Search Results (52)

Accurate skin lesion classification is crucial for the early detection of malignant lesions, including melanoma, as well as improved patient outcomes. While convolutional neural networks (CNNs) excel at capturing local morphological features, they struggle with global context modeling essential for comprehensive lesion assessment. Vision transformers address this limitation but suffer from quadratic computational complexity O(n²), hindering deployment in resource-constrained clinical environments. We propose DermaMamba, a novel dual-branch fusion architecture that integrates CNN-based local feature extraction with Vision Mamba (VMamba) for efficient global context modeling with linear complexity O(n). Our approach introduces a state space fusion mechanism with adaptive weighting that dynamically balances local and global features based on lesion characteristics. We incorporate medical domain knowledge through multi-directional scanning strategies and ABCDE (Asymmetry, Border irregularity, Color variation, Diameter, Evolution) rule feature integration. Extensive experiments on the ISIC dataset show that DermaMamba achieves 92.1% accuracy, 91.7% precision, 91.3% recall, and 91.5% mac-F1 score, which outperforms the best baseline by 2.0% accuracy with 2.3× inference speedup and 40% memory reduction. The improvements are statistically significant based on a significance test (p < 0.001, Cohen’s d > 0.8), with greater than 79% confidence also preserved on challenging boundary cases. These results establish DermaMamba as an effective solution bridging diagnostic accuracy and computational efficiency for clinical deployment. Full article

Ocular disease (OD) represents a complex medical condition affecting humans. OD diagnosis is a challenging process in the current medical system, and blindness may occur if the disease is not detected at its initial phase. Recent studies showed significant outcomes in the identification of OD using deep learning (DL) models. Thus, this work aims to develop a multi-classification DL-based model for the classification of seven ODs, including normal (NOR), age-related macular degeneration (AMD), diabetic retinopathy (DR), glaucoma (GLU), maculopathy (MAC), non-proliferative diabetic retinopathy (NPDR), and proliferative diabetic retinopathy (PDR), using color fundus images (CFIs). This work proposes a custom model named the ocular disease detection model (ODDM) based on a CNN. The proposed ODDM is trained and tested on a publicly available ocular disease dataset (ODD). Additionally, the SMOTE Tomek (SM-TOM) approach is also used to handle the imbalanced distribution of the OD images in the ODD. The performance of the ODDM is compared with seven baseline models, including DenseNet-201 (R₁), EfficientNet-B0 (R₂), Inception-V3 (R₃), MobileNet (R₄), Vgg-16 (R₅), Vgg-19 (R₆), and ResNet-50 (R₇). The proposed ODDM obtained a 98.94% AUC, along with 97.19% accuracy, a recall of 88.74%, a precision of 95.23%, and an F1-score of 88.31% in classifying the seven different types of OD. Furthermore, ANOVA and Tukey HSD (Honestly Significant Difference) post hoc tests are also applied to represent the statistical significance of the proposed ODDM. Thus, this study concludes that the results of the proposed ODDM are superior to those of baseline models and state-of-the-art models. Full article

Maternal and child health during pregnancy is an important issue in global public health, and the classification accuracy of fetal cardiotocography (CTG), as a key tool for monitoring fetal health during pregnancy, is directly related to the effectiveness of early diagnosis and intervention. Due to the serious category imbalance problem of CTG data, traditional models find it challenging to take into account a small number of categories of samples, increasing the risk of leakage and misdiagnosis. To solve this problem, this paper proposes a two-step innovation: firstly, we design a method of adaptive adjustment of misclassification loss function weights (MAAL), which dynamically identifies and increases the focus on misclassified samples based on misclassification rates. Secondly, a primary and secondary correction network model (MAC-NET) is constructed to carry out secondary correction for the misclassified samples of the primary model. Experimental results show that the method proposed in this paper achieves 99.39% accuracy on the UCI publicly available fetal health dataset, and also obtains excellent performance on other domain imbalance datasets. This demonstrates that the model is not only effective in alleviating the problem of category imbalance, but also has very high clinical utility. Full article

Accurate antimicrobial susceptibility testing (AST) of cefiderocol remains a diagnostic challenge, especially in infections caused by metallo-β-lactamase (MBL)-producing Klebsiella pneumoniae. While disk diffusion offers a cost-effective alternative to broth microdilution, it is highly sensitive to factors such as media composition and the presence of atypical colony morphology. The objective of this study was to evaluate how different agar media and interpretations of isolated colonies affect the performance and reliability of cefiderocol AST by disk diffusion. A total of 50 clinical K. pneumoniae MBL isolates were tested using disk diffusion on Columbia with blood, MacConkey, and chromogenic agars from three manufacturers. Inhibition zones were compared with MICs from broth microdilution. Statistical analyses included paired t-tests and Spearman correlation to assess media effects and zone morphology impact. Variability in inhibition zone diameters was observed between media, notably with chromogenic agar. The most consistent results were obtained using Graso Biotech and Thermo Fisher Columbia with blood agar. Isolated colonies were observed in over half the samples and, depending on how they were interpreted, led to major changes in classification accuracy. Up to 64% of results fell into the EUCAST area of technical uncertainty (ATU), and categorical agreement varied across media and interpretive criteria. Disk diffusion for cefiderocol may be used in resource-limited settings but only if rigorously standardized using validated media, consistent zone reading, and ATU-aware interpretive strategies. In borderline cases or when morphological anomalies are present, broth microdilution should be considered the sole reliable method. Clinical microbiologists are advised to exercise caution with ambiguous results and seek expert or confirmatory testing when needed. Full article

Edge-computing applications demand ultra-low-power architectures for both feature extraction and classification tasks. In this manuscript, a Keyword Spotting (KWS) system tailored for energy-constrained portable environments is proposed. A 16-channel analog filter bank is employed for audio feature extraction, followed by a digital Gated Recurrent Unit (GRU) classifier. The filter bank is behaviorally modeled, making use of second-order band-pass transfer functions, simulating the analog front-end (AFE) processing. To enable efficient deployment, the GRU classifier is trained using a Learned Step Size (LSQ) and Look-Up Table (LUT)-aware quantization method. The resulting quantized model, with 4-bit weights and 8-bit activation functions (W4A8), achieves 91.35% accuracy across 12 classes, including 10 keywords from the Google Speech Command Dataset v2 (GSCDv2), with less than 1% degradation compared to its full-precision counterpart. The model is estimated to require only 34.8 kB of memory and 62,400 multiply–accumulate (MAC) operations per inference in real-time settings. Furthermore, the robustness of the AFE against noise and analog impairments is evaluated by injecting Gaussian noise and perturbing the filter parameters (center frequency and quality factor) in the test data, respectively. The obtained results confirm a strong classification performance even under degraded circuit-level conditions, supporting the suitability of the proposed system for ultra-low-power, noise-resilient edge applications. Full article

Background: Children generally face a higher incidence of airway management complications, intubation difficulties, and the risk of failed intubation. Currently, there is sufficient evidence in clinical practice for the use of videolaryngoscopes in pediatric airway management. However, there are a number of standard-blade videolaryngoscopes available for children. In addition, there is no clear recommendation on which videolaryngoscope is superior. The primary objective of this study is to compare the first pass success rate and the Percentage of Glottic Opening (POGO) scores with Cormack–Lehane (CML) scores obtained through direct and indirect laryngoscopy with HugeMed and McGrath Mac videolaryngoscopes in pediatric patients with an unanticipated, difficult airway. Materials and Methods: Following the Ethics Committee approval and written parental consents, a total of 40 elective surgical patients, aged 3 and under, with ASA 1–3 risk classification, and undergoing general anesthesia, were included in the study. After induction of general anesthesia, the first group of patients (Group McGrath, n = 20) was intubated with the McGrath Mac videolaryngoscope, and the second group (Group HugeMed, n = 20) with the HugeMed videolaryngoscope. Before intubation, CML and POGO scores were recorded for both groups using direct and indirect laryngoscopy with videolaryngoscopes. Intubation time, number of attempts, need for cricoid pressure, optimization maneuver requirement, and hemodynamic parameters were recorded for both groups. Results: There was no significant difference between groups in demographic data including age, gender, body mass index, ASA, and hemodynamic parameters. A significant improvement was observed in CML and POGO scores using indirect laryngoscopy (p < 0.001). CML scores obtained with the McGrath Mac were significantly lower than the HugeMed Group (p = 0.0034). The mean POGO value calculated with indirect laryngoscopy was significantly higher in the McGrath Group compared to the HugeMed Group (92.63 ± 6.09 vs. 88.75 ± 4.44, respectively). Conclusions: Videolaryngoscopes improved laryngeal visualization in children under 3 years old. Compared to HugeMed, in indirect laryngoscopy, the McGrath Mac videolaryngoscope was found to be superior, with better CML and POGO scores. However, number of tracheal intubation attempts, success rate, complication risk, and hemodynamic parameters did not show any significant difference between the groups. Clinical trial registration number was NCT06484517. Full article

Vector–matrix multiplication (VMM), which dominates the computational workload in neural networks, accounts for over 99% of all operations, particularly in Convolutional Neural Networks (CNNs). These operations, consisting of multiply-and-accumulate (MAC) functions, are straightforward but demand massive parallelism, often involving billions of operations per layer. This computational demand negatively affects processing time, energy consumption, and memory bandwidth due to frequent external memory access. To efficiently address these challenges, this paper investigates the implementation of a full neural network for image classification, using TensorFlow as a software baseline, and compares it with a hardware counterpart mapped onto resistive RAM-based crossbar arrays, a practical implementation of the memristor concept. By leveraging the inherent ability of RRAM crossbars to perform VMMs in a single step, we demonstrate how RRAM-based neural networks can achieve efficient in-memory analog computing. To ensure realistic and practical results, the hardware implemented utilizes RRAM memory cells characterized through silicon measurements. Furthermore, the design exclusively considers positive weights and biases to minimize the area overhead, resulting in a lightweight hardware solution. This approach achieves an energy consumption of 190 fJ/MAC operation for the crossbar array, highlighting its efficiency in power-constrained applications despite a drop in the prediction confidence of 27.5% compared to the software approach. Full article

Background/Objectives: Cerebral palsy (CP) is the most common childhood motor disorder, with unilateral cerebral palsy (UCP) presenting with asymmetrical motor function that can cause decreased upper limb function. Constraint-Induced Movement Therapy (CIMT) is an evidence-based intervention that addresses upper limb functional limitations, but further study on combining interventions with CIMT is warranted. Combining CIMT with virtual reality (VR) is hypothesized to enhance engagement and therapeutic outcomes. This study compared the effectiveness of CIMT alone versus CIMT combined with VR (CIMT + VR) in improving upper limb function and occupational performance in children with UCP. Methods: A blinded, randomized, controlled trial included children aged 5–13 years with Manual Ability Classification System (MACS) levels I–III. The participants were randomized into CIMT or CIMT + VR groups and completed a standardized 10-day camp protocol (60 h). Pre-intervention and post-intervention assessments included the Assisting Hand Assessment (AHA) and the Canadian Occupational Performance Measure (COPM). Secondary measures included acceptability ratings of VR devices and fidelity. Results: Thirty-two participants, with a mean age of 9 years and 3 months (3 years 1 month), MACS I = 4, II = 20, and III = 8, completed this study. CIMT and CIMT + VR led to significant improvements in upper limb function, with no statistically significant differences between the groups in bilateral hand use and occupational performance. Conclusions: These findings reinforce the efficacy of CIMT while highlighting the potential of VR to enhance engagement when the child prefers to interact with the technology, underscoring the importance of individualized approaches that consider a child’s preferences and responsiveness to different intervention modalities. Full article

Background: The aim was to explore independent wheeled mobility in children with CP, and identify predictors of early independent wheeled mobility and changes over time across birth cohorts. Methods: We included data from the Norwegian Quality and Surveillance Registry for Cerebral Palsy (NorCP) comprising 11,565 assessments of 1780 children born in 2002–2019. Variables included demographic data, Gross Motor Function Classification System (GMFCS) and Manual Ability Classification System (MACS) levels, wheelchair use, and independent wheeled mobility. Cox proportional hazard regression was used to identify predictors for early independent wheeled mobility. Kaplan–Meier survival curves were used to compare birth cohorts. Results: Of 769 (43%) children who used a wheelchair, 511 (67%) had independent wheeled mobility. Two thirds of the children (n = 337) achieved independent wheeled mobility before age 7. Most children with independent wheeled mobility used powered wheelchairs. Children at GMFCS levels III and IV were more likely to reach independent wheeled mobility at an early age. Children at MACS levels III–V had a lower probability of early independent wheeled mobility. The average age of achieving independent mobility decreased from 9.5 to 4.0 years between birth years 2002 and 2019. Conclusions: Two in three children were independent wheelchair users before 7 years of age, and the age of obtaining independent wheeled mobility has decreased over the last 20 years. Children with better hand function were more likely to obtain early independent wheeled mobility. Early intervention programs to promote mobility, development and participation should include powered mobility, adapted steering options, and interventions for hand function. Full article

Background and Objectives: Hemiplegic or unilateral cerebral palsy (UCP) is primarily characterized by motor impairment, mainly affecting the upper limb. Research has centered on factors influencing the varying degrees of motor deficit in UCP, using neuroscience advancements for in vivo exploration of brain structure (morphometry) and cortical reorganization (functional magnetic resonance imaging (fMRI)). This study aims to evaluate functional activation in the motor cortex in UCP and to explore how lesion characteristics and timing affect neuroplasticity and motor function. Materials and Methods: Between 2017 and 2021, structural and functional MRIs were performed on 44 UCP patients (mean age 15.5 years, 24 males, 20 females), all with Manual Ability Classification System (MACS) levels I-III and Intelligence Quotient (IQ) ≥ 50. The lesion characteristics of size, type, and time of occurrence (ante-, peri-, or early postnatal) were analyzed. An association was sought between the characteristics of the lesion and the degree of motor deficit of the upper limb, as determined by the MACS level. fMRI assessed cortical activation during a finger-tapping task for the paretic hand and compared activation patterns based on lesion characteristics. Results: Six lesion types were identified, with arterial ischemic stroke being the most common and largest in volume. Lesion size strongly correlated with patients’ MACS levels, while lesion type and timing showed no association with the severity of motor impairment classified by MACS. Motor reorganization varied, with activation occurring ipsi-, contra-, or bilaterally to the affected hand, depending on lesion size and type. Smaller, subcortical lesions primarily showed ipsilesional activation, while larger, cortical lesions did not exhibit a specific group activation, possibly due to varying individual reorganization. No association was found between the lesion timing and the reorganization model. Conclusions: Motor functional reorganization in UCP is closely linked to lesion characteristics, with smaller, subcortical lesions favoring typical organization in the contralateral motor cortex. The timing of the lesion does not significantly affect cortical reorganization. Lesion size was a key determinant of motor function, whereas lesion type (e.g., ischemic stroke) and timing (early vs. late occurrence) were less critical for predicting functional outcome. Full article

Background: Women with an aplastic uterus (ESHRE/ESGE classification) or Müllerian agenesis (ASRM MAC 2021) might present with functional uterine remnants. Our study aimed to report the clinical course of symptomatic uterine rudiments in adolescents and adults with Mayer–Rokitansky–Küster–Hauser syndrome (MRKHS). Methods: This study involved 20 patients with MRKHS who, between 2012 and 2023, underwent surgery for symptomatic uterine horns at the mean age of 25.2 years in the Division of Gynaecology, Gynaecological and Obstetric Clinical Hospital, Poznan University of Medical Sciences, Poland. The records of the patients were retrospectively analysed. Results: The volume of the uterine horns ranged from 0.8 to 58.3 cm³, and the volume of the endometrial cavity within the horns ranged from 0.03 to 12 cm³, with no significant difference between adolescents and adults (p = 0.36). In five patients (25%), MRKHS was identified during the diagnosis of recurrent pelvic pain at the age of 12.6–14.8 years. In 19 patients, uterine rudiments were removed: unilaterally in 3 patients (16%), bilaterally in 16 patients (84%), and laparoscopically in 89% of cases. In one patient, the horn was preserved (horno-neovaginal anastomosis). Histopathology confirmed the presence of the endometrium in uterine rudiments ipsilateral to the pain location in 75% of cases. Four patients (20%) were diagnosed with endometriosis. Conclusions: Recurrent pelvic pain in patients with MRKHS should prompt the diagnosis of functional uterine rudiments. The resection of symptomatic uterine horns can result in the complete resolution of pain. Patients with endometriosis are at risk of pain recurrence. In some patients strongly desirous of menstruation, horno-neovaginal anastomosis can be cautiously attempted. Full article

Since image recognition systems use image data acquired by image sensors for analysis by AI technology, an important security issue is guaranteeing the authenticity of data transmitted from image sensors to successfully perform inference using AI. There have been reports of physical attacks on image sensor interfaces by tampering with images to cause misclassifications in AI classification results. As a countermeasure against these attacks, it is effective to add authenticity to image data with a message authentication code (MAC). For the implementation of this, it is important to have technologies for generating MAC keys on image sensors and to create an environment for secure MAC verification on the host device. For MAC key generation, we used the CIS-PUF technology, which generates MAC keys from PUF responses and random numbers from CMOS image sensor variations. For the secure MAC verification, we used TEE technology, which executes security-critical processes in an environment isolated from the normal operating system. In this study, we propose and demonstrate an image tampering detection system based on MAC verification with CIS-PUF and OP-TEE in an open portable TEE on an ARM processor. In the experiments, we demonstrated a system that computed and transmitted MAC for captured images using the CIS-PUF key and then performed MAC verification in the secure world of the OP-TEE. Full article

Suppose R is a finite commutative local ring, then it is known that R has four positive integers $p,n,m,k$ called the invariants of R, where p is a prime number. This paper investigates the structure and classification up to isomorphism of local rings with residue field ${\mathbb{F}}_{p^m}$ and of length 4. Specifically, it gives a comprehensive characterization of Frobenius local rings of order $p^{4m}$. Furthermore, we provide a detailed enumeration of the classes of all such rings with respect to their invariants $p,n,m,k$. Finite Frobenius rings are particularly advantageous for coding theory. This suitability arises from the fact that two classical theorems by MacWilliams, the Extension Theorem and the MacWilliams relations for symmetrized weight enumerators, can be generalized from finite fields to finite Frobenius rings. Full article

Background: Early motor development is fundamental in driving cognitive skill acquisition. Motor delays in children with cerebral palsy (CP) often limit exploratory behaviors, decreasing opportunities or the quality of cognitive development, emphasizing the importance of early intervention. This study aimed to assess immediate and 5-month motor and cognitive changes in infants and toddlers at risk of or with CP after participation in a community-based program. Methods: Twenty-two children (mean age: 22 ± 7 months) classified using the Gross Motor Function Classification System (GMFCS) and mini-Manual Ability Classification System (mini-MACS) participated in a 6-day community-based activity program, with outcomes assessed using the Developmental Assessment of Young Children (DAYC-2). Results: Participants who met their motor goals post-participation had significantly higher cognitive scores (p = 0.006) 5 months after the program. Participants with higher functional motor abilities (GMFCS levels I–II, p = 0.052; mini-MACS levels I–II, p = 0.004) demonstrated better cognitive scores at 5 months, adjusted for baseline scores, than those with lower functional motor abilities. Conclusions: This study highlights the impact of motor improvements following an evidence-based community program on later cognitive development. Prospective studies investigating the mechanisms and mediation of cognitive progress in children with CP should investigate the effects of early motor interventions on long-term developmental trajectories. Full article

In dynamic scenarios, the status of a Radio Frequency Identification (RFID) system fluctuates with environmental changes. The key to improving system efficiency lies in the real-time monitoring and evaluation of the system status, along with adaptive adjustments to the system parameters and read algorithms. This paper focuses on the status changes in RFID systems in dynamic scenarios, aiming to enhance system robustness and reading performance, ensuring high link quality, reasonable resource scheduling, and real-time status evaluation under varying conditions. This paper comprehensively considers the system parameter settings in dynamic scenarios, integrating the interaction model between readers and tags. The system’s real-time status is evaluated from both the physical layer and the Medium Access Control (MAC) layer perspectives. For the physical layer, a link quality evaluation model based on Uniform Manifold Approximation and Projection (UMAP) and K-Means clustering is proposed from the link quality. For the MAC layer, a multi-criteria decision-making evaluation model based on combined weighting and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is proposed, which comprehensively considers both subjective and objective factors, utilizing the TOPSIS algorithm for an accurate evaluation of the MAC layer system status. For the RFID system, this paper proposes a real-time status evaluation model based on the Classification and Regression Tree (CART), which synthesizes the evaluation results of the physical layer and MAC layer. Finally, engineering tests and verification were conducted on the RFID robot system in mobile scenarios. The results showed that the clustering average silhouette coefficient of the physical layer link quality evaluation model based on K-Means was 0.70184, indicating a relatively good clustering effect. The system status evaluation model of the MAC layer, based on the combined weighting-TOPSIS method, demonstrated good flexibility and generalization. The real-time status evaluation model of the RFID system, based on CART, achieved a classification accuracy of 98.3%, with an algorithm runtime of 0.003 s. Compared with other algorithms, it had a higher classification accuracy and shorter runtime, making it well suited for the real-time evaluation of the RFID robot system’s status in dynamic scenarios. Full article