Diagnostic System Research Articles

Gender bias in assessing narcissistic personality: Exploring the utility of the ICD-11 dimensional model.

Narcissistic personality disorder as captured in categorical diagnostic systems (e.g., DSM-5) emphasizes grandiose features more associated with masculine norms and under-emphasizes vulnerable features more associated with femininity. This poses significant implications in diagnostic outcome and clinical treatment in women with narcissistic preoccupations. Research finds that clinicians using the DSM-5 categorical system tend to diagnose vulnerable narcissism in women as other 'feminized' personality disorders (e.g., borderline), but no research has explored gender differences in narcissism using the new ICD-11 dimensional framework for personality disorders. This study investigated the clinical utility of the ICD-11 approach in capturing gender differences in narcissistic presentations. Adopting an online vignette-based study, mental health clinicians (N = 157; 71.3% female) completed ratings of ICD-11 personality disorder severity and trait domains for two cases reflecting 'grandiose' and 'vulnerable' narcissism in hypothetical male or female patients. The results showed that ratings of core impairments in personality functioning and overall severity were consistent irrespective of patient or clinician gender, contrasting prior research using categorical models. While some differences were observed in trait domain (e.g., negative affectivity) between patient gender, these results suggest the clinical utility of the ICD-11 model as emphasizing elements of personality functioning in the process of assessment and diagnosis, therefore potentially being less susceptible to influences of gender stereotype in aiding clinical conceptualization.

Analysis of anterior segment in primary angle closure suspect with deep learning models

ObjectiveTo analyze primary angle closure suspect (PACS) patients’ anatomical characteristics of anterior chamber configuration, and to establish artificial intelligence (AI)-aided diagnostic system for PACS screening.MethodsA total of 1668 scans of 839 patients were included in this cross-sectional study. The subjects were divided into two groups: PACS group and normal group. With anterior segment optical coherence tomography scans, the anatomical diversity between two groups was compared, and anterior segment structure features of PACS were extracted. Then, AI-aided diagnostic system was constructed, which based different algorithms such as classification and regression tree (CART), random forest (RF), logistic regression (LR), VGG-16 and Alexnet. Then the diagnostic efficiencies of different algorithms were evaluated, and compared with junior physicians and experienced ophthalmologists.ResultsRF [sensitivity (Se) = 0.84; specificity (Sp) = 0.92; positive predict value (PPV) = 0.82; negative predict value (NPV) = 0.95; area under the curve (AUC) = 0.90] and CART (Se = 0.76, Sp = 0.93, PPV = 0.85, NPV = 0.92, AUC = 0.90) showed better performance than LR (Se = 0.68, Sp = 0.91, PPV = 0.79, NPV = 0.90, AUC = 0.86). In convolutional neural networks (CNN), Alexnet (Se = 0.83, Sp = 0.95, PPV = 0.92, NPV = 0.87, AUC = 0.85) was better than VGG-16 (Se = 0.84, Sp = 0.90, PPV = 0.85, NPV = 0.90, AUC = 0.79). The performance of 2 CNN algorithms was better than 5 junior physicians, and the mean value of diagnostic indicators of 2 CNN algorithm was similar to experienced ophthalmologists.ConclusionPACS patients have distinct anatomical characteristics compared with health controls. AI models for PACS screening are reliable and powerful, equivalent to experienced ophthalmologists.

Early Breast Cancer Detection Using Artificial Intelligence Techniques Based on Advanced Image Processing Tools

The early detection of breast cancer is essential for improving treatment outcomes, and recent advancements in artificial intelligence (AI), combined with image processing techniques, have shown great potential in enhancing diagnostic accuracy. This study explores the effects of various image processing methods and AI models on the performance of early breast cancer diagnostic systems. By focusing on techniques such as Wiener filtering and total variation filtering, we aim to improve image quality and diagnostic precision. The novelty of this study lies in the comprehensive evaluation of these techniques across multiple medical imaging datasets, including a DCE-MRI dataset for breast-tumor image segmentation and classification (BreastDM) and the Breast Ultrasound Image (BUSI), Mammographic Image Analysis Society (MIAS), Breast Cancer Histopathological Image (BreakHis), and Digital Database for Screening Mammography (DDSM) datasets. The integration of advanced AI models, such as the vision transformer (ViT) and the U-KAN model—a U-Net structure combined with Kolmogorov–Arnold Networks (KANs)—is another key aspect, offering new insights into the efficacy of these approaches in different imaging contexts. Experiments revealed that Wiener filtering significantly improved image quality, achieving a peak signal-to-noise ratio (PSNR) of 23.06 dB and a structural similarity index measure (SSIM) of 0.79 using the BreastDM dataset and a PSNR of 20.09 dB with an SSIM of 0.35 using the BUSI dataset. When combined filtering techniques were applied, the results varied, with the MIAS dataset showing a decrease in SSIM and an increase in the mean squared error (MSE), while the BUSI dataset exhibited enhanced perceptual quality and structural preservation. The vision transformer (ViT) framework excelled in processing complex image data, particularly with the BreastDM and BUSI datasets. Notably, the Wiener filter using the BreastDM dataset resulted in an accuracy of 96.9% and a recall of 96.7%, while the combined filtering approach further enhanced these metrics to 99.3% accuracy and 98.3% recall. In the BUSI dataset, the Wiener filter achieved an accuracy of 98.0% and a specificity of 98.5%. Additionally, the U-KAN model demonstrated superior performance in breast cancer lesion segmentation, outperforming traditional models like U-Net and U-Net++ across datasets, with an accuracy of 93.3% and a sensitivity of 97.4% in the BUSI dataset. These findings highlight the importance of dataset-specific preprocessing techniques and the potential of advanced AI models like ViT and U-KAN to significantly improve the accuracy of early breast cancer diagnostics.

Stacking Ensemble Artificial Intelligence Model for Heart Disease Diagnosis

Personalized treatment plans, predictive analytics, and artificial intelligence (AI)-driven diagnostics are becoming more and more popular as a way to improve decision-making, expedite operations, and improve patient care. But there are still a number of substantial barriers to overcome, which includes but not limited to issues with user adoption, trust, prejudice, and fairness brought on by resistance from healthcare providers and a lack of confidence in the system's recommendations. To overcome these challenges and realize the full potential of AI-driven solutions, the system's accuracy and safety through meticulous testing and validation of AI algorithms becomes indispensable. This research provides a hybrid AI model that blends three base models with a Meta model in order to diagnose heart disease effectively. The essence is to revalidate the existing AI diagnostic models for cardiac diseases diagnostics and to tackle the concerns impeding the full utilization of the available AI diagnostic system. The study makes use of each model's advantages by merging these various and complimentary algorithms into a stacking ensemble model to create a diagnostic system that is more potent. Using publicly available heart disease data, the model performs remarkably well; it achieves 89% accuracy, 85% recall (sensitivity), 92% specificity, and 89% precision. This hybrid model's performance and proven efficacy are expected to boost trust in the system's recommendations and encourage broader implementation in clinical practice.

A Review of ECG Classification Techniques Based FPGA

Electrocardiogram (ECG) signals are particularly used in the diagnosis and supervision of different cardiovascular diseases. The accurate and efficient classification of ECG signals is of critical importance in clinical applications. FPGA-based systems have been identified to offer an efficient solution to the implementation of real-time ECG signal classification systems because of their parallel processing, reprogrammable nature, and low power consumption. Thus, this review paper aims to explore the existing ECG classification techniques with a focus on FPGA implementation. The review discussed several classification methods, including adaptive algorithms and neural networks, which have been optimized for arrhythmia detection. Notably, Neural network techniques like ANN, CNN, and spiking neural networks are preferable due to their ability to provide superior accuracy. For instance, Mathias et al. developed a high-precision neural network with an impressive accuracy of 99.82%. Similarly, Arona et al. deployed a DCNN on FPGA, achieving accuracies reaching up to 99.67%. Researchers widely used the MIT-BIH dataset to evaluate ECG classification techniques, This paper presents new trends and focuses on future research prospects in this field. Hence, the findings of the present review can help researchers and engineers in developing effective and efficient FPGA-based ECG monitoring and diagnostic systems for clinical and healthcare applications.

A novel peptide pair-based rapid fluorescent diagnostic system for malaria Plasmodium falciparum detection

Advanced diagnostic materials, such as aptamers, are required due to the scarcity of efficient diagnostic antibodies and the low sensitivity of rapid diagnostic kits at detecting the malaria parasite, Plasmodium falciparum. MethodsTwo peptides M2.9 [(KPTAEQTESPELQSAPEN) and M2.17 (KILFNVYSPLGCTCECWV)] were designed using simple epitope prediction tools and modified against the merozoite surface antigen 2 of P. falciparum (Pf.MSP2) by 3-dimensional modeling based on binding affinity. Based on five prediction tools for hydropathy, M2.17 was selected as an appropriate capture peptide. A peptide-based fluorescence-linked immunosorbent assay (FLISA) and a peptide pair-based fluorescent immunochromatographic test strip (FICT) were developed to detect P. falciparum 3D7 (drug-sensitive) and P. falciparum K1 (multi drugs-resistant) strains. ResultsBioinformatic analysis of two peptides demonstrated the potential binding affinity with the merozoite surface protein 2 of P. falciparum (Pf.MSP2) with a positive hydropathy value. The limit of detection (LOD) of FLISA was 10 parasites/μL and of a peptide pair-linked rapid FICT system was 5 and 200 parasites/μL for P. falciparum 3D7 and K1, respectively. Compared to commercial rapid detection systems (RDTs), a peptide pair-linked FICT system exhibited a 20-fold greater efficiency in detecting P. falciparum 3D7 and specifically discriminated another protozoan spp. ConclusionA peptide pair-linked rapid diagnostic strip could be an alternative to conventional RDTs for monitoring wild-type and drug-resistant malaria parasites.

Machine Learning Platform for Disease Diagnosis with Contrast CT Scans

Machine learning has gained significant recognition as a powerful approach for medical diagnosis using medical images. Among various medical imaging modalities, contrast-enhanced CT (CECT) is utilized to obtain additional diagnostic information that improves visualization and evaluation of certain abnormalities in the human body, as well as to observe temporal changes in lesions and tumors across different time phases. However, developing such medical diagnostic systems presents two significant challenges: high technical complexity and substantial development effort. This paper presents a software platform that effectively addresses these challenges. Specifically, we propose a unified software process that fully automates contrast-enhanced CT (CECT)-specific disease diagnosis, with key tasks performed by leveraging task-specific machine learning models to enhance accuracy. The platform incorporates a suite of specialized machine learning models into the diagnostic process, enabling precise diagnosis of lesions, malignancies, tumors, tumor characteristics, and temporal changes over phases. Moreover, the platform has been designed according to the Open–Closed Principle, allowing it to be applicable to a wide range of CECT-based diagnostic systems. The platform has been implemented in Python using the Scikit-learn and TensorFlow libraries. To validate its applicability and reusability, a hepatocellular carcinoma (HCC) diagnosis system has been implemented.

USING THE ARDUINO PLATFORM IN THE RESEARCH OF INTERNAL COMBUSTION ENGINES

Modern measuring systems used in the study of internal combustion engines require significant investments. The universal Arduino platform offers ready-made powerful hardware modules for data collection (shields) and control, which work in a wide range of frequencies and signal amplitudes, provide their analysis and processing, allow to implement equipment management, and have a relatively low cost and free software with standard libraries. These facts testify to the high relevance of the use of the Arduino platform in the study of internal combustion engines. The purpose of this work is to determine the possibilities and features of using the Arduino hardware and software platform in the study of processes occurring in energy power plants with internal combustion engines, early prototyping of their control and diagnostic systems. The paper considers the possibility of hardware and software connection of sensors for measuring basic physical quantities to the Arduino platform: crankshaft rotation frequency (based on induction sensors and Hall sensors), pressure, air and fuel flow, temperatures (resistance sensors and thermocouples). In addition, the characteristics (dependence of the measurement parameter on the output value) of some popular sensors used in the study of internal combustion engines are given. It is important to consider that the equipment used for the study of processes in the ICE must meet the certification requirements. In the case of Arduino, this certification may not be available. However, the recommendations for the use of various sensors, shields and Arduino boards can be applied if the measured quantity is not the determining factor. It is important to consider these limitations and use Arduino with an understanding of the capabilities and limitations of the platform. The use of Arduino in the educational process in the training of specialists in the field of power engineering and in the research of energy installations of vehicles will allow students to apply the knowledge, skills and abilities acquired in the learning process at the hardware and software levels, which will create additional motivation for further study devices and principles of operation of automated and automatic vehicle control systems.

REAL-TIME PARAMETRIC DIAGNOSTICS OF MARINE DIESEL ENGINES

Using modern high-performance microcontrollers with wireless interfaces, built-in ADC and low overall consumption, it is possible to develop a portable real-time parametric diagnostic system for marine engines. The system is based on the use of modern Android/iOS gadgets that receive information from sensors via Bluetooth and then make the necessary calculations and display charts and data in real time. The system being developed uses a combination of a gas pressure sensor in the working cylinder and a vibroacoustic sensor, which expands the diagnostic capabilities of marine diesel engines under operating conditions. This solution makes it possible to diagnose the fuel injection system, the valves control mechanism, as well as some other engine systems. In order to develop a portable diagnostic system for marine diesel engines, it is first necessary to solve the problem of analytically determining TDC, since such a system does not involve the use of special sensors for this. Parameters of irregular engine operation are considered, which can be calculated in real time using time diagrams of pressure and vibration. Methods for expressly assessing the stability of the functioning of the main engine systems by monitoring and analyzing a number of successive operating cycles are considered. To assess the unevenness of engine operation, a dispersion estimate of deviations of the main parameters is used. For a comprehensive assessment of engine stability in real time, the CII (cycle’s irregularity index) criterion is proposed. The assessment of fuel injection irregularity in the engine cylinder can be carried out by analyzing the phase fronts of the vibration signal of the injector. Coefficients for assessing the irregularity of fuel injection and gas distribution valves timing are also proposed, using dispersion analysis of vibrograms fronts. The data processing methods proposed in the article will make it possible to analyze the stability of operating cycles, as well as to perform optimal tuning of engine systems and monitor the results during operation.

Recent advance progress of HL-3 experiments

Abstract Since the first plasma realized in 2020, a series of key systems on HL-3 (known as HL-2M before) tokamak have been equipped/upgraded, including in-vessel components (the first wall, lower divertor, and toroidal cryogenic/water-cooling/baking/glow discharge systems, etc.), auxiliary heating system of 11 MW, and 28 diagnostic systems (to measure the plasma density, electron temperature, radiation, magnetic field, etc.). Magnet field systems were commissioned firstly for divertor plasma discharges. During the 2nd experimental campaign of HL-3 tokamak, several great progresses have been achieved. Firstly, the successful operation with plasma current larger than 1 MA was achieved under a divertor configuration. Secondly, the advanced divertor concept with two distinct snowflake configurations was realized. It is found that the distribution of ion saturation current and heat flux on bottom plate becomes wide due to magnetic surface expansion, demonstrating the advantage of such configuration in the heat flux mitigation. In addition, using the combination of NBI, ECRH and LHCD, the standard sawtoothing high confinement mode of megampere plasma was firstly accessed on the HL-3. The successful commissioning of HL-3 is beneficial for the initial operation of ITER.

Revolutionizing breast ultrasound diagnostics with EfficientNet-B7 and Explainable AI

Breast cancer is a leading cause of mortality among women globally, necessitating precise classification of breast ultrasound images for early diagnosis and treatment. Traditional methods using CNN architectures such as VGG, ResNet, and DenseNet, though somewhat effective, often struggle with class imbalances and subtle texture variations, leading to reduced accuracy for minority classes such as malignant tumors. To address these issues, we propose a methodology that leverages EfficientNet-B7, a scalable CNN architecture, combined with advanced data augmentation techniques to enhance minority class representation and improve model robustness. Our approach involves fine-tuning EfficientNet-B7 on the BUSI dataset, implementing RandomHorizontalFlip, RandomRotation, and ColorJitter to balance the dataset and improve model robustness. The training process includes early stopping to prevent overfitting and optimize performance metrics. Additionally, we integrate Explainable AI (XAI) techniques, such as Grad-CAM, to enhance the interpretability and transparency of the model’s predictions, providing visual and quantitative insights into the features and regions of ultrasound images influencing classification outcomes. Our model achieves a classification accuracy of 99.14%, significantly outperforming existing CNN-based approaches in breast ultrasound image classification. The incorporation of XAI techniques enhances our understanding of the model’s decision-making process, thereby increasing its reliability and facilitating clinical adoption. This comprehensive framework offers a robust and interpretable tool for the early detection and diagnosis of breast cancer, advancing the capabilities of automated diagnostic systems and supporting clinical decision-making processes.

Spectral decomposition for collective Thomson scattering based on an improved genetic algorithm.

Collective Thomson scattering (CTS) is a diagnostic technique that obtains ion temperature and ion composition of plasma by spectral decomposition from scattering spectra. Bayesian estimation and least squares fitting are usually applied in this spectral decomposition process. Nevertheless, these spectral decomposition methods strongly rely on measurements of other diagnostic systems, and the measurement errors of other systems would influence the spectral decomposition results. In this article, an improved genetic algorithm is applied to decompose the scattering spectra of CTS. By analyzing the sensitivity of plasma parameters, the width and slope of the scattering spectrum are found to be strongly associated with ion temperature. Based on this correlation relation, a new fitness function is designed to provide a more precise estimation of ion temperature. Meanwhile, adaptive crossover and mutation operators are introduced to solve the premature convergence problem. This improved genetic algorithm with the new fitness function can obtain a more precise ion temperature from scattering spectra of CTS and does not rely on the measurement of other diagnostic systems, which has an extensive application prospect in data processing of CTS.

The E × B magnetized plasma device (EMPD).

A plasma device has been created to study dynamic plasma coupling in an E × B-drifting magnetized plasma. The E × B magnetized plasma device is a 1.2m diameter by 2m long cylindrical chamber with two sets of Helmholtz coils in a mirror configuration. A steady-state axial hollow cathode source injects a plasma discharge in electrical contact with a floating conductor at a range that forms a unique axisymmetric equipotential surface or Virtual Cathode Lightsaber (VCL). The VCL generates two plasma populations streaming relative to one another providing a suitable environment for the investigation of dynamic plasma coupling. The plasma density, radial electric field, and plasma rotational velocity outside the VCL are shown to be influenced by the current-voltage relationship of the cathode and applied magnetic field strength. A basic characterization of the device and plasma environment is presented with an emphasis on diagnostics systems and the analytical techniques utilized.

Enactivism: a contemporary perspective of a reconceptualization of Osteopathy

Enactivism is a philosophical and scientific approach that emphasizes the role of the body and its interactions with the environment in shaping cognitive processes and subjective experiences. Meanwhile, osteopathy is a person-centered health care discipline, highlighting the structure-function interrelationship of the body and its selfregulation mechanisms. Both approaches value the body and the environment in health. Several authors have been discussing the urgent need for a reconceptualization of osteopathy and also suggesting integrate biological, psychological and social aspects. Thinking osteopathy as a Therapeutic Rationality, implies recognize its fundamental dimensions: Human Morphology, Vital Dynamics, Medical Doctrine, Diagnostic System and Therapeutic System, all integrated by a philosophical Cosmology, as the original term Medical rationality states, but also embrace a broader perspective allowing an individual and unique process of each person, reflecting the transformation of contemporary medicine to a person approach. Enactivism principles can serve as a basis for a reconceptualization of osteopathy, integrating environmental, psychological, social, and spiritual factors. Osteopathic concepts can probably be updated through the convergence between enactivism and osteopathy, promoting more meaningful and evidence-based clinical practice. Advancing in this direction requires a collaborative dialogue between researchers, health professionals and interested people, seeking an integrated understanding of the relationship between body, mind, environment and health.

Efficient, specific and direct detection of double-stranded DNA targets using Cas12f1 nucleases and engineered guide RNAs

To address the limitations of the CRISPR/Cas12f1 system in clinical diagnostics, which require the complex preparation of single-stranded DNA (ssDNA) or in vitro transcripts (RNA), we developed a fluorescent biosensor named PDTCTR (PAM-dependent dsDNA Target-activated Cas12f1 Trans Reporter). This innovative biosensor integrates Recombinase Polymerase Amplification (RPA) with the Cas12f_ge4.1 system, facilitating the direct detection of double-stranded DNA (dsDNA). PDTCTR represents a significant leap forward, exhibiting a detection sensitivity that is a hundredfold greater than the original Cas12f1 system. It demonstrates the capability to detect Mycoplasma pneumoniae (M. pneumoniae) and Hepatitis B virus (HBV) with excellent sensitivity of 10 copies per microliter (16.8 attomolar) and distinguishes single nucleotide variations (SNVs) with high precision, including the EGFR (L858R) mutations prevalent in non-small cell lung cancer (NSCLC). Clinical evaluations of PDTCTR have demonstrated its high sensitivity and specificity, with rates ranging from 93%∼100% and 100%, respectively, highlighting its potential to revolutionize diagnostic approaches for infectious diseases and cancer-related SNVs.This research underscores the substantial advancements in CRISPR technology for clinical diagnostics and its promising future in early disease detection and personalized medicine.

The Application of Nanotechnology for the Diagnosis and Treatment of Endocrine Disorders: A Review of Current Trends, Toxicology and Future Perspective.

The endocrine system regulates many biological systems, and disruptions may result in disorders, such as diabetes, thyroid dysfunction, Cushing's syndrome, and obesity. The total incidence of endocrine illnesses was found to be 47.4%, excluding type 2 diabetes mellitus, with a significant frequency of newly diagnosed endocrine disorders. Nanotechnology manipulates particles at the atomic and molecular levels, opening up new paths for studying disease etiology and therapeutic alternatives. The goal of using nanomaterials in the treatment of endocrine illnesses is to create endogenous nano-biosensors that can detect even modest changes in hormone levels and react spontaneously to restore normal function. The size and surface characteristics of nanoparticles enhances the sensitivity in nano-sensors and are functionalized for targeted drug delivery. Nano-sized carriers composed of lipids, polymers, carbon, or metals have been shown to work much better than standard drug delivery methods. Nanoparticles (NPs) offer various advantages over current methods for diagnosing and treating endocrine disorders, acting as hydrogels for insulin delivery and wound healing. Incorporating selenium NPs into inorganic nanoparticles enhances their bioactivity and targeted delivery. Gold NPs show a promising precise insulin delivery. Mesoporous silica NPs maintain glycemic level effectively and lipid and polymeric NPs protect drugs from degradation in the gastrointestinal tract. Carbon nanotubes (CNTs) have become popular in thyroid surgeries. These characteristics make nanoparticles valuable for developing effective diagnostic and therapeutic systems. NP-based medicines have been thoroughly researched in order to identify the beginning point for the creation of theranostics, which may function in two ways: as imaging agents or therapeutics. The study posits that nanotechnology bridges diagnostics and therapies, potentially revolutionizing endocrine disorder treatments. This review delves into nanotechnology techniques, emphasizing their applications in diagnosing and treating diabetes mellitus.

Smart molecular probes with controllable photophysical property for smart medicine

AbstractPrecision medicine calls for advanced theranostics that integrate controllable diagnostic and therapeutic capabilities into one platform for disease treatment in the early stage. Phototheranostics such as fluorescence imaging (FLI), photoacoustic imaging (PAI), photodynamic therapy (PDT), and photothermal therapy (PTT) have attracted considerable attention in recent years, which mainly employ different excited‐state energy dissipation pathways of a chromophore. According to the Jablonski diagram, FLI is related to the radiative process, PAI and PTT are derived from the nonradiative thermal deactivation, and PDT originates from the triplet state energy, in which these processes are usually competitive. Therefore, it is critically important to precisely tune the photophysical energy transformation processes to realize certain diagnosis and treatment properties in optimal state for boosting biomedical applications. Currently, there are mainly two strategies including chemical structure and aggregate behavior changes that relate to the regulation of excited state energy dissipation. In this review, we will discuss the recent advances of smart molecular probes that the photophysical properties can be regulated by external triggers and their applications in biomedical fields. We will summarize the development of activatable phototheranostic molecular probes in response to stimuli such as reactive oxygen species, pH, light, hypoxia, enzyme and gas. The assembly and disassembly of molecular aggregates that greatly affect the photophysical energy transformation processes will also be highlighted. This review aims to provide valuable insights into the development of more accurate diagnostic and therapeutic systems, thereby advancing the emerging field of smart medicine.

Multimodal Convolutional Neural Network-Based Algorithm for Real-Time Detection and Differentiation of Malignant and Inflammatory Biliary Strictures in Cholangioscopy: a Proof of Concept Study with Video

Deep learning algorithms gained attention for detection (CADe) of biliary tract cancer (BTC) in digital single-operator cholangioscopy (dSOC). We developed a multimodal convolutional neural network (CNN) for detection (CADe) characterization and discriminating (CADx) between malignant, inflammatory and normal biliary tissue in raw dSOC videos. In addition, clinical metadata was included in the CNN algorithm to overcome limitations of image-only models. Based on dSOC videos and images of 111 patients (total of 15,158 still frames), we developed and validated a real-time CNN-based algorithm for CADe and CADx. We established an image-only model and metadata injection approach. In addition, we validated frame-wise and case-based predictions on complete dSOC video sequences. Model embeddings were visualized and class-activation maps highlighted relevant image regions. The concatenation-based CADx approach achieved a per-frame AUC of 0.871, sensitivity of 0.809 (95% CI: [0.784-0.832]), specificity of 0.773 [0.761-0.785], PPV of 0.450 [0.423-0.467], and NPV of 0.946 [0.940-0.954] with respect to malignancy on 5,715 test frames from complete videos of 20 patients. For case-based diagnosis using average prediction scores, six out of eight malignant cases and all twelve benign cases were identified correctly. Our algorithm distinguishes malignant and inflammatory bile duct lesions in dSOC videos, indicating the potential of CNN-based diagnostic support systems for both, CADe and CADx. The integration of non-image data can improve CNN based support systems, targeting current challenges in the assessment of biliary strictures.

ценка риска формирования у детей вторичного иммунодефицита в условиях контаминации биосред алюминием и полиморфизма гена клеточной гибели FAS rs1159120 и антигенраспознающего гена толл-подобного рецептора TLR4 rs1927911

Secondary immunodeficiency remains an incompletely understood medical problem, and despite a significant number of international and scientific studies, there is no complete picture of the causes and consequences of this pathology. Metal cations have been proven to participate in the formation of acquired immunodeficiency. In particular, aluminum properties as an immune suppressor have been established and its targets in the body have been identified in case aluminum was present in biological media. However, no evaluations have been accomplished so far as regards the role of specific point genetic changes, that is, polymorphisms in the genes of immune system compartments that determine the risk of negative effects caused by contamination with metal cations, including aluminum. It is quite relevant to search and substantiate immunogenetic markers to create an indicator system for diagnostics and prevention of secondary immunodeficiency states in children associated with aluminum contamination in biological media. We examined 97 preschool children exposed to elevated levels of airborne aluminum (in an area influenced by a metallurgic production). The study groups were divided depending on either presence or absence of secondary immunodeficiency as immune system pathology (common variable immunodeficiency D83). Several markers of the immune system were evaluated: aluminum-specific IgG, CD3+, CD4+, CD8+, CD127-, CD95+, CD284+, and phagocytic activity; we also evaluated polymorphism of TLR4 A8595G (rs1927911) and FAS C14405T (rs1159120) genes of innate and acquired immunity. According to the results obtained by examining biological media composition, children with secondary immunodeficiency had 1.8 times higher aluminum levels in urine (0.0095 ± 0.0014 vs. 0.0054 ± 0.0009 mg/dm3, reference range < 0.0075 mg/dm3) as opposed to their conditionally healthy peers. We established an authentic inverse dependence between the expression level of the main CD clusters (CD3+: r = -0.38; CD4+: r = -0.39; CD8+: r = -0.26) as well as indicators of phagocytic activity (r = -0.22–0.23) and the level of aluminum contamination in biological media (urine). Expression of T-mature lymphocyte clusters was found to be inhibited by 1.3–3.1 times (including T-helper, effector T-lymphocytes, NK-killers, regulatory lymphocytes) and we also detected some changes in expression of specific immunoglobulin of IgG class to aluminum. All this results in an unacceptable level of relative risk (RR = 1.23–1.63) of developing secondary immunodeficiency against increased frequency of allele C and genotype CC of FAS gene (rs1159120) by 1.2 and 1.5 times respectively, as well as minor allele G of TLR4 gene (rs1927911) by 1.8 times relative to the comparison group (OR = 4.05; CI: 1.41–11.59; p = 0.006; RR = 1.23; CI: 1.02–1.48) and (OR = 2.01; CI: 1.04–3.91; p = 0.037; RR = 1.64; CI:1.46–1.94). Toll-dependent and FAS-dependent mechanism of this risk is associated with aluminum contamination. It is recommended to use a combination of immune and genetic markers as indicator ones when evaluating the immune system state, in order to prevent the risk (RR = 1.23–1.63) of secondary immunodeficiency associated with aluminum contamination in biological media.

Assessing risks of secondary immunodeficiency in children with aluminum contamination in biological media and polymorphism of the cell death gene FAS rs1159120 and the antigen-recognizing gene of the toll-like receptor TLR4 rs1927911

Secondary immunodeficiency remains an incompletely understood medical problem, and despite a significant number of international and scientific studies, there is no complete picture of the causes and consequences of this pathology. Metal cations have been proven to participate in the formation of acquired immunodeficiency. In particular, aluminum properties as an immune suppressor have been established and its targets in the body have been identified in case aluminum was present in biological media. However, no evaluations have been accomplished so far as regards the role of specific point genetic changes, that is, polymorphisms in the genes of immune system compartments that determine the risk of negative effects caused by contamination with metal cations, including aluminum. It is quite relevant to search and substantiate immunogenetic markers to create an indicator system for diagnostics and prevention of secondary immunodeficiency states in children associated with aluminum contamination in biological media. We examined 97 preschool children exposed to elevated levels of airborne aluminum (in an area influenced by a metallurgic production). The study groups were divided depending on either presence or absence of secondary immunodeficiency as immune system pathology (common variable immunodeficiency D83). Several markers of the immune system were evaluated: aluminum-specific IgG, CD3+, CD4+, CD8+, CD127-, CD95+, CD284+, and phagocytic activity; we also evaluated polymorphism of TLR4 A8595G (rs1927911) and FAS C14405T (rs1159120) genes of innate and acquired immunity. According to the results obtained by examining biological media composition, children with secondary immunodeficiency had 1.8 times higher aluminum levels in urine (0.0095 ± 0.0014 vs. 0.0054 ± 0.0009 mg/dm3, reference range < 0.0075 mg/dm3) as opposed to their conditionally healthy peers. We established an authentic inverse dependence between the expression level of the main CD clusters (CD3+: r = -0.38; CD4+: r = -0.39; CD8+: r = -0.26) as well as indicators of phagocytic activity (r = -0.22–0.23) and the level of aluminum contamination in biological media (urine). Expression of T-mature lymphocyte clusters was found to be inhibited by 1.3–3.1 times (including T-helper, effector T-lymphocytes, NK-killers, regulatory lymphocytes) and we also detected some changes in expression of specific immunoglobulin of IgG class to aluminum. All this results in an unacceptable level of relative risk (RR = 1.23–1.63) of developing secondary immunodeficiency against increased frequency of allele C and genotype CC of FAS gene (rs1159120) by 1.2 and 1.5 times respectively, as well as minor allele G of TLR4 gene (rs1927911) by 1.8 times relative to the comparison group (OR = 4.05; CI: 1.41–11.59; p = 0.006; RR = 1.23; CI: 1.02–1.48) and (OR = 2.01; CI: 1.04–3.91; p = 0.037; RR = 1.64; CI:1.46–1.94). Toll-dependent and FAS-dependent mechanism of this risk is associated with aluminum contamination. It is recommended to use a combination of immune and genetic markers as indicator ones when evaluating the immune system state, in order to prevent the risk (RR = 1.23–1.63) of secondary immunodeficiency associated with aluminum contamination in biological media.