Romiyal George, Sathiyamohan Nishankar, Selvarajah Thuseethan
et al.
Federated learning has emerged as a privacy-preserving and efficient approach for deploying intelligent agricultural solutions. Accurate edge-based diagnosis across geographically dispersed farms is crucial for recognising tomato diseases in sustainable farming. Traditional centralised training aggregates raw data on a central server, leading to communication overhead, privacy risks and latency. Meanwhile, edge devices require lightweight networks to operate effectively within limited resources. In this paper, we propose U-FedTomAtt, an ultra-lightweight federated learning framework with attention for tomato disease recognition in resource-constrained and distributed environments. The model comprises only 245.34K parameters and 71.41 MFLOPS. First, we propose an ultra-lightweight neural network with dilated bottleneck (DBNeck) modules and a linear transformer to minimise computational and memory overhead. To mitigate potential accuracy loss, a novel local-global residual attention (LoGRA) module is incorporated. Second, we propose the federated dual adaptive weight aggregation (FedDAWA) algorithm that enhances global model accuracy. Third, our framework is validated using three benchmark datasets for tomato diseases under simulated federated settings. Experimental results show that the proposed method achieves 0.9910% and 0.9915% Top-1 accuracy and 0.9923% and 0.9897% F1-scores on SLIF-Tomato and PlantVillage tomato datasets, respectively.
The lungs are the essential organs of respiration, and this system is significant in the carbon dioxide and exchange between oxygen that occurs in human life. However, several lung diseases, which include pneumonia, tuberculosis, COVID-19, and lung cancer, are serious healthiness challenges and demand early and precise diagnostics. The methodological study has proposed a new deep learning framework called NASNet-ViT, which effectively incorporates the convolution capability of NASNet with the global attention mechanism capability of Vision Transformer ViT. The proposed model will classify the lung conditions into five classes: Lung cancer, COVID-19, pneumonia, TB, and normal. A sophisticated multi-faceted preprocessing strategy called MixProcessing has been used to improve diagnostic accuracy. This preprocessing combines wavelet transform, adaptive histogram equalization, and morphological filtering techniques. The NASNet-ViT model performs at state of the art, achieving an accuracy of 98.9%, sensitivity of 0.99, an F1-score of 0.989, and specificity of 0.987, outperforming other state of the art architectures such as MixNet-LD, D-ResNet, MobileNet, and ResNet50. The model's efficiency is further emphasized by its compact size, 25.6 MB, and a low computational time of 12.4 seconds, hence suitable for real-time, clinically constrained environments. These results reflect the high-quality capability of NASNet-ViT in extracting meaningful features and recognizing various types of lung diseases with very high accuracy. This work contributes to medical image analysis by providing a robust and scalable solution for diagnostics in lung diseases.
Brain diseases, such as Alzheimer's disease and brain tumors, present profound challenges due to their complexity and societal impact. Recent advancements in brain foundation models have shown significant promise in addressing a range of brain-related tasks. However, current brain foundation models are limited by task and data homogeneity, restricted generalization beyond segmentation or classification, and inefficient adaptation to diverse clinical tasks. In this work, we propose SAM-Brain3D, a brain-specific foundation model trained on over 66,000 brain image-label pairs across 14 MRI sub-modalities, and Hypergraph Dynamic Adapter (HyDA), a lightweight adapter for efficient and effective downstream adaptation. SAM-Brain3D captures detailed brain-specific anatomical and modality priors for segmenting diverse brain targets and broader downstream tasks. HyDA leverages hypergraphs to fuse complementary multi-modal data and dynamically generate patient-specific convolutional kernels for multi-scale feature fusion and personalized patient-wise adaptation. Together, our framework excels across a broad spectrum of brain disease segmentation and classification tasks. Extensive experiments demonstrate that our method consistently outperforms existing state-of-the-art approaches, offering a new paradigm for brain disease analysis through multi-modal, multi-scale, and dynamic foundation modeling.
Progressive neurodegenerative diseases, including Alzheimer's disease (AD), multiple sclerosis (MS), Parkinson's disease (PD), and amyotrophic lateral sclerosis (ALS), exhibit complex, nonlinear trajectories that challenge deterministic modeling. Traditional time-domain analyses of multiomic and neuroimaging data often fail to capture hidden oscillatory patterns, limiting predictive accuracy. We propose a theoretical mathematical framework that transforms time-series data into frequency or s-domain using Fourier and Laplace transforms, models neuronal dynamics via Hamiltonian formulations, and employs quantum-classical hybrid computing with variational quantum eigensolvers (VQE) for enhanced pattern detection. This theoretical construct serves as a foundation for future empirical works in quantum-enhanced analysis of neurodegenerative diseases. We extend this to quaternionic representations with three imaginary axes ($i, j, k$) to model multistate Hamiltonians in multifaceted disorders, drawing from quantum neuromorphic computing to capture entangled neural dynamics \citep{Pehle2020, Emani2019}. This approach leverages quantum advantages in handling high-dimensional amplitude-phase data, enabling outlier detection and frequency signature analysis. Potential clinical applications include identifying high-risk patients with rapid progression or therapy resistance using s-domain biomarkers, supported by quantum machine learning (QML) precedents achieving up to 99.89% accuracy in Alzheimer's classification \citep{Belay2024, Bhowmik2025}. This framework aims to lay the groundwork for redefining precision medicine for neurodegenerative diseases through future validations.
Maryam Nurhuda, Ken-ichi Otake, Susumu Kitagawa
et al.
Human breath contains over 3000 volatile organic compounds, abnormal concentrations of which can indicate the presence of certain diseases. Recently, metal-organic framework (MOF)-metal oxide composite materials have been explored for chemiresistive sensor applications, however their ability to detect breath compounds associated with specific diseases remains unknown. In this work, we present a new high-throughput computational protocol for evaluating the sensing ability of MOF-metal oxide towards small organic compounds. This protocol uses a cluster-based method for accelerated structure relaxation, and a combination of binding energies and density-of-states analysis to evaluate sensing ability, the latter measured using Wasserstein distances. We apply this protocol to the case of the MOF-metal oxide composite material NM125-TiO2 and show that it is consistent with previously reported experimental results for this system. We examine the sensing ability of NM125-TiO2 for over 100 human-breath compounds spanning 13 different diseases. Statistical inference then allows us to identifies ones which subsequent experimental efforts should focus on. Overall, this work provides new tools for computational sensor research, while also illustrating how computational materials science can be integrated into the field of preventative medicine.
Fernando Rodriguez Avellaneda, Jorge Mateu, Paula Moraga
Understanding the spread of infectious diseases such as COVID-19 is crucial for informed decision-making and resource allocation. A critical component of disease behavior is the velocity with which disease spreads, defined as the rate of change between time and space. In this paper, we propose a spatio-temporal modeling approach to determine the velocities of infectious disease spread. Our approach assumes that the locations and times of people infected can be considered as a spatio-temporal point pattern that arises as a realization of a spatio-temporal log-Gaussian Cox process. The intensity of this process is estimated using fast Bayesian inference by employing the integrated nested Laplace approximation (INLA) and the Stochastic Partial Differential Equations (SPDE) approaches. The velocity is then calculated using finite differences that approximate the derivatives of the intensity function. Finally, the directions and magnitudes of the velocities can be mapped at specific times to examine better the spread of the disease throughout the region. We demonstrate our method by analyzing COVID-19 spread in Cali, Colombia, during the 2020-2021 pandemic.
Modeling disease progression is crucial for improving the quality and efficacy of clinical diagnosis and prognosis, but it is often hindered by a lack of longitudinal medical image monitoring for individual patients. To address this challenge, we propose the first Medical Video Generation (MVG) framework that enables controlled manipulation of disease-related image and video features, allowing precise, realistic, and personalized simulations of disease progression. Our approach begins by leveraging large language models (LLMs) to recaption prompt for disease trajectory. Next, a controllable multi-round diffusion model simulates the disease progression state for each patient, creating realistic intermediate disease state sequence. Finally, a diffusion-based video transition generation model interpolates disease progression between these states. We validate our framework across three medical imaging domains: chest X-ray, fundus photography, and skin image. Our results demonstrate that MVG significantly outperforms baseline models in generating coherent and clinically plausible disease trajectories. Two user studies by veteran physicians, provide further validation and insights into the clinical utility of the generated sequences. MVG has the potential to assist healthcare providers in modeling disease trajectories, interpolating missing medical image data, and enhancing medical education through realistic, dynamic visualizations of disease progression.
Detecting diseases from social media has diverse applications, such as public health monitoring and disease spread detection. While language models (LMs) have shown promising performance in this domain, there remains ongoing research aimed at refining their discriminating representations. In this paper, we propose a novel method that integrates Contrastive Learning (CL) with language modeling to address this challenge. Our approach introduces a self-augmentation method, wherein hidden representations of the model are augmented with their own representations. This method comprises two branches: the first branch, a traditional LM, learns features specific to the given data, while the second branch incorporates augmented representations from the first branch to encourage generalization. CL further refines these representations by pulling pairs of original and augmented versions closer while pushing other samples away. We evaluate our method on three NLP datasets encompassing binary, multi-label, and multi-class classification tasks involving social media posts related to various diseases. Our approach demonstrates notable improvements over traditional fine-tuning methods, achieving up to a 2.48% increase in F1-score compared to baseline approaches and a 2.1% enhancement over state-of-the-art methods.
Agnieszka M. Frydrych, Richard Parsons, Omar Kujan
Abstract Objectives Malnutrition is common among patients with head and neck cancer (HNC) and associated with poorer outcomes. Oral nutritional supplements (ONS) are often prescribed, with concerns raised about their cariogenicity. This study examined ONS use and caries experience in patients with HNC 12 months post‐diagnosis. Methods Fifty‐four patients with HNC referred for pre‐radiotherapy dental assessment were recruited. Data collected included: age, gender, residential postcode, smoking, alcohol use, HNC characteristics, dental history, oral hygiene habits, dietary advice and ONS use. Data was collected at diagnosis, during radiotherapy and 6 weeks, three, six‐ and 12‐months post‐treatment completion. Results Fifty‐one subjects completed the study. 76.5% of the participants used ONS for an average of 13.8 weeks. Caries developed in 22.9% of ONS users and 11.1% of non‐users ( p = 0.6585). The mean overall duration of ONS use was 18.7 weeks for the caries group and 8.5 weeks for the caries‐free group ( p = 0.1507). Lack of collaboration and disconnection was noted between dietary advice given by dieticians and dentists. Conclusions ONS use is common among patients with HNC. Larger studies are needed to establish the reasons for caries development and impacts of ONS use on oral health. Importance of multidisciplinary management of malnutrition is highlighted.
Md Mahfuzur Rahman Siddiquee, Jay Shah, Teresa Wu
et al.
Harnessing the power of deep neural networks in the medical imaging domain is challenging due to the difficulties in acquiring large annotated datasets, especially for rare diseases, which involve high costs, time, and effort for annotation. Unsupervised disease detection methods, such as anomaly detection, can significantly reduce human effort in these scenarios. While anomaly detection typically focuses on learning from images of healthy subjects only, real-world situations often present unannotated datasets with a mixture of healthy and diseased subjects. Recent studies have demonstrated that utilizing such unannotated images can improve unsupervised disease and anomaly detection. However, these methods do not utilize knowledge specific to registered neuroimages, resulting in a subpar performance in neurologic disease detection. To address this limitation, we propose Brainomaly, a GAN-based image-to-image translation method specifically designed for neurologic disease detection. Brainomaly not only offers tailored image-to-image translation suitable for neuroimages but also leverages unannotated mixed images to achieve superior neurologic disease detection. Additionally, we address the issue of model selection for inference without annotated samples by proposing a pseudo-AUC metric, further enhancing Brainomaly's detection performance. Extensive experiments and ablation studies demonstrate that Brainomaly outperforms existing state-of-the-art unsupervised disease and anomaly detection methods by significant margins in Alzheimer's disease detection using a publicly available dataset and headache detection using an institutional dataset. The code is available from https://github.com/mahfuzmohammad/Brainomaly.
Rice is considered a strategic crop in Egypt as it is regularly consumed in the Egyptian people's diet. Even though Egypt is the highest rice producer in Africa with a share of 6 million tons per year, it still imports rice to satisfy its local needs due to production loss, especially due to rice disease. Rice blast disease is responsible for 30% loss in rice production worldwide. Therefore, it is crucial to target limiting yield damage by detecting rice crops diseases in its early stages. This paper introduces a public multispectral and RGB images dataset and a deep learning pipeline for rice plant disease detection using multi-modal data. The collected multispectral images consist of Red, Green and Near-Infrared channels and we show that using multispectral along with RGB channels as input archives a higher F1 accuracy compared to using RGB input only.
Yousef Alhwaiti, Muhammad Ishaq, Muhammad Hameed Siddiqi
et al.
The tomato is one of the most important fruits on earth. It plays an important and useful role in the agricultural production of any country. This research propose a novel smart technique for early detection of late blight diseases in tomatoes. This work improve the dataset with an increase in images from the field (the Plant Village dataset) and proposed a hybrid algorithm composed of support vector machines (SVM) and histogram-oriented gradients (HOG) for real-time detection of late blight tomato disease. To propose a HOG-based SVM model for early detection of late blight tomato leaf disease. To check the performance of the proposed model in terms of MSE, accuracy, precision, and recall as compared to Decision Tree and KNN. The integration of advanced technology in agriculture has the potential to revolutionize the industry, making it more efficient, sustainable, and profitable. This research work on the early detection of tomato diseases contributes to the growing importance of smart farming, the need for climate-smart agriculture, the rising need to more efficiently utilize natural resources, and the demand for higher crop yields. The proposed hybrid algorithm of SVM and HOG has significant potential for the early detection of late blight disease in tomato plants. The performance of the proposed model against decision tree and KNN algorithms and the results may assist in selecting the best algorithm for future applications. The research work can help farmers make data-driven decisions to optimize crop yield and quality while also reducing the environmental impact of farming practices.
To characterize atypical brain dynamics under diseases, prevalent studies investigate functional magnetic resonance imaging (fMRI). However, most of the existing analyses compress rich spatial-temporal information as the brain functional networks (BFNs) and directly investigate the whole-brain network without neurological priors about functional subnetworks. We thus propose a novel graph learning framework to mine fMRI signals with topological priors from brain parcellation for disease diagnosis. Specifically, we 1) detect diagnosis-related temporal features using a "Transformer" for a higher-level BFN construction, and process it with a following graph convolutional network, and 2) apply an attention-based multiple instance learning strategy to emphasize the disease-affected subnetworks to further enhance the diagnosis performance and interpretability. Experiments demonstrate higher effectiveness of our method than compared methods in the diagnosis of early mild cognitive impairment. More importantly, our method is capable of localizing crucial brain subnetworks during the diagnosis, providing insights into the pathogenic source of mild cognitive impairment.
Understanding the spread of diseases through complex networks is of great interest where realistic, heterogeneous contact patterns play a crucial role in the spread. Most works have focused on mean-field behavior -- quantifying how contact patterns affect the emergence and stability of (meta)stable endemic states in networks. On the other hand, much less is known about longer time scale dynamics, such as disease extinction, whereby inherent process stochasticity and contact heterogeneity interact to produce large fluctuations that result in the spontaneous clearance of infection. Here we show that heterogeneity in both susceptibility and infectiousness (incoming and outgoing degree, respectively) has a non-trivial effect on extinction in directed contact networks, both speeding-up and slowing-down extinction rates depending on the relative proportion of such edges in a network, and on whether the heterogeneities in the incoming and outgoing degrees are correlated or anticorrelated. In particular, we show that weak anticorrelated heterogeneity can increase the disease stability, whereas strong heterogeneity gives rise to markedly different results for correlated and anticorrelated heterogeneous networks. All analytical results are corroborated through various numerical schemes including network Monte-Carlo simulations.
The frequent emergence of diseases with the potential to become threats at local and global scales, such as influenza A(H1N1), SARS, MERS, and recently COVID-19 disease, makes it crucial to keep designing models of disease propagation and strategies to prevent or mitigate their effects in populations. Since isolated systems are exceptionally rare to find in any context, especially in human contact networks, here we examine the susceptible-infected-recovered model of disease spreading in a multiplex network formed by two distinct networks or layers, interconnected through a fraction $q$ of shared individuals (overlap). We model the interactions through weighted networks, because person-to-person interactions are diverse (or disordered); weights represent the contact times of the interactions. Using branching theory supported by simulations, we analyze a social distancing strategy that reduces the average contact time in both layers, where the intensity of the distancing is related to the topology of the layers. We find that the critical values of the distancing intensities, above which an epidemic can be prevented, increase with the overlap $q$. Also we study the effect of the social distancing on the mutual giant component of susceptible individuals, which is crucial to keep the functionality of the system. In addition, we find that for relatively small values of the overlap $q$, social distancing policies might not be needed at all to maintain the functionality of the system.
Liangying Yin, Carlos Kwan-long Chau, Yu-Ping Lin
et al.
Genome-wide association studies(GWAS) have proven to be highly useful in revealing the genetic basis of complex diseases. At present, most GWAS are studies of a particular single disease diagnosis against controls. However, in practice, an individual is often affected by more than one condition/disorder. For example, patients with coronary artery disease(CAD) are often comorbid with diabetes mellitus(DM). Along a similar line, it is often clinically meaningful to study patients with one disease but without a comorbidity. For example, obese DM may have different pathophysiology from non-obese DM. Here we developed a statistical framework to uncover susceptibility variants for comorbid disorders (or a disorder without comorbidity), using GWAS summary statistics only. In essence, we mimicked a case-control GWAS in which the cases are affected with comorbidities or a disease without a relevant comorbid condition (in either case, we may consider the cases as those affected by a specific subtype of disease, as characterized by the presence or absence of comorbid conditions). We extended our methodology to deal with continuous traits with clinically meaningful categories (e.g. lipids). In addition, we illustrated how the analytic framework may be extended to more than two traits. We verified the feasibility and validity of our method by applying it to simulated scenarios and four cardiometabolic (CM) traits. We also analyzed the genes, pathways, cell-types/tissues involved in CM disease subtypes. LD-score regression analysis revealed some subtypes may indeed be biologically distinct with low genetic correlations. Further Mendelian randomization analysis found differential causal effects of different subtypes to relevant complications. We believe the findings are of both scientific and clinical value, and the proposed method may open a new avenue to analyzing GWAS data.