Related papers: Embracing Massive Medical Data

Online continual learning requires the models to learn from constant, endless streams of data. While significant efforts have been made in this field, most were focused on mitigating the catastrophic forgetting issue to achieve better…

Continual learning is considered a promising step towards next-generation Artificial Intelligence (AI), where deep neural networks (DNNs) make decisions by continuously learning a sequence of different tasks akin to human learning…

In this work, we consider learning sparse models in large scale settings, where the number of samples and the feature dimension can grow as large as millions or billions. Two immediate issues occur under such challenging scenario: (i)…

Deep learning has revolutionized many industries by enabling models to automatically learn complex patterns from raw data, reducing dependence on manual feature engineering. However, deep learning algorithms are sensitive to input data, and…

Pretrained Multimodal Large Language Models (MLLMs) are increasingly used in sensitive domains such as medical AI, where privacy regulations like HIPAA and GDPR require specific removal of individuals' or institutions' data. This motivates…

Traditional brain lesion segmentation models for multi-modal MRI are typically tailored to specific pathologies, relying on datasets with predefined modalities. Adapting to new MRI modalities or pathologies often requires training separate…

Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased. In artificial learning systems, lifelong…

While previous studies have demonstrated the potential of AI to diagnose diseases in imaging data, clinical implementation is still lagging behind. This is partly because AI models require training with large numbers of examples only…

In order to mimic the human ability of continual acquisition and transfer of knowledge across various tasks, a learning system needs the capability for continual learning, effectively utilizing the previously acquired skills. As such, the…

Current deep learning based disease diagnosis systems usually fall short in catastrophic forgetting, i.e., directly fine-tuning the disease diagnosis model on new tasks usually leads to abrupt decay of performance on previous tasks. What is…

Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. Although extensive research has focused on developing efficient machine…

In spite of remarkable success of the convolutional neural networks on semantic segmentation, they suffer from catastrophic forgetting: a significant performance drop for the already learned classes when new classes are added on the data,…

Learning on big data brings success for artificial intelligence (AI), but the annotation and training costs are expensive. In future, learning on small data that approximates the generalization ability of big data is one of the ultimate…

The exponential growth of volume, variety and velocity of data is raising the need for investigations of automated or semi-automated ways to extract useful patterns from the data. It requires deep expert knowledge and extensive…

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…

In real-world clinical settings, traditional deep learning-based classification methods struggle with diagnosing newly introduced disease types because they require samples from all disease classes for offline training. Class incremental…

Medical imaging plays an important role in the medical sector in identifying diseases. X-ray, computed tomography (CT) scans, and magnetic resonance imaging (MRI) are a few examples of medical imaging. Most of the time, these imaging…

Standard deep learning-based classification approaches require collecting all samples from all classes in advance and are trained offline. This paradigm may not be practical in real-world clinical applications, where new classes are…

Biomedical data is inherently multimodal, consisting of electronic health records, medical imaging, digital pathology, genome sequencing, wearable sensors, and more. The application of artificial intelligence tools to these multifaceted…

Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data. However, there are two major obstacles making it challenging to implement for real life…