RESUMEN
As the dimensionality, throughput and complexity of cytometry data increases, so does the demand for user-friendly, interactive analysis tools that leverage high-performance machine learning frameworks. Here we introduce FlowAtlas: an interactive web application that enables dimensionality reduction of cytometry data without down-sampling and that is compatible with datasets stained with non-identical panels. FlowAtlas bridges the user-friendly environment of FlowJo and computational tools in Julia developed by the scientific machine learning community, eliminating the need for coding and bioinformatics expertise. New population discovery and detection of rare populations in FlowAtlas is intuitive and rapid. We demonstrate the capabilities of FlowAtlas using a human multi-tissue, multi-donor immune cell dataset, highlighting key immunological findings. FlowAtlas is available at https://github.com/gszep/FlowAtlas.jl.git.
Asunto(s)
Biología Computacional , Citometría de Flujo , Inmunofenotipificación , Programas Informáticos , Humanos , Inmunofenotipificación/métodos , Citometría de Flujo/métodos , Biología Computacional/métodos , Aprendizaje AutomáticoRESUMEN
This paper studies an optimal synchronous control protocol design for nonlinear multi-agent systems under partially known dynamics and uncertain external disturbance. Under some mild assumptions, Hamilton-Jacobi-Isaacs equation is derived by the performance index function and system dynamics, which serves as an equivalent formulation. Distributed policy iteration adaptive dynamic programming is developed to obtain the numerical solution to the Hamilton-Jacobi-Isaacs equation. Three theoretical results are given about the proposed algorithm. First, the iterative variables is proved to converge to the solution to Hamilton-Jacobi-Isaacs equation. Second, the L2-gain performance of the closed loop system is achieved. As a special case, the origin of the nominal system is asymptotically stable. Third, the obtained control protocol constitutes an Nash equilibrium solution. Neural network-based implementation is designed following the main results. Finally, two numerical examples are provided to verify the effectiveness of the proposed method.
RESUMEN
The consumption of high fat-high energy diets (HF-HEDs) continues to rise worldwide and parallels the rise in maternal obesity (MO) that predisposes offspring to cardiometabolic disorders. Although the underlying mechanisms are unclear, thyroid hormones (TH) modulate cardiac maturation in utero. Therefore, we aimed to determine the impact of a high fat-high energy diet (HF-HED) on the hormonal, metabolic and contractility profile of the non-human primate (NHP) fetal heart. At â¼9 months preconception, female baboons (Papio hamadryas) were randomly assigned to either a control diet or HF-HED. At 165 days gestational age (term = 184 days), fetuses were delivered by Caesarean section under anaesthesia, humanely killed, and left ventricular cardiac tissue (Control (n = 6 female, 6 male); HF-HED (n = 6 F, 6 M)) was collected. Maternal HF-HED decreased the concentration of active cardiac TH (i.e. triiodothyronine (T3)), and type 1 iodothyronine deiodinase (DIO1) mRNA expression. Maternal HF-HED decreased the abundance of cardiac markers of insulin-mediated glucose uptake phosphorylated insulin receptor substrate 1 (Ser789) and glucose transporter 4, and increased protein abundance of key oxidative phosphorylation complexes (I, III, IV) and mitochondrial abundance in both sexes. Maternal HF-HED alters cardiac TH status, which may induce early signs of cardiac insulin resistance. This may increase the risk of cardiometabolic disorders in later life in offspring born to these pregnancies. KEY POINTS: Babies born to mothers who consume a high fat-high energy diet (HF-HED) prior to and during pregnancy are predisposed to an increased risk of cardiometabolic disorders across the life course. Maternal HF-HED prior to and during pregnancy decreased thyroid hormone triiodothyronine (T3) concentrations and type 1 iodothyronine deiodinase DIO1 mRNA expression in the non-human primate fetal heart. Maternal HF-HED decreased markers of insulin-dependent glucose uptake, phosphorylated insulin receptor substrate 1 and glucose transporter 4 in the fetal heart. Maternal HF-HED increased mitochondrial abundance and mitochondrial OXPHOS complex I, III and IV in the fetal heart. Fetuses from HF-HED pregnancies are predisposed to cardiometabolic disorders that may be mediated by changes in T3, placing them on a poor lifetime cardiovascular health trajectory.
RESUMEN
Accurately predicting the Modulus of Resilience (MR) of subgrade soils, which exhibit non-linear stress-strain behaviors, is crucial for effective soil assessment. Traditional laboratory techniques for determining MR are often costly and time-consuming. This study explores the efficacy of Genetic Programming (GEP), Multi-Expression Programming (MEP), and Artificial Neural Networks (ANN) in forecasting MR using 2813 data records while considering six key parameters. Several Statistical assessments were utilized to evaluate model accuracy. The results indicate that the GEP model consistently outperforms MEP and ANN models, demonstrating the lowest error metrics and highest correlation indices (R2). During training, the GEP model achieved an R2 value of 0.996, surpassing the MEP (R2 = 0.97) and ANN (R2 = 0.95) models. Sensitivity and SHAP (SHapley Additive exPlanations) analysis were also performed to gain insights into input parameter significance. Sensitivity analysis revealed that confining stress (21.6%) and dry density (26.89%) are the most influential parameters in predicting MR. SHAP analysis corroborated these findings, highlighting the critical impact of these parameters on model predictions. This study underscores the reliability of GEP as a robust tool for precise MR prediction in subgrade soil applications, providing valuable insights into model performance and parameter significance across various machine-learning (ML) approaches.
RESUMEN
Bentonite plastic concrete (BPC) is extensively used in the construction of water-tight structures like cut-off walls in dams, etc., because it offers high plasticity, improved workability, and homogeneity. Also, bentonite is added to concrete mixes for the adsorption of toxic metals. The modified design of BPC, as compared to normal concrete, requires a reliable tool to predict its strength. Thus, this study presents a novel attempt at the application of two innovative evolutionary techniques known as multi-expression programming (MEP) and gene expression programming (GEP) and a boosting-based algorithm known as AdaBoost to predict the 28-day compressive strength ( ) of BPC based on its mixture composition. The MEP and GEP algorithms expressed their outputs in the form of an empirical equation, while AdaBoost failed to do so. The algorithms were trained using a dataset of 246 points gathered from published literature having six important input factors for predicting. The developed models were subject to error evaluation, and the results revealed that all algorithms satisfied the suggested criteria and had a correlation coefficient (R) greater than 0.9 for both the training and testing phases. However, AdaBoost surpassed both MEP and GEP in terms of accuracy and demonstrated a lower testing RMSE of 1.66 compared to 2.02 for MEP and 2.38 for GEP. Similarly, the objective function value for AdaBoost was 0.10 compared to 0.176 for GEP and 0.16 for MEP, which indicated the overall good performance of AdaBoost compared to the two evolutionary techniques. Also, Shapley additive analysis was done on the AdaBoost model to gain further insights into the prediction process, which revealed that cement, coarse aggregate, and fine aggregate are the most important factors in predicting the strength of BPC. Moreover, an interactive graphical user interface (GUI) has been developed to be practically utilized in the civil engineering industry for prediction of BPC strength.
RESUMEN
Retention indices are values that characterize the retention of a compound in gas chromatography. In practice, retention indices are often assumed to depend only on the structure of the molecule and the type of the stationary phase, but this approximation is incorrect. This study is devoted to studying the dependence of retention indices on the column heating rate in the linear temperature programming mode, using a large and diverse data set. In the NIST 20 database, most data records are recorded in this mode. For stationary phases based on poly(5%-diphenyl-95%-dimethyl)siloxane (5%-phenyl-PDMS), there is a high proportion of records with heating rates of 10-15 K/min. In practice, such a high heating rate is rarely used and the use of such data may cause errors. A search was made for groups of records that were taken from the same primary source, recorded for the same compound and the same stationary phase, but differing in a heating rate. For each of these groups, the value D, the angular coefficient (slope) of the dependence of the retention index on the heating rate, was calculated. This value can take both positive and negative values. The highest values and the greatest variation of D values are observed for polar stationary phases, but further consideration was performed for 5%-phenyl-PDMS due to its greater practical significance. For these stationary phases, the highest D values are observed for aromatic and polyaromatic molecules; oxygen-containing compounds, on the contrary, exhibit lower D values. Negative D values are observed for many trimethylsilyl derivatives. A data set of D values for 756 molecules was selected and published online. There is almost no correlation between D and the retention index, lipophilicity factor logP, and molecular weight. Significant correlations with the number of cycles, the number of rotatable bonds, and the number of aromatic atoms were observed. Linear equations quantitatively relating the molecular descriptors to the D value were constructed. A number of cycles and halogen atoms were shown to contribute positively to the D value, while a number of oxygen atoms and bonds subject to internal rotation contributed negatively. The strong influence of the values related to the conformational rigidity of molecules and the weak influence of polarity allow us to suppose that the entropic factor has a key influence on the D value. A simple empirical linear equation for estimating the value of D is derived and presented in this study. Several machine learning methods for predicting D are compared. The best results are shown by gradient boosting and a random forest. However, the random forest does not achieve high accuracy in predicting the retention indices themselves.
RESUMEN
Given a family of linear constraints and a linear objective function one can consider whether to apply a Linear Programming (LP) algorithm or use a Linear Superiorization (LinSup) algorithm on this data. In the LP methodology one aims at finding a point that fulfills the constraints and has the minimal value of the objective function over these constraints. The Linear Superiorization approach considers the same data as linear programming problems but instead of attempting to solve those with linear optimization methods it employs perturbation resilient feasibility-seeking algorithms and steers them toward feasible points with reduced (not necessarily minimal) objective function values. Previous studies compared LP and LinSup in terms of their respective outputs and the resources they use. In this paper we investigate these two approaches in terms of their sensitivity to condition numbers of the system of linear constraints. Condition numbers are a measure for the impact of deviations in the input data on the output of a problem and, in particular, they describe the factor of error propagation when given wrong or erroneous data. Therefore, the ability of LP and LinSup to cope with increased condition numbers, thus with ill-posed problems, is an important matter to consider which was not studied until now. We investigate experimentally the advantages and disadvantages of both LP and LinSup on examplary problems of linear programming with multiple condition numbers and different problem dimensions.
RESUMEN
Modern project managers cope with significant challenges to schedule and control projects considering dynamic environments, frequent uncertainties, strict project deadlines, and stricter sustainable requirements above all. Sustainability taking into account resource utilization has been recently associated with project management. Hence, this paper presents a new mixed-integer linear programming (MILP) model with two objectives for a resource-constrained project scheduling problem (RCPSP) with multiple skills and multiple modes, assuming preemptive and non-preemptive activities in an uncertain environment. Given the importance of sustainable developments in projects, the considered objectives are to maximize job opportunities and minimize project duration, resource costs, and total energy consumption. To deal with the model, an AUGNMECON2VIKOR algorithm is utilized to create Pareto solutions. In this model, project activities can be crashed by allocating extra resources. Furthermore, multi-skill resources are used to perform project activities. This study also investigates the impact of these resources on project scheduling. To deal with uncertain circumstances, a fuzzy chance-constrained programming method is employed to develop a robust possibilistic programming model. With respect to the increasing significance of sustainability in project management, this study pioneers the examination of the impact of sustainable factors on project scheduling. Finally, the proposed formulation is validated using instances from the well-known PSPLIB and MMLIB test sets. Finally, a comparison is drawn between the presented solution method considering AUGMECON2VIKOR and AUGMECON2.
Asunto(s)
Algoritmos , Modelos Teóricos , Conservación de los Recursos Naturales/métodos , Desarrollo SostenibleRESUMEN
This study identifies the optimal combination of active and passive thermoplastic materials for producing multi-material programmable 3D structures. These structures can undergo shape changes with varying radii of curvature over time when exposed to hot water. The research focuses on examining the thermal, thermomechanical, and mechanical properties of active (PLA) and passive (PRO-PLA, ABS, and TPU) materials. It also includes the experimental determination of the radius of curvature of the programmed 3D structures. The pairing of active PLA with passive PRO-PLA was found to be the most effective for creating complex programmable 3D structures capable of two-sided transformation. This efficacy is attributed to the adequate apparent shear strength, significant differences in thermomechanical shrinkage between the two materials, identical printing parameters for both materials, and the lowest bending storage modulus of PRO-PLA among the passive materials within the activation temperature range. Multi-material 3D printing has also proven to be a suitable method for producing programmable 3D structures for practical applications such as phone stands, phone cases, door hangers, etc. It facilitates the programming of the active material and ensures the dimensional stability of the passive components of programmable 3D structures during thermal activation.
RESUMEN
The genetic blueprint for the essential functions of life is encoded in DNA, which is translated into proteins-the engines driving most of our metabolic processes. Recent advancements in genome sequencing have unveiled a vast diversity of protein families, but compared with the massive search space of all possible amino acid sequences, the set of known functional families is minimal. One could say nature has a limited protein "vocabulary." A major question for computational biologists, therefore, is whether this vocabulary can be expanded to include useful proteins that went extinct long ago or have never evolved (yet). By merging evolutionary algorithms, machine learning, and bioinformatics, we can develop highly customized "designer proteins." We dub the new subfield of computational evolution, which employs evolutionary algorithms with DNA string representations, biologically accurate molecular evolution, and bioinformatics-informed fitness functions, Evolutionary Algorithms Simulating Molecular Evolution.
Asunto(s)
Algoritmos , Biología Computacional , Evolución Molecular , Biología Computacional/métodos , Proteínas/genética , Proteínas/química , Proteínas/metabolismo , Simulación por ComputadorRESUMEN
A neural network model is constructed to solve convex quadratic multi-objective programming problem (CQMPP). The CQMPP is first converted into an equivalent single-objective convex quadratic programming problem by the mean of the weighted sum method, where the Pareto optimal solution (POS) are given by diversifying values of weights. Then, for given various values weights, multiple projection neural networks are employded to search for Pareto optimal solutions. Based on employing Lyapunov theory, the proposed neural network approach is established to be stable in the sense of Lyapunov and it is globally convergent to an exact optimal solution of the single-objective problem. The simulation results also show that the presented model is feasible and efficient.
RESUMEN
BACKGROUND: To decide what programming parameters to use for cochlear implants (CIs) in partial deaf patients can be challenging. OBJECTIVE: The processor programming form, categorised as electrical complement (EC), electro-acoustic-stimulation (EAS) or electric stimulation (ES), and difficulties switching programming form were investigated. METHODS: A retrospective investigation of medical records and audiograms was conducted in adult patients intended for EC and EAS. RESULTS: Eighty-four ears (80 patients) were included. Twenty ears were initially fitted with EC, 32 with EAS, 30 with ES and 2 with both EC and EAS. Sixty-four ears met the criteria to use EC or EAS at initial fitting, however only 54 ears were fitted with EC or EAS initially. Twenty-eight patients altered between at least two programming forms and six of those experienced difficulties to adapt to a new form when their low-frequency hearing deteriorated. Twenty-five percent of patients initially fitted with EC or EAS switched programming form within two years. DISCUSSION: Further studies on how to choose the most beneficial sound processor programming parameters for EC and EAS, and when to change between programming forms, are warranted as well as clear guidance on choosing the right candidates for EC and EAS.
RESUMEN
Nicotine is developmentally toxic. Prenatal nicotine exposure (PNE) affects the development of multiple fetal organs and causes susceptibility to a variety of diseases in offspring. In this study, we aimed to investigate the effect of PNE on cartilage development and osteoarthritis susceptibility in female offspring rats. Wistar rats were orally gavaged with nicotine on days 9-20 of pregnancy. The articular cartilage was obtained at gestational day (GD) 20 and postnatal week (PW) 24, respectively. Further, the effect of nicotine on chondrogenic differentiation was explored by the chondrogenic differentiation model in human Wharton's jelly-derived mesenchymal stem cells (WJ-MSCs). The PNE group showed significantly shallower Safranin O staining and lower Collagen 2a1 content of articular cartilage in female offspring rats. Further, we found that PNE activated pyroptosis in the articular cartilage at GD20 and PW24. In vitro experiments revealed that nicotine inhibited chondrogenic differentiation and activated pyroptosis. After interfering with nod-like receptors3 (NLRP3) expression by SiRNA, it was found that pyroptosis mediated the chondrogenic differentiation inhibition of WJ-MSCs induced by nicotine. In addition, we found that α7-nAChR antagonist α-BTX reversed nicotine-induced NLRP3 and P300 high expression. And, P300 SiRNA reversed the increase of NLRP3 mRNA expression and histone acetylation level in its promoter region induced by nicotine. In conclusion, PNE caused chondrodysplasia and poor articular cartilage quality in female offspring rats. PNE increased the histone acetylation level of NLRP3 promoter region by α7-nAChR/P300, which resulting in the high expression of NLRP3. Further, NLRP3 mediated the inhibition of chondrogenic differentiation by activating pyroptosis.
RESUMEN
Background: In large supplementary feeding programs for children, it is challenging to create and sustain contextual, acceptable, nutritionally complete, and diverse supplemental foods. For example, the Indian Supplementary Nutrition Program (SNP) supplements the dietary intake of children, pregnant and lactating women, and severely acutely malnourished (SAM) children by offering dry take home rations (THRs) or hot cooked meals (HCMs) across India, but an optimization tool is necessary to create local contextual recipes for acceptable and nutritionally adequate products. Objectives: This study aimed to create a linear programming (LP) model to optimize diverse food provisions for a SNP to meet its program guidelines, using locally available foods, within budgetary allocations. Methods: A LP algorithm with appropriate constraints was used to generate an optimal THR based on raw foods, or an optimal weekly HCM menu comprised of a lunch meal with mid-morning snacks, based on user choices of foods and recipes. The database of foods used was created by a prospective survey conducted across all states of India for this purpose, such that the recipe and food optimization was diverse and specific to the guidelines for each beneficiary group. Results: An interactive web-based app, which can optimize feeding programs at any population level, was developed for use by program implementers and is hosted at https://www.datatools.sjri.res.in/SNP/. In the Indian example analyzed here, the recommended optimized diets met the guidelines for diversified and nutritionally complete SNP provision but at a cost that was almost 25% higher than the present Indian budget allocation. Conclusions: The optimization model developed demonstrates that contextual SNP diets can be created to meet macronutrient and most essential micronutrient needs of large-scale feeding programs, but appropriate diversification entails additional costs.
RESUMEN
OBJECTIVE: In order to facilitate the tracing of infectious diseases in a small area and to effectively carry out disease control and epidemiological investigations, this research proposes a novel spatiotemporal model to estimate effective reproduction number(Re)for infectious diseases, based on the fundamental concept of contact tracing. METHODS: This study utilizes the incidence of hand, foot, and mouth disease (HFMD) among children in Bishan District, Chongqing, China from 2015 to 2019. The study incorporates the epidemiological characteristics of HFMD and aims to construct a Spatiotemporal Correlation Discrimination of HFMD. Utilizing ARC ENGINE and C# programming for the creation of a spatio-temporal database dedicated to HFMD to facilitate data collection and analysis. The scientific validity of the proposed method was verified by comparing the effective reproduction number obtained by the traditional SEIR model. RESULTS: We have ascertained the optimal search radius for the spatiotemporal search model to be 1.5 km. Upon analyzing the resulting Re values, which range from 1.14 to 4.75, we observe a skewed distribution pattern from 2015 to 2019. The median and quartile Re value recorded is 2.42 (1.98, 2.72). Except for 2018, the similarity coefficient r of the years 2015, 2016, 2017, and 2019 were all close to 1, and p <0.05 in the comparison of the two models, indicating that the Re values obtained by using the search model and the traditional SEIR model are correlated and closely related. The results exhibited similarity between the Re curves of both models and the epidemiological characteristics of HFMD. Finally, we illustrated the regional distribution of Re values obtained by the search model at various time intervals on Geographic Information System (GIS) maps which highlighted variations in the incidence of diseases across different communities, neighborhoods, and even smaller areas. CONCLUSION: The model comprehensively considers both temporal variation and spatial heterogeneity in disease transmission and accounts for each individual's distinct time of onset and spatial location. This proposed method differs significantly from existing mathematical models used for estimating Re in that it is founded on reasonable scientific assumptions and computer algorithms programming that take into account real-world spatiotemporal factors. It is particularly well-suited for estimating the Re of infectious diseases in relatively stable mobile populations within small geographical areas.
Asunto(s)
Enfermedad de Boca, Mano y Pie , Análisis Espacio-Temporal , Enfermedad de Boca, Mano y Pie/epidemiología , Humanos , China/epidemiología , Número Básico de Reproducción/estadística & datos numéricos , Incidencia , Niño , Enfermedades Transmisibles/epidemiología , Preescolar , Femenino , Masculino , Modelos EpidemiológicosRESUMEN
Background: Currently, intensity-modulated radiation therapy (IMRT) is commonly used in radiotherapy clinics. However, designing a treatment plan with multiple beam angles depends on the experience of human planners, and is mostly achieved using a trial-and-error approach. It is preferrable but challenging to solve this issue automatically and mathematically using an optimization approach. The goal of this study is to develop a mixed-integer linear programming (MILP) approach for the beam angle optimization (BAO) of non-coplanar IMRT for liver cancer. Methods: MILP models for the BAO of both coplanar and non-coplanar IMRT treatment plans were developed. The beam angles of the IMRT plans were first selected by the MILP model built using mathematical optimization software. Next, the IMRT plans with the selected beam angles was created in a commercial treatment planning system. Finally, the fluence map and dose distribution of the IMRT plans were generated under pre-defined dose-volume constraints. The IMRT plans of 10 liver cancer patients previously treated at our institute were used to assessed the proposed MILP models. For each patient, both coplanar and non-coplanar IMRT plans with beam angles optimized by the MILP models were compared with the IMRT plan clinically approved by physicians. Results: The MILP model-guided IMRT plans showed reduced doses for most of the organs at risk (OARs). Compared with the IMRT plans clinically approved by physicians, the doses for the spinal cord (28.5 vs. 36.1, P=0.001<0.05) and liver (27.6 vs. 29.1, P=0.005<0.05) decreased significantly in the IMRT plans with non-coplanar beams selected by the MILP models. Conclusions: The MILP model is an effective tool for the BAO in coplanar and non-coplanar IMRT treatment planning. It facilitates the automation of IMRT treatment planning for current high-precision radiotherapy.
RESUMEN
Introduction: Thyroid ultrasound provides valuable insights for thyroid disorders but is hampered by subjectivity. Automated analysis utilizing large datasets holds immense promise for objective and standardized assessment in screening, thyroid nodule classification, and treatment monitoring. However, there remains a significant gap in the development of applications for the automated analysis of Hashimoto's thyroiditis (HT) using ultrasound. Objective: To develop an automated thyroid ultrasound analysis (ATUS) algorithm using the C# programming language to detect and quantify ultrasonographic characteristics associated with HT. Materials and Methods: This study describes the development and evaluation of an ATUS algorithm using C#. The algorithm extracted relevant features (texture, vascularization, echogenicity) from preprocessed ultrasound images and utilizes machine learning techniques to classify them as "normal" or indicative of HT. The model is trained and validated on a comprehensive dataset, with performance assessed through metrics like accuracy, sensitivity, and specificity. The findings highlight the potential for this C#-based ATUS algorithm to offer objective and standardized assessment for HT diagnosis. Results: The program preprocesses images (grayscale conversion, normalization, etc.), segments the thyroid region, extracts features (texture, echogenicity), and utilizes a pre-trained model for classification ("normal" or "suspected Hashimoto's thyroiditis"). Using a sample image, the program successfully preprocessed, segmented, and extracted features. The predicted classification ("suspected HT") with high probability (0.92) aligns with the pre-established diagnosis, suggesting potential for objective HT assessment. Conclusion: C#-based ATUS algorithm successfully detects and quantifies HT features, showcasing the potential of advanced programming in medical image analysis.
Introdução: A ultrassonografia da tireoide fornece informações valiosas para distúrbios da tireoide, mas é dificultada pela sua subjetividade. A análise automatizada utilizando grandes conjuntos de dados é uma grande promessa para avaliação objetiva e triagem padronizada, classificação de nódulos tireoidianos e monitoramento de tratamento. No entanto, permanece uma lacuna significativa no desenvolvimento de aplicações para a análise automatizada da tireoidite de Hashimoto (TH) por meio de ultrassonografia. Objetivo: Desenvolver um algoritmo automatizado da análise ultrassonográfica da tireoide (AUST) utilizando a linguagem de programação C# para detectar e quantificar características ultrassonográficas associadas à TH. Materiais e Métodos: Este estudo descreve o desenvolvimento e avaliação de um algoritmo AUST utilizando programação C#. O algoritmo extrai características relevantes (textura, vascularização, ecogenicidade) de imagens de ultrassonografia pré-processadas e utiliza técnicas de aprendizado de máquina para classificá-las como "normais" ou indicativas de TH. O modelo é treinado e validado em um conjunto de dados abrangente, com desempenho avaliado por meio de métricas como precisão, sensibilidade e especificidade. As descobertas destacam o potencial deste algoritmo AUST baseado em programação C# para oferecer avaliação objetiva e padronizada para o diagnóstico de TH. Resultados: O programa pré-processa imagens (conversão em escala de cinza, normalização, etc.), segmentos da tireoide, extrai características (textura, ecogenicidade) e utiliza um modelo pré-treinado para classificação ("normal" ou "suspeita de tireoidite de Hashimoto"). Usando uma imagem de amostra, o programa pré-processou, segmentou e extraiu recursos com sucesso. A classificação prevista ("suspeita de TH") com alta probabilidade (0,92) alinha-se ao diagnóstico pré-estabelecido, sugerindo potencial para avaliação objetiva da TH. Conclusão: O algoritmo AUST baseado em programação C# detectou e quantificou com sucesso as características da TH, mostrando o potencial da programação avançada na análise de imagens médicas.