Search

Federated learning (FL) enables collaborative model training across clients while preserving data privacy. However, FL faces the challenge of data heterogeneity, leading to biased local models that deviate from the global model during optimization. And existing FL algorithms like Federated Averaging (FedAvg) suffer from this issue. To address this problem, we propose a novel approach called multi-branch prototype federated learning (FedMBP).

The emerging deep learning algorithms have shown significant potential in the development of efficient computer-aided diagnosis tools for automated detection of lung infections using chest radiographs. However, many existing methods are slice-based and require manual selection of appropriate slices from the entire CT scan, which is tedious and requires expert radiologists.

The success of self-supervised learning (SSL) has mostly been attributed to the availability of unlabeled yet large-scale datasets. However, in a specialized domain such as medical imaging which is a lot different from natural images, the assumption of data availability is unrealistic and impractical, as the data itself is scanty and found in small databases, collected for specific prognosis tasks.

Motion compensation is effective for reducing motion blur in cardiac gated imaging. In this work, we investigate the potential benefit of incorporating an anatomical similarity measure in training a deep learning (DL) network for motion compensation on cardiac gated SPECT images, which are known to suffer from limited data counts and exhibit image intensity distortion (due to partial-volume effect) associated with cardiac motion.

Unsupervised anomaly detection (UAD) has been widely implemented in industrial and medical applications, which reduces the cost of manual annotation and improves efficiency in disease diagnosis. Recently, deep auto-encoder with its variants has demonstrated its advantages in many UAD scenarios. Training on the normal data, these models are expected to locate anomalies by producing higher reconstruction error for the abnormal areas than the normal ones.

While conventional multi-modal emotion recognition (MER) focuses only on model learning for modality fusion, we are interested in tuning multi-modal data fed to MER model in the testing phase. Tuning the influence of each input may cause MER performance significantly due to the nature of MER datasets consisting of heterogeneous modalities.

The application of Visual Question Answering (VQA) in the medical field has significantly impacted traditional medical research methods. A mature medical visual question answering system can greatly help the patients' diagnosis. The Visual Question Answering Model in the generic domain is not compelling enough for the feature alignment in medical image and text semantics because of the complex diversity of clinical problems and the difficulties in multi-modal reasoning.

In this paper, a dynamic dual-graph fusion convolutional network is proposed to improve Alzheimer's disease (AD) diagnosis performance.

The scarcity of annotated data, particularly for rare diseases, limits the variability of training data and the range of detectable lesions, presenting a significant challenge for supervised anomaly detection in medical imaging. To solve this problem, we propose a novel unsupervised method for medical image anomaly detection: Attention-Augmented Differentiable top-k Feature Adaptation (ADFA).

Event cameras generate data based on the amount of motion present in the captured scene, making them attractive sensors for solving object tracking tasks. In this paper, we present a framework for tracking humans using a single event camera which consists of three components. First, we train a Graph Neural Network (GNN) to recognize a person within the stream of events.