Exploring the Efficacy of Artificial Intelligence: A Comprehensive Analysis of CHAT-GPT's Accuracy and Completeness in Addressing Urinary Incontinence Queries.

BACKGROUND: Artificial intelligence models are increasingly gaining popularity among patients and healthcare professionals. While it is impossible to restrict patient's access to different sources of information on the Internet, healthcare professional needs to be aware of the content-quality available across different platforms. OBJECTIVE: To investigate the accuracy and completeness of Chat Generative Pretrained Transformer (ChatGPT) in addressing frequently asked questions related to the management and treatment of female urinary incontinence (UI), compared to recommendations from guidelines. METHODS: This is a cross-sectional study. Two researchers developed 14 frequently asked questions related to UI. Then, they were inserted into the ChatGPT platform on September 16, 2023. The accuracy (scores from 1 to 5) and completeness (score from 1 to 3) of ChatGPT's answers were assessed individually by two experienced researchers in the Women's Health field, following the recommendations proposed by the guidelines for UI. RESULTS: Most of the answers were classified as "more correct than incorrect" (n = 6), followed by "incorrect information than correct" (n = 3), "approximately equal correct and incorrect" (n = 2), "near all correct" (n = 2, and "correct" (n = 1). Regarding the appropriateness, most of the answers were classified as adequate, as they provided the minimum information expected to be classified as correct. CONCLUSION: These results showed an inconsistency when evaluating the accuracy of answers generated by ChatGPT compared by scientific guidelines. Almost all the answers did not bring the complete content expected or reported in previous guidelines, which highlights to healthcare professionals and scientific community a concern about using artificial intelligence in patient counseling.

StAC-DA: Structure aware cross-modality domain adaptation framework with image and feature-level adaptation for medical image segmentation.

Objective: Convolutional neural networks (CNNs) have achieved state-of-the-art results in various medical image segmentation tasks. However, CNNs often assume that the source and target dataset follow the same probability distribution and when this assumption is not satisfied their performance degrades significantly. This poses a limitation in medical image analysis, where including information from different imaging modalities can bring large clinical benefits. In this work, we present an unsupervised Structure Aware Cross-modality Domain Adaptation (StAC-DA) framework for medical image segmentation. Methods: StAC-DA implements an image- and feature-level adaptation in a sequential two-step approach. The first step performs an image-level alignment, where images from the source domain are translated to the target domain in pixel space by implementing a CycleGAN-based model. The latter model includes a structure-aware network that preserves the shape of the anatomical structure during translation. The second step consists of a feature-level alignment. A U-Net network with deep supervision is trained with the transformed source domain images and target domain images in an adversarial manner to produce probable segmentations for the target domain. Results: The framework is evaluated on bidirectional cardiac substructure segmentation. StAC-DA outperforms leading unsupervised domain adaptation approaches, being ranked first in the segmentation of the ascending aorta when adapting from Magnetic Resonance Imaging (MRI) to Computed Tomography (CT) domain and from CT to MRI domain. Conclusions: The presented framework overcomes the limitations posed by differing distributions in training and testing datasets. Moreover, the experimental results highlight its potential to improve the accuracy of medical image segmentation across diverse imaging modalities.

Artificial Intelligence, the Production of Scientific Texts, and the Implications for Sleep Science: Exploring Emerging Paradigms and Perspectives.

The emergence of artificial intelligence (AI) has revolutionized many fields, including natural language processing, and marks a potential paradigm shift in the way we evaluate knowledge. One significant innovation in this area is ChatGPT, a large language model based on the GPT-3.5 architecture created by OpenAI, with one of its main aims being to aid in general text writing, including scientific texts. Here, we highlight the challenges and opportunities related to using generative AI and discuss both the benefits of its use, such as saving time by streamlining the writing process and reducing the amount of time spent on mundane tasks, and the potential drawbacks, including concerns regarding the accuracy and reliability of the information generated and its ethical use. In respect of both education and the writing of scientific texts, clear rules and objectives and institutional principles must be established for the use of AI. We also consider the positive and negative effects of the use of AI technologies on interpersonal interactions and behavior, and, as sleep scientists, its potential impacts on sleep. Striking a balance between the benefits and potential drawbacks of integrating AI into society demands ongoing research by experts, the wide dissemination of the scientific results, as well as continued public discourse on the subject.

Stochastic image spectroscopy: a discriminative generative approach to hyperspectral image modelling and classification.

This paper introduces a new latent variable probabilistic framework for representing spectral data of high spatial and spectral dimensionality, such as hyperspectral images. We use a generative Bayesian model to represent the image formation process and provide interpretable and efficient inference and learning methods. Surprisingly, our approach can be implemented with simple tools and does not require extensive training data, detailed pixel-by-pixel labeling, or significant computational resources. Numerous experiments with simulated data and real benchmark scenarios show encouraging image classification performance. These results validate the unique ability of our framework to discriminate complex hyperspectral images, irrespective of the presence of highly discriminative spectral signatures.

Protein Language Models and Machine Learning Facilitate the Identification of Antimicrobial Peptides.

Peptides are bioactive molecules whose functional versatility in living organisms has led to successful applications in diverse fields. In recent years, the amount of data describing peptide sequences and function collected in open repositories has substantially increased, allowing the application of more complex computational models to study the relations between the peptide composition and function. This work introduces AMP-Detector, a sequence-based classification model for the detection of peptides' functional biological activity, focusing on accelerating the discovery and de novo design of potential antimicrobial peptides (AMPs). AMP-Detector introduces a novel sequence-based pipeline to train binary classification models, integrating protein language models and machine learning algorithms. This pipeline produced 21 models targeting antimicrobial, antiviral, and antibacterial activity, achieving average precision exceeding 83%. Benchmark analyses revealed that our models outperformed existing methods for AMPs and delivered comparable results for other biological activity types. Utilizing the Peptide Atlas, we applied AMP-Detector to discover over 190,000 potential AMPs and demonstrated that it is an integrative approach with generative learning to aid in de novo design, resulting in over 500 novel AMPs. The combination of our methodology, robust models, and a generative design strategy offers a significant advancement in peptide-based drug discovery and represents a pivotal tool for therapeutic applications.

Peptide-based drug discovery through artificial intelligence: towards an autonomous design of therapeutic peptides.

With their diverse biological activities, peptides are promising candidates for therapeutic applications, showing antimicrobial, antitumour and hormonal signalling capabilities. Despite their advantages, therapeutic peptides face challenges such as short half-life, limited oral bioavailability and susceptibility to plasma degradation. The rise of computational tools and artificial intelligence (AI) in peptide research has spurred the development of advanced methodologies and databases that are pivotal in the exploration of these complex macromolecules. This perspective delves into integrating AI in peptide development, encompassing classifier methods, predictive systems and the avant-garde design facilitated by deep-generative models like generative adversarial networks and variational autoencoders. There are still challenges, such as the need for processing optimization and careful validation of predictive models. This work outlines traditional strategies for machine learning model construction and training techniques and proposes a comprehensive AI-assisted peptide design and validation pipeline. The evolving landscape of peptide design using AI is emphasized, showcasing the practicality of these methods in expediting the development and discovery of novel peptides within the context of peptide-based drug discovery.

Deep Learning Models to Reduce Stray Light in TJ-II Thomson Scattering Diagnostic.

Nuclear fusion is a potential source of energy that could supply the growing needs of the world population for millions of years. Several experimental thermonuclear fusion devices try to understand and control the nuclear fusion process. A very interesting diagnostic called Thomson scattering (TS) is performed in the Spanish fusion device TJ-II. This diagnostic takes images to measure the temperature and density profiles of the plasma, which is heated to very high temperatures to produce fusion plasma. Each image captures spectra of laser light scattered by the plasma under different conditions. Unfortunately, some images are corrupted by noise called stray light that affects the measurement of the profiles. In this work, we propose the use of deep learning models to reduce the stray light that appears in the diagnostic. The proposed approach utilizes a Pix2Pix neural network, which is an image-to-image translation based on a generative adversarial network (GAN). This network learns to translateimages affected by stray light to images without stray light. This allows for the effective removal of the noise that affects the measurements of the TS diagnostic, avoiding the need for manual image processing adjustments. The proposed method shows a better performance, reducing the noise up to 98% inimages, which surpassesprevious works that obtained 85% for the validation dataset.

Exploring the Performance of ChatGPT Versions 3.5, 4, and 4 With Vision in the Chilean Medical Licensing Examination: Observational Study.

Background: The deployment of OpenAI's ChatGPT-3.5 and its subsequent versions, ChatGPT-4 and ChatGPT-4 With Vision (4V; also known as "GPT-4 Turbo With Vision"), has notably influenced the medical field. Having demonstrated remarkable performance in medical examinations globally, these models show potential for educational applications. However, their effectiveness in non-English contexts, particularly in Chile's medical licensing examinations-a critical step for medical practitioners in Chile-is less explored. This gap highlights the need to evaluate ChatGPT's adaptability to diverse linguistic and cultural contexts. Objective: This study aims to evaluate the performance of ChatGPT versions 3.5, 4, and 4V in the EUNACOM (Examen Único Nacional de Conocimientos de Medicina), a major medical examination in Chile. Methods: Three official practice drills (540 questions) from the University of Chile, mirroring the EUNACOM's structure and difficulty, were used to test ChatGPT versions 3.5, 4, and 4V. The 3 ChatGPT versions were provided 3 attempts for each drill. Responses to questions during each attempt were systematically categorized and analyzed to assess their accuracy rate. Results: All versions of ChatGPT passed the EUNACOM drills. Specifically, versions 4 and 4V outperformed version 3.5, achieving average accuracy rates of 79.32% and 78.83%, respectively, compared to 57.53% for version 3.5 (P<.001). Version 4V, however, did not outperform version 4 (P=.73), despite the additional visual capabilities. We also evaluated ChatGPT's performance in different medical areas of the EUNACOM and found that versions 4 and 4V consistently outperformed version 3.5. Across the different medical areas, version 3.5 displayed the highest accuracy in psychiatry (69.84%), while versions 4 and 4V achieved the highest accuracy in surgery (90.00% and 86.11%, respectively). Versions 3.5 and 4 had the lowest performance in internal medicine (52.74% and 75.62%, respectively), while version 4V had the lowest performance in public health (74.07%). Conclusions: This study reveals ChatGPT's ability to pass the EUNACOM, with distinct proficiencies across versions 3.5, 4, and 4V. Notably, advancements in artificial intelligence (AI) have not significantly led to enhancements in performance on image-based questions. The variations in proficiency across medical fields suggest the need for more nuanced AI training. Additionally, the study underscores the importance of exploring innovative approaches to using AI to augment human cognition and enhance the learning process. Such advancements have the potential to significantly influence medical education, fostering not only knowledge acquisition but also the development of critical thinking and problem-solving skills among health care professionals.

Performance of a commercially available Generative Pre-trained Transformer (GPT) in describing radiolucent lesions in panoramic radiographs and establishing differential diagnoses.

OBJECTIVES: To evaluate the performance of a commercially available Generative Pre-trained Transformer (GPT) in describing and establishing differential diagnoses for radiolucent lesions in panoramic radiographs. MATERIALS AND METHODS: Twenty-eight panoramic radiographs, each containing a single radiolucent lesion, were evaluated in consensus by three examiners and a commercially available ChatGPT-3.5 model. They provided descriptions regarding internal structure (radiodensity, loculation), periphery (margin type, cortication), shape, location (bone, side, region, teeth/structures), and effects on adjacent structures (effect, adjacent structure). Diagnostic impressions related to origin, behavior, and nature were also provided. The GPT program was additionally prompted to provide differential diagnoses. Keywords used by the GPT program were compared to those used by the examiners and scored as 0 (incorrect), 0.5 (partially correct), or 1 (correct). Mean score values and standard deviation were calculated for each description. Performance in establishing differential diagnoses was assessed using Rank-1, -2, and - 3. RESULTS: Descriptions of margination, affected bone, and origin received the highest scores: 0.93, 0.93, and 0.87, respectively. Shape, region, teeth/structures, effect, affected region, and nature received considerably lower scores ranging from 0.22 to 0.50. Rank-1, -2, and - 3 demonstrated accuracy in 25%, 57.14%, and 67.85% of cases, respectively. CONCLUSION: The performance of the GPT program in describing and providing differential diagnoses for radiolucent lesions in panoramic radiographs is variable and at this stage limited in its use for clinical application. CLINICAL RELEVANCE: Understanding the potential role of GPT systems as an auxiliary tool in image interpretation is imperative to validate their clinical applicability.

Cardiac fat segmentation using computed tomography and an image-to-image conditional generative adversarial neural network.

In recent years, research has highlighted the association between increased adipose tissue surrounding the human heart and elevated susceptibility to cardiovascular diseases such as atrial fibrillation and coronary heart disease. However, the manual segmentation of these fat deposits has not been widely implemented in clinical practice due to the substantial workload it entails for medical professionals and the associated costs. Consequently, the demand for more precise and time-efficient quantitative analysis has driven the emergence of novel computational methods for fat segmentation. This study presents a novel deep learning-based methodology that offers autonomous segmentation and quantification of two distinct types of cardiac fat deposits. The proposed approach leverages the pix2pix network, a generative conditional adversarial network primarily designed for image-to-image translation tasks. By applying this network architecture, we aim to investigate its efficacy in tackling the specific challenge of cardiac fat segmentation, despite not being originally tailored for this purpose. The two types of fat deposits of interest in this study are referred to as epicardial and mediastinal fats, which are spatially separated by the pericardium. The experimental results demonstrated an average accuracy of 99.08% and f1-score 98.73 for the segmentation of the epicardial fat and 97.90% of accuracy and f1-score of 98.40 for the mediastinal fat. These findings represent the high precision and overlap agreement achieved by the proposed methodology. In comparison to existing studies, our approach exhibited superior performance in terms of f1-score and run time, enabling the images to be segmented in real time.

La Inteligencia Artificial Generativa en la escena de la educación superior en ciencias de la salud / Generative Artificial Intelligence on the Scene of Higher Education in the Health Sciences

Introducción: este artículo se enfoca en la experiencia de un Instituto Universitario de gestión privada de la ciudad de Buenos Aires al abordar la inteligencia artificial (IA) en educación. El objetivo es compartir líneas de acción y resultados para promover la reflexión y apropiación crítica de esta tecnología en la comunidad educativa. Desarrollo: se presenta un relato de experiencia referido al diseño de cuatro líneas de acción para abordar el uso de aplicaciones de IA generativa (IAGen) en la educación superior en ciencias de la salud: elaboración de un estado de la cuestión; indagación de conocimientos en la comunidad educativa; capacitaciones para actores institucionales clave; producción de materiales guía. Resultados: se observa un creciente interés en la IAGen en la comunidad educativa. Se registran experiencias positivas con aplicaciones de IAGen, encontrándolas intuitivas y útiles para la investigación y la enseñanza. Sin embargo, se destacan desafíos, como la falta de conocimiento sobre cómo usar estas herramientas de manera eficaz. La formación ha sido clave para abordar estos desafíos y se ha llevado a cabo para integrantes del equipo del Departamento de Educación, autoridades y docentes. Conclusión: la IAGen está atravesando integralmente la educación superior en el campo de las ciencias de la salud. Las instituciones universitarias tienen la responsabilidad de promover el desarrollo de competencias digitales y criterios de uso responsables. A medida que la IAGen continúa desarrollándose, es esencial abordar nuevos desafíos y regulaciones, promoviendo la reflexión y la formación continua en la comunidad educativa. El trabajo interdisciplinario y la colaboración entre diversas áreas de gestión institucional son fundamentales para abordar estos cambios tecnológicos en la educación. (AU)

Introduction:This article focuses on the experience of a privately managed University Institute in Buenos Aires city when addressing artificial intelligence (AI) in education. The aim is to share strategies and outcomes to encourage reflection and critical engagement with this technology within the educational community. Development: We present a narrative of experience concerning the design of four lines of action to address the uses of generative AI applications (GenAI) in higher education in health sciences: drafting a state-of-the-art report; probing knowledge within the educational community; training sessions for core institutional actors; production of guide materials. Results: There is a growing interest in GenAI within the educational community. We register positive experiences with IAGen applications, finding them intuitive and useful for research and teaching. However, we highlight challenges, such as gaps in knowledge on how to use these tools most effectively. Training has been crucial in addressing these challenges and has been conducted for members of the Education Department team, authorities, and teachers. Conclusion: GenAI is fundamentally permeating higher education in the field of health sciences. University institutions are responsible for promoting the development of digital competencies and standards of responsible use. As GenAI continues to evolve, addressing new challenges and regulations is essential, encouraging reflection and ongoing training within the educational community. Interdisciplinary work and collaboration among various areas of institutional management are critical to address these technological changes in education. (AU)

Accelerating the Discovery and Design of Antimicrobial Peptides with Artificial Intelligence.

Peptides modulate many processes of human physiology targeting ion channels, protein receptors, or enzymes. They represent valuable starting points for the development of new biologics against communicable and non-communicable disorders. However, turning native peptide ligands into druggable materials requires high selectivity and efficacy, predictable metabolism, and good safety profiles. Machine learning models have gradually emerged as cost-effective and time-saving solutions to predict and generate new proteins with optimal properties. In this chapter, we will discuss the evolution and applications of predictive modeling and generative modeling to discover and design safe and effective antimicrobial peptides. We will also present their current limitations and suggest future research directions, applicable to peptide drug design campaigns.

A Study on Generative Models for Visual Recognition of Unknown Scenes Using a Textual Description.

In this study, we investigate the application of generative models to assist artificial agents, such as delivery drones or service robots, in visualising unfamiliar destinations solely based on textual descriptions. We explore the use of generative models, such as Stable Diffusion, and embedding representations, such as CLIP and VisualBERT, to compare generated images obtained from textual descriptions of target scenes with images of those scenes. Our research encompasses three key strategies: image generation, text generation, and text enhancement, the latter involving tools such as ChatGPT to create concise textual descriptions for evaluation. The findings of this study contribute to an understanding of the impact of combining generative tools with multi-modal embedding representations to enhance the artificial agent's ability to recognise unknown scenes. Consequently, we assert that this research holds broad applications, particularly in drone parcel delivery, where an aerial robot can employ text descriptions to identify a destination. Furthermore, this concept can also be applied to other service robots tasked with delivering to unfamiliar locations, relying exclusively on user-provided textual descriptions.

Optimizing Clinical Diabetes Diagnosis through Generative Adversarial Networks: Evaluation and Validation.

The escalating prevalence of Type 2 Diabetes (T2D) represents a substantial burden on global healthcare systems, especially in regions such as Mexico. Existing diagnostic techniques, although effective, often require invasive procedures and labor-intensive efforts. The promise of artificial intelligence and data science for streamlining and enhancing T2D diagnosis is well-recognized; however, these advancements are frequently constrained by the limited availability of comprehensive patient datasets. To mitigate this challenge, the present study investigated the efficacy of Generative Adversarial Networks (GANs) for augmenting existing T2D patient data, with a focus on a Mexican cohort. The researchers utilized a dataset of 1019 Mexican nationals, divided into 499 non-diabetic controls and 520 diabetic cases. GANs were applied to create synthetic patient profiles, which were subsequently used to train a Random Forest (RF) classification model. The study's findings revealed a notable improvement in the model's diagnostic accuracy, validating the utility of GAN-based data augmentation in a clinical context. The results bear significant implications for enhancing the robustness and reliability of Machine Learning tools in T2D diagnosis and management, offering a pathway toward more timely and effective patient care.

Clinical Research With Large Language Models Generated Writing-Clinical Research with AI-assisted Writing (CRAW) Study.

IMPORTANCE: The scientific community debates Generative Pre-trained Transformer (GPT)-3.5's article quality, authorship merit, originality, and ethical use in scientific writing. OBJECTIVES: Assess GPT-3.5's ability to craft the background section of critical care clinical research questions compared to medical researchers with H-indices of 22 and 13. DESIGN: Observational cross-sectional study. SETTING: Researchers from 20 countries from six continents evaluated the backgrounds. PARTICIPANTS: Researchers with a Scopus index greater than 1 were included. MAIN OUTCOMES AND MEASURES: In this study, we generated a background section of a critical care clinical research question on "acute kidney injury in sepsis" using three different methods: researcher with H-index greater than 20, researcher with H-index greater than 10, and GPT-3.5. The three background sections were presented in a blinded survey to researchers with an H-index range between 1 and 96. First, the researchers evaluated the main components of the background using a 5-point Likert scale. Second, they were asked to identify which background was written by humans only or with large language model-generated tools. RESULTS: A total of 80 researchers completed the survey. The median H-index was 3 (interquartile range, 1-7.25) and most (36%) researchers were from the Critical Care specialty. When compared with researchers with an H-index of 22 and 13, GPT-3.5 was marked high on the Likert scale ranking on main background components (median 4.5 vs. 3.82 vs. 3.6 vs. 4.5, respectively; p < 0.001). The sensitivity and specificity to detect researchers writing versus GPT-3.5 writing were poor, 22.4% and 57.6%, respectively. CONCLUSIONS AND RELEVANCE: GPT-3.5 could create background research content indistinguishable from the writing of a medical researcher. It was marked higher compared with medical researchers with an H-index of 22 and 13 in writing the background section of a critical care clinical research question.

Performance of ChatGPT on the Peruvian National Licensing Medical Examination: Cross-Sectional Study.

BACKGROUND: ChatGPT has shown impressive performance in national medical licensing examinations, such as the United States Medical Licensing Examination (USMLE), even passing it with expert-level performance. However, there is a lack of research on its performance in low-income countries' national licensing medical examinations. In Peru, where almost one out of three examinees fails the national licensing medical examination, ChatGPT has the potential to enhance medical education. OBJECTIVE: We aimed to assess the accuracy of ChatGPT using GPT-3.5 and GPT-4 on the Peruvian National Licensing Medical Examination (Examen Nacional de Medicina [ENAM]). Additionally, we sought to identify factors associated with incorrect answers provided by ChatGPT. METHODS: We used the ENAM 2022 data set, which consisted of 180 multiple-choice questions, to evaluate the performance of ChatGPT. Various prompts were used, and accuracy was evaluated. The performance of ChatGPT was compared to that of a sample of 1025 examinees. Factors such as question type, Peruvian-specific knowledge, discrimination, difficulty, quality of questions, and subject were analyzed to determine their influence on incorrect answers. Questions that received incorrect answers underwent a three-step process involving different prompts to explore the potential impact of adding roles and context on ChatGPT's accuracy. RESULTS: GPT-4 achieved an accuracy of 86% on the ENAM, followed by GPT-3.5 with 77%. The accuracy obtained by the 1025 examinees was 55%. There was a fair agreement (κ=0.38) between GPT-3.5 and GPT-4. Moderate-to-high-difficulty questions were associated with incorrect answers in the crude and adjusted model for GPT-3.5 (odds ratio [OR] 6.6, 95% CI 2.73-15.95) and GPT-4 (OR 33.23, 95% CI 4.3-257.12). After reinputting questions that received incorrect answers, GPT-3.5 went from 41 (100%) to 12 (29%) incorrect answers, and GPT-4 from 25 (100%) to 4 (16%). CONCLUSIONS: Our study found that ChatGPT (GPT-3.5 and GPT-4) can achieve expert-level performance on the ENAM, outperforming most of our examinees. We found fair agreement between both GPT-3.5 and GPT-4. Incorrect answers were associated with the difficulty of questions, which may resemble human performance. Furthermore, by reinputting questions that initially received incorrect answers with different prompts containing additional roles and context, ChatGPT achieved improved accuracy.

Bone-GAN: Generation of virtual bone microstructure of high resolution peripheral quantitative computed tomography.

BACKGROUND: Data-driven development of medical biomarkers of bone requires a large amount of image data but physical measurements are generally too restricted in size and quality to perform a robust training. PURPOSE: This study aims to provide a reliable in silico method for the generation of realistic bone microstructure with defined microarchitectural properties. Synthetic bone samples may improve training of neural networks and serve for the development of new diagnostic parameters of bone architecture and mineralization. METHODS: One hundred-fifty cadaveric lumbar vertebrae from 48 different male human spines were scanned with a high resolution peripheral quantitative CT. After prepocessing the scans, we extracted 10,795 purely spongeous bone patches, each with a side length of 32 voxels (5 mm) and isotropic voxel size of 164 µm. We trained a volumetric generative adversarial network (GAN) in a progressive manner to create synthetic microstructural bone samples. We then added a style transfer technique to allow the generation of synthetic samples with defined microstructure and gestalt by simultaneously optimizing two entangled loss functions. Reliability testing was performed by comparing real and synthetic bone samples on 10 well-understood microstructural parameters. RESULTS: The method was able to create synthetic bone samples with visual and quantitative properties that effectively matched with the real samples. The GAN contained a well-formed latent space allowing to smoothly morph bone samples by their microstructural parameters, visual appearance or both. Optimum performance has been obtained for bone samples with voxel size 32 × 32 × 32, but also samples of size 64 × 64 × 64 could be synthesized. CONCLUSIONS: Our two-step-approach combines a parameter-agnostic GAN with a parameter-specific style transfer technique. It allows to generate an unlimited anonymous database of microstructural bone samples with sufficient realism to be used for the development of new data-driven methods of bone-biomarkers. Particularly, the style transfer technique can generate datasets of bone samples with specific conditions to simulate certain bone pathologies.

A novel sEMG data augmentation based on WGAN-GP.

The classification of sEMG signals is fundamental in applications that use mechanical prostheses, making it necessary to work with generalist databases that improve the accuracy of those classifications. Therefore, synthetic signal generation can be beneficial in enriching a database to make it more generalist. This work proposes using a variant of generative adversarial networks to produce synthetic biosignals of sEMG. A convolutional neural network (CNN) was used to classify the movements. The results showed good performance with an increase of 4.07% in a set of movement classification accuracy when 200 synthetic samples were included for each movement. We compared our results to other methodologies, such as Magnitude Warping and Scaling. Both methodologies did not have the same performance in the classification.

Dual U-Net-Based Conditional Generative Adversarial Network for Blood Vessel Segmentation with Reduced Cerebral MR Training Volumes.

Segmenting vessels in brain images is a critical step for many medical interventions and diagnoses of illnesses. Recent advances in artificial intelligence provide better models, achieving a human-like level of expertise in many tasks. In this paper, we present a new approach to segment Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) images, relying on fewer training samples than state-of-the-art methods. We propose a conditional generative adversarial network with an adapted generator based on a concatenated U-Net with a residual U-Net architecture (UUr-cGAN) to carry out blood vessel segmentation in TOF-MRA images, relying on data augmentation to diminish the drawback of having few volumes at disposal for training the model, while preventing overfitting by using regularization techniques. The proposed model achieves 89.52% precision and 87.23% in Dice score on average from the cross-validated experiment for brain blood vessel segmentation tasks, which is similar to other state-of-the-art methods while using considerably fewer training samples. UUr-cGAN extracts important features from small datasets while preventing overfitting compared to other CNN-based methods and still achieve a relatively good performance in image segmentation tasks such as brain blood vessels from TOF-MRA.

Removal of smoke effects in laparoscopic surgery via adversarial neural network and the dark channel prior.

BACKGROUND: In laparoscopic surgery, image quality can be severely degraded by surgical smoke caused by the use of tissue dissection tools that reduce the visibility of the observed organs and tissues. OBJECTIVE: Improve visibility in laparoscopic surgery by combining image processing techniques based on classical methods and artificial intelligence. METHOD: Development of a hybrid approach to eliminating the effects of surgical smoke, based on the combination of the dark channel prior (DCP) method and a pixel-to-pixel neural network architecture known as a generative adversarial network (GAN). RESULTS: Experimental results have shown that the proposed method achieves better performance than individual DCP and GAN results in terms of restoration quality, obtaining (according to PSNR and SSIM index metrics) better results than some related state-of-the-art methods. CONCLUSIONS: The proposed approach decreases the risks and time of laparoscopic surgery because once the network is trained, the system can improve real-time visibility.

ANTECEDENTES: Durante la cirugía laparoscópica, la calidad de la imagen puede verse gravemente degradada por el humo quirúrgico causado por el uso de herramientas de disección de tejidos que reducen la visibilidad de los órganos y tejidos. OBJETIVO: Mejorar la visibilidad en cirugía laparoscópica mediante la combinación de técnicas de procesamiento de imágenes basadas en técnicas clásicas e inteligencia artificial. MÉTODO: Desarrollo de un enfoque híbrido para la eliminación de los efectos del humo quirúrgico, basado en la combinación del método del principio del canal oscuro (DCP, dark channel prior) y una arquitectura de red neuronal píxel a píxel conocida como red antagónica generativa (GAN, generative adversial network). RESULTADOS: Los resultados experimentales han demostrado que el método propuesto logra un mejor rendimiento que los resultados individuales de DCP y GAN en cuanto a calidad de la restauración, obteniendo (según las métricas de la proporción máxima de señal a ruido [PSNR, Peak Signal-to-Noise Ratio] y el índice de similitud estructural [SSIM, Structural Similarity Index]) mejores resultados que otros métodos relacionados. CONCLUSIONES: El enfoque propuesto disminuye los riesgos y el tiempo de la cirugía laparoscópica, ya que una vez que la red está correctamente entrenada, el sistema puede mejorar la visibilidad en tiempo real.