AI-driven tools for Medical Imaging and Visualization (IN2107)
Modern healthcare is undergoing a digital transformation driven by the convergence of Artificial Intelligence (AI), medical imaging, and advanced visualization techniques. In particular, deep learning has demonstrated remarkable progress in medical image analysis, enabling improvements in image reconstruction and preprocessing, automated segmentation of anatomical and pathological structures, feature representation learning, and image visualization. These AI-driven imaging tools can have a profound impact on clinical workflows by enhancing diagnostic accuracy, facilitating image acquisition, enabling diagnostic standardization, and advancing medical training [1] [2].
Despite these advances, the clinical implementation of AI-based tools continues to face several challenges, including the standardization of workflows for image analysis, achieving model generalizability and fairness across patient populations and clinical sites [3], the fusion of multimodal information by combining different imaging modalities and clinical text, and the adoption of innovative visualization frameworks like augmented and mixed reality.
In this seminar, we will discuss recent advancements in medical image processing and their role in developing AI-assisted tools for clinical decision support and intervention. In particular, we will cover state-of-the-art techniques for biomedical image registration in space and time, fully automated and promptable segmentation models, and the use of virtual and augmented reality technologies to bring medical imaging data to life for surgical planning, medical training, and image-guided interventions. Furthermore, we will examine practical challenges associated with deploying these technologies in clinical settings and discuss their current and potential impact on modern healthcare practice.
References
[1] R. Najjar, “Redefining Radiology: A Review of Artificial Intelligence Integration in Medical Imaging,” Diagnostics, vol. 13, no. 17, p. 2760, Aug. 2023.
[2] A. Hosny, C. Parmar, J. Quackenbush, L. H. Schwartz, and H. J. W. L. Aerts, “Artificial intelligence in radiology,” Nature Reviews Cancer, vol. 18, no. 8, pp. 500–510, May 2018.
[3] Y. Yang, H. Zhang, J. W. Gichoya, D. Katabi, and M. Ghassemi, “The limits of fair medical imaging AI in real-world generalization,” Nature Medicine, vol. 30, no. 10, pp. 2838–2848, Jun. 2024.
Key topics to be covered include:
- Traditional medical image visualization and navigation in the clinic
- Image registration across modalities and time
- Fully automated and promptable segmentation in medical imaging
- 3D rendering and virtual or augmented reality in medical imaging
- State-of-the-art methods
Requirements:
- Background in image processing and machine learning/deep learning
- Interest in AI-tools for medical imaging
- Interest in research
Please register via the TUM matching system: https://matching.in.tum.de
Check the intro slides here:
Julia A. Schnabel
Professor for Computational Imaging and AI in Medicine, Director of the Institute of Machine Learning in Biomedical Imaging
My research interests include machine/deep learning, nonlinear motion modeling, as well as multimodal and quantitative imaging, for cancer-, cardiac-, neuro- and perinatal imaging.