About UsBiomedical Image Computing Lab was established by Prof. Tammy Riklin Raviv. Our lab develops advanced methods in computer vision, deep learning, and computational neuroscience to address fundamental problems in biological, medical, and natural image domains. We are motivated by both theoretical challenges and real-world needs, working at the interface of algorithmic innovation and scientific discovery.
We work across scales — from cellular microscopy to brain imaging and large-scale natural datasets — and address challenges of data quality analysis, domain adaptation, and multimodal fusion, alongside the broader need for transparent and trustworthy AI systems. This involves developing ways to curate and anonymize data, creating models that can adapt across varying sources and conditions, and designing frameworks that integrate heterogeneous information into coherent and context-aware predictions. By combining methodological innovation with application-driven insights, we wish to push the boundaries of what can be achieved in automated image and data analysis.
The Biomedical Image Computing (BMIC) lab develops deep learning, AI, and computer vision methods for understanding complex visual, biomedical, and medical imaging data. We are particularly interested in methods that do more than produce accurate predictions: we aim to build models that can integrate information across modalities, adapt across domains and imaging conditions, explain what they learn, and assess the reliability of their outputs.
These methodological questions are driven by close collaborations with biologists, neuroscientists, and radiologists. In microscopy imaging, we develop tools for single-cell analysis, including cell segmentation and tracking, lineage analysis, and the study of cellular dynamics over time. In neuroimaging, we work with structural, diffusion, and functional brain MRI to study brain structure and function, aging processes, disease progression, tractography, brain decoding, and functional brain networks. More broadly, our goal is to transform rich and complex imaging data into quantitative insight that can support biological discovery, clinical interpretation, and a deeper understanding of living systems.
Our long-term vision is to bridge the gap between methodological innovation and practical impact, creating AI tools that are scalable, generalizable, interpretable, and trustworthy. By tackling the core challenges of data quality, adaptability, integration, and transparency, our research aims to contribute to the development of next-generation AI systems with broad relevance in science, medicine, and industry.
We are always looking for excellent and passionate Master’s and PhD students!
Please send us an email including your updated CV and all relevant grade lists
