Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Experimental design for multi-channel imaging via task-driven feature selection

Blumberg, Stefano B., Slator, Paddy J. ORCID: https://orcid.org/0000-0001-6967-989X and Alexander, Daniel C. 2024. Experimental design for multi-channel imaging via task-driven feature selection. Presented at: The International Conference on Learning Representations (ICLR) 2024, Vienna, Austria, 7-11 May 2024. Proceedings of 12th International Conference on Learning Representations. ICLR,

[thumbnail of 5650_experimental_design_for_multi_.pdf] PDF - Accepted Post-Print Version
Download (2MB)

Abstract

This paper presents a data-driven, task-specific paradigm for experimental design, to shorten acquisition time, reduce costs, and accelerate the deployment of imaging devices. Current approaches in experimental design focus on model-parameter estimation and require specification of a particular model, whereas in imaging, other tasks may drive the design. Furthermore, such approaches often lead to intractable optimization problems in real-world imaging applications. Here we present a new paradigm for experimental design that simultaneously optimizes the design (set of image channels) and trains a machine-learning model to execute a user-specified image-analysis task. The approach obtains data densely-sampled over the measurement space (many image channels) for a small number of acquisitions, then identifies a subset of channels of prespecified size that best supports the task. We propose a method: TADRED for TAsk-DRiven Experimental Design in imaging, to identify the most informative channel-subset whilst simultaneously training a network to execute the task given the subset. Experiments demonstrate the potential of TADRED in diverse imaging applications: several clinically-relevant tasks in magnetic resonance imaging; and remote sensing and physiological applications of hyperspectral imaging. Results show substantial improvement over classical experimental design, two recent application-specific methods within the new paradigm, and state-of-the-art approaches in supervised feature selection. We anticipate further applications of our approach.

Item Type: Conference or Workshop Item (Paper)
Status: In Press
Schools: Schools > Computer Science & Informatics
Research Institutes & Centres > Cardiff University Brain Research Imaging Centre (CUBRIC)
Publisher: ICLR
Related URLs:
Date of First Compliant Deposit: 29 February 2024
Date of Acceptance: 16 January 2024
Last Modified: 06 May 2025 16:15
URI: https://orca.cardiff.ac.uk/id/eprint/166677

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics