Miolane's research contributes to building theoretical foundations and developing practical tools to create computational representations of biological structures — organs, cells, molecules — from biomedical images. Modeling the healthy and pathological states of these structures is crucial for applications in biology and medicine, ranging from our understanding of cancers to the diagnosis of neurodegenerative diseases. Specifically, she focuses on quantifying biological shapes and their variations in biomedical imaging datasets -— using tools from geometry, statistics, machine learning, deep learning and computer vision. Such "shape descriptors" are then correlated with healthy or pathological conditions, thanks to collaborations with biologists and clinicians within academia or industry.