Search Results (266)

Background/Objectives: Epilepsy is a neurological disorder that severely impacts patients’ quality of life. In clinical practice, specific pharmacological and surgical interventions are tailored to distinct seizure types. The identification of the epileptogenic zone enables the implementation of surgical procedures and neuromodulation therapies. Consequently, accurate classification of seizure types and precise determination of focal epileptic signals are critical to provide clinicians with essential diagnostic insights for optimizing therapeutic strategies. Traditional machine learning approaches are constrained in their efficacy due to limited capability in autonomously extracting features. Methods: This study proposes a novel deep learning framework integrating temporal and spatial information extraction to address this limitation. Multivariate variational mode decomposition (MVMD) is employed to maintain inter-channel mode alignment during the decomposition of multi-channel epileptic signals, ensuring the synchronization of time–frequency characteristics across channels and effectively mitigating mode mixing and mode mismatch issues. Results: The Bern–Barcelona database is employed to classify focal epileptic signals, with the proposed framework achieving an accuracy of 98.85%, a sensitivity of 98.75%, and a specificity of 98.95%. For multi-class seizure type classification, the TUSZ database is utilized. Subject-dependent experiments yield an accuracy of 96.17% with a weighted F1-score of 0.962. Meanwhile, subject-independent experiments attain an accuracy of 87.97% and a weighted F1-score of 0.884. Conclusions: The proposed framework effectively integrates temporal and spatial domain information derived from multi-channel epileptic signals, thereby significantly enhancing the algorithm’s classification performance. The performance on unseen patients demonstrates robust generalization capability, indicating the potential clinical applicability in assisting neurologists with epileptic signal classification. Full article

Providing students with effective learning resources is essential for improving educational outcomes—especially in complex and conceptually diverse fields such as Mathematics and Computer Science. To better understand how these subjects are communicated, this study investigates the linguistic structures embedded in academic texts from selected subfields within both disciplines. In particular, we focus on meta-languages—the linguistic tools used to express definitions, axioms, intuitions, and heuristics within a discipline. The primary objective of this research is to identify which subfields of Mathematics and Computer Science share similar meta-languages. Identifying such correspondences may enable the rephrasing of content from less familiar subfields using styles that students already recognize from more familiar areas, thereby enhancing accessibility and comprehension. To pursue this aim, we compiled text corpora from multiple subfields across both disciplines. We compared their meta-languages using a combination of supervised (Neural Network) and unsupervised (clustering) learning methods. Specifically, we applied several clustering algorithms—K-means, Partitioning around Medoids (PAM), Density-Based Clustering, and Gaussian Mixture Models—to analyze inter-discipline similarities. To validate the resulting classifications, we used XLNet, a deep learning model known for its sensitivity to linguistic patterns. The model achieved an accuracy of 78% and an F1-score of 0.944. Our findings show that subfields can be meaningfully grouped based on meta-language similarity, offering valuable insights for tailoring educational content more effectively. To further verify these groupings and explore their pedagogical relevance, we conducted both quantitative and qualitative research involving student participation. This paper presents findings from the qualitative component—namely, a content analysis of semi-structured interviews with software engineering students and lecturers. Full article

Parkinson’s disease (PD) is a chronic neurodegenerative disorder that progressively impairs motor functions. Clinical assessments have traditionally relied on rating scales such as the Movement Disorder Society Unified Parkinson Disease Rating Scale (MDS-UPDRS); however, these evaluations are susceptible to rater-dependent variability and may miss subtle motor changes. This study explored objective and quantitative methods for assessing motor function in PD patients using the Quantum Metaglove, a sensory glove produced by MANUS^®, which was used to record finger movements during three tasks: finger tapping, hand gripping, and pronation–supination. Classic and geometric motor features (the latter based on Clifford algebra, an advanced approach for trajectory shape analysis) were extracted. The resulting data were used to train various machine learning algorithms (k-NN, SVM, and Naive Bayes) to distinguish healthy subjects from PD patients. The integration of traditional kinematic and geometric approaches improves objective hand movement analysis, providing new diagnostic opportunities. In particular, geometric trajectory analysis provides more interpretable information than conventional signal processing methods. This study highlights the value of wearable technologies and Clifford algebra-based algorithms as tools that can complement clinical assessment. They are capable of reducing inter-rater variability and enabling more continuous and precise monitoring of hand motor movements in patients with PD. Full article

Background and Objectives: Gait is a fundamental human behavior essential for individual autonomy and well-being; it reflects a complex inter-joint coordination that can change with aging. Materials and Methods: This study applied a network-based fingerprinting approach to evaluate the stability and individuality of gait coordination in adults (mean age: 41.6) and older adults (mean age: 73.5). Each participant completed two gait recordings, from which we constructed kinematic networks (i.e., kinectome) representing joint–velocity correlations. Then, borrowing from network fingerprinting techniques, we computed measures of intra-subject similarity (Iself), inter-subject similarity within the same group (Iothers), cross-group similarity (Iextra), and individual discriminability (Differentiation rate, DR). Results: While Iself was comparable across groups, older adults showed higher Iothers and lower DR, indicating more homogeneous and less distinctive coordination patterns. Furthermore, Iothers was significantly higher than Iextra in the older group only, suggesting age-specific convergence in motor behavior. Conclusions: These findings support the hypothesis that aging reduces the individuality of gait coordination, possibly due to adaptive or degenerative changes in motor control. Kinectome-based fingerprinting thus offers a promising tool for capturing subtle shifts in neuromotor organizations linked to aging. Full article

Background/Objectives: To determine the inter-rater agreement of visual and AI-based assessments of a renowned semi-quantitative chest CT scoring system (Pan-score) used to evaluate the severity of pulmonary involvement (e.g., ground-glass opacities, consolidations) in patients suffering from COVID-19. Methods: This retrospective study includes patients with PCR-confirmed COVID-19, who received a chest CT scan (not more than three days prior to or after the positive PCR test) between 21 March 2020 and 30 December 2022. The five lung lobes were scored separately on a scale from 0 (no pulmonary involvement) to 5 (>75% pulmonary involvement) by a radiology specialist, an experienced assistant physician, a medical student, and a dedicated AI-based software tool for chest CT. Weighted Cohen’s κ values were calculated to assess the reliability of agreement between the different readers. Results: A total of 569 consecutive patients (381 males [67.0%], 188 females [33.0%]; mean age 68.8 years) with confirmed COVID-19 were evaluated. All of them received at least one chest CT scan. There was a significant difference (p < 0.001) between the mean Pan-score evaluated by the three human readers (9.35 ± 6.03) and the score computed fully automatically by the software (10.44 ± 5.10). However, the inter-rater agreement both between the three different human readers and between the human readers and the AI was high throughout, with κ values of 0.71–0.86 and 0.83, respectively. The slice thickness of the reconstructed CT images did not have an impact on the inter-rater agreement, but the total score was significantly higher when the images were acquired following the administration of i. v. contrast media. Conclusions: The evaluated chest CT scoring system is user-friendly due to its simplicity, though it is generally prone to inaccuracies, since the estimation of the extent of pulmonary involvement is quite subjective. Nevertheless, the inter-rater agreement was high throughout, both between the differently experienced human readers and between the human readers and the AI software. In summary, the Pan-score seems to be a reliable approach to estimate the extent of pulmonary involvement in patients suffering from COVID-19. Full article

Background/Objectives: Virtual non-contrast (VNC) images derived from dual-energy CTA (DE-CTA) could potentially replace true non-contrast (TNC) scans while reducing radiation exposure. This study evaluated the image quality of VNC compared to TNC for assessing native arteries and bypass grafts in patients with peripheral arterial disease (PAD). Methods: We retrospectively analyzed 175 patients (111 men, 64 women, mean age: 69.3 ± 9.5 years) with PAD who underwent lower extremity DE-CTA. Mean attenuation and image noise values of TNC and VNC images were measured in native arteries and bypass grafts at six arterial levels, from the aorta to the popliteal arteries, using circular regions of interest (ROI). Signal-to-noise ratios (SNRs) and contrast-to-noise ratios (CNRs) were calculated. Three independent radiologists evaluated the subjective image quality of VNC images compared to baseline TNC scans for overall quality (4-point Likert scale), and for residual contrast medium (CM), calcium subtractions, and bypass graft visualization (3-point Likert scales). Radiation dose parameters (DLP, CTDIvol) were recorded to estimate effective dose values (ED) and the potential radiation dose reduction. Differences between TNC and VNC measurements and radiation dose parameters were compared using a paired t-test. Interobserver agreement was assessed with Gwet’s AC2. Results: VNC attenuation and noise values were significantly lower across all native arterial levels (p < 0.05, mean difference: 4.7 HU–10.8 HU) and generally lower at all bypass regions (mean difference: 2.2 HU–13.8 HU). Mean image quality scores were 3.03 (overall quality), 2.99 (residual contrast), 2.04 (subtracted calcifications), and 3.0 (graft visualization). Inter-reader agreement was excellent for each assessment (AC2 ≥ 0.81). The estimated radiation dose reduction was 36.8% (p < 0.0001). Conclusions: VNC reconstructions demonstrated comparable image quality to TNC in a PAD assessment and offer substantial radiation dose reduction, supporting their potential as a promising alternative in clinical practice. Further prospective studies and optimization of reconstruction algorithms remain essential to confirm diagnostic accuracy and address remaining technical limitations. Full article

Objective: The accurate visualization of root canal systems on periapical radiographs is critical for successful endodontic treatment. This study aimed to evaluate and compare the effectiveness of several image enhancement algorithms—including a novel Total Variation–Contrast-Limited Adaptive Histogram Equalization (TV-CLAHE) technique—in improving the detectability of root canal configurations in mandibular incisors, using cone-beam computed tomography (CBCT) as the gold standard. A null hypothesis was tested, assuming that enhancement methods would not significantly improve root canal detection compared to original radiographs. Method: A retrospective analysis was conducted on 60 periapical radiographs of mandibular incisors, resulting in 420 images after applying seven enhancement techniques: Histogram Equalization (HE), Contrast-Limited Adaptive Histogram Equalization (CLAHE), CLAHE optimized with Pelican Optimization Algorithm (CLAHE-POA), Global CLAHE (G-CLAHE), k-Caputo Fractional Differential Operator (KCFDO), and the proposed TV-CLAHE. Four experienced observers (two radiologists and two dentists) independently assessed root canal visibility. Subjective evaluation was performed using an own scale inspired by a 5-point Likert scale, and the detection accuracy was compared to the CBCT findings. Quantitative metrics including Peak Signal-to-Noise Ratio (PSNR), Signal-to-Noise Ratio (SNR), image entropy, and Structural Similarity Index Measure (SSIM) were calculated to objectively assess image quality. Results: Root canal detection accuracy improved across all enhancement methods, with the proposed TV-CLAHE algorithm achieving the highest performance (93–98% accuracy), closely approaching CBCT-level visualization. G-CLAHE also showed substantial improvement (up to 92%). Statistical analysis confirmed significant inter-method differences (p < 0.001). TV-CLAHE outperformed all other techniques in subjective quality ratings and yielded superior SNR and entropy values. Conclusions: Advanced image enhancement methods, particularly TV-CLAHE, significantly improve root canal visibility in 2D radiographs and offer a practical, low-cost alternative to CBCT in routine dental diagnostics. These findings support the integration of optimized contrast enhancement techniques into endodontic imaging workflows to reduce the risk of missed canals and improve treatment outcomes. Full article

Background: Identifying high-grade strictures (HGS) in patients with primary sclerosing cholangitis (PSC) relies upon subjective assessments of magnetic resonance cholangiopancreatography (MRCP). Quantitative MRCP (MRCP+) provides objective evaluation of MRCP examinations, which may help make these assessments more consistent and improve patient management and selection for intervention. We evaluated the impact of MRCP+ on clinicians’ confidence in diagnosing HGS in patients with PSC. Methods: Three expert abdominal radiologists independently assessed 28 patients with PSC. Radiological reads of MRCPs were performed twice, in a random order, three weeks apart, then a third time with MRCP+. HGS presence was recorded on semi-quantitative confidence scales. The cases where readers definitively agreed on presence/absence of HGS were used to assess inter- and intra-reader agreement and confidence. Results: When using MRCP alone, high intra-reader agreement was observed in identifying HGS within both intra- and extrahepatic ducts (64.3% and 70.8%, respectively), while inter-reader agreement was significantly lower for intrahepatic ducts (42.9%) than extrahepatic ducts (66.1%) (p < 0.01). Using MRCP+ in the third read significantly improved inter-reader agreement for intrahepatic HGS detection to 67.9% versus baseline reads (p = 0.02) and was comparable with extrahepatic ducts. Reader confidence tended to increase when supplemented with MRCP+, and inter-reader variability decreased. MRCP+ metrics had good performance in identifying HGS in both extra-hepatic (AUC:0.85) and intra-hepatic ducts (AUC:0.75). Conclusions: MRCP evaluation supported by quantitative metrics tended to increase individual reader confidence and reduce inter-reader variability for detecting HGS. Our results indicate that MRCP+ might help standardize MRCP assessment and subsequent management for patients with PSC. Full article

Background/Objectives: The integration of artificial intelligence (AI) in medical imaging is rapidly advancing, yet its application in gynecologic use remains limited. This proof-of-concept study presents the development and validation of a convolutional neural network (CNN) designed to automatically detect and classify endometrial polyps. Methods: A multicenter dataset (n = 3) comprising 65 hysteroscopies was used, yielding 33,239 frames and 37,512 annotated objects. Still frames were extracted from full-length videos and annotated for the presence of histologically confirmed polyps. A YOLOv1-based object detection model was used with a 70–20–10 split for training, validation, and testing. Primary performance metrics included recall, precision, and mean average precision at an intersection over union (IoU) ≥ 0.50 (mAP50). Frame-level classification metrics were also computed to evaluate clinical applicability. Results: The model achieved a recall of 0.96 and precision of 0.95 for polyp detection, with a mAP50 of 0.98. At the frame level, mean recall was 0.75, precision 0.98, and F1 score 0.82, confirming high detection and classification performance. Conclusions: This study presents a CNN trained on multicenter, real-world data that detects and classifies polyps simultaneously with high diagnostic and localization performance, supported by explainable AI features that enhance its clinical integration and technological readiness. Although currently limited to binary classification, this study demonstrates the feasibility and potential of AI to reduce diagnostic subjectivity and inter-observer variability in hysteroscopy. Future work will focus on expanding the model’s capabilities to classify a broader range of endometrial pathologies, enhance generalizability, and validate performance in real-time clinical settings. Full article

Road irregularities generate vibrations that are transmitted to cyclists’ hands. This paper describes a purpose-designed laboratory setup and data processing method to assess vibration-induced numbness and discomfort. The rear wheel of a road bike was coupled with a smart trainer for indoor cycling, while the front wheel was supported by a vibrating platform to simulate road–bike interaction. The vibrotactile perception threshold (VPT) is measured in the fingers, and a questionnaire was used to assess the discomfort in different parts of the hand using a unipolar scale. To validate the method, ten male volunteers underwent two one-hour cycling sessions, one for each of the two handlebar designs tested. VPT was measured in the index and little fingers of the right hand at 8 and 31.5 Hz before and after each session, while the discomfort questionnaire was completed at the end of each session. The discomfort scores showed a strong inter-subject variability, indicating the necessity to combine them with the objective measurements of the VPT, which is shown to be sensitive in identifying the perception shift due to vibration exposure and the differences between the fingers. This study demonstrates the effectiveness of the proposed method for assessing hand numbness and discomfort in cyclists. Full article

In the Hispanic world, the analysis of discourse particles from a microdiachronic perspective has emerged as a relatively recent area of research that has already demonstrated its efficacy, particularly in the context of Spain. However, in the case of Mexico, this type of study is still marginal. The objective of this paper is to analyze hacer de cuenta in Mexican Spanish during the 20th and 21st centuries to illustrate its processes of grammaticalization and pragmatization. To this end, a comprehensive analysis of the CREA and CORDE corpora, as well as six corpora of Mexican Spanish, was conducted. This methodological approach was proposed for three reasons. Firstly, it facilitated the acquisition of a diverse sample of examples. Secondly, it ensured the inclusion of corpora from different decades. Thirdly, it obtained examples that approximate orality. The findings suggest that during this period, hacer de cuenta was undergoing a process of pragmatization. Consequently, it can be regarded as a discourse particle that primarily encodes an intersubjective value, through which the speaker attempts to share with the interlocutor the way she/he conceptualizes a particular event. Full article

Background/Objectives: Traditional dietary screeners face significant limitations: they rely on subjective self-reporting, average intake estimates, and are influenced by a participant’s awareness of being observed—each of which can distort results. These factors reduce both accuracy and reproducibility. The Guide Against Age-Related Disease (GARD) addresses these issues by applying Assembly Theory to objectively quantify food and food behavior (FFB) complexity. This study aims to validate the GARD as a structured, bias-resistant tool for dietary assessment in clinical and research settings. Methods: The GARD survey was administered in an internal medicine clinic within a suburban hospital system in the southeastern U.S. The tool assessed six daily eating windows, scoring high-complexity FFBs (e.g., fresh plants, social eating, fasting) as +1 and low-complexity FFBs (e.g., ultra-processed foods, refined ingredients, distracted eating) as –1. To minimize bias, patients were unaware of scoring criteria and reported only what they ate the previous day, avoiding broad averages. A computer algorithm then scored responses based on complexity, independent of dietary guidelines. Internal (face, convergent, and discriminant) validity was assessed using Spearman rho correlations. Results: Face validation showed high inter-rater agreement using predefined Assembly Index (A_i) and Copy Number (N_i) thresholds. Positive correlations were found between high-complexity diets and behaviors (rho = 0.533–0.565, p < 0.001), while opposing constructs showed moderate negative correlations (rho = –0.363 to −0.425, p < 0.05). GARD scores aligned with established diet patterns: Mediterranean diets averaged +22; Standard American Diet averaged −10. Full article

Background/objectives: Proteus mirabilis is a frequent causative agent of urinary and wound infections in both community and hospital settings. It develops resistance to expanded-spectrum cephalosporins (ESCs) due to the production of extended-spectrum β-lactamases (ESBLs) or plasmid-mediated AmpC β-lactamases (p-AmpCs). Recently, carbapenem-resistant isolates of P. mirabilis emerged due to the production of carbapenemases, mostly belonging to Ambler classes B and D. Here, we report an outbreak of infections due to carbapenem-resistant P. mirabilis that were observed in a psychiatric hospital in Zagreb, Croatia. The characteristics of ESBL and carbapenemase-producing P. mirabilis isolates, associated with an outbreak, were analyzed. Materials and methods: The antibiotic susceptibility testing was performed by the disk-diffusion and broth dilution methods. The double-disk synergy test (DDST) and inhibitor-based test with clavulanic and phenylboronic acid were applied to screen for ESBLs and p-AmpCs, respectively. Carbapenemases were screened by the modified Hodge test (MHT), while carbapenem hydrolysis was investigated by the carbapenem inactivation method (CIM) and EDTA-carbapenem-inactivation method (eCIM). The nature of the ESBLs, carbapenemases, and fluoroquinolone-resistance determinants was investigated by PCR. Plasmids were characterized by PCR-based replicon typing (PBRT). Selected isolates were subjected to molecular characterization of the resistome by an Inter-Array Genotyping Kit CarbaResisit and whole-genome sequencing (WGS). Results: In total, 20 isolates were collected and analyzed. All isolates exhibited resistance to amoxicillin alone and when combined with clavulanic acid, cefuroxime, cefotaxime, ceftriaxone, cefepime, imipenem, ceftazidime–avibactam, ceftolozane–tazobactam, gentamicin, amikacin, and ciprofloxacin. There was uniform susceptibility to ertapenem, meropenem, and cefiderocol. The DDST and combined disk test with clavulanic acid were positive, indicating the production of an ESBL. The MHT was negative in all except one isolate, while the CIM showed moderate sensitivity, but only with imipenem as the indicator disk. Furthermore, eCIM tested positive in all of the CIM-positive isolates, consistent with a metallo-β-lactamase (MBL). PCR and sequencing of the selected amplicons identified VIM-1 and VIM-4. The Inter-Array Genotyping Kit CarbaResist and WGS identified β-lactam resistance genes bla_VIM, bla_CTX-M-15, and bla_TEM genes; aminoglycoside resistance genes aac(3)-IId, aph(6)-Id, aph(3″)-Ib, aadA1, armA, and aac(6′)-IIc; as well as resistance genes for sulphonamides sul1 and sul2, trimethoprim dfr1, chloramphenicol cat, and tetracycline tet(J). Conclusions: This study revealed an epidemic spread of carbapenemase-producing P. mirabilis in two wards in a psychiatric hospital. Due to the extensively resistant phenotype (XDR), therapeutic options were limited. This is the first report of carbapenemase-producing P. mirabilis in Croatia. Full article

Expressive imitation in the performing arts is typically trained through animal behavior imitation, aiming not only to reproduce action trajectories but also to recreate rhythm, style and emotional states. However, evaluation of such animal imitation behaviors relies heavily on teachers’ subjective judgments, lacking structured criteria, exhibiting low inter-rater consistency and being difficult to quantify. To enhance the objectivity and interpretability of the scoring process, this study develops a machine learning and structured pose data-based auxiliary evaluation framework for imitation quality. The proposed framework innovatively constructs three types of feature sets, namely baseline, ablation, and enhanced, and integrates recursive feature elimination with feature importance ranking to identify a stable and interpretable set of core structural features. This enables the training of machine learning models with strong capabilities in structured modeling and sensitivity to informative features. The analysis of the modeling results indicates that temporal–rhythm features play a significant role in score prediction and that only a small number of key feature values are required to model teachers’ ratings with high precision. The proposed framework not only lays a methodological foundation for standardized and AI-assisted evaluation in performing arts education but also expands the application boundaries of computer vision and machine learning in this field. Full article

Background/Objectives: Sarcomas are a rare and heterogeneous group of malignant tumors, which makes early detection and grading particularly challenging. Diagnosis traditionally relies on expert visual interpretation of histopathological biopsies and radiological imaging, processes that can be time-consuming, subjective and susceptible to inter-observer variability. Methods: In this study, we aim to explore the potential of artificial intelligence (AI), specifically radiomics and machine learning (ML), to support sarcoma diagnosis and grading based on MRI scans. We extracted quantitative features from both raw and wavelet-transformed images, including first-order statistics and texture descriptors such as the gray-level co-occurrence matrix (GLCM), gray-level size-zone matrix (GLSZM), gray-level run-length matrix (GLRLM), and neighboring gray tone difference matrix (NGTDM). These features were used to train ML models for two tasks: binary classification of healthy vs. pathological tissue and prognostic grading of sarcomas based on the French FNCLCC system. Results: The binary classification achieved an accuracy of 76.02% using a combination of features from both raw and transformed images. FNCLCC grade classification reached an accuracy of 57.6% under the same conditions. Specifically, wavelet transforms of raw images boosted classification accuracy, hinting at the large potential that image transforms can add to these tasks. Conclusions: Our findings highlight the value of combining multiple radiomic features and demonstrate that wavelet transforms significantly enhance classification performance. By outlining the potential of AI-based approaches in sarcoma diagnostics, this work seeks to promote the development of decision support systems that could assist clinicians. Full article