Ultra-short echo-time magnetic resonance imaging lung segmentation with under-Annotations and domain shift.

Autor: Guo F; Department of Medical Biophysics, University of Toronto, Toronto, ON, M4N 3M5, Canada., Capaldi DP; Department of Radiation Oncology, Stanford University, CA, 94305, USA., McCormack DG; Division of Respirology, Department of Medicine, Western University, London, ON, N6A 5B7, Canada., Fenster A; Robarts Research Institute, School of Biomedical Engineering, Western University, London, ON, N6A 5B7, Canada., Parraga G; Division of Respirology, Department of Medicine, Western University, London, ON, N6A 5B7, Canada; Robarts Research Institute, School of Biomedical Engineering, Western University, London, ON, N6A 5B7, Canada. Electronic address: gparraga@robarts.ca.
Jazyk: angličtina
Zdroj: Medical image analysis [Med Image Anal] 2021 Aug; Vol. 72, pp. 102107. Date of Electronic Publication: 2021 Jun 02.
DOI: 10.1016/j.media.2021.102107
Abstrakt: Ultra-short echo-time (UTE) magnetic resonance imaging (MRI) provides enhanced visualization of pulmonary structural and functional abnormalities and has shown promise in phenotyping lung disease. Here, we describe the development and evaluation of a lung segmentation approach to facilitate UTE MRI methods for patient-based imaging. The proposed approach employs a k-means algorithm in kernel space for pair-wise feature clustering and imposes image domain continuous regularization, coined as continuous kernel k-means (CKKM). The high-order CKKM algorithm was simplified through upper bound relaxation and solved within an iterative continuous max-flow framework. We combined the CKKM with U-net and atlas-based approaches and comprehensively evaluated the performance on 100 images from 25 patients with asthma and bronchial pulmonary dysplasia enrolled at Robarts Research Institute (Western University, London, Canada) and Centre Hospitalier Universitaire (Sainte-Justine, Montreal, Canada). For U-net, we trained the network five times on a mixture of five different images with under-annotations and applied the model to 64 images from the two centres. We also trained a U-net on five images with full and brush annotations from one centre, and tested the model on 32 images from the other centre. For an atlas-based approach, we employed three atlas images to segment 64 target images from the two centres through straightforward atlas registration and label fusion. We applied the CKKM algorithm to the baseline U-net and atlas outputs and refined the initial segmentation through multi-volume image fusion. The integration of CKKM substantially improved baseline results and yielded, with minimal computational cost, segmentation accuracy, and precision that were greater than some state-of-the-art deep learning models and similar to experienced observer manual segmentation. This suggests that deep learning and atlas-based approaches may be utilized to segment UTE MRI datasets using relatively small training datasets with under-annotations.
Competing Interests: Declaration of Competing Interest No conflicts of interest, financial or otherwise, are declared by F Guo, D Capaldi, DG McCormack, A Fenster, and G Parraga.
(Copyright © 2021 Elsevier B.V. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: