Jul 2026· International Research Journal on Advanced Engineering Hub (IRJAEH)· 0 citations· 12 references
Abstract
Timely analysis of cardiac MRI data is essential for early diagnosis and clinical intervention in cardiovascular illness, which continues to be the one world's leading causes of death. However, cross-institutional data sharing is ethically and legally problematic due to the nature of sensitive medical imaging data, which restricts the capacity to train reliable diagnosis models on the variety of the patient groups. A federated DL system for privacy-preserving anomaly detection and classification in cardiac MRI is presented in this work. It is intended to function in various simulated hospital settings without disclosing raw patient data. The suggested system, HeartMRI-FL, combines two deep learning models, an adaptive sub-client splitting mechanism, client-level differential privacy, and a Flower-based federated learning architecture— a supervised classifier for categorizing cardiac conditions and a convolutional autoencoder for unsupervised anomaly detection. Real-time training triggers, prediction queries, and result visualization are provided by a supplementary Angular-based clinical dashboard that interacts with the federated backend over a REST API. The system not only supports popular medical imaging formats like DICOM, NIfTI, and JPEG, but it also demonstrates that substantial diagnostic performance may be achieved without centralizing patient data. The federated approach provides a workable route toward privacy-compliant multi-institutional cardiac imaging analysis by achieving competitive accuracy while upholding formal differential privacy commitments, as confirmed by experimental results.
Remote arrhythmia monitoring in Internet of Medical Things (IoMT) systems is challenged by electrocardiogram (ECG) class imbalance, acquisition heterogeneity, and privacy restrictions that limit centralized data sharing. These challenges become more severe in federated learning (FL), where clients may exhibit statistically heterogeneous, non-independent and non-identically distributed (non-IID) data, label skew, and few or no examples of rare arrhythmia classes. This study investigates beat-level arrhythmia classification under heterogeneous and class-missing federated ECG distributions. Beat segments from the MIT–BIH Arrhythmia and St. Petersburg INCART databases were allocated without sample reuse across the original pathology-aware synthetic clients, producing controlled class imbalance and class-missing distributions. Stratified beat-level training, validation, and test subsets were then used to train and evaluate a compact one-dimensional convolutional neural network–bidirectional long short-term memory (1D CNN–BiLSTM) model augmented with a convolutional block attention module (CBAM). To address class imbalance and client heterogeneity, the Synthetic Minority Oversampling Technique (SMOTE) is applied only to local training data and combined with cross-entropy loss, macro-F1-based checkpoint selection, client-specific batch-normalization parameters, and a validation-weighted rare-class-aware aggregation rule. Evaluation is reported using both the native six-class label space <inline-formula> <tex-math notation="LaTeX">$\{N,L,R,V,A,F\}$ </tex-math></inline-formula> and the Association for the Advancement of Medical Instrumentation (AAMI) EC57 grouped categories <inline-formula> <tex-math notation="LaTeX">$\mathcal {N}/\mathcal {S}/\mathcal {V}/\mathcal {F}$ </tex-math></inline-formula>. Across seven non-IID clients and six matched random seeds, the proposed method achieves the highest final-round FL performance among the evaluated strategies, with an accuracy of <inline-formula> <tex-math notation="LaTeX">$0.8590 \pm 0.0053$ </tex-math></inline-formula>, a six-class macro-F1 of <inline-formula> <tex-math notation="LaTeX">$0.8428 \pm 0.0109$ </tex-math></inline-formula>, and an AAMI macro-F1 of <inline-formula> <tex-math notation="LaTeX">$0.8256 \pm 0.0110$ </tex-math></inline-formula>. The largest gains are observed on low-resource minority-bearing clients, particularly the atrial/supraventricular-bearing and fusion-bearing virtual users. Rare-class diagnostics show that, under the evaluated low-support setting, fusion-class performance on the only fusion-positive downstream client is limited primarily by precision rather than recall. Deployment-oriented single-window inference feasibility is evaluated on a Raspberry Pi 5 using frozen TensorFlow Lite artifacts, achieving a 95th-percentile inference latency below 34 ms and a serialized model size below 1 MB. These results indicate that rare-class-aware personalized FL can improve minority-class-sensitive ECG classification under heterogeneous, label-sparse client distributions without sharing raw ECG data. However, persistent <inline-formula> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula>–<inline-formula> <tex-math notation="LaTeX">$V$ </tex-math></inline-formula> ambiguity and limited fusion-beat support remain important targets for future rhythm-context modeling.
Somayyeh Dehghani, Samuel Pierre· IEEE Access· 0 citations
The proposed FL framework provides a privacy-preserving, explainable, and computationally efficient solution for collaborative AI in medical imaging by combining adaptive federated learning, secure privacy mechanisms, and explainable AI techniques, demonstrating strong potential for deployment in multi-hospital clinical environments.
Chandra Shakher Tyagi, Partheeban Nagappan, T. R· Research on Biomedical Engin...· 0 citations
Deep learning based medical diagnosis systems are often hindered by privacy restrictions on patients’ health data. In this paper, we propose a privacy preserving decentralized algorithm for multi-label classification of chest diseases using Federated Learning (FL). We experimented on 26,218 images sampled from NIH Chest X-ray dataset with a ResNeSt-50 deep neural network to classify 8 thoracic abnormalities. ResNeSt-50 incorporates Split-Attention mechanisms, which improve multiscale feature extraction for chest disease classification. As chest x-rays are low contrast images by nature, we applied Contrast Limited Adaptive Histogram Equalization (CLAHE) preprocessing to input images. The experimental results show that our proposed FL method obtains a competitive accuracy score of 7.04/8.0 (88.01%) compared to the non-decentralized baseline with the added benefits of FL, such as reduction in validation loss. This work aims to serve as a baseline for future work in FL for chest imaging.
Varsha Jayakumar, Arathi Madhu, D. G· 2026 4th International Confe...· 0 citations
The suggested framework serves as an accurate, scalable, and privacy-preserving approach for distributed medical imaging and aggregates only the model parameters at the central server rather than the raw medical data.
Guda Madhu, Nirmalajyothi Narisetty· International journal of com...· 0 citations
The rapid growth of Industry 4.0 has led to the use of artificial intelligence and the Internet of Medical Things (IoMT) in many healthcare applications, facilitating remote diagnosis, data collection, data analysis, and healthcare management. The IOMT provides a healthcare framework that collects biomedical data from patients via sensors or devices, stores it in the cloud, analyzes it, and provides clinical diagnoses. However, the privacy, security, reliability, and integrity of the healthcare data is challenging due to different cyber attacks on the IoMT framework. Therefore, this paper presents a deep learning-based network attack detection method, IoMT attack detection (IADNet), based on a 1-D deep convolutional neural network to capture multilevel correlations and a long short-term memory (LSTM) to capture long-term dependencies in network attributes. Further, it provides the dynamic synthetic minority oversampling technique (DSMOTE) for data augmentation, mitigating data scarcity by generating synthetic samples for training. The IADNet provides the overall accuracy of 99.12%, precision of 99.12%, recall of 95.50%, and F1-score of 97.24% for the original dataset, whereas it resulted in improved accuracy of 99.80%, recall of 98.80%, precision of 98.80%, and F1-score of 98.80% for the DSMOTE augmented dataset.
Rajashree Bhokare, Urmila Patil· International journal of com...· 0 citations
The Internet of Things (IoT) makes it possible to monitor patients continuously through wearable, networked medical devices. Yet, the healthcare systems built with the use of IoT are extremely susceptible to cyberattacks, including denial-of-service, spoofing, and unauthorized access that generate anomalous and incredibly unbalanced network traffic. There are two significant flaws associated with many deep learning (DL) and machine learning (ML) models of IoT security, including low performance in the presence of a very high-class imbalance and hyperparameter sensitivity. This work proposes an anomaly detection framework based on the imbalanced maximizing area under the curve proximal support vector machine (ImAUC-PSVM) model and the differential evolution (DE) algorithm for effective hyperparameter tuning. The ImAUC-PSVM directly optimizes the AUC metric, which makes it robust to imbalanced traffic without the need for data resampling or cost-sensitive schemes. The DE algorithm is further enhanced by the use of a new mutation strategy that works with k-means clustering to select strong solution groups and guide the search. The proposed model is tested on the NSL-KDD (Network Security Laboratory-Knowledge Discovery in Databases) and MAWI (Measurement and Analysis on the Widely Integrated Distributed Environment Internet) datasets. The experiment findings report an average F-measure of 89.948 and 91.665, respectively. The proposed system produces F-measure values of 89.95% and 91.67% on NSL-KDD and MAWI datasets, which exceed baseline model results while requiring less computational power. The research data proves that the developed model provides efficient anomaly detection for IoT healthcare systems, which enables practical system deployment in actual healthcare environments.
Zhou Yuan, Yaofeng Miao· Journal of engineering and a...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
