RESUMEN
Adenomyosis and leiomyomas are common benign uterine disorders characterized by abnormal cellular proliferation. The BCL6 protein, a transcriptional repressor implicated in cell proliferation and oncogenesis, has been linked to the pathogenesis of endometriosis. This study investigates BCL6 expression in adenomyosis, leiomyomas, and normal myometrium using immunohistochemistry and deep learning neural networks. We analyzed paraffin blocks from total hysterectomies performed between 2009 and 2017, confirming diagnoses through pathological review. Immunohistochemistry was conducted using an automated system, and BCL6 expression was quantified using Fiji-ImageJ software. A supervised deep learning neural network was employed to classify samples based on DAB staining. Our results show that BCL6 expression is significantly higher in leiomyomas compared to adenomyosis and normal myometrium. No significant difference in BCL6 expression was observed between adenomyosis and controls. The deep learning neural network accurately classified samples with a high degree of precision, supporting the immunohistochemical findings. These findings suggest that BCL6 plays a role in the pathogenesis of leiomyomas, potentially contributing to abnormal smooth muscle cell proliferation. The study highlights the utility of automated immunohistochemistry and deep learning techniques in quantifying protein expression and classifying uterine pathologies. Future studies should investigate the expression of BCL6 in adenomyosis and endometriosis to further elucidate its role in uterine disorders.
Asunto(s)
Adenomiosis , Aprendizaje Profundo , Leiomioma , Miometrio , Proteínas Proto-Oncogénicas c-bcl-6 , Neoplasias Uterinas , Humanos , Femenino , Adenomiosis/metabolismo , Adenomiosis/patología , Proteínas Proto-Oncogénicas c-bcl-6/metabolismo , Proteínas Proto-Oncogénicas c-bcl-6/genética , Miometrio/metabolismo , Miometrio/patología , Leiomioma/metabolismo , Leiomioma/patología , Neoplasias Uterinas/metabolismo , Neoplasias Uterinas/patología , Inmunohistoquímica , Adulto , Persona de Mediana Edad , Redes Neurales de la ComputaciónRESUMEN
Accurate malaria diagnosis with precise identification of Plasmodium species is crucial for an effective treatment. While microscopy is still the gold standard in malaria diagnosis, it relies heavily on trained personnel. Artificial intelligence (AI) advances, particularly convolutional neural networks (CNNs), have significantly improved diagnostic capabilities and accuracy by enabling the automated analysis of medical images. Previous models efficiently detected malaria parasites in red blood cells but had difficulty differentiating between species. We propose a CNN-based model for classifying cells infected by P. falciparum, P. vivax, and uninfected white blood cells from thick blood smears. Our best-performing model utilizes a seven-channel input and correctly predicted 12,876 out of 12,954 cases. We also generated a cross-validation confusion matrix that showed the results of five iterations, achieving 63,654 out of 64,126 true predictions. The model's accuracy reached 99.51%, a precision of 99.26%, a recall of 99.26%, a specificity of 99.63%, an F1 score of 99.26%, and a loss of 2.3%. We are now developing a system based on real-world quality images to create a comprehensive detection tool for remote regions where trained microscopists are unavailable.
Asunto(s)
Aprendizaje Profundo , Malaria Falciparum , Malaria Vivax , Redes Neurales de la Computación , Plasmodium falciparum , Plasmodium vivax , Plasmodium vivax/aislamiento & purificación , Plasmodium falciparum/aislamiento & purificación , Humanos , Malaria Vivax/diagnóstico , Malaria Vivax/parasitología , Malaria Falciparum/parasitología , Malaria Falciparum/diagnóstico , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
Bananas (Musa spp.) are a critical global food crop, providing a primary source of nutrition for millions of people. Traditional methods for disease monitoring and detection are often time-consuming, labor-intensive, and prone to inaccuracies. This study introduces an AI-powered multiplatform georeferenced surveillance system designed to enhance the detection and management of banana wilt diseases. We developed and evaluated several deep learning foundation models, including YOLO-NAS, YOLOv8, YOLOv9, and Faster-RCNN to perform accurate disease detection on both platforms. Our results demonstrate the superior performance of YOLOv9 in detecting healthy, Fusarium Wilt and Xanthomonas Wilt diseased plants in aerial images, achieving high mAP@50, precision and recall metrics ranging from 55 to 86%. In terms of ground level images, we organized the dataset based on disease occurrence in Africa, Latin America, India, Asia and Australia. For this platform, YOLOv8 outperforms the rest and achieves mAP@50, precision and recall between 65 and 99% depending on the plant part and region. Additionally, we incorporated Explainable AI techniques, such as Gradient-weighted Class Activation Mapping, to enhance model transparency and trustworthiness. Human in the Loop Artificial Intelligence was also utilized to enhance the ground level model's predictions.
Asunto(s)
Musa , Enfermedades de las Plantas , Musa/microbiología , Enfermedades de las Plantas/microbiología , Humanos , Fusarium/aislamiento & purificación , Aprendizaje Profundo , Xanthomonas/aislamiento & purificación , Inteligencia ArtificialRESUMEN
Endoscopy is vital for detecting and diagnosing gastrointestinal diseases. Systematic examination protocols are key to enhancing detection, particularly for the early identification of premalignant conditions. Publicly available endoscopy image databases are crucial for machine learning research, yet challenges persist, particularly in identifying upper gastrointestinal anatomical landmarks to ensure effective and precise endoscopic procedures. However, many existing datasets have inconsistent labeling and limited accessibility, leading to biased models and reduced generalizability. This paper introduces GastroHUN, an open dataset documenting stomach screening procedures based on a systematic protocol. GastroHUN includes 8,834 images from 387 patients and 4,729 labeled video sequences, all annotated by four experts. The dataset covers 22 anatomical landmarks in the stomach and includes an additional category for unqualified images, making it a valuable resource for AI model development. By providing a robust public dataset and baseline deep learning models for image and sequence classification, GastroHUN serves as a benchmark for future research and aids in the development of more effective algorithms.
Asunto(s)
Estómago , Humanos , Estómago/diagnóstico por imagen , Aprendizaje Profundo , Aprendizaje AutomáticoRESUMEN
Sulci are a fundamental part of brain morphology, closely linked to brain function, cognition, and behavior. Tertiary sulci, characterized as the shallowest and smallest subtype, pose a challenging task for detection. The diagonal sulcus (ds), located in a crucial area in language processing, has a prevalence between 50% and 60%. Automatic detection of the ds is an unexplored field: while some sulci segmenters include the ds, their accuracy is usually low. In this work, we present a deep learning based model for ds detection using a fine-tuning approach with limited training labeled data. A convolutional autoencoder was employed to learn specific features related to brain morphology with unlabeled data through self-supervised learning. Subsequently, the pre-trained network was fine-tuned to detect the ds using a less extensive labeled dataset. We achieved a mean F1-score of 0.7176 (SD=0.0736) for the test set and a F1-score of 0.72 for a second held-out set, surpassing the results of a standard software and other alternative deep learning models. We conducted an interpretability analysis of the results using occlusion maps and observed that the models focused on adjacent sulci to the ds for prediction, consistent with the approach taken by experts in manual annotation. We also analyzed the challenges of manual labeling by conducting a thorough examination of interrater agreement on a small dataset and its relationship with our model's performance. Finally, we applied our method on a population analysis and reported the prevalence of ds in a case study.
Asunto(s)
Aprendizaje Profundo , Humanos , Aprendizaje Automático Supervisado , Imagen por Resonancia Magnética/métodos , Masculino , Femenino , Adulto , Procesamiento de Imagen Asistido por Computador/métodos , Redes Neurales de la Computación , Corteza Cerebral/diagnóstico por imagenRESUMEN
Antimicrobial peptides (AMPs) are promising candidates to combat multidrug-resistant pathogens. However, the high cost of extensive wet-lab screening has made AI methods for identifying and designing AMPs increasingly important, with machine learning (ML) techniques playing a crucial role. AI approaches have recently revolutionised this field by accelerating the discovery of new peptides with anti-infective activity, particularly in preclinical mouse models. Initially, classical ML approaches dominated the field, but recently there has been a shift towards deep learning (DL) models. Despite significant contributions, existing reviews have not thoroughly explored the potential of large language models (LLMs), graph neural networks (GNNs) and structure-guided AMP discovery and design. This review aims to fill that gap by providing a comprehensive overview of the latest advancements, challenges and opportunities in using AI methods, with a particular emphasis on LLMs, GNNs and structure-guided design. We discuss the limitations of current approaches and highlight the most relevant topics to address in the coming years for AMP discovery and design.
Asunto(s)
Péptidos Antimicrobianos , Aprendizaje Automático , Péptidos Antimicrobianos/química , Péptidos Antimicrobianos/farmacología , Animales , Inteligencia Artificial , Descubrimiento de Drogas/métodos , Antiinfecciosos/farmacología , Antiinfecciosos/química , Humanos , Redes Neurales de la Computación , Ratones , Aprendizaje ProfundoRESUMEN
The work aims to leverage computer vision and artificial intelligence technologies to quantify key components in food distribution services. Specifically, it focuses on dish counting, content identification, and portion size estimation in a dining hall setting. An RGB camera is employed to capture the tray delivery process in a self-service restaurant, providing test images for plate counting and content identification algorithm comparison, using standard evaluation metrics. The approach utilized the YOLO architecture, a widely recognized deep learning model for object detection and computer vision. The model is trained on labeled image data, and its performance is assessed using a precision-recall curve at a confidence threshold of 0.5, achieving a mean average precision (mAP) of 0.873, indicating robust overall performance. The weight estimation procedure combines computer vision techniques to measure food volume using both RGB and depth cameras. Subsequently, density models specific to each food type are applied to estimate the detected food weight. The estimation model's parameters are calibrated through experiments that generate volume-to-weight conversion tables for different food items. Validation of the system was conducted using rice and chicken, yielding error margins of 5.07% and 3.75%, respectively, demonstrating the feasibility and accuracy of the proposed method.
Asunto(s)
Algoritmos , Inteligencia Artificial , Alimentos , Procesamiento de Imagen Asistido por Computador/métodos , Aprendizaje Profundo , HumanosRESUMEN
Plant stress detection involves the process of Identification, Classification, Quantification, and Prediction (ICQP) in crop stress. Numerous approaches exist for plant stress identification; however, a majority rely on expert personnel or invasive techniques. While expert employees demonstrate proficiency across various plants, this approach demands a substantial workforce to ensure the quality of crops. Conversely, invasive techniques entail leaf dismemberment. To overcome these challenges, an alternative is to employ image processing to interpret areas where plant geometry is observable, eliminating the dependency on skilled labor or the need for crop dismemberment. However, this alternative introduces the challenge of accurately interpreting ambiguous image features. Motivated by the latter, we propose a methodology for plant stress detection using 3D reconstruction and deep learning from a single RGB image. For that, our methodology has three steps. First, the plant recognition step provides the segmentation, location, and delimitation of the crop. Second, we propose a leaf detection analysis to classify and locate the boundaries between the different leaves. Finally, we use a Deep Neural Network (DNN) and the 3D reconstruction for plant stress detection. Experimental results are encouraging, showing that our approach has high performance under real-world scenarios. Also, the proposed methodology has 22.86% higher precision, 24.05% higher recall, and 23.45% higher F1-score than the 2D classification method.
Asunto(s)
Productos Agrícolas , Imagenología Tridimensional , Hojas de la Planta , Estrés Fisiológico , Imagenología Tridimensional/métodos , Estrés Fisiológico/fisiología , Redes Neurales de la Computación , Aprendizaje Profundo , Procesamiento de Imagen Asistido por Computador/métodos , AlgoritmosRESUMEN
Explainable Artificial Intelligence (XAI) is an emerging machine learning field that has been successful in medical image analysis. Interpretable approaches are able to "unbox" the black-box decisions made by AI systems, aiding medical doctors to justify their diagnostics better. In this paper, we analyze the performance of three different XAI strategies for medical image analysis in ophthalmology. We consider a multimodal deep learning model that combines optical coherence tomography (OCT) and infrared reflectance (IR) imaging for the diagnosis of age-related macular degeneration (AMD). The classification model is able to achieve an accuracy of 0.94, performing better than other unimodal alternatives. We analyze the XAI methods in terms of their ability to identify retinal damage and ease of interpretation, concluding that grad-CAM and guided grad-CAM can be combined to have both a coarse visual justification and a fine-grained analysis of the retinal layers. We provide important insights and recommendations for practitioners on how to design automated and explainable screening tests based on the combination of two image sources.
Asunto(s)
Degeneración Macular , Tomografía de Coherencia Óptica , Humanos , Degeneración Macular/diagnóstico por imagen , Degeneración Macular/diagnóstico , Degeneración Macular/clasificación , Tomografía de Coherencia Óptica/métodos , Inteligencia Artificial , Aprendizaje Profundo , Retina/diagnóstico por imagen , Retina/patología , Imagen Multimodal/métodos , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
Blood pressure (BP) is one of the most prominent indicators of potential cardiovascular disorders. Traditionally, BP measurement relies on inflatable cuffs, which is inconvenient and limit the acquisition of such important health-related information in general population. Based on large amounts of well-collected and annotated data, deep-learning approaches present a generalization potential that arose as an alternative to enable more pervasive approaches. However, most existing work in this area currently uses datasets with limitations, such as lack of subject identification and severe data imbalance that can result in data leakage and algorithm bias. Thus, to offer a more properly curated source of information, we propose a derivative dataset composed of 380 hours of the most common biomedical signals, including arterial blood pressure, photoplethysmography, and electrocardiogram for 1,524 anonymized subjects, each having 30 segments of 30 seconds of those signals. We also validated the proposed dataset through experiments using state-of-the-art deep-learning methods, as we highlight the importance of standardized benchmarks for calibration-free blood pressure estimation scenarios.
Asunto(s)
Determinación de la Presión Sanguínea , Presión Sanguínea , Aprendizaje Profundo , Fotopletismografía , Humanos , Determinación de la Presión Sanguínea/métodos , Electrocardiografía , MasculinoRESUMEN
Purpose.This paper introduces a deep learning method for myocardial strain analysis while also evaluating the efficacy of the method across a public and a private dataset for cardiac pathology discrimination.Methods.We measure the global and regional myocardial strain in cSAX CMR images by first identifying a ROI centered in the LV, obtaining the cardiac structures (LV, RV and Myo) and estimating the motion of the myocardium. Finally, we compute the strain for the heart coordinate system and report the global and regional strain.Results.We validated our method in two public datasets (ACDC, 80 subjects, and CMAC, 16 subjects) and a private dataset (SSC, 75 subjects), containing healthy and pathological cases (acute myocardial infarction, DCM and HCM). We measured the mean Dice coefficient and Hausdorff distance for segmentation accuracy, and the absolute end point error for motion accuracy, and we conducted a study of the discrimination power of the strain and strain rate between populations of healthy and pathological subjects. The results demonstrated that our method effectively quantifies myocardial strain and strain rate, showing distinct patterns across different cardiac conditions achieving notable statistical significance. Results also show that the method's accuracy is on par with iterative non-parametric registration methods and is also capable of estimating regional strain values.Conclusion.Our method proves to be a powerful tool for cardiac strain analysis, achieving results comparable to other state-of-the-art methods, and computational efficiency over traditional methods.
Asunto(s)
Aprendizaje Profundo , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Corazón/diagnóstico por imagen , Miocardio/patología , Imagen por Resonancia Magnética/métodos , Masculino , Infarto del Miocardio/diagnóstico por imagen , Femenino , Algoritmos , Persona de Mediana Edad , Bases de Datos Factuales , AdultoRESUMEN
Mass spectrometry (MS)-based metabolomics analysis is a powerful tool, but it comes with its own set of challenges. The MS workflow involves multiple steps before its interpretation in what is denominate data mining. Data mining consists of a two-step process. First, the MS data is ordered, arranged, and presented for filtering before being analyzed. Second, the filtered and reduced data are analyzed using statistics to remove further variability. This holds true particularly for MS-based untargeted metabolomics studies, which focused on understanding fold changes in metabolic networks. Since the task of filtering and identifying changes from a large dataset is challenging, automated techniques for mining untargeted MS-based metabolomic data are needed. The traditional statistics-based approach tends to overfilter raw data, which may result in the removal of relevant data and lead to the identification of fewer metabolomic changes. This limitation of the traditional approach underscores the need for a new method. In this work, we present a novel deep learning approach using node embeddings (powered by GNNs), edge embeddings, and anomaly detection algorithm to analyze the data generated by mass spectrometry (MS)-based metabolomics called GEMNA (Graph Embedding-based Metabolomics Network Analysis), for example for an untargeted volatile study on Mentos candy, the data clusters produced by GEMNA were better than the ones used traditional tools, i.e., GEMNA has [Formula: see text], vs. the traditional approach has [Formula: see text].
Asunto(s)
Algoritmos , Minería de Datos , Espectrometría de Masas , Metabolómica , Metabolómica/métodos , Espectrometría de Masas/métodos , Minería de Datos/métodos , Humanos , Aprendizaje Profundo , Redes y Vías Metabólicas , MetabolomaRESUMEN
INTRODUCTION: Interictal epileptiform discharges (IEDs) in electroencephalograms (EEGs) are an important biomarker for epilepsy. Currently, the gold standard for IED detection is the visual analysis performed by experts. However, this process is expert-biased, and time-consuming. Developing fast, accurate, and robust detection methods for IEDs based on EEG may facilitate epilepsy diagnosis. We aim to assess the performance of deep learning (DL) and classic machine learning (ML) algorithms in classifying EEG segments into IED and non-IED categories, as well as distinguishing whether the entire EEG contains IED or not. METHODS: We systematically searched PubMed, Embase, and Web of Science following PRISMA guidelines. We excluded studies that only performed the detection of IEDs instead of binary segment classification. Risk of Bias was evaluated with Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Meta-analysis with the overall area under the Summary Receiver Operating Characteristic (SROC), sensitivity, and specificity as effect measures, was performed with R software. RESULTS: A total of 23 studies, comprising 3,629 patients, were eligible for synthesis. Eighteen models performed discharge-level classification, and 6 whole-EEG classification. For the IED-level classification, 3 models were validated in an external dataset with more than 50 patients and achieved a sensitivity of 84.9 % (95 % CI: 82.3-87.2) and a specificity of 68.7 % (95 % CI: 7.9-98.2). Five studies reported model performance using both internal validation (cross-validation) and external datasets. The meta-analysis revealed higher performance for internal validation, with 90.4 % sensitivity and 99.6 % specificity, compared to external validation, which showed 78.1 % sensitivity and 80.1 % specificity. CONCLUSION: Meta-analysis showed higher performance for models validated with resampling methods compared to those using external datasets. Only a minority of models use more robust validation techniques, which often leads to overfitting.
Asunto(s)
Electroencefalografía , Epilepsia , Humanos , Inteligencia Artificial , Aprendizaje Profundo , Electroencefalografía/métodos , Electroencefalografía/normas , Epilepsia/diagnóstico , Epilepsia/fisiopatología , Aprendizaje AutomáticoRESUMEN
Human-robot collaboration will play an important role in the fourth industrial revolution in applications related to hostile environments, mining, industry, forestry, education, natural disaster and defense. Effective collaboration requires robots to understand human intentions and tasks, which involves advanced user profiling. Voice-based communication, rich in complex information, is key to this. Beamforming, a technology that enhances speech signals, can help robots extract semantic, emotional, or health-related information from speech. This paper describes the implementation of a system that provides substantially improved signal-to-noise ratio (SNR) and speech recognition accuracy to a moving robotic platform for use in human-robot interaction (HRI) applications in static and dynamic contexts. This study focuses on training deep learning-based beamformers using acoustic model-based multi-style training with measured room impulse responses (RIRs). The results show that this approach outperforms training with simulated RIRs or matched measured RIRs, especially in dynamic conditions involving robot motion. The findings suggest that training with a broad range of measured RIRs is sufficient for effective HRI in various environments, making additional data recording or augmentation unnecessary. This research demonstrates that deep learning-based beamforming can significantly improve HRI performance, particularly in challenging acoustic environments, surpassing traditional beamforming methods.
Asunto(s)
Acústica , Robótica , Humanos , Robótica/métodos , Aprendizaje Profundo , Relación Señal-Ruido , Procesamiento de Señales Asistido por ComputadorRESUMEN
BACKGROUND: Recently, machine learning (ML), deep learning (DL), and natural language processing (NLP) have provided promising results in the free-form radiological reports' classification in the respective medical domain. In order to classify radiological reports properly, a high-quality annotated and curated dataset is required. Currently, no publicly available breast imaging-based radiological dataset exists for the classification of Breast Imaging Reporting and Data System (BI-RADS) categories and breast density scores, as characterized by the American College of Radiology (ACR). To tackle this problem, we construct and annotate a breast imaging-based radiological reports dataset and its benchmark results. The dataset was originally in Spanish. Board-certified radiologists collected and annotated it according to the BI-RADS lexicon and categories at the Breast Radiology department, TecSalud Hospitals Monterrey, Mexico. Initially, it was translated into English language using Google Translate. Afterwards, it was preprocessed by removing duplicates and missing values. After preprocessing, the final dataset consists of 5046 unique reports from 5046 patients with an average age of 53 years and 100% women. Furthermore, we used word-level NLP-based embedding techniques, term frequency-inverse document frequency (TF-IDF) and word2vec to extract semantic and syntactic information. We also compared the performance of ML, DL and large language models (LLMs) classifiers for BI-RADS category classification. RESULTS: The final breast imaging-based radiological reports dataset contains 5046 unique reports. We compared K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient-Boosting (GB), Extreme Gradient Boosting (XGB), Long Short-Term Memory (LSTM), Bidirectional Encoder Representations from Transformers (BERT) and Biomedical Generative Pre-trained Transformer (BioGPT) classifiers. It is observed that the BioGPT classifier with preprocessed data performed 6% better with a mean sensitivity of 0.60 (95% confidence interval (CI), 0.391-0.812) compared to the second best performing classifier BERT, which achieved mean sensitivity of 0.54 (95% CI, 0.477-0.607). CONCLUSION: In this work, we propose a curated and annotated benchmark dataset that can be used for BI-RADS and breast density category classification. We also provide baseline results of most ML, DL and LLMs models for BI-RADS classification that can be used as a starting point for future investigation. The main objective of this investigation is to provide a repository for the investigators who wish to enter the field to push the boundaries further.
Asunto(s)
Benchmarking , Aprendizaje Profundo , Aprendizaje Automático , Procesamiento de Lenguaje Natural , Humanos , Femenino , Persona de Mediana Edad , Neoplasias de la Mama/diagnóstico por imagen , Neoplasias de la Mama/clasificación , Mamografía/clasificación , Conjuntos de Datos como Asunto , Sistemas de Información Radiológica/normas , AdultoRESUMEN
There has been increased interest in understanding the neural substrates of intelligence and several human traits from neuroimaging data. Deep learning can be used to predict different cognitive measures, such as general and fluid intelligence, from different functional magnetic resonance imaging experiments providing information about the main brain areas involved in these predictions. Using neuroimaging and behavioral data from 874 subjects provided by the Human Connectome Project, we predicted various cognitive scores using dynamic functional connectivity derived from language and working memory functional magnetic resonance imaging task states, using a 360-region multimodal atlas. The deep model joins multiscale convolutional and long short-term memory layers and was trained under a 10-fold stratified cross-validation. We removed the confounding effects of gender, age, total brain volume, motion and the multiband reconstruction algorithm using multiple linear regression. We can explain 17.1% and 16% of general intelligence variance for working memory and language tasks, respectively. We showed that task-based dynamic functional connectivity has more predictive power than resting-state dynamic functional connectivity when compared to the literature and that removing confounders significantly reduces the prediction performance. No specific cortical network showed significant relevance in the prediction of general and fluid intelligence, suggesting a spatial homogeneous distribution of the intelligence construct in the brain.
Asunto(s)
Encéfalo , Cognición , Conectoma , Aprendizaje Profundo , Inteligencia , Imagen por Resonancia Magnética , Memoria a Corto Plazo , Humanos , Imagen por Resonancia Magnética/métodos , Masculino , Femenino , Conectoma/métodos , Cognición/fisiología , Encéfalo/fisiología , Encéfalo/diagnóstico por imagen , Adulto , Inteligencia/fisiología , Memoria a Corto Plazo/fisiología , Adulto Joven , LenguajeRESUMEN
MicroRNAs (miRNAs) have been implicated in human disorders, from cancers to infectious diseases. Targeting miRNAs or their target genes with small molecules offers opportunities to modulate dysregulated cellular processes linked to diseases. Yet, predicting small molecules associated with miRNAs remains challenging due to the small size of small molecule-miRNA datasets. Herein, we develop a generalized deep learning framework, sChemNET, for predicting small molecules affecting miRNA bioactivity based on chemical structure and sequence information. sChemNET overcomes the limitation of sparse chemical information by an objective function that allows the neural network to learn chemical space from a large body of chemical structures yet unknown to affect miRNAs. We experimentally validated small molecules predicted to act on miR-451 or its targets and tested their role in erythrocyte maturation during zebrafish embryogenesis. We also tested small molecules targeting the miR-181 network and other miRNAs using in-vitro and in-vivo experiments. We demonstrate that our machine-learning framework can predict bioactive small molecules targeting miRNAs or their targets in humans and other mammalian organisms.
Asunto(s)
Aprendizaje Profundo , MicroARNs , Pez Cebra , MicroARNs/genética , MicroARNs/metabolismo , Pez Cebra/genética , Animales , Humanos , Eritrocitos/efectos de los fármacos , Eritrocitos/metabolismo , Bibliotecas de Moléculas Pequeñas/farmacología , Bibliotecas de Moléculas Pequeñas/química , Desarrollo Embrionario/efectos de los fármacos , Desarrollo Embrionario/genética , Redes Neurales de la ComputaciónRESUMEN
BACKGROUND: Artificial intelligence (AI)-enabled electrocardiography (ECG) can be used to predict risk of future disease and mortality but has not yet been adopted into clinical practice. Existing model predictions do not have actionability at an individual patient level, explainability, or biological plausibi. We sought to address these limitations of previous AI-ECG approaches by developing the AI-ECG risk estimator (AIRE) platform. METHODS: The AIRE platform was developed in a secondary care dataset (Beth Israel Deaconess Medical Center [BIDMC]) of 1â163â401 ECGs from 189â539 patients with deep learning and a discrete-time survival model to create a patient-specific survival curve with a single ECG. Therefore, AIRE predicts not only risk of mortality, but also time-to-mortality. AIRE was validated in five diverse, transnational cohorts from the USA, Brazil, and the UK (UK Biobank [UKB]), including volunteers, primary care patients, and secondary care patients. FINDINGS: AIRE accurately predicts risk of all-cause mortality (BIDMC C-index 0·775, 95% CI 0·773-0·776; C-indices on external validation datasets 0·638-0·773), future ventricular arrhythmia (BIDMC C-index 0·760, 95% CI 0·756-0·763; UKB C-index 0·719, 95% CI 0·635-0·803), future atherosclerotic cardiovascular disease (0·696, 0·694-0·698; 0·643, 0·624-0·662), and future heart failure (0·787, 0·785-0·789; 0·768, 0·733-0·802). Through phenome-wide and genome-wide association studies, we identified candidate biological pathways for the prediction of increased risk, including changes in cardiac structure and function, and genes associated with cardiac structure, biological ageing, and metabolic syndrome. INTERPRETATION: AIRE is an actionable, explainable, and biologically plausible AI-ECG risk estimation platform that has the potential for use worldwide across a wide range of clinical contexts for short-term and long-term risk estimation. FUNDING: British Heart Foundation, National Institute for Health and Care Research, and Medical Research Council.
Asunto(s)
Inteligencia Artificial , Enfermedades Cardiovasculares , Electrocardiografía , Humanos , Enfermedades Cardiovasculares/mortalidad , Femenino , Medición de Riesgo/métodos , Persona de Mediana Edad , Masculino , Anciano , Adulto , Reino Unido , Brasil/epidemiología , Aprendizaje ProfundoRESUMEN
OBJECTIVE: This study aimed to implement and evaluate a Deep Convolutional Neural Network for classifying myofibroblastic lesions into benign and malignant categories based on patch-based images. METHODS: A Residual Neural Network (ResNet50) model, pre-trained with weights from ImageNet, was fine-tuned to classify a cohort of 20 patients (11 benign and 9 malignant cases). Following annotation of tumor regions, the whole-slide images (WSIs) were fragmented into smaller patches (224 × 224 pixels). These patches were non-randomly divided into training (308,843 patches), validation (43,268 patches), and test (42,061 patches) subsets, maintaining a 78:11:11 ratio. The CNN training was caried out for 75 epochs utilizing a batch size of 4, the Adam optimizer, and a learning rate of 0.00001. RESULTS: ResNet50 achieved an accuracy of 98.97%, precision of 99.91%, sensitivity of 97.98%, specificity of 99.91%, F1 score of 98.94%, and AUC of 0.99. CONCLUSIONS: The ResNet50 model developed exhibited high accuracy during training and robust generalization capabilities in unseen data, indicating nearly flawless performance in distinguishing between benign and malignant myofibroblastic tumors, despite the small sample size. The excellent performance of the AI model in separating such histologically similar classes could be attributed to its ability to identify hidden discriminative features, as well as to use a wide range of features and benefit from proper data preprocessing.
Asunto(s)
Redes Neurales de la Computación , Humanos , Interpretación de Imagen Asistida por Computador/métodos , Aprendizaje Profundo , Sensibilidad y Especificidad , Neoplasias de Cabeza y Cuello/patología , Neoplasias de Cabeza y Cuello/clasificaciónRESUMEN
Objetive. Decoding speech from brain activity can enable communication for individuals with speech disorders. Deep neural networks (DNNs) have shown great potential for speech decoding applications. However, the limited availability of large datasets containing neural recordings from speech-impaired subjects poses a challenge. Leveraging data from healthy participants can mitigate this limitation and expedite the development of speech neuroprostheses while minimizing the need for patient-specific training data.Approach. In this study, we collected a substantial dataset consisting of recordings from 56 healthy participants using 64 EEG channels. Multiple neural networks were trained to classify perceived sentences in the Spanish language using subject-independent, mixed-subjects, and fine-tuning approaches. The dataset has been made publicly available to foster further research in this area.Main results. Our results demonstrate a remarkable level of accuracy in distinguishing sentence identity across 30 classes, showcasing the feasibility of training DNNs to decode sentence identity from perceived speech using EEG. Notably, the subject-independent approach rendered accuracy comparable to the mixed-subjects approach, although with higher variability among subjects. Additionally, our fine-tuning approach yielded even higher accuracy, indicating an improved capability to adapt to individual subject characteristics, which enhances performance. This suggests that DNNs have effectively learned to decode universal features of brain activity across individuals while also being adaptable to specific participant data. Furthermore, our analyses indicate that EEGNet and DeepConvNet exhibit comparable performance, outperforming ShallowConvNet for sentence identity decoding. Finally, our Grad-CAM visualization analysis identifies key areas influencing the network's predictions, offering valuable insights into the neural processes underlying language perception and comprehension.Significance. These findings advance our understanding of EEG-based speech perception decoding and hold promise for the development of speech neuroprostheses, particularly in scenarios where subjects cannot provide their own training data.