EMBC 2025 papers accepted


Two articles have been accepted for the incoming 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, held in Bella Center, Copenhagen, Denmark, July 14-17, 2025.


1- The first article is titled “Symptomatic and Asymptomatic Carotid Plaques Classification using CT Images and Hybrid Deep Transfer Learning “. This paper proposes a data-driven model for classifying symptomatic and asymptomatic carotid plaques using Computed Tomography (CT) images. We present a hybrid deep transfer learning framework that combines CNN architectures for feature extraction. The extracted features effectively capture complex local and global textures and the carotid artery’s morphological characteristics. These features were subsequently used as inputs for various machine learning models, whose performance was rigorously evaluated on real-world data. The results demonstrate the feasibility and effectiveness of the proposed method in classifying carotid plaques and highlight its potential to improve clinical diagnosis and risk assessment.

Overview of the proposed pipeline for classifying symptomatic and asymptomatic carotid plaques using a hybrid deep learning and machine learning framework. The pipeline begins with CT scan collection, followed by intensity windowing and region of interest (ROI) segmentation targeting the internal carotid artery, bifurcation, and common carotid artery. Deep features are then extracted using pre-trained convolutional neural networks (VGG16, ResNet, and DenseNet). These features are subsequently used to train a machine learning classifier, which undergoes hyperparameter tuning to optimize performance. The final model predicts whether the plaque is symptomatic or asymptomatic, supporting clinical decision-making.


1- The Second article is titled “Mamba-CAM-Sleep: A Mamba-based Channel Attention Model for Sleep Staging Classification” . Sleep stage classification is essential for diagnosing sleep disorders. This work proposes Mamba-CAM-Sleep, a novel framework that utilizes the polysomnography (PSG) records and leverages a state-space backbone (Mamba) and channel attention-based graph neural network for sleep staging classification. The Mamba backbone enhances long-range temporal dependencies, which is crucial for capturing the sleep stage transitions, while channel attention improves discriminative feature extraction across multi-channel signals. The proposed approach is validated on the DOD-H benchmark dataset. The model attains an F1 score of 80.4% and a Cohen’s kappa of 76.3%, outperforming existing methods (LSTM, SimpleSleepNet, Robust-SleepNet, DeepSleepNet) by 3.0 − 6.0% and 2.2 − 10.8% in F1 and kappa, respectively. Notably, our framework demonstrates superior robustness, as evidenced by lower standard deviations (±2.1 F1, ±2.5 kappa), and excels in classifying challenging stages such as N1 (53.9%) and N3 (74.7%), surpassing prior works by 3.3−16.5%. Ablation studies validate the effectiveness of the proposed architectural innovations. The proposed Mamba-CAM-Sleep framework is a scalable, reliable solution for clinical sleep staging, striking a balance
between high accuracy and practical deployability.

The proposed framework combines Mamba and channel attention modules. The input consists of multiple feature channels, which are first processed by the Mamba module to extract high-level feature representations. The output of the Mamba module is then passed through a channel attention mechanism to emphasize the most informative channels. Next, a graph structure learning module captures relationships between features and constructs a graph representation. This graph representation is further processed by a Graph Neural Network (GNN) layer.Finally, the output is passed to a classification head that predicts the class labels based on the refined features