Detail

Keywords

Artificial Intelligence; Image Interpretation, Computer-Assisted; Image Processing, Computer-Assisted; Optical Imaging; Retina

Research group(s)

• Christian Doppler Laboratory for Ophthalmic Image Analysis (OPTIMA)
  Research Area: Since 2013 the interdisciplinary OPTIMA group is pioneering in the introduction of artificial intelligence into ophthalmology.
  Members:
  Sebastian M. Waldstein
  Bianca S. Gerendas
  Hrvoje Bogunović
  Philipp Seeböck
• Christian Doppler Lab for Artificial Intelligence in Retina
  Head: Hrvoje Bogunović
  Research Area: Since 2021, the Lab is focused on enabling AI-driven clinical decision support systems (CDSSs) for the effective management of retinal diseases from optical imaging.
  Members:
  Hrvoje Bogunović

Research interests

My main general research interests are in medical image computing and machine learning with applications in healthcare.
I am particularly interested in developing machine learning methodologies for predicting disease progression and in knowledge discovery from large clinical longitudinal imaging datasets.

Selected publications

1. Emre, T. et al. (2024) ‘3DTINC: Time-Equivariant Non-Contrastive Learning for Predicting Disease Progression from Longitudinal OCTs’, IEEE Transactions on Medical Imaging, pp. 1–1. Available at: https://doi.org/10.1109/tmi.2024.3391215.
2. Lachinov, D. et al. (2024) ‘Learning Spatio-Temporal Model of Disease Progression With NeuralODEs From Longitudinal Volumetric Data’, IEEE Transactions on Medical Imaging, 43(3), pp. 1165–1179. Available at: https://doi.org/10.1109/tmi.2023.3330576.
3. Chakravarty, A. et al. (2024) ‘Morph-SSL: Self-Supervision with Longitudinal Morphing for Forecasting AMD Progression from OCT Volumes’, IEEE Transactions on Medical Imaging, pp. 1–1. Available at: https://doi.org/10.1109/tmi.2024.3390940.
4. Seeböck, P. et al. (2024) ‘Anomaly guided segmentation: Introducing semantic context for lesion segmentation in retinal OCT using weak context supervision from anomaly detection’, Medical Image Analysis, 93, p. 103104. Available at: https://doi.org/10.1016/j.media.2024.103104.
5. Morano, J. et al. (2024) ‘Deep Multimodal Fusion of Data With Heterogeneous Dimensionality via Projective Networks’, IEEE Journal of Biomedical and Health Informatics, 28(4), pp. 2235–2246. Available at: https://doi.org/10.1109/jbhi.2024.3352970.