Image Analysis

Director: Sotirios Tsaftaris

Curriculum overview

The curriculum in Image Analysis focuses on the analysis of large-scale multimodal imaging data arising in the natural and life sciences. Motivated by the explosion in such imaging data, the goal is to develop high-throughput and high-precision strategies to analyze intelligently these vast data sets to prove expert-driven hypothesis but also unearth unseen patterns. Such vast datasets arise from studying various organs (e.g., the heart) and organisms (humans, other model organisms such small or large animals, and plants), with multiple modalities (MRI, PET, and optical at various scales), which span multiple dimensions (e.g., 2D, 3D, multispectral), and are dynamic and repeated. This scenario is particularly prevalent now, where this type of analysis is needed to speed up imaging studies that accompany genotype-driven experiments. Research is focused on combining (and devising new) machine learning and data mining algorithms with innovative feature extraction, sparse data representation, and scientific visualization, to achieve the above goals. Students learn a variety of image analysis and machine learning methods and develop new image processing and analysis algorithms that are tailored towards taking advantage of cloud infrastructures. The skills of handling large amounts of data and processing them in a distributed fashion are particularly sought-after in the job market due to the recent interest in 'big data'.

Input and Output Profiles

This curriculum aims at preparing researchers and professionals with a wide knowledge of the theoretical foundations and tools of Image Analysis. Perspective students should preferably have a master-level background in computer science, engineering, physics, mathematics, statistics or in a related field. Graduates from the curriculum are qualified to work in universities, public and industrial research centers, and to take on professional roles and high-profile tasks and responsibilities in both private companies and public institutions.

Reference area(s): Computer Science (main), Systems Engineering.

Research Units contributing to the curriculum: PRIAn - Pattern Recognition and Image Analysis (main), DYSCO - Dynamical Systems, Control, and Optimization, SysMA - System Modelling and Analysis, Networks - Complex Networks.

PhD candidates also have the opportunity to collaborate with other institutions that work with IMT Research Units.

Coursework: See full course list