Diagnostics最新文献

{"title":"AI-Augmented Quantitative MRI Predicts Spontaneous Intracranial Hypotension.","authors":"Yi-Jhe Huang, Jyh-Wen Chai, Wen-Hsien Chen, Hung-Chieh Chen, Da-Chuan Cheng","doi":"10.3390/diagnostics15182339","DOIUrl":"10.3390/diagnostics15182339","url":null,"abstract":"<p><p><b>Background/Objectives</b>: Spontaneous intracranial hypotension (SIH), caused by spinal cerebrospinal fluid (CSF) leakage, commonly presents with orthostatic headache and CSF hypovolemia. While CSF dynamics in the cerebral aqueduct are well studied, alterations in spinal CSF flow remain less defined. We aimed to quantitatively assess spinal CSF flow at C2 using phase-contrast (PC) MRI enhanced by artificial intelligence (AI) and to evaluate its utility for diagnosing SIH and predicting responses to epidural blood patch (EBP). <b>Methods</b>: We enrolled 31 patients with MRI-confirmed SIH and 26 age- and sex-matched healthy volunteers (HVs). All participants underwent ECG-gated cine PC-MRI at the C2 level and whole-spine MR myelography. AI-based segmentation using YOLOv4 and a pulsatility-based algorithm was used to extract quantitative CSF flow metrics. Between-group comparisons were analyzed using Mann-Whitney U tests, and receiver operating characteristic (ROC) analysis was used to evaluate diagnostic and predictive performance. <b>Results</b>: Compared to HVs, SIH patients showed significantly reduced CSF flow parameters across all metrics, including upward/downward mean flow, peak flow, total flow per cycle, and absolute stroke volume (all <i>p</i> < 0.001). ROC analysis revealed excellent diagnostic accuracy for multiple parameters, particularly downward peak flow (AUC = 0.844) and summation of peak flow (AUC = 0.841). Importantly, baseline CSF flow metrics significantly distinguished patients who required one versus multiple epidural blood patches (EBPs) (all <i>p</i> < 0.001). ROC analysis demonstrated that several parameters achieved near-perfect to perfect accuracy in predicting EBP success, with AUCs up to 1.0 and 100% sensitivity/specificity. <b>Conclusions</b>: AI-enhanced PC-MRI enables the robust, quantitative evaluation of spinal CSF dynamics in SIH. These flow metrics not only differentiate SIH patients from healthy individuals but also predict response to EBP treatment with high accuracy. Quantitative CSF flow analysis may support both diagnosis and personalized treatment planning in SIH.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468366/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison of Supervised Machine Learning Models to Logistic Regression Model Using Tooth-Related Factors to Predict the Outcome of Nonsurgical Periodontal Treatment.","authors":"Ali J B Al-Sharqi, Mohammed Taha Ahmed Baban, Nada K Imran, Sarhang S Gul, Ali A Abdulkareem","doi":"10.3390/diagnostics15182333","DOIUrl":"10.3390/diagnostics15182333","url":null,"abstract":"<p><p><b>Background/Objectives:</b> Conventional logistic regression is widely used in the field of dentistry, specifically for prediction purposes in longitudinal studies. This study aimed to compare the validity of different supervised machine learning (ML) models to the conventional logistic regression (LR) model to predict the outcomes of nonsurgical periodontal treatment (NSPT). <b>Methods:</b> Patients diagnosed with periodontitis received full periodontal charting, including bleeding on probing (BoP), probing pocket depth (PPD), and clinical attachment loss (CAL). Furthermore, the tooth type, tooth location, tooth surface, arch type, and gingival phenotype were also collected as site-specific predictors. Later, root surface debridement was provided and treatment outcomes were evaluated after 3 months. Site-specific predictors were used to train five ML models, including random forest (RF), decision tree (DT), support vector classifier (SVC), K-nearest neighbors (KNN), and Gaussian naïve Bayes (GNB), to develop predictive models. <b>Results:</b> Site-specific predictors of 1108 examined sites were used, and the overall accuracy prediction of the conventional LR model was 70.4%, with PPD statistically significantly associated with the outcome of NSPT (odds ratio = 0.577, <i>p</i> = 0.001). Among the ML models examined, only GNB and SVC showed comparable prediction accuracy (71.0% and 70.4%, respectively) to the LR model, whereas the prediction accuracies of KNN, RF, and DT were 65.0%, 62.0%, and 61.0%, respectively. Similarly, baseline PPD was shown to be the most important featured predictor by both the RF and DT models. <b>Conclusions</b>: The evidence suggests that supervised ML models do not outperform the LR model in predicting the outcomes of NSPT. A larger sample size and more predictors of periodontitis are necessary to enhance the accuracy of ML models over the LR model in predicting the outcomes of NSPT.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468186/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145174168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dilated Composite Odontoma in a Mesiodens.","authors":"Aakriti Chandra, Nilima Thosar, Ramakrishna Yeluri, Ishani Rahate, Dhruvi Solanki","doi":"10.3390/diagnostics15182335","DOIUrl":"10.3390/diagnostics15182335","url":null,"abstract":"<p><p>Dilated Composite Odontoma also known as Dens invaginatus, \"dens in dente\", or \"tooth within tooth\" is a rare dental anomaly resulting from enamel organ infolding during tooth development, often leading to complications like caries and pulp infection. With a prevalence of 7.45%, it commonly affects upper lateral incisors, predominantly as a Type I morphology. Mesiodens, a supernumerary tooth in the anterior maxillary midline, occurs in 89.7% of single cases and 10.3% of bilateral cases. The coexistence of dens invaginatus in a mesiodens is extremely rare, posing diagnostic and treatment challenges. This report presents a unique case of dentin invagination in a mesiodens.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12469172/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Endometriosis and Myalgic Encephalomyelitis/Chronic Fatigue Syndrome: A Systematic Review and Meta-Analysis.","authors":"Sabrina Compton, Rodolf Alkabalan, Judd Cadet, Azin Mastali, Prakash V A K Ramdass","doi":"10.3390/diagnostics15182332","DOIUrl":"10.3390/diagnostics15182332","url":null,"abstract":"<p><p><b>Background/Objectives</b>: Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) and endometriosis are debilitating conditions that share overlapping features of chronic inflammation and immune dysregulation, yet their epidemiological relationship remains poorly characterized. The objective of this study was to investigate the association between ME/CFS and endometriosis, examining shared risk factors, clinical correlates, and epidemiological patterns. <b>Methods</b>: We conducted a systematic review and meta-analysis. Two independent reviewers screened 236 records after duplicate removal, with seventeen studies undergoing full-text review and thirteen meeting inclusion criteria for meta-analysis. Data were extracted using standardized forms and analyzed using random-effects models in R, with heterogeneity assessed using I² statistics and the risk of bias evaluated using the JBI critical appraisal tool. <b>Results</b>: Our meta-analysis of five studies (<i>n</i> = 2261 participants) revealed that women with endometriosis had 2.79-fold higher odds (95% CI: 2.00-3.89) of developing ME/CFS compared to controls. Similarly, our fixed-effects meta-analysis of two studies assessing the association of ME/CFS and endometriosis yielded a pooled OR of 2.52 (95% CI: 2.45-2.60, <i>p</i> < 0.001). There was minimal statistical heterogeneity (I² = 0.0%, <i>p</i> > 0.7969) for both meta-analyses. <b>Conclusions</b>: This study demonstrates a significant bidirectional association between endometriosis and ME/CFS, driven by shared mechanisms of immune dysregulation and chronic inflammation. Despite high heterogeneity, the consistent effect sizes support clinical vigilance for comorbidity. Future research should prioritize standardized diagnostic criteria to elucidate causal pathways. These findings underscore the need for integrated care approaches to address overlapping symptomatology in affected patients.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468137/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145174074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comprehensive Characterization of a Cluster of Mucopolysaccharidosis IIIB in Ecuador.","authors":"María Lucía Castro Moreira, Yorran Hardman Araújo Montenegro, Angélica Salatino-Oliveira, Héctor Quintero Montano, Rodolfo F Niz Bareiro, Simone Silva Dos Santos-Lopes, Thiago Ramos da Silva, Lucas Kelvy Sales Azevedo, Karyme Beatrice Lourenço da Silva, Affonso Weslley de Almeida Moreira, Suzany Silva Araujo, Francyne Kubaski, Franciele Barbosa Trapp, Ana Carolina Brusius-Facchin, Fernanda Medeiros Sebastião, Kristiane Michelin-Tirelli, Guilherme Baldo, Roberto Giugliani, Durval Palhares","doi":"10.3390/diagnostics15182337","DOIUrl":"10.3390/diagnostics15182337","url":null,"abstract":"<p><p><b>Background/Objectives:</b> Sanfilippo Syndrome type B or Mucopolysaccharidosis type IIIB (MPS IIIB, OMIM 252920) is a lysosomal storage disease caused by deficiency of alpha-N-acetylglucosaminidase (NAGLU, E.C. 3.2.1.50) due to pathogenic variants in the <i>NAGLU</i> gene (17q21.2). The disease is characterized by progressive neurological manifestations, marked by cognitive decline, with relatively mild somatic involvement. We aim to present relevant information on a cluster of MPS IIIB identified in Ecuador, particularly regarding their clinical, biochemical, genetic, demographic, and ancestry characteristics. <b>Methods:</b> We present a characterization of a clinical, biochemical, genetic and demographic cluster of MPS IIIB patients in Ecuador, located in four main regions: Manabí, Guayas, Los Ríos, and Santo Domingo de los Tsáchilas. The patients included were diagnosed due to increased levels of urinary glycosaminoglycans (uGAG), plus deficient activity of NAGLU, and/or identification of biallelic pathogenic mutations in the <i>NAGLU</i> gene. Patients' charts were reviewed for biochemical findings, medical history, clinical manifestations and assessments. <b>Results:</b> We present the results of clinical, biochemical, genetic and demographic characterization of a cluster in Ecuador with 24 patients identified with Sanfilippo syndrome type IIIB, resulting in an estimated incidence of 1.5/100,000. The mean age at diagnosis was 8.8 years, with symptom onset at 4.5 years on average. All patients exhibited elevated levels of uGAG and undetectable NAGLU activity, and all of them presented the c.1487T>C (p.Leu496Pro) variant in the <i>NAGLU</i> gene in homozygosis, indicating a possible founder effect, with the exception of one heterozygous one (p.Leu496Pro/p.Arg482Gln). A positive correlation between age of diagnosis and the concentration of one isoform of heparan sulfate (HS-OS) was found (<i>p</i> < 0.05). Clinical findings included neuropsychomotor developmental delay (75%), neurological regression (65%), hepatomegaly (55%), growth deficiency (50%), coarse facies (45%) and hernia (40%). Male patients presented earlier onset of symptoms. Maternal ancestry was successfully determined for 21 of the 24 patients. The majority were of Native American ancestry (71.4%), followed by European (19%), African (4.8%), and Asian (4.8%) lineages. Haplogroup A was the most prevalent (42.9%), followed by haplogroups D (19%), C, U, and H (each 9.5%), and R and L2 (each 4.8%). <b>Conclusions:</b> Ancestry can indicate a possible mechanism to explain the heterogeneous symptomatic presentation. These findings highlight the need for further research on genetic and environmental influences on disease severity in this population.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468815/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145174154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prevalence of the Peroneus Quartus Muscle and Its Association with Peroneal Tendon Pathologies: An MRI Study of 1160 Ankles.","authors":"Yavuz Yuksel, Tarkan Ergun, Ozkan Kose","doi":"10.3390/diagnostics15182329","DOIUrl":"10.3390/diagnostics15182329","url":null,"abstract":"<p><p><b>Background/Objectives:</b> The peroneus quartus (PQ) muscle is a supernumerary muscle in the lateral compartment of the leg. Although frequently asymptomatic, it may contribute to peroneal tendon (PT) disorders due to mechanical crowding in the retromalleolar groove. This study aimed to determine the prevalence of the PQ muscle on MRI and assess its association with PT pathologies. <b>Materials and Methods:</b> This retrospective study evaluated 1160 ankle MRI scans from 1073 patients (mean age, 42.7 ± 14.5 years; 643 females, 430 males). The presence of the PQ muscle and associated PT pathologies, including tenosynovitis, tendinitis, and tendon tears of the peroneus brevis tendon (PBT) and peroneus longus tendon (PLT), was recorded. Statistical analyses were performed using chi-square tests, and associations were expressed as odds ratios (OR) with 95% confidence intervals (CI). <b>Results:</b> The PQ muscle was identified in 123 of 1160 ankles, corresponding to a prevalence of 10.6%. Its incidence was significantly higher in males (12.7%) than in females (9.2%) (<i>p</i> = 0.018), while the side distribution showed no statistically significant difference. PQ presence was associated with PBT pathology, particularly tendinitis and longitudinal tears, and with PLT tendinitis, whereas no clear association was observed with tenosynovitis or PLT tears. <b>Conclusions:</b> The PQ muscle is a relatively common anatomical variant, present in 10.6% of ankles on MRI scans. Its presence is significantly associated with PT abnormalities, especially PBT tendinitis and tears. Awareness of PQ may aid clinicians and radiologists in assessing lateral ankle pain and peroneal tendon disorders.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468075/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Cervical Nuclei Segmentation in Pap Smear Images Using Enhanced Morphological Thresholding Techniques.","authors":"Wan Azani Mustafa, Khalis Khiruddin, Syahrul Affandi Saidi, Khairur Rijal Jamaludin, Halimaton Hakimi, Mohd Aminudin Jamlos","doi":"10.3390/diagnostics15182328","DOIUrl":"10.3390/diagnostics15182328","url":null,"abstract":"<p><p><b>Background and Objective:</b> Cervical cancer remains one of the leading causes of death among women worldwide, particularly in regions with limited access to early screening. Pap smear screening is the primary tool for early detection, but manual interpretation is labor-intensive, subjective, and prone to inconsistency and misdiagnosis. Accurate segmentation of cervical cell nuclei is essential for automated analysis but is often hampered by overlapping cells, poor contrast, and staining variability. This research aims to develop an improved algorithm for accurate cervical nucleus segmentation to support automated Pap smear analysis. <b>Method:</b> The proposed method involves a combination of adaptive gamma correction for contrast enhancement, followed by Otsu thresholding for segmentation. Post-processing is performed using adaptive morphological operations to refine the results. The system is evaluated using standard image quality assessment metrics and validated against ground truth annotations. <b>Result:</b> The results show a significant improvement in segmentation performance over conventional methods. The proposed algorithm achieved a Precision of 0.9965, an F-measure of 97.29%, and an Accuracy of 98.39%. The PSNR value of 16.62 indicates enhanced image clarity after preprocessing. The method also improved sensitivity, leading to better identification of nuclei boundaries. Advanced preprocessing techniques, including edge-preserving filters and multi-Otsu thresholding, contributed to more accurate cell separation. The segmentation method proved effective across varying cell overlaps and staining conditions. Comparative evaluations with traditional clustering methods confirmed its superior performance. <b>Conclusions:</b> The proposed algorithm delivers robust and accurate segmentation of cervical cell nuclei, addressing common challenges in Pap smear image analysis. It provides a consistent framework for automated screening tools. This work enhances diagnostic reliability in cervical cancer screening and offers a foundation for broader applications in medical image analysis.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468220/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145174057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic Modality Influences Tuberculosis Detection in People Living with HIV: Eight Years of Data from a Thai Referral Center.","authors":"Wannarat Pongpirul, Phanupong Phutrakool, Krit Pongpirul","doi":"10.3390/diagnostics15182327","DOIUrl":"10.3390/diagnostics15182327","url":null,"abstract":"<p><p><b>Background:</b> Tuberculosis (TB) remains a leading cause of death among people living with HIV (PLWH), yet diagnostic methods vary in accuracy, accessibility, and implementation. Understanding how diagnostic modality influences TB detection is essential to optimizing co-infection management. <b>Methods:</b> We conducted a retrospective analysis of institutional data from Bamrasnaradura Infectious Diseases Institute (BIDI), Thailand, covering 2016-2023. TB detection rates were assessed across five diagnostic methods-chest radiography (CXR), smear microscopy, acid-fast bacilli (AFB) staining, culture, and GeneXpert MTB/RIF-relative to annual HIV-related visit volumes. <b>Results:</b> Among 56,599 HIV-related visits, TB detection rates varied substantially by diagnostic method. CXR was the most commonly used tool, detecting TB in up to 99 cases out of 6964 visits (1.42%) in 2016, though declining to 23 cases out of 6947 visits (0.33%) in 2023. GeneXpert was employed more consistently, yielding between 7 cases out of 7577 visits (0.09%) and 13 cases out of 6593 visits (0.20%) annually. Smear microscopy and AFB staining declined markedly, falling below 0.22% after 2020. These patterns reflect a gradual transition toward molecular diagnostics, which offer improved accuracy but remain underutilized in lower-tier settings. To address these gaps, we incorporated trend analyses confirming significant temporal shifts and propose a tiered TB screening framework tailored to resource availability across healthcare levels. <b>Conclusions:</b> TB detection among PLWH is strongly influenced by the diagnostic method used. Unlike HIV diagnosis-which is definitive and standardized-TB diagnosis remains fragmented and resource-dependent. Context-sensitive screening protocols are urgently needed to improve TB case detection and management, particularly in lower-level HIV care facilities.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468846/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Brain Tumor MRI Segmentation Using ARU-Net with Residual-Attention Modules.","authors":"Erdal Özbay, Feyza Altunbey Özbay","doi":"10.3390/diagnostics15182326","DOIUrl":"10.3390/diagnostics15182326","url":null,"abstract":"<p><p><b>Background/Objectives:</b> Accurate segmentation of brain tumors in Magnetic Resonance Imaging (MRI) scans is critical for diagnosis and treatment planning due to their life-threatening nature. This study aims to develop a robust and automated method capable of precisely delineating heterogeneous tumor regions while improving segmentation accuracy and generalization. <b>Methods:</b> We propose Attention Res-UNet (ARU-Net), a novel Deep Learning (DL) architecture integrating residual connections, Adaptive Channel Attention (ACA), and Dimensional-space Triplet Attention (DTA) modules. The encoding module efficiently extracts and refines relevant feature information by applying ACA to the lower layers of convolutional and residual blocks. The DTA is fixed to the upper layers of the decoding module, decoupling channel weights to better extract and fuse multi-scale features, enhancing both performance and efficiency. Input MRI images are pre-processed using Contrast Limited Adaptive Histogram Equalization (CLAHE) for contrast enhancement, denoising filters, and Linear Kuwahara filtering to preserve edges while smoothing homogeneous regions. The network is trained using categorical cross-entropy loss with the Adam optimizer on the BTMRII dataset, and comparative experiments are conducted against baseline U-Net, DenseNet121, and Xception models. Performance is evaluated using accuracy, precision, recall, F1-score, Dice Similarity Coefficient (DSC), and Intersection over Union (IoU) metrics. <b>Results:</b> Baseline U-Net showed significant performance gains after adding residual connections and ACA modules, with DSC improving by approximately 3.3%, accuracy by 3.2%, IoU by 7.7%, and F1-score by 3.3%. ARU-Net further enhanced segmentation performance, achieving 98.3% accuracy, 98.1% DSC, 96.3% IoU, and a superior F1-score, representing additional improvements of 1.1-2.0% over the U-Net + Residual + ACA variant. Visualizations confirmed smoother boundaries and more precise tumor contours across all six tumor classes, highlighting ARU-Net's ability to capture heterogeneous tumor structures and fine structural details more effectively than both baseline U-Net and other conventional DL models. <b>Conclusions:</b> ARU-Net, combined with an effective pre-processing strategy, provides a highly reliable and precise solution for automated brain tumor segmentation. Its improvements across multiple evaluation metrics over U-Net and other conventional models highlight its potential for clinical application and contribute novel insights to medical image analysis research.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468718/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Relationship Between FIB-4 Score and Dynapenia in Older Adults.","authors":"Guner Kilic, Ali Karatas, Mehmet Cindoruk, Tarkan Karakan, Derya Kirman, Beril Demir, Suleyman Emre Kocyigit","doi":"10.3390/diagnostics15182323","DOIUrl":"10.3390/diagnostics15182323","url":null,"abstract":"<p><p><b>Background/Objectives:</b> We evaluated whether fibrosis-4 (FIB-4) is associated with dynapenia and functional status in adults ≥65 years, and its value as a geriatric screening tool. <b>Methods</b>: In this cross-sectional study (July 2023-July 2025), 537 outpatients aged ≥65 years were evaluated. FIB-4 was calculated by the standard formula; a high-risk threshold of ≥2.0 was applied for age ≥65. Participants were compared as low- and high-FIB-4. Functional status was assessed by Basic Activities of Daily Living (ADLs), instrumental ADLs, and gait and balance tests. Dynapenia was defined as low muscle strength. Comorbidities, geriatric syndromes, and laboratory findings were recorded. <b>Results:</b> The high-FIB-4 group was older (78.6 ± 6.0 vs. 75.6 ± 5.8 years), had fewer women, and had lower BMI. POMA and instrumental ADLs scores were lower in the high-FIB-4 group, while basic ADLs and TUG duration did not differ significantly. Low grip strength was more frequent with high FIB-4. In sex-stratified analyses, FIB-4 correlated positively with age and aspartate transaminase (AST), and negatively with platelet count, leukocyte count, handgrip strength, POMA, and instrumental ADLs in women. In regression analysis low grip strength was associated with high FIB-4 score, but this relationship disappeared regardless of confounding factor in older female people. Lower BMI and higher leucocyte count is a risk factor for high FIB-4 score in the dynapenia group. <b>Conclusions:</b> FIB-4 reflects not only hepatic fibrosis risk but also geriatric vulnerability linked to dynapenia and functional decline in older adults. With age-adjusted cutoffs, FIB-4 may serve as a practical early-warning screen alongside nutritional and physical-performance assessments.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12468370/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145174149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}