Evaluation of a hybrid pipeline for automated segmentation of solid lesions based on mathematical algorithms and deep learning

Burrows, Liam, Chen, Ke ORCID: 0000-0002-6093-6623, Guo, Weihong, Hossack, Martin, McWilliams, Richard G and Torella, Francesco ORCID: 0000-0003-0529-7387 (2022) Evaluation of a hybrid pipeline for automated segmentation of solid lesions based on mathematical algorithms and deep learning. Scientific Reports, 12 (1). 14216-.

Access the full-text of this item by clicking on the Open Access link.

Text Evaluation of a hybrid pipeline for automated segmentation of solid lesions based on mathematical algorithms and deep learni.pdf - Published version Download (1MB) | Preview

Abstract

<jats:title>Abstract</jats:title><jats:p>We evaluate the accuracy of an original hybrid segmentation pipeline, combining variational and deep learning methods, in the segmentation of CT scans of stented aortic aneurysms, abdominal organs and brain lesions. The hybrid pipeline is trained on 50 aortic CT scans and tested on 10. Additionally, we trained and tested the hybrid pipeline on publicly available datasets of CT scans of abdominal organs and MR scans of brain tumours. We tested the accuracy of the hybrid pipeline against a gold standard (manual segmentation) and compared its performance to that of a standard automated segmentation method with commonly used metrics, including the DICE and JACCARD and volumetric similarity (VS) coefficients, and the Hausdorff Distance (HD). Results. The hybrid pipeline produced very accurate segmentations of the aorta, with mean DICE, JACCARD and VS coefficients of: 0.909, 0.837 and 0.972 in thrombus segmentation and 0.937, 0.884 and 0.970 for stent and lumen segmentation. It consistently outperformed the standard automated method. Similar results were observed when the hybrid pipeline was trained and tested on publicly available datasets, with mean DICE scores of: 0.832 on brain tumour segmentation, and 0.894/0.841/0.853/0.847/0.941 on left kidney/right kidney/spleen/aorta/liver organ segmentation.</jats:p>

Item Type:	Article
Uncontrolled Keywords:	Tomography, X-Ray Computed, Algorithms, Image Processing, Computer-Assisted, Deep Learning
Divisions:	Faculty of Science and Engineering > School of Physical Sciences
Depositing User:	Symplectic Admin
Date Deposited:	13 Sep 2022 14:21
Last Modified:	18 Jan 2023 20:46
DOI:	10.1038/s41598-022-18173-0
Open Access URL:	https://www.nature.com/articles/s41598-022-18173-0
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3163170

Available Versions of this Item

• Evaluation of a hybrid pipeline for automated segmentation of solid lesions based on mathematical algorithms and deep learning. (deposited 24 Aug 2022 09:48)
  • Evaluation of a hybrid pipeline for automated segmentation of solid lesions based on mathematical algorithms and deep learning. (deposited 13 Sep 2022 14:21) [Currently Displayed]