Uncertainty estimation in unsupervised MR-CT synthesis of scoliotic spines

Karthik, Enamundram Naga, Cheriet, Farida et Laporte, Catherine. 2023. « Uncertainty estimation in unsupervised MR-CT synthesis of scoliotic spines ». IEEE Open Journal of Engineering in Medicine and Biology.
(In press)

Preview

PDF Laporte-C-2023-26490.pdf - Accepted Version Use licence: Creative Commons CC BY. Download (2MB) | Preview

Abstract

Uncertainty estimations through approximate Bayesian inference provide interesting insights to deep neural networks’ behavior. In unsupervised learning tasks, where expert labels are unavailable, it becomes ever more important to critique the model through uncertainties. Methods: This paper presents a proof-of-concept for generalizing the aleatoric and epistemic un- certainties in unsupervised MR-CT synthesis of scoliotic spines. A novel adaptation of the cycle-consistency constraint in CycleGAN is proposed such that the model predicts the aleatoric uncertainty maps in addition to the standard volume-to-volume translation between Magnetic Resonance (MR) and Computed Tomography (CT) data. Results: Ablation experiments were performed to understand uncertainty estimation as an implicit regularizer and a measure of the model’s confidence. Conclusion: The aleatoric uncertainty helps in distinguishing between the bone and soft- tissue regions in CT and MR data during translation, while the epistemic uncertainty provides interpretable information to the user for downstream tasks.

Item Type:	Peer reviewed article published in a journal
Professor:	Professor Laporte, Catherine
Affiliation:	Génie électrique
Date Deposited:	30 May 2023 20:56
Last Modified:	31 May 2023 15:04
URI:	https://espace2.etsmtl.ca/id/eprint/26490

Actions (login required)

View Item