This changes to that: combining causal and non-causal explanations to generate disease progression in capsule endoscopy.

Vats, Anuja; Mohammed, Ahmed; Pedersen, Marius; Wiratunga, Nirmalie

Abstract

The need to understand the decision-making mechanisms of deep learning networks has led to a growing effort in exploring both modal-dependent and model-agnostic research methods. Although both of these ideas provide transparency for automated decision making, most methodologies focus on either using the modal-gradients (model- dependent) or ignoring the model internal states and reasoning with a model's behavior/outcome (model-agnostic) to instances. In this work, we propose a unified explanation approach that given an instance combines both model-dependent and agnostic explanations to produce an explanation set. The generated explanations are not only consistent in the neighborhood of a sample but can highlight causal relationships between image content and the outcome. We use the Wireless Capsule Endoscopy (WCE) domain to illustrate the effectiveness of our explanations. The saliency maps generated by our approach are competitive on the softmax information score.

Citation

VATS, A., MOHAMMED, A., PEDERSEN, M. and WIRATUNGA, N. 2023. This changes to that: combining causal and non-causal explanations to generate disease progression in capsule endoscopy. In Proceedings of the 2023 IEEE international conference on acoustics, speech and signal processing (ICASSP 2023), 4-10 June 2023, Rhodes Island, Greece. Piscataway: IEEE [online], paper number 1771. Available from: https://doi.org/10.1109/ICASSP49357.2023.10096931

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2023 IEEE international conference on acoustics, speech and signal processing (ICASSP 2023)
• Start Date: Jun 4, 2023
• End Date: Jun 10, 2023
• Acceptance Date: Feb 15, 2023
• Online Publication Date: May 5, 2023
• Publication Date: Dec 31, 2023
• Deposit Date: Feb 17, 2023
• Publicly Available Date: Feb 17, 2023
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Series Title: ICASSP proceedings
• Series ISSN: 1520-6149; 2379-190X
• ISBN: 9781728163284
• DOI: https://doi.org/10.1109/ICASSP49357.2023.10096931
• Keywords: Explainable AI; Counterfactual; Semifactual; Saliency map; Capsule endoscopy
• Public URL: https://rgu-repository.worktribe.com/output/1888154