Deep learning

FSDM: An efficient video super-resolution method based on Frames-Shift Diffusion Model

Video super-resolution is a fundamental task aimed at enhancing video quality through intricate modeling techniques. Recent advancements in diffusion models have significantly enhanced image super-resolution processing capabilities. However, their integration into video super-resolution workflows remains constrained due to the computational complexity of temporal fusion modules, demanding more computational resources compared to their image counterparts. To address this challenge, we propose a novel approach: a Frames-Shift Diffusion Model based on the image diffusion models. Compared to directly training diffusion-based video super-resolution models, redesigning the diffusion process of image models without introducing complex temporal modules requires minimal training consumption. We incorporate temporal information into the image super-resolution diffusion model by using optical flow and perform multi-frame fusion. This model adapts the diffusion process to smoothly transition from image super-resolution to video super-resolution diffusion without additional weight parameters. As a result, the Frames-Shift Diffusion Model efficiently processes videos frame by frame while maintaining computational efficiency and achieving superior performance. It enhances perceptual quality and achieves comparable performance to other state-of-the-art diffusion-based VSR methods in PSNR and SSIM. This approach optimizes video super-resolution by simplifying the integration of temporal data, thus addressing key challenges in the field.

Advancements in one-dimensional protein structure prediction using machine learning and deep learning

The accurate prediction of protein structures remains a cornerstone challenge in structural bioinformatics, essential for understanding the intricate relationship between protein sequence, structure, and function. Recent advancements in Machine Learning (ML) and Deep Learning (DL) have revolutionized this field, offering innovative approaches to tackle one- dimensional (1D) protein structure annotations, including secondary structure, solvent accessibility, and intrinsic disorder. This review highlights the evolution of predictive methodologies, from early machine learning models to sophisticated deep learning frameworks that integrate sequence embeddings and pretrained language models. Key advancements, such as AlphaFold's transformative impact on structure prediction and the rise of protein language models (PLMs), have enabled unprecedented accuracy in capturing sequence-structure relationships. Furthermore, we explore the role of specialized datasets, benchmarking competitions, and multimodal integration in shaping state-of-the-art prediction models. By addressing challenges in data quality, scalability, interpretability, and task-specific optimization, this review underscores the transformative impact of ML, DL, and PLMs on 1D protein prediction while providing insights into emerging trends and future directions in this rapidly evolving field.

Ionic Device: From Neuromorphic Computing to Interfacing with the Brain

In living organisms, the modulation of ion conductivity in ion channels of neuron cells enables intelligent behaviors, such as generating, transmitting, and storing neural signals. Drawing inspiration from these natural processes, researchers have fabricated ionic devices that replicate the functions of the nervous system. However, this field remains in its infancy, necessitating extensive foundational research in ionic device preparation, algorithm development, and biological interaction. This review summarizes recently developed neuromorphic ionic devices into three categories based on the materials states: liquid, semi-solid, and solid. The neural network algorithms embedded in these devices for neuromorphic computing are introduced, and future directions for the development of bidirectional human-computer interaction and hybrid human-computer intelligence are discussed.

Machine learning and multi-omics integration: advancing cardiovascular translational research and clinical practice

The global burden of cardiovascular diseases continues to rise, making their prevention, diagnosis and treatment increasingly critical. With advancements and breakthroughs in omics technologies such as high-throughput sequencing, multi-omics approaches can offer a closer reflection of the complex physiological and pathological changes in the body from a molecular perspective, providing new microscopic insights into cardiovascular diseases research. However, due to the vast volume and complexity of data, accurately describing, utilising, and translating these biomedical data demands substantial effort. Researchers and clinicians are actively developing artificial intelligence (AI) methods for data-driven knowledge discovery and causal inference using various omics data. These AI approaches, integrated with multi-omics research, have shown promising outcomes in cardiovascular studies. In this review, we outline the methods for integrating machine learning, one of the most successful applications of AI, with omics data and summarise representative AI models developed that leverage various omics data to facilitate the exploration of cardiovascular diseases from underlying mechanisms to clinical practice. Particular emphasis is placed on the effectiveness of using AI to extract potential molecular information to address current knowledge gaps. We discuss the challenges and opportunities of integrating omics with AI into routine diagnostic and therapeutic practices and anticipate the future development of novel AI models for wider application in the field of cardiovascular diseases.

Mapping Cell Identity from scRNA-seq: A primer on computational methods

Single cell (sc) technologies mark a conceptual and methodological breakthrough in our way to study cells, the base units of life. Thanks to these technological developments, large-scale initiatives are currently ongoing aimed at mapping of all the cell types in the human body, with the ambitious aim to gain a cell-level resolution of physiological development and disease. Since its broad applicability and ease of interpretation scRNA-seq is probably the most common sc-based application. This assay uses high throughput RNA sequencing to capture gene expression profiles at the sc-level. Subsequently, under the assumption that differences in transcriptional programs correspond to distinct cellular identities, ad-hoc computational methods are used to infer cell types from gene expression patterns. A wide array of computational methods were developed for this task. However, depending on the underlying algorithmic approach and associated computational requirements, each method might have a specific range of application, with implications that are not always clear to the end user. Here we will provide a concise overview on state-of-the-art computational methods for cell identity annotation in scRNA-seq, tailored for new users and non-computational scientists. To this end, we classify existing tools in five main categories, and discuss their key strengths, limitations and range of application.

AI and Data-Driven Advancements in Industry 4.0

Industrial artificial intelligence is rapidly evolving, driven by an unprecedented explosion of diverse data modalities [...].

REMI: Few-Shot ISAR Target Classification Via Robust Embedding and Manifold Inference

Unknown image deformation and few-shot issues have posed significant challenges to inverse synthetic aperture radar (ISAR) target classification. To achieve robust feature representation and precise correlation modeling, this article proposes a novel two-stage few-shot ISAR classification network, dubbed as robust embedding and manifold inference (REMI). In the robust embedding stage, a multihead spatial transformation network (MH-STN) is designed to adjust unknown image deformations from multiple perspectives. Then, the grouped embedding network (GEN) integrates and compresses diverse information by grouped feature extraction, intermediate feature fusion, and global feature embedding. In the manifold inference stage, a masked Gaussian graph attention network (MG-GAT) is devised to capture the irregular manifold of samples in the embedding space. In particular, the node features are described by Gaussian distributions, with interactions guided by the masked attention mechanism. Experimental results on two ISAR datasets demonstrate that REMI significantly improves the performance of few-shot classification and exhibits robustness in various scenarios.

Three systems of circuit formation: assembly, updating and tuning

Understanding the relationship between genotype and neuronal circuit phenotype necessitates an integrated view of genetics, development, plasticity and learning. Challenging the prevailing notion that emphasizes learning and plasticity as primary drivers of circuit assembly, in this Perspective, we delineate a tripartite framework to clarify the respective roles that learning and plasticity might have in this process. In the first part of the framework, which we term System One, neural circuits are established purely through genetically driven algorithms, in which spike timing-dependent plasticity serves no instructive role. We propose that these circuits equip the animal with sufficient skill and knowledge to successfully engage the world. Next, System Two is governed by rare but critical 'single-shot learning' events, which occur in response to survival situations and prompt rapid synaptic reconfiguration. Such events serve as crucial updates to the existing hardwired knowledge base of an organism. Finally, System Three is characterized by a perpetual state of synaptic recalibration, involving continual plasticity for circuit stabilization and fine-tuning. By outlining the definitions and roles of these three core systems, our framework aims to resolve existing ambiguities related to and enrich our understanding of neural circuit formation.

An explainable deep learning platform for molecular discovery

Deep learning approaches have been increasingly applied to the discovery of novel chemical compounds. These predictive approaches can accurately model compounds and increase true discovery rates, but they are typically black box in nature and do not generate specific chemical insights. Explainable deep learning aims to 'open up' the black box by providing generalizable and human-understandable reasoning for model predictions. These explanations can augment molecular discovery by identifying structural classes of compounds with desired activity in lieu of lone compounds. Additionally, these explanations can guide hypothesis generation and make searching large chemical spaces more efficient. Here we present an explainable deep learning platform that enables vast chemical spaces to be mined and the chemical substructures underlying predicted activity to be identified. The platform relies on Chemprop, a software package implementing graph neural networks as a deep learning model architecture. In contrast to similar approaches, graph neural networks have been shown to be state of the art for molecular property prediction. Focusing on discovering structural classes of antibiotics, this protocol provides guidelines for experimental data generation, model implementation and model explainability and evaluation. This protocol does not require coding proficiency or specialized hardware, and it can be executed in as little as 1-2 weeks, starting from data generation and ending in the testing of model predictions. The platform can be broadly applied to discover structural classes of other small molecules, including anticancer, antiviral and senolytic drugs, as well as to discover structural classes of inorganic molecules with desired physical and chemical properties.

Visual search and real-image similarity: An empirical assessment through the lens of deep learning

The ability to predict how efficiently a person finds an object in the environment is a crucial goal of attention research. Central to this issue are the similarity principles initially proposed by Duncan and Humphreys, which outline how the similarity between target and distractor objects (TD) and between distractor objects themselves (DD) affect search efficiency. However, the search principles lack direct quantitative support from an ecological perspective, being a summary approximation of a wide range of lab-based results poorly generalisable to real-world scenarios. This study exploits deep convolutional neural networks to predict human search efficiency from computational estimates of similarity between objects populating, potentially, any visual scene. Our results provide ecological evidence supporting the similarity principles: search performance continuously varies across tasks and conditions and improves with decreasing TD similarity and increasing DD similarity. Furthermore, our results reveal a crucial dissociation: TD and DD similarities mainly operate at two distinct layers of the network: DD similarity at the intermediate layers of coarse object features and TD similarity at the final layers of complex features used for classification. This suggests that these different similarities exert their major effects at two distinct perceptual levels and demonstrates our methodology's potential to offer insights into the depth of visual processing on which the search relies. By combining computational techniques with visual search principles, this approach aligns with modern trends in other research areas and fulfils longstanding demands for more ecologically valid research in the field of visual search.

Future of allergy and immunology: Is artificial intelligence the key in the digital era?

Artificial intelligence (AI) is reshaping allergy and immunology by integrating cutting-edge technology to enhance patient outcomes and redefine clinical practices and research. This review evaluates AI's evolving role, emphasizing its impact on diagnostic accuracy, personalized treatments, and innovative research methodologies. AI has advanced diagnostic tools, such as models predicting allergen sensitivity, and enhanced immunotherapy strategies. Its ability to process extensive data sets has enabled deeper understanding of allergic diseases and immune system responses, leading to more accurate, effective, and tailored treatments. Furthermore, AI is facilitating personalized care through AI-driven allergen mapping, automated patient monitoring, and targeted immunotherapy. The integration of AI into clinical practice promises a future in which allergy and immunology are characterized by precisely customized health care solutions. This review adheres to Preferred Reporting Items for Systematic reviews and Meta-Analyses flowchart, with a comprehensive analysis of databases, including Scopus, Web of Science, PubMed, and preprint platforms using keywords related to AI and allergy and immunology. From an initial pool of 192 studies, 20 documents were selected based on inclusion criteria. Our findings highlight how AI is transforming allergy and immunology by enhancing patient care, research methodologies, and clinical innovation, offering a glimpse into the near future of technology-driven health care in these fields.

Enhancement Strategies of Calcium Looping Technology and CaO-Based Sorbents for Carbon Capture

As global warming intensifies and energy resources deplete, carbon capture and sustainable energy conversion technologies gain increasing importance. Among these, calcium looping (CaL) technology has demonstrated promising cost-effectiveness and ease of integration with other systems. However, severe sintering of CaO-based sorbents occurs during cyclic carbonation and calcination, resulting in a significant decrease in CO2 capture capacity and stability. This paper reviews enhancement strategies in aggregate for synthetic CaO-based sorbents over the past 10 years, compiling a tabular dataset of 1042 reported materials, to compare the effects of synthesis methods and operation conditions on decay rate and CO2 capture capacity. Sol-gel, combustion, and template synthesis methods are recommended for producing high porosity CaO-based sorbents. The calcium precursors and organic acids used during synthesis, and addition of dopants, also play important roles in affecting the sorbent performance. This paper also examines the relationship between material synthesis, operation conditions, and performance of CaO-based sorbents to determine the feasibility of applying machine learning technology in materials development. This paper also discusses several possible artificial intelligence strategies with potential for designing innovative CaO-based sorbents suitable for long-term industrial applications, with the XGBoost model providing promising predictive capacity, particularly when working with relatively small, tabular, datasets.

An artificial intelligence tool that may assist with interpretation of rapid plasma reagin test for syphilis: Development and on-site evaluation

OBJECTIVES

The rapid plasma reagin (RPR) test, a traditional method for diagnosing syphilis and evaluating treatment efficacy, relies on subjective interpretation and requires high technical proficiency. This study aimed to develop and validate a user-friendly RPR-artificial intelligence (AI) interpretative tool.

METHODS

A dataset comprising 600 images of photographed RPR cards from 276 negative and 223 positive RPR samples was used for model development. The reference result was based on consistent interpretations by at least two out of three experienced laboratory personnel. Then an interpretative model was developed using deep learning algorithms and loaded into smartphones for on-site interpretation at two clinical centers from October 2023 to April 2024.

RESULTS

The model demonstrated an accuracy of 82·67% (95% CI 71·82%-90·09%) for reactive circles and 84·44% (95% CI 69·94%-93·01%) for non-reactive circles. In the field study, 669 specimens showed a sensitivity of 94·85% (95% CI 89·29%-97·73%), specificity of 91·56% (95% CI 88·78%-93·71%), and concordance of 92·23% (95% CI 89·87%-94·09%). The positive predictive value was 74·14% (95% CI 66·86%-80·33%) and negative predictive value was 98.59% (95% CI 96·98%-99·38%).

CONCLUSIONS

The tool assists in RPR interpretation standardization, enabling data traceability, and quality control for remote and underdeveloped areas.

A neuromuscular clinician's primer on machine learning

Artificial intelligence is the future of clinical practice and is increasingly utilized in medical management and clinical research. The release of ChatGPT3 in 2022 brought generative AI to the headlines and rekindled public interest in software agents that would complete repetitive tasks and save time. Artificial intelligence/machine learning underlies applications and devices which are assisting clinicians in the diagnosis, monitoring, formulation of prognosis, and treatment of patients with a spectrum of neuromuscular diseases. However, these applications have remained in the research sphere, and neurologists as a specialty are running the risk of falling behind other clinical specialties which are quicker to embrace these new technologies. While there are many comprehensive reviews on the use of artificial intelligence/machine learning in medicine, our aim is to provide a simple and practical primer to educate clinicians on the basics of machine learning. This will help clinicians specializing in neuromuscular and electrodiagnostic medicine to understand machine learning applications in nerve and muscle ultrasound, MRI imaging, electrical impendence myography, nerve conductions and electromyography and clinical cohort studies, and the limitations, pitfalls, regulatory and ethical concerns, and future directions. The question is not whether artificial intelligence/machine learning will change clinical practice, but when and how. How future neurologists will look back upon this period of transition will be determined not by how much changed or by how fast clinicians embraced this change but by how much patient outcomes were improved.

Flexible iontronic sensing

The emerging flexible iontronic sensing (FITS) technology has introduced a novel modality for tactile perception, mimicking the topological structure of human skin while providing a viable strategy for seamless integration with biological systems. With research progress, FITS has evolved from focusing on performance optimization and structural enhancement to a new phase of integration and intelligence, positioning it as a promising candidate for next-generation wearable devices. Therefore, a review from the perspective of technological development trends is essential to fully understand the current state and future potential of FITS devices. In this review, we examine the latest advancements in FITS. We begin by examining the sensing mechanisms of FITS, summarizing research progress in material selection, structural design, and the fabrication of active and electrode layers, while also analysing the challenges and bottlenecks faced by different segments in this field. Next, integrated systems based on FITS devices are reviewed, highlighting their applications in human-machine interaction, healthcare, and environmental monitoring. Additionally, the integration of artificial intelligence into FITS is explored, focusing on optimizing front-end device design and improving the processing and utilization of back-end data. Finally, building on existing research, future challenges for FITS devices are identified and potential solutions are proposed.

Automatic Diagnosis of Hepatocellular Carcinoma and Metastases Based on Computed Tomography Images

Liver cancer, a leading cause of cancer mortality, is often diagnosed by analyzing the grayscale variations in liver tissue across different computed tomography (CT) images. However, the intensity similarity can be strong, making it difficult for radiologists to visually identify hepatocellular carcinoma (HCC) and metastases. It is crucial for the management and prevention strategies to accurately differentiate between these two liver cancers. This study proposes an automated system using a convolutional neural network (CNN) to enhance diagnostic accuracy to detect HCC, metastasis, and healthy liver tissue. This system incorporates automatic segmentation and classification. The liver lesions segmentation model is implemented using residual attention U-Net. A 9-layer CNN classifier implements the lesions classification model. Its input is the combination of the results of the segmentation model with original images. The dataset included 300 patients, with 223 used to develop the segmentation model and 77 to test it. These 77 patients also served as inputs for the classification model, consisting of 20 HCC cases, 27 with metastasis, and 30 healthy. The system achieved a mean Dice score of 87.65 % in segmentation and a mean accuracy of 93.97 % in classification, both in the test phase. The proposed method is a preliminary study with great potential in helping radiologists diagnose liver cancers.

Torsion Graph Neural Networks

Geometric deep learning (GDL) models have demonstrated a great potential for the analysis of non-Euclidian data. They are developed to incorporate the geometric and topological information of non-Euclidian data into the end-to-end deep learning architectures. Motivated by the recent success of discrete Ricci curvature in graph neural network (GNNs), we propose TorGNN, an analytic Torsion enhanced Graph Neural Network model. The essential idea is to characterize graph local structures with an analytic torsion based weight formula. Mathematically, analytic torsion is a topological invariant that can distinguish spaces which are homotopy equivalent but not homeomorphic. In our TorGNN, for each edge, a corresponding local simplicial complex is identified, then the analytic torsion (for this local simplicial complex) is calculated, and further used as a weight (for this edge) in message-passing process. Our TorGNN model is validated on link prediction tasks from sixteen different types of networks and node classification tasks from four types of networks. It has been found that our TorGNN can achieve superior performance on both tasks, and outperform various state-of-the-art models. This demonstrates that analytic torsion is a highly efficient topological invariant in the characterization of graph structures and can significantly boost the performance of GNNs.

Evaluation of validity and reliability of AI Chatbots as public sources of information on dental trauma

AIM

This study aimed to assess the validity and reliability of AI chatbots, including Bing, ChatGPT 3.5, Google Gemini, and Claude AI, in addressing frequently asked questions (FAQs) related to dental trauma.

METHODOLOGY

A set of 30 FAQs was initially formulated by collecting responses from four AI chatbots. A panel comprising expert endodontists and maxillofacial surgeons then refined these to a final selection of 20 questions. Each question was entered into each chatbot three times, generating a total of 240 responses. These responses were evaluated using the Global Quality Score (GQS) on a 5-point Likert scale (5: strongly agree; 4: agree; 3: neutral; 2: disagree; 1: strongly disagree). Any disagreements in scoring were resolved through evidence-based discussions. The validity of the responses was determined by categorizing them as valid or invalid based on two thresholds: a low threshold (scores of ≥ 4 for all three responses) and a high threshold (scores of 5 for all three responses). A chi-squared test was used to compare the validity of the responses between the chatbots. Cronbach's alpha was calculated to assess the reliability by evaluating the consistency of repeated responses from each chatbot.

CONCLUSION

The results indicate that the Claude AI chatbot demonstrated superior validity and reliability compared to ChatGPT and Google Gemini, whereas Bing was found to be less reliable. These findings underscore the need for authorities to establish strict guidelines to ensure the accuracy of medical information provided by AI chatbots.

Generation of short-term follow-up chest CT images using a latent diffusion model in COVID-19

PURPOSE

Despite a global decrease in the number of COVID-19 patients, early prediction of the clinical course for optimal patient care remains challenging. Recently, the usefulness of image generation for medical images has been investigated. This study aimed to generate short-term follow-up chest CT images using a latent diffusion model in patients with COVID-19.

MATERIALS AND METHODS

We retrospectively enrolled 505 patients with COVID-19 for whom the clinical parameters (patient background, clinical symptoms, and blood test results) upon admission were available and chest CT imaging was performed. Subject datasets (n = 505) were allocated for training (n = 403), and the remaining (n = 102) were reserved for evaluation. The image underwent variational autoencoder (VAE) encoding, resulting in latent vectors. The information consisting of initial clinical parameters and radiomic features were formatted as a table data encoder. Initial and follow-up latent vectors and the initial table data encoders were utilized for training the diffusion model. The evaluation data were used to generate prognostic images. Then, similarity of the prognostic images (generated images) and the follow-up images (real images) was evaluated by zero-mean normalized cross-correlation (ZNCC), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM). Visual assessment was also performed using a numerical rating scale.

RESULTS

Prognostic chest CT images were generated using the diffusion model. Image similarity showed reasonable values of 0.973 ± 0.028 for the ZNCC, 24.48 ± 3.46 for the PSNR, and 0.844 ± 0.075 for the SSIM. Visual evaluation of the images by two pulmonologists and one radiologist yielded a reasonable mean score.

CONCLUSIONS

The similarity and validity of generated predictive images for the course of COVID-19-associated pneumonia using a diffusion model were reasonable. The generation of prognostic images may suggest potential utility for early prediction of the clinical course in COVID-19-associated pneumonia and other respiratory diseases.

Physics-informed neural networks for enhanced reference evapotranspiration estimation in Morocco: Balancing semi-physical models and deep learning

Reference evapotranspiration (ETo) is essential for agricultural water management, crop productivity, and irrigation systems. The Penman-Monteith (PM) equation is the standard method for estimating ETo, but its data-intensive nature makes it impractical, especially in situations where the cost of full standardized weather station is prohibitive, maintenance is inadequate, or data quality and continuity are compromised. To overcome those limitations, various semi-physical (SP) and empirical models with limited weather parameters were developed. In this context, artificial intelligence methods for ETo estimation are gaining more attention, balancing simplicity, minimal data requirements, and high accuracy. However, their data-driven nature raises concerns regarding explainability, trustworthiness, adherence to bio-physical laws, and reliability in operational settings. To address this issue, this paper, inspired by the emerging field of Physics-Informed Neural Networks (PINNs), evaluates the integration of SP models into the loss function during the learning process. The new residual loss combines two losses -the data-driven loss and the loss from SP- through a θ parameter, allowing for a convex combination. In-situ agrometeorological data were collected at four automatic weather stations in Tensift Watershed in Morocco, including air temperature (Ta), solar radiation (Rs), relative humidity (RH), and wind speed (Ws). The study integrates Priestley-Taylor (PT), Makkink (MK), Hargreaves-Samani (HS), and Abtew (AB), under four scenarios of data availability levels: (1) Ta, Rs and RH; (2) Ta and Rs; (3) only Ta; and (4) only Rs. The investigation begins with quality-controlling the data and studying the driving factors of ETo. Next, the SP models were calibrated using the CMA-ES optimization algorithm. The proposed PINN was trained and evaluated, first, for the equal contribution scenario (θ = 0.5) and then for θ in the interval [0, 1] with a step of 0.2, thus analyzing the impact of θ on the PINN performance. For the equal contribution, the results showed that the integration had improved the PINN performance in all scenarios in terms of the RMSE and R2, surpassing the fully data-driven model (θ = 0) and the baseline model (θ = 1). Additionally, for all θ within the interval [0.2, 0.8], the PINN required less training to reach optimal values. Finally, the optimal θ values were determined for each scenario using CMA-ES and were 0.258, 0.771, 0.7226 and 0.169 for PT, MK, HS and AB, respectively. While PINNs demonstrated a promising approach for accurate ETo estimation and consequently improved water resource management, the study also represents a step towards implementing controlled, trustworthy, and physics-informed AI in environmental science.

Artificial intelligence in surgical medicine: a brief review

The application of artificial intelligence (AI) technology in the medical field, particularly in surgical operations, has evolved from science fiction to a crucial tool. With continuous advancements in computational power and algorithmic technology, AI is reshaping the surgical medicine landscape. From preoperative diagnosis and planning to intraoperative real-time navigation and assistance and postoperative rehabilitation and follow-up management, AI technology has significantly enhanced the precision and safety of surgical procedures. This paper systematically reviews the development and current applications of AI in surgery, focusing on specific case studies of AI in surgical procedures, diagnostic assistance, intraoperative navigation, and postoperative management, highlighting its significant contributions to improving surgical precision and safety. Despite the obvious advantages of AI in improving surgical success, reducing postoperative complications, and accelerating patient recovery, its use in surgery still faces numerous challenges, including its cost-effectiveness, dependency, data privacy and security, clinical integration, and physician training. This review summarizes the current applications of AI in surgical medicine, highlights its benefits and limitations, and discusses the challenges and future directions of integrating AI into surgical practice.

Optimized strategies for developing high-speed muscle activity monitors utilizing multi-resolution energy operator

Introduction: Electromyographic (EMG) activity monitoring constitutes the core of foundational research for the application of EMG signals in medical diagnostics, sports science, and human-machine interaction. However, the current research trend predominantly focuses on the recognition technologies of EMG signals, while the techniques for accurately detecting the onset and offset points of muscle activity-the change-point detection of EMG signals-have not received the necessary attention and thorough investigation. Methods: A novel method for EMG signal activity detection based on a variant version of the Teager-Kaiser energy operator (TKEO), namely the multi-resolution energy operator (MTEO), is proposed. Two strategies for constructing EMG activity monitors using MTEO are presented. One is a threshold-based detector (MEOTD) relying on signal baseline segment information, and the other is a detector mimicking the structure of a convolutional neural network (MEONND) without requiring prior knowledge of the signal. A semi-subjective evaluation model based on the Analytic Hierarchy Process (AHP) is used to evaluate the performance of the monitors on real EMG data. Results and discussion: The results show that the MTEO has stronger preprocessing ability for EMG signals, and that the MTEO-based monitors are more reliable and accurate. In particular, the MEONND can achieve both computational efficiency and accuracy simultaneously. The proposed method for EMG signal activity detection improves both detection quality and efficiency without increasing algorithm complexity. This method can be applied to various fields that involve EMG signal analysis, such as ergonomics, human-machine interaction, and biomedical engineering.

Deep learning-based MVIT-MLKA model for accurate classification of pancreatic lesions: a multicenter retrospective cohort study

BACKGROUND

Accurate differentiation between benign and malignant pancreatic lesions is critical for effective patient management. This study aimed to develop and validate a novel deep learning network using baseline computed tomography (CT) images to predict the classification of pancreatic lesions.

METHODS

This retrospective study included 864 patients (422 men, 442 women) with confirmed histopathological results across three medical centers, forming a training cohort, internal testing cohort, and external validation cohort. A novel hybrid model, Multi-Scale Large Kernel Attention with Mobile Vision Transformer (MVIT-MLKA), was developed, integrating CNN and Transformer architectures to classify pancreatic lesions. The model's performance was compared with traditional machine learning methods and advanced deep learning models. We also evaluated the diagnostic accuracy of radiologists with and without the assistance of the optimal model. Model performance was assessed through discrimination, calibration, and clinical applicability.

RESULTS

The MVIT-MLKA model demonstrated superior performance in classifying pancreatic lesions, achieving an AUC of 0.974 (95% CI 0.967-0.980) in the training set, 0.935 (95% CI 0.915-0.954) in the internal testing set, and 0.924 (95% CI 0.902-0.945) in the external validation set, outperforming traditional models and other deep learning models (P < 0.05). Radiologists aided by the MVIT-MLKA model showed significant improvements in diagnostic accuracy and sensitivity compared to those without model assistance (P < 0.05). Grad-CAM visualization enhanced model interpretability by effectively highlighting key lesion areas.

CONCLUSION

The MVIT-MLKA model efficiently differentiates between benign and malignant pancreatic lesions, surpassing traditional methods and significantly improving radiologists' diagnostic performance. The integration of this advanced deep learning model into clinical practice has the potential to reduce diagnostic errors and optimize treatment strategies.

A review of geospatial exposure models and approaches for health data integration

BACKGROUND

Geospatial methods are common in environmental exposure assessments and increasingly integrated with health data to generate comprehensive models of environmental impacts on public health.

OBJECTIVE

Our objective is to review geospatial exposure models and approaches for health data integration in environmental health applications.

METHODS

We conduct a literature review and synthesis.

RESULTS

First, we discuss key concepts and terminology for geospatial exposure data and models. Second, we provide an overview of workflows in geospatial exposure model development and health data integration. Third, we review modeling approaches, including proximity-based, statistical, and mechanistic approaches, across diverse exposure types, such as air quality, water quality, climate, and socioeconomic factors. For each model type, we provide descriptions, general equations, and example applications for environmental exposure assessment. Fourth, we discuss the approaches used to integrate geospatial exposure data and health data, such as methods to link data sources with disparate spatial and temporal scales. Fifth, we describe the landscape of open-source tools supporting these workflows.

Decoding pathology: the role of computational pathology in research and diagnostics

Traditional histopathology, characterized by manual quantifications and assessments, faces challenges such as low-throughput and inter-observer variability that hinder the introduction of precision medicine in pathology diagnostics and research. The advent of digital pathology allowed the introduction of computational pathology, a discipline that leverages computational methods, especially based on deep learning (DL) techniques, to analyze histopathology specimens. A growing body of research shows impressive performances of DL-based models in pathology for a multitude of tasks, such as mutation prediction, large-scale pathomics analyses, or prognosis prediction. New approaches integrate multimodal data sources and increasingly rely on multi-purpose foundation models. This review provides an introductory overview of advancements in computational pathology and discusses their implications for the future of histopathology in research and diagnostics.

Strategies for generating synthetic computed tomography-like imaging from radiographs: A scoping review

BACKGROUND

Advancements in tomographic medical imaging have revolutionized diagnostics and treatment monitoring by offering detailed 3D visualization of internal structures. Despite the significant value of computed tomography (CT), challenges such as high radiation dosage and cost barriers limit its accessibility, especially in low- and middle-income countries. Recognizing the potential of radiographic imaging in reconstructing CT images, this scoping review aims to explore the emerging field of synthesizing 3D CT-like images from 2D radiographs by examining the current methodologies.

METHODS

A scoping review was carried out following PRISMA-SR guidelines. Eligibility criteria for the articles included full-text articles published up to September 9, 2024, studying methodologies for the synthesis of 3D CT images from 2D biplanar or four-projection x-ray images. Eligible articles were sourced from PubMed MEDLINE, Embase, and arXiv.

RESULTS

76 studies were included. The majority (50.8 %, n = 30) were published between 2010 and 2020 (38.2 %, n = 29) and from 2020 onwards (36.8 %, n = 28), with European (40.8 %, n = 31), North American (26.3 %, n = 20), and Asian (32.9 %, n = 25) institutions being primary contributors. Anatomical regions varied, with 17.1 % (n = 13) of studies not using clinical data. Further, studies focused on the chest (25 %, n = 19), spine and vertebrae (17.1 %, n = 13), coronary arteries (10.5 %, n = 8), and cranial structures (10.5 %, n = 8), among other anatomical regions. Convolutional neural networks (CNN) (19.7 %, n = 15), generative adversarial networks (21.1 %, n = 16) and statistical shape models (15.8 %, n = 12) emerged as the most applied methodologies. A limited number of studies included explored the use of conditional diffusion models, iterative reconstruction algorithms, statistical shape models, and digital tomosynthesis.

CONCLUSION

This scoping review summarizes current strategies and challenges in synthetic imaging generation. The development of 3D CT-like imaging from 2D radiographs could reduce radiation risk while simultaneously addressing financial and logistical obstacles that impede global access to CT imaging. Despite initial promising results, the field encounters challenges with varied methodologies and frequent lack of proper validation, requiring further research to define synthetic imaging's clinical role.

DLPVI: Deep learning framework integrating projection, view-by-view backprojection, and image domains for high- and ultra-sparse-view CBCT reconstruction

This study proposes a deep learning framework, DLPVI, which integrates projection, view-by-view backprojection (VVBP), and image domains to improve the quality of high-sparse-view and ultra-sparse-view cone-beam computed tomography (CBCT) images. The DLPVI comprises a projection domain sub-framework, a VVBP domain sub-framework, and a Transformer-based image domain model. First, full-view projections were restored from sparse-view projections via the projection domain sub-framework, then filtered and view-by-view backprojected to generate VVBP raw data. Next, the VVBP raw data was processed by the VVBP domain sub-framework to suppress residual noise and artifacts, and produce CBCT axial images. Finally, the axial images were further refined using the image domain model. The DLPVI was trained, validated, and tested on CBCT data from 163, 30, and 30 real patients respectively. Quantitative metrics including root-mean-square error (RMSE), peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM) were calculated to evaluate the method performance. The DLPVI was compared with 15 state-of-the-art (SOTA) methods, including 2 projection domain models, 10 image domain models, and 3 projection-image dual-domain frameworks, on 1/8 high-sparse-view and 1/16 ultra-sparse-view reconstruction tasks. Statistical analysis was conducted using the Kruskal-Wallis test, followed by the post-hoc Dunn's test. Experimental results demonstrated that the DLPVI outperformed all 15 SOTA methods for both tasks, with statistically significant improvements (p < 0.05 in Kruskal-Wallis test and p < 0.05/15 in Dunn's test). The proposed DLPVI effectively improves the quality of high- and ultra-sparse-view CBCT images.

Development of a Novel Nomogram Based on Ultrasonic Radiomics for Predicting Intrauterine Pregnancy After Frozen Embryo Transfer Cycle

OBJECTIVES

This study aimed to develop a nomogram for predicting intrauterine pregnancy after an in vitro frozen embryo transfer cycle using endometrial ultrasound radiomics.

METHODS

A total of 211 patients who underwent ultrasound examination on the day of endometrial transformation before the frozen embryo transfer cycle were enrolled. The patients were divided into an intrauterine pregnancy group and a pregnancy failure group based on ultrasound results. Clinical characteristics and radiomic features were analyzed using univariate and multivariate logistic regression analyses. A nomogram prediction model was established based on radiomic signatures and significant clinical factors. The model's robustness was assessed in training and external validation cohorts.

RESULTS

Nine radiomic features were selected using least absolute shrinkage and selection operator (LASSO), and the radiomics score (Rad-score) was calculated as the sum of each feature multiplied by the nonzero coefficient from LASSO. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve based on the Rad-score was 0.72, 0.65, and 0.69 in the training, validation, and combined cohorts, respectively. To improve diagnostic efficiency, the Rad-score was further integrated with clinical factors to form a novel predictive nomogram. The results indicated that the AUC increased to 0.81, 0.67, and 0.77 in the training, validation, and combined cohorts, respectively. Decision curve analysis showed that the radiomics nomogram was clinically useful.

CONCLUSION

The radiomics and clinical predictive nomogram can effectively predict intrauterine pregnancy after in vitro frozen embryo transfer and can be further applied in clinical strategy.

DDoCT: Morphology preserved dual-domain joint optimization for fast sparse-view low-dose CT imaging

Computed tomography (CT) is continuously becoming a valuable diagnostic technique in clinical practice. However, the radiation dose exposure in the CT scanning process is a public health concern. Within medical diagnoses, mitigating the radiation risk to patients can be achieved by reducing the radiation dose through adjustments in tube current and/or the number of projections. Nevertheless, dose reduction introduces additional noise and artifacts, which have extremely detrimental effects on clinical diagnosis and subsequent analysis. In recent years, the feasibility of applying deep learning methods to low-dose CT (LDCT) imaging has been demonstrated, leading to significant achievements. This article proposes a dual-domain joint optimization LDCT imaging framework (termed DDoCT) which uses noisy sparse-view projection to reconstruct high-performance CT images with joint optimization in projection and image domains. The proposed method not only addresses the noise introduced by reducing tube current, but also pays special attention to issues such as streak artifacts caused by a reduction in the number of projections, enhancing the applicability of DDoCT in practical fast LDCT imaging environments. Experimental results have demonstrated that DDoCT has made significant progress in reducing noise and streak artifacts and enhancing the contrast and clarity of the images.

Network embedding: The bridge between water distribution network hydraulics and machine learning

Machine learning has been increasingly used to solve management problems of water distribution networks (WDNs). A critical research gap, however, remains in the effective incorporation of WDN hydraulic characteristics in machine learning. Here we present a new water distribution network embedding (WDNE) method that transforms the hydraulic relationships of WDN topology into a vector form to be best suited for machine learning algorithms. The nodal relationships are characterized by local structure, global structure and attribute information. A conjoint use of two deep auto-encoder embedding models ensures that the hydraulic relationships and attribute information are simultaneously preserved and are effectively utilized by machine learning models. WDNE provides a new way to bridge WDN hydraulics with machine learning. It is first applied to a pipe burst localization problem. The results show that it can increase the performance of machine learning algorithms, and enable a lightweight machine learning algorithm to achieve better accuracy with less training data compared with a deep learning method reported in the literature. Then, applications in node grouping problems show that WDNE enables machine learning algorithms to make use of WDN hydraulic information, and integrates WDN structural relationships to achieve better grouping results. The results highlight the potential of WDNE to enhance WDN management by improving the efficiency of machine learning models and broadening the range of solvable problems. Codes are available at https://github.com/ZhouGroupHFUT/WDNE.

Forecasting migraine attacks by managing daily lifestyle: a systematic review as a basis to develop predictive algorithms

Recent studies attempting to develop forecasting models for new migraine attack onsets, overviewing triggers and protectors, are encouraging but necessitate further improvements to produce forecasting models with high predictive accuracy. This updated review of available data holds the potential to enhance the precision of predicting a migraine attack. This study aims to evaluate how lifestyle factors affect migraine frequency in adults with episodic migraine, to contribute to the development of an effective migraine forecasting model. A comprehensive search of databases, including PubMed, ScienceDirect, Google Scholar, and Scopus, was conducted considering studies published from 2018 to December 2023, following the PRISMA guidelines. Critical evaluation was conducted using the Joanna Briggs Institute's appraisal tools. The lifestyle modifications examined in this review included dietary habits, physical activity, sleep, and stress management. Of the 36 studies analysed, which predominantly exhibited low to moderate bias, 18 investigated dietary habits, 7 explored physical activity, 11 assessed stress management, and 5 investigated sleep patterns. The evidence from these 36 studies advocates for the implementation of lifestyle modifications in migraine management. Furthermore, these outcomes carry valuable implications from the standpoint of migraine forecasting models. The most consistent results were observed in relation to specific diets, dietary supplements, and physical activity. Although trends were noted in stress management and sleep, further research is required to elucidate their influence on migraine frequency and their integration into a migraine forecasting model. This study is registered on PROSPERO (ID CRD42024511300).

Using a Deep Learning Model to Predict Postoperative Visual Outcomes of Idiopathic Epiretinal Membrane Surgery

PURPOSE

This study assessed the performance of various deep learning models in predicting the postoperative outcomes of idiopathic epiretinal membrane (ERM) surgery based on preoperative optical coherence tomography (OCT) images.

DESIGN

Validation of algorithms to predict the outcomes of ERM surgery based on OCT data.

METHODS

Internal training and validation were performed using 1,392 OCT images from 696 eyes. External testing was performed using 152 OCT images from 76 eyes. This study assessed three deep learning models, including Inception-v3, ResNet-101, and VGG-19. Grad-CAM was employed for hotspot analysis. The dataset was split into a training set (80%) and a validation set (20%). Subjects presenting an improvement of ≥2 lines on the Snellen chart at 1-year postsurgery were classified as pronounced visual improvement, whereas those presenting an improvement of <2 lines were classified as limited visual improvement. Using an external test dataset, we compared assessments by seven ophthalmologists with the prediction of deep learning model. The main outcome measures were recall, specificity, precision, F1 score, accuracy, and area under the receiver operating characteristic curve (AUROC).

RESULTS

ResNet-101 achieved the best overall performance, as evidenced by the following metrics: recall (0.90), specificity (0.90), precision (0.91), F1-score (0.90), accuracy (0.90), and AUROC (0.97). In Grad-CAM heatmap analysis, the logic of ResNet-101 closely resembled that of clinical physicians. Overall, the performance of this deep learning model was significantly better than that of general ophthalmologists and non-retina specialists and was slightly superior to that of retina specialists.

CONCLUSIONS

Deep learning based on preoperative OCT images proved highly effective in predicting the outcomes of ERM surgery and elucidating the structural mechanisms underlying the phenomena observed in OCT images.

Multiscale Modeling and Simulation of Zwitterionic Anti-fouling Materials

Zwitterionic materials with cationic and anionic moieties in the same chain, being electrically neutral, have excellent hydrophilicity, stability, biocompatibility, and outstanding anti-biofouling performance. Because of their unique properties, zwitterionic materials are widely applied to membrane separation, drug delivery, surface coating, etc. However, what is the root of their unique properties? It is necessary to study the structure-property relationships of zwitterionic compounds to guide the design and development of zwitterionic materials. Modeling and simulation methods are considered to be efficient technologies for understanding advanced materials in principle. This Review systematically summarizes the computational exploration of zwitterionic materials in recent years. First, the classes of zwitterionic materials are summarized. Second, the different scale simulation methods are introduced briefly. To reveal the structure-property relationships of zwitterionic materials, multiscale modeling and simulation studies at different spatial and temporal scales are summarized. The study results indicated that the strong electrostatic interaction between zwitterions with water molecules promotes formation of a stable hydration layer, namely, superhydrophilicity, leading to the excellent anti-fouling properties. Finally, we offer our viewpoint on the development and application of simulation techniques on zwitterionic materials exploration in the future. This work establishes a bridge from atomic and molecular scales to mesoscopic and macroscopic scales and helps to provide an in-depth understanding of the structure-property relationships of zwitterionic materials.

Computer-assisted prescription of erythropoiesis-stimulating agents in patients undergoing maintenance hemodialysis: a randomized control trial for artificial intelligence model selection

Objective

Machine learning (ML) algorithms are promising tools for managing anemia in hemodialysis (HD) patients. However, their efficacy in predicting erythropoiesis-stimulating agents (ESAs) doses remains uncertain. This study aimed to evaluate the effectiveness of a contemporary artificial intelligence (AI) model in prescribing ESA doses compared to physicians for HD patients.

Materials and Methods

This double-blinded control trial randomized participants into traditional doctor (Dr) and AI groups. In the Dr group, doses of ESA were determined by following clinical guideline recommendations, while in the AI group, they were predicted by the developed models named Random effects (REEM) trees, Mixed-effect random forest (MERF), Long short-term memory (LSTM) networks-I, and LSTM-II. The primary outcome was the capability to maintain patients' hemoglobin (Hb) value near 11 g/dL with a margin of 0.25 g/dL after treating the suggested ESA, with the secondary outcome being Hb value between 10 and 12 g/dL.

Results

A total of 124 participants were enrolled, with 104 completing the study. The mean Hb values were 10.8 and 10.9 g/dL in the AI and Dr groups, respectively, with 69.7% and 73.5% of participants in the respective groups maintaining Hb levels between 10 and 12 g/dL. Only the REEM trees model passed the non-inferiority test for the primary outcome with a margin of 0.25 g/dL and the secondary outcome with a margin of 15%. There was no difference in severe adverse events between the 2 groups.

Conclusion

The REEM trees AI model demonstrated non-inferiority to physicians in prescribing ESA doses for HD patients, maintaining Hb levels within the therapeutic target.

ClinicalTrialsgov Identifier

NCT04185519.

Radiogenomic explainable AI with neural ordinary differential equation for identifying post-SRS brain metastasis radionecrosis

BACKGROUND

Stereotactic radiosurgery (SRS) is widely used for managing brain metastases (BMs), but an adverse effect, radionecrosis, complicates post-SRS management. Differentiating radionecrosis from tumor recurrence non-invasively remains a major clinical challenge, as conventional imaging techniques often necessitate surgical biopsy for accurate diagnosis. Machine learning and deep learning models have shown potential in distinguishing radionecrosis from tumor recurrence. However, their clinical adoption is hindered by a lack of explainability, limiting understanding and trust in their diagnostic decisions.

PURPOSE

To utilize a novel neural ordinary differential equation (NODE) model for discerning BM post-SRS radionecrosis from recurrence. This approach integrates image-deep features, genomic biomarkers, and non-image clinical parameters within a synthesized latent feature space. The trajectory of each data sample towards the diagnosis decision can be visualized within this feature space, offering a new angle on radiogenomic data analysis foundational for AI explainability.

METHODS

By hypothesizing that deep feature extraction can be modeled as a spatiotemporally continuous process, we designed a novel model based on heavy ball NODE (HBNODE) in which deep feature extraction was governed by a second-order ODE. This approach enabled tracking of deep neural network (DNN) behavior by solving the HBNODE and observing the stepwise derivative evolution. Consequently, the trajectory of each sample within the Image-Genomic-Clinical (I-G-C) space became traceable. A decision-making field (F) was reconstructed within the feature space, with its gradient vectors directing the data samples' trajectories and intensities showing the potential. The evolution of F reflected the cumulative feature contributions at intermediate states to the final diagnosis, enabling quantitative and dynamic comparisons of the relative contribution of each feature category over time. A velocity curve was designed to determine key intermediate states (locoregional ∇F = 0) that are most predictive. Subsequently, a non-parametric model aggregated the optimal solutions from these key states to predict outcomes. Our dataset included 90 BMs from 62 NSCLC patients, and 3-month post-SRS T1+c MR image features, seven NSCLC genomic features, and seven clinical features were analyzed. An 8:2 train/test assignment was employed, and five independent models were trained to ensure robustness. Performance was benchmarked in sensitivity, specificity, accuracy, and ROCAUC, and results were compared against (1) a DNN using only image-based features, and (2) a combined "I+G+C" features without the HBNODE model.

RESULTS

The temporal evolution of gradient vectors and potential fields in F suggested that clinical features contribute the most during the initial stages of the HBNODE implementation, followed by imagery features taking dominance in the latter ones, while genomic features contribute the least throughout the process. The HBNODE model successfully identified and assembled key intermediate states, exhibiting competitive performance with an ROCAUC of 0.88 ± 0.04, sensitivity of 0.79 ± 0.02, specificity of 0.86 ± 0.01, and accuracy of 0.84 ± 0.01, where the uncertainties represent standard deviations. For comparison, the image-only DNN model achieved an ROCAUC of 0.71 ± 0.05 and sensitivity of 0.66 ± 0.32 (p = 0.086), while the "I+G+C" model without HBNODE reported an ROCAUC of 0.81 ± 0.02 and sensitivity of 0.58 ± 0.11 (p = 0.091).

CONCLUSION

The HBNODE model effectively identifies BM radionecrosis from recurrence, enhancing explainability within XAI frameworks. Its performance encourages further exploration in clinical settings and suggests potential applicability across various XAI domains.

Machine Learning to Predict Outcomes of Fetal Cardiac Disease: A Pilot Study

Prediction of outcomes following a prenatal diagnosis of congenital heart disease (CHD) is challenging. Machine learning (ML) algorithms may be used to reduce clinical uncertainty and improve prognostic accuracy. We performed a pilot study to train ML algorithms to predict postnatal outcomes based on clinical data. Specific objectives were to predict (1) in utero or neonatal death, (2) high-acuity neonatal care and (3) favorable outcomes. We included all fetuses with cardiac disease at Sunnybrook Health Sciences Centre, Toronto, Canada, from 2012 to 2021. Prediction models were created using the XgBoost algorithm (tree-based) with fivefold cross-validation. Among 211 cases of fetal cardiac disease, 61 were excluded (39 terminations, 21 lost to follow-up, 1 isolated arrhythmia), leaving a cohort of 150 fetuses. Fifteen (10%) demised (10 neonates) and 65 (48%) of live births required high acuity neonatal care. Of those with clinical follow-up, 60/87 (69%) had a favorable outcome. Prediction models for fetal or neonatal death, high acuity neonatal care and favorable outcome had AUCs of 0.76, 0.84 and 0.73, respectively. The most important predictors for death were the presence of non-cardiac abnormalities combined with more severe CHD. High acuity of postnatal care was predicted by anti Ro antibody and more severe CHD. Favorable outcome was most predicted by no right heart disease combined with genetic abnormalities, and maternal medications. Prediction models using ML provide good discrimination of key prenatal and postnatal outcomes among fetuses with congenital heart disease.

ChatGPT in Oncology Diagnosis and Treatment: Applications, Legal and Ethical Challenges

PURPOSE OF REVIEW

This study aims to systematically review the trajectory of artificial intelligence (AI) development in the medical field, with a particular emphasis on ChatGPT, a cutting-edge tool that is transforming oncology's diagnosis and treatment practices.

RECENT FINDINGS

Recent advancements have demonstrated that ChatGPT can be effectively utilized in various areas, including collecting medical histories, conducting radiological & pathological diagnoses, generating electronic medical record (EMR), providing nutritional support, participating in Multidisciplinary Team (MDT) and formulating personalized, multidisciplinary treatment plans. However, some significant challenges related to data privacy and legal issues that need to be addressed for the safe and effective integration of ChatGPT into clinical practice. ChatGPT, an emerging AI technology, opens up new avenues and viewpoints for oncology diagnosis and treatment. If current technological and legal challenges can be overcome, ChatGPT is expected to play a more significant role in oncology diagnosis and treatment in the future, providing better treatment options and improving the quality of medical services.

Methodology and development of a machine learning probability calculator: Data heterogeneity limits ability to predict recurrence after arthroscopic Bankart repair

PURPOSE

The aim of this study was to develop and train a machine learning (ML) algorithm to create a clinical decision support tool (i.e., ML-driven probability calculator) to be used in clinical practice to estimate recurrence rates following an arthroscopic Bankart repair (ABR).

METHODS

Data from 14 previously published studies were collected. Inclusion criteria were (1) patients treated with ABR without remplissage for traumatic anterior shoulder instability and (2) a minimum of 2 years follow-up. Risk factors associated with recurrence were identified using bivariate logistic regression analysis. Subsequently, four ML algorithms were developed and internally validated. The predictive performance was assessed using discrimination, calibration and the Brier score.

RESULTS

In total, 5591 patients underwent ABR with a recurrence rate of 15.4% (n = 862). Age <35 years, participation in contact and collision sports, bony Bankart lesions and full-thickness rotator cuff tears increased the risk of recurrence (all p < 0.05). A single shoulder dislocation (compared to multiple dislocations) lowered the risk of recurrence (p < 0.05). Due to the unavailability of certain variables in some patients, a portion of the patient data had to be excluded before pooling the data set to create the algorithm. A total of 797 patients were included providing information on risk factors associated with recurrence. The discrimination (area under the receiver operating curve) ranged between 0.54 and 0.57 for prediction of recurrence.

CONCLUSION

ML was not able to predict the recurrence following ABR with the current available predictors. Despite a global coordinated effort, the heterogeneity of clinical data limited the predictive capabilities of the algorithm, emphasizing the need for standardized data collection methods in future studies.

LEVEL OF EVIDENCE

Level IV, retrospective cohort study.

Self-Supervised Multi-Scale Multi-Modal Graph Pool Transformer for Sellar Region Tumor Diagnosis

The sellar region tumor is a brain tumor that only exists in the brain sellar, which affects the central nervous system. The early diagnosis of the sellar region tumor subtypes helps clinicians better understand the best treatment and recovery of patients. Magnetic resonance imaging (MRI) has proven to be an effective tool for the early detection of sellar region tumors. However, the existing sellar region tumor diagnosis still remains challenging due to the small amount of dataset and data imbalance. To overcome these challenges, we propose a novel self-supervised multi-scale multi-modal graph pool Transformer (MMGPT) network that can enhance the multi-modal fusion of small and imbalanced MRI data of sellar region tumors. MMGPT can strengthen feature interaction between multi-modal images, which makes our model more robust. A contrastive learning equipped auto-encoder (CAE) via self-supervised learning (SSL) is adopted to learn more detailed information between different samples. The proposed CAE transfers the pre-trained knowledge to the downstream tasks. Finally, a hybrid loss is equipped to relieve the performance degradation caused by data imbalance. The experimental results show that the proposed method outperforms state-of-the-art methods and obtains higher accuracy and AUC in the classification of sellar region tumors.

Soft sensor modeling using deep learning with maximum relevance and minimum redundancy for quality prediction of industrial processes

Deep learning techniques such as autoencoder (AE) and stacked autoencoders (SAE) have gained growing popularity in soft sensor applications. However, they often encounter several disadvantages, such as poor correlations between the extracted hidden features and the quality variable, inevitable information loss resulting from the layer-wise feature extraction, and information redundancy between the hidden features. Thus, a maximal relevance and minimal redundancy-based representation learning (MRMRRL) is proposed for quality prediction of industrial processes. MRMRRL obtains significant performance enhancement by combining the merits from three channels. First, the relevance between the input and output variable is taken into account for enabling quality-relevant feature extraction. Second, kernel principal component analysis (KPCA) is performed on the feature space of AE hidden layer for achieving redundancy reduction of hidden features. Third, inputs with high quality relevance are fed to the extension layer nodes for enabling information compensation. The experimental results show that, compared with the baseline SAE, the performance of MRMRRL is improved by about 37 % and 38 % for two application examples, respectively. Significant performance enhancement of MRMRRL can be also obtained compared to several state-of-the-art deep learning soft sensors. These results demonstrate the effectiveness and superiority of the proposed MRMRRL approach in extracting quality-related hidden features while ensuring automatic elimination of hidden feature redundancy and maintaining structure simplicity.

Multi-region nomogram for predicting central lymph node metastasis in papillary thyroid carcinoma using multimodal imaging: A multicenter study

BACKGROUND AND OBJECTIVE

Central lymph node metastasis (CLNM) is associated with high recurrence rate and low survival in patients with papillary thyroid carcinoma (PTC). However, there is no satisfactory model to predict CLNM in PTC. This study aimed to integrate PTC deep learning feature based on ultrasound (US) images, fat radiomics features based on computed tomography (CT) images and clinical characteristics to construct a multimodal and multi-region nomogram (MMRN) for predicting the CLNM in PTC.

METHODS

We enrolled 661 patients diagnosed with PTC by thyroidectomy from two independent centers. Patients were divided into the primary cohort, internal test cohort (ITC), and external test cohort (ETC), and collected their US images and CT images. Resnet50 was employed to predict the CLNM status of PTC based on US images. Using radiomics feature extraction methods to extract fat radiomics features from CT images. Feature selection was conducted using the least absolute shrinkage and selection operator (LASSO) regression. The predictive performance of the MMRN was evaluated using five-fold cross-validation. We comprehensively evaluated the DLRCN and compared it with five radiologists.

RESULTS

In the ITC and ETC, the area under the curves (AUCs) of MMRN were 0.829 (95 % CI: 0.822, 0.835) and 0.818 (95 % CI: 0.808, 0.828). The calibration curve revealed good predictive accuracy between the actual probability and predicted probability (P > 0.05). Decision curve analysis showed that the MMRN was clinically useful. Under equal specificity or sensitivity, the performance of MMRN increased by 6.5 % or 2.9 % compared to radiologist assessments. The incorporation of fat radiomics features led to significant net reclassification improvement (NRI) and integrated discrimination improvement (IDI) (NRI=0.174, P < 0.05, IDI=0.035, P < 0.05).

CONCLUSION

The MMRN demonstrated good performance in predicting the CLNM status of PTC, which was comparable to radiologist assessments. The fat radiomics features exhibited supplementary value for predicting CLNM in PTC.

Improving cross-domain generalizability of medical image segmentation using uncertainty and shape-aware continual test-time domain adaptation

Continual test-time adaptation (CTTA) aims to continuously adapt a source-trained model to a target domain with minimal performance loss while assuming no access to the source data. Typically, source models are trained with empirical risk minimization (ERM) and assumed to perform reasonably on the target domain to allow for further adaptation. However, ERM-trained models often fail to perform adequately on a severely drifted target domain, resulting in unsatisfactory adaptation results. To tackle this issue, we propose a generalizable CTTA framework. First, we incorporate domain-invariant shape modeling into the model and train it using domain-generalization (DG) techniques, promoting target-domain adaptability regardless of the severity of the domain shift. Then, an uncertainty and shape-aware mean teacher network performs adaptation with uncertainty-weighted pseudo-labels and shape information. As part of this process, a novel uncertainty-ranked cross-task regularization scheme is proposed to impose consistency between segmentation maps and their corresponding shape representations, both produced by the student model, at the patch and global levels to enhance performance further. Lastly, small portions of the model's weights are stochastically reset to the initial domain-generalized state at each adaptation step, preventing the model from 'diving too deep' into any specific test samples. The proposed method demonstrates strong continual adaptability and outperforms its peers on five cross-domain segmentation tasks, showcasing its effectiveness and generalizability.

Genomic prediction with NetGP based on gene network and multi-omics data in plants

Genomic selection (GS) is a new breeding strategy. Generally, traditional methods are used for predicting traits based on the whole genome. However, the prediction accuracy of these models remains limited because they cannot fully reflect the intricate nonlinear interactions between genotypes and traits. Here, a novel single nucleotide polymorphism (SNP) feature extraction technique based on the Pearson-Collinearity Selection (PCS) is firstly presented and improves prediction accuracy across several known models. Furthermore, gene network prediction model (NetGP) is a novel deep learning approach designed for phenotypic prediction. It utilizes transcriptomic dataset (Trans), genomic dataset (SNP) and multi-omics dataset (Trans + SNP). The NetGP model demonstrated better performance compared to other models in genomic predictions, transcriptomic predictions and multi-omics predictions. NetGP multi-omics model performed better than independent genomic or transcriptomic prediction models. Prediction performance evaluations using several other plants' data showed good generalizability for NetGP. Taken together, our study not only offers a novel and effective tool for plant genomic selection but also points to new avenues for future plant breeding research.

Study on Novel Surface Defect Detection Methods for Aeroengine Turbine Blades Based on the LFD-YOLO Framework

This study proposes a novel defect detection method to address the low accuracy and insufficient efficiency encountered during surface defect detection on aeroengine turbine blades (ATBs). The proposed approach employs the LDconv model to adjust the size and shape of convolutional kernels dynamically, integrates the deformable attention mechanism (DAT) to capture minute defect features effectively, and uses Focaler-CIoU to optimize the bounding box loss function of the detection network. Our approaches collectively provide precise detection of surface defects on ATBs. The results show that the proposed method achieves a mean average precision (mAP0.5) of 96.2%, an F-measure of 96.7%, and an identification rate (Ir) of 98.8%, while maintaining a detection speed of over 25 images per second. The proposed method meets the stringent requirements for accuracy and real-time performance in ATB surface defect detection.

Artificial Intelligence in Prosthodontics

Artificial intelligence (AI) has significantly impacted numerous industries, including health care, dentistry, and specifically prosthodontics. This review focuses on AI's role in prosthodontics, detailing its use in diagnosis, design, and manufacturing. AI-driven systems analyze intraoral scans, improve prosthetic planning, and aid in robotic procedures. Emerging technologies, such as generative AI for prosthetic design and AI-driven material innovation, are discussed alongside the ethical and regulatory challenges facing broader adoption. The review highlights AI's potential to transform prosthodontic workflows, facilitating more accurate, efficient, and personalized care, while also pointing to future developments such as real-time monitoring and enhanced collaboration platforms.

Multimodal Ensemble Fusion Deep Learning Using Histopathological Images and Clinical Data for Glioma Subtype Classification

Glioma is the most common malignant tumor of the central nervous system, and diffuse Glioma is classified as grades II-IV by world health organization (WHO). In the the cancer genome atlas (TCGA) Glioma dataset, grade II and III Gliomas are classified as low-grade glioma (LGG), and grade IV Gliomas as glioblastoma multiforme (GBM). In clinical practice, the survival and treatment process with Glioma patients depends on properly diagnosing the subtype. With this background, there has been much research on Glioma over the years. Among these researches, the origin and evolution of whole slide images (WSIs) have led to many attempts to support diagnosis by image analysis. On the other hand, due to the disease complexities of Glioma patients, multimodal analysis using various types of data rather than a single data set has been attracting attention. In our proposed method, multiple deep learning models are used to extract features from histopathology images, and the features of the obtained images are concatenated with those of the clinical data in a fusion approach. Then, we perform patch-level classification by machine learning (ML) using the concatenated features. Based on the performances of the deep learning models, we ensemble feature sets from top three models and perform further classifications. In the experiments with our proposed ensemble fusion AI (EFAI) approach using WSIs and clinical data of diffuse Glioma patients on TCGA dataset, the classification accuracy of the proposed multimodal ensemble fusion method is 0.936 with an area under the curve (AUC) value of 0.967 when tested on a balanced dataset of 240 GBM, 240 LGG patients. On an imbalanced dataset of 141 GBM, 242 LGG patients the proposed method obtained the accuracy of 0.936 and AUC of 0.967. Our proposed ensemble fusion approach significantly outperforms the classification using only histopathology images alone with deep learning models. Therefore, our approach can be used to support the diagnosis of Glioma patients and can lead to better diagnosis.

Ratiometric, 3D Fluorescence Spectrum with Abundant Information for Tetracyclines Discrimination via Dual Biomolecules Recognition and Deep Learning

Tetracyclines are widely used in bacteria infection treatment, while the subtle chemical differences between tetracyclines make it a challenge to accurate discrimination via biosensors. A 3D fluorescence spectrum can provide fingerprint structure information for many analytes, but a single probe-based method is prone to information overlap. Here, aptamers are first reported to obtain abundant information in a ratiometric, 3D fluorescence spectrum for deep learning to accurately discriminate tetracyclines. So, each tetracycline can be related to a distinct, ratiometric, 3D fluorescence spectrum via the strategy of dual biomolecules recognition. One artificial neural network model can efficiently treat this fingerprint information, and the qualitative/quantitative analysis of tetracyclines is successfully realized. The proposed dual biomolecule recognition strategy has been demonstrated to show a higher accuracy than a conventional single probe method. So, the ratiometric 3D fluorescence spectrum can enrich the fingerprint information for deep learning, providing a new strategy for 3D fluorescence-based analytes discrimination.

Deep learning analysis for rheumatologic imaging: current trends, future directions, and the role of human

Rheumatic diseases, such as rheumatoid arthritis (RA), osteoarthritis (OA), and spondyloarthritis (SpA), present diagnostic and management challenges due to their impact on connective tissues and the musculoskeletal system. Traditional imaging techniques, including plain radiography, ultrasounds, computed tomography, and magnetic resonance imaging (MRI), play a critical role in diagnosing and monitoring these conditions, but face limitations like inter-observer variability and time-consuming assessments. Recently, deep learning (DL), a subset of artificial intelligence, has emerged as a promising tool for enhancing medical imaging analysis. Convolutional neural networks, a DL model type, have shown great potential in medical image classification, segmentation, and anomaly detection, often surpassing human performance in tasks like tumor identification and disease severity grading. In rheumatology, DL models have been applied to plain radiography, ultrasounds, and MRI for assessing joint damage, synovial inflammation, and disease progression in RA, OA, and SpA patients. Despite the promise of DL, challenges such as data bias, limited explainability, and the need for large annotated datasets remain significant barriers to its widespread adoption. Furthermore, human oversight and value judgment are essential for ensuring the ethical use and effective implementation of DL in clinical settings. This review provides a comprehensive overview of DL's applications in rheumatologic imaging and explores its future potential in enhancing diagnosis, treatment decisions, and personalized medicine.

Mapping conformational landscape in protein folding: Benchmarking dimensionality reduction and clustering techniques on the Trp-Cage mini-protein

Quantitative characterization of protein conformational landscapes is a computationally challenging task due to their high dimensionality and inherent complexity. In this study, we systematically benchmark several widely used dimensionality reduction and clustering methods to analyze the conformational states of the Trp-Cage mini-protein, a model system with well-documented folding dynamics. Dimensionality reduction techniques, including Principal Component Analysis (PCA), Time-lagged Independent Component Analysis (TICA), and Variational Autoencoders (VAE), were employed to project the high-dimensional free energy landscape onto 2D spaces for visualization. Additionally, clustering methods such as K-means, hierarchical clustering, HDBSCAN, and Gaussian Mixture Models (GMM) were used to identify discrete conformational states directly in the high-dimensional space. Our findings reveal that density-based clustering approaches, particularly HDBSCAN, provide physically meaningful representations of free energy minima. While highlighting the strengths and limitations of each method, our study underscores that no single technique is universally optimal for capturing the complex folding pathways, emphasizing the necessity for careful selection and interpretation of computational methods in biomolecular simulations. These insights will contribute to refining the available tools for analyzing protein conformational landscapes, enabling a deeper understanding of folding mechanisms and intermediate states.

RNA structure prediction using deep learning - A comprehensive review

In computational biology, accurate RNA structure prediction offers several benefits, including facilitating a better understanding of RNA functions and RNA-based drug design. Implementing deep learning techniques for RNA structure prediction has led tremendous progress in this field, resulting in significant improvements in prediction accuracy. This comprehensive review aims to provide an overview of the diverse strategies employed in predicting RNA secondary structures, emphasizing deep learning methods. The article categorizes the discussion into three main dimensions: feature extraction methods, existing state-of-the-art learning model architectures, and prediction approaches. We present a comparative analysis of various techniques and models highlighting their strengths and weaknesses. Finally, we identify gaps in the literature, discuss current challenges, and suggest future approaches to enhance model performance and applicability in RNA structure prediction tasks. This review provides a deeper insight into the subject and paves the way for further progress in this dynamic intersection of life sciences and artificial intelligence.