Manuscript Topics

Generative artificial intelligence (GenAI) refers to the artificial intelligence techniques that enable the creation of new artifacts from the existing content like text, audio files, or images. The GenAI models have strong resistance against overfitting, spurious correlations and model bias because they rely on fewer parameters and human labels, and they run on algorithms that abstract the inputs’ underlying pattern and guarantee the higher quality products by self-learning from the available dataset. Typical generative AI implementations include generative adversarial networks (GANs), transformers, and variational auto-encoder. The generative AI has been described as the most promising advances in the world of AI, and has rendered great benefits in amounts of technical fields such as film restoration, image-image conversion, novel drug design, text to image translation, etc. The GenAI has also shown great potentials for empowering the medical big data analytics, whose tasks such as medical image reconstruction, organ detection and segmentation, cross modal image synthesis, fusion of medical imaging and electronic health records, are essentially GenAI problems and thus perfect match the advantages of GenAI. Some attempts have been performed to exploit GenAI for medical big data analytics, such as the GANs-based data augmentation for training the AI models with limited sample data. However, there exist some new engineering challenges such as cross-model data analysis, fusion of text and electronic signals, multi-source data heterogeneity, information security, and privacy preserving. Promising solutions are in high demand to fully exploit the potentials of GenAI for medical big data analytics.

Technical Topics of the Special Issue

A wide range of researchers, from the computer science community, biomedical engineering research group, as well as the industrial community are welcome to submit their state-of-the-art achievements focus on GenAI driven medical big data analytics.

Topics include but are not limited to:
• Novel GenAI algorithms
• GenAI for medical image processing
• GenAI for cross-modality image synthesis
• GenAI-based synthetic electronic health records
• GenAI for electronic health records processing
• GenAI for physiological measurements
• GenAI for early diagnosis of disease
• GenAI for healthcare information fusion
• GenAI for smart treatments
• Data augmentation with GenAI solutions
• Security and privacy in the GenAI

Instructions for authors
https://www.aimspress.com/mbe/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/