of in the previous 3 years (from 2020 to 2022) and, therefore, without the presence of the Nurse Navigator. The control group data come from clinical documentation. The number and time slots of contact with the ONN were recorded through the use of a company mobile phone active 24/7 through phone calls and messages. The number of examinations and consultations is known through online requests. The satisfaction assessment was carried out through the use of externally validated questionnaire Patient Satisfaction with Cancer Care (PSCC). The follow-up was performed by telephone and recorded on documentation according to established parameters. A total of 200 patients were analyzed. Both the study and control groups included 100 patients each. The average time between the first contact with the patient and the execution of the diagnostic test was 7 days in the cases compared to 28 days in the control group. The waiting time for the Multi-Disciplinary Team discussion (MDT) was 3 days for the study group compared to 6 days in the control group. The average time taken for the first oncological visit was 3 days in the study group compared to 18 days in the controls. The time from first contact to the operating session was 20 days compared to 45 in controls. Each patient had an average of 10 phone calls with the ONN. For all patients accompanied at the first diagnosis, at least 2 radiological and laboratory tests were organized. Oncology appointment for treatment evaluations after delivery of the histological report was communicated within a maximum of 3 working days. A patient satisfaction questionnaire achieved a response rate of 100%, with an average score of 87.0/90. The telephone follow-up had a response rate of 100% of patients and revealed a decrease in problems at the 30-day check-up compared to that of 7 days after discharge. (Activity of Daily Living 20% vs 8%; nutritional problems 40% vs 21%, pain 18% vs 2%; surgical wounds 45% vs 1%; mobilization 8% vs 0%). The data demonstrate that ONN service improves the quality and outcomes of surgical oncology patients' pathway. The professional role of the ONN, with predefined technical and non-technical skills, should also be officially recognized by the healthcare system and hospital administration.
PubMed: 38955954
DOI: 10.1007/s13304-024-01916-1 -
CEN Case Reports Jul 2024A 76-year-old woman was admitted with progressive renal function decline. A kidney biopsy was performed because of myeloperoxidase anti-neutrophil cytoplasmic antibody...
A 76-year-old woman was admitted with progressive renal function decline. A kidney biopsy was performed because of myeloperoxidase anti-neutrophil cytoplasmic antibody (ANCA; 333 IU/mL), proteinuria (1.21 g/d), and urinary erythrocyte sediment (10-19/high-power field). Renal-limited ANCA-positive vasculitis with pauci-immune necrotizing crescentic glomerulonephritis (ANCA-associated vasculitis, AAV) was diagnosed. Glucocorticoid therapy was started, and the patient responded well. About 1 year later, avacopan treatment was started and glucocorticoid therapy was discontinued. Avacopan did not normalize ANCA levels and did not make urinary findings negative. However, further progression of renal function decline is prevented. Factors attributed to the development of AAV in this case were investigated; AAV developed after the second dose of the COVID-19 vaccine and ANCA levels re-elevated after the fifth dose. This suggests that the COVID-19 vaccine may have contributed to the development of AAV in this elderly patient. Avacopan monotherapy has been shown to be effective as maintenance therapy to control the progression of renal failure although not sufficient for complete remission of AAV.
PubMed: 38955948
DOI: 10.1007/s13730-024-00910-1 -
International Urology and Nephrology Jul 2024This investigation sought to validate the clinical precision and practical applicability of AI-enhanced three-dimensional sonographic imaging for the identification of...
PURPOSE
This investigation sought to validate the clinical precision and practical applicability of AI-enhanced three-dimensional sonographic imaging for the identification of anterior urethral stricture.
METHODS
The study enrolled 63 male patients with diagnosed anterior urethral strictures alongside 10 healthy volunteers to serve as controls. The imaging protocol utilized a high-frequency 3D ultrasound system combined with a linear stepper motor, which enabled precise and rapid image acquisition. For image analysis, an advanced AI-based segmentation process using a modified U-net algorithm was implemented to perform real-time, high-resolution segmentation and three-dimensional reconstruction of the urethra. A comparative analysis was performed against the surgically measured stricture lengths. Spearman's correlation analysis was executed to assess the findings.
RESULTS
The AI model completed the entire processing sequence, encompassing recognition, segmentation, and reconstruction, within approximately 5 min. The mean intraoperative length of urethral stricture was determined to be 14.4 ± 8.4 mm. Notably, the mean lengths of the urethral strictures reconstructed by manual and AI models were 13.1 ± 7.5 mm and 13.4 ± 7.2 mm, respectively. Interestingly, no statistically significant disparity in urethral stricture length between manually reconstructed and AI-reconstructed images was observed. Spearman's correlation analysis underscored a more robust association of AI-reconstructed images with intraoperative urethral stricture length than manually reconstructed 3D images (0.870 vs. 0.820). Furthermore, AI-reconstructed images provided detailed views of the corpus spongiosum fibrosis from multiple perspectives.
CONCLUSIONS
The research heralds the inception of an innovative, efficient AI-driven sonographic approach for three-dimensional visualization of urethral strictures, substantiating its viability and superiority in clinical application.
PubMed: 38955940
DOI: 10.1007/s11255-024-04137-y