HomePeopleResearch and SupportPublicationsNews


HATSID: Hierarchical Analysis of Temporal and Spatial Image Data

From intelligent data acquisition via smart data-management to confident predictions





Images contain very rich information, and digital cameras combined with image processing and analysis can detect and quantify a range of patterns and processes. The valuable information is however often sparse, and the ever increasing speed at which data is collected results in data-volumes that exceed the computational resources available. The HATSID project takes a hierarchical approach to acquisition, analysis, and interpretation of image data. We develop computationally efficient measurements for data description, confidence-driven machine learning for determination of interestingness, and a theory and framework to apply intelligent spatial and temporal information hierarchies, distributing data to computational resources and storage options based on low-level image features. We will focus our efforts on microscopy data, and work in three specific areas where image collection results in data volumes difficult to handle with today's computational resources, namely
• large-scale time-lapse experiments exploring the dynamics of cells and drug delivery particles in collaboration with Astra Zeneca
• nanometer-resolution transmission electron microscopy data of in collaboration with Vironova AB
• multi-modal digital pathology data from SciLifeLab Sweden.
We expect the resulting methodologies and frameworks to be highly relevant also for other scientific and industrial applications, including surveillance, predictive maintenance and quality control.

Funding:

The project is funded by the Swedish Foundation for Strategic Research, see the press release.

People involved:

Carolina Wählby
PI, PhD, Professor in Quantitative Microscopy
Andreas Hellander
Co-PI, Associate Professor
Ola Spjuth
Co-PI, Associate Professor

Collaborators:



via Lars Carlsson, Ola Engkvist, Johan Karlsson and Alan Sabirsh



via Ida-Maria Sintorn



via Mats Nilsson