Lumbar and Thoracic Vertebrae Segmentation in CT Scans Using a 3D Multi-Object Localization and Segmentation CNN

Xiaofan Xiong; Stephen A Graves; Brandie A Gross; John M Buatti; Reinhard R Beichel

doi:10.3390/tomography10050057

Back

Lumbar and Thoracic Vertebrae Segmentation in CT Scans Using a 3D Multi-Object Localization and Segmentation CNN

Journal article

Open access

Peer reviewed

Lumbar and Thoracic Vertebrae Segmentation in CT Scans Using a 3D Multi-Object Localization and Segmentation CNN

Xiaofan Xiong, Stephen A Graves, Brandie A Gross, John M Buatti and Reinhard R Beichel

Tomography (Ann Arbor), Vol.10(5), pp.738-760

05/13/2024

DOI: 10.3390/tomography10050057

PMCID: PMC11125921

PMID: 38787017

Files and links (1)

url

https://doi.org/10.3390/tomography10050057View

Published (Version of record) Open Access

Abstract

Radiation treatment of cancers like prostate or cervix cancer requires considering nearby bone structures like vertebrae. In this work, we present and validate a novel automated method for the 3D segmentation of individual lumbar and thoracic vertebra in computed tomography (CT) scans. It is based on a single, low-complexity convolutional neural network (CNN) architecture which works well even if little application-specific training data are available. It is based on volume patch-based processing, enabling the handling of arbitrary scan sizes. For each patch, it performs segmentation and an estimation of up to three vertebrae center locations in one step, which enables utilizing an advanced post-processing scheme to achieve high segmentation accuracy, as required for clinical use. Overall, 1763 vertebrae were used for the performance assessment. On 26 CT scans acquired for standard radiation treatment planning, a Dice coefficient of 0.921 ± 0.047 (mean ± standard deviation) and a signed distance error of 0.271 ± 0.748 mm was achieved. On the large-sized publicly available VerSe2020 data set with 129 CT scans depicting lumbar and thoracic vertebrae, the overall Dice coefficient was 0.940 ± 0.065 and the signed distance error was 0.109 ± 0.301 mm. A comparison to other methods that have been validated on VerSe data showed that our approach achieved a better overall segmentation performance.

Female

Humans

Imaging, Three-Dimensional - methods

Lumbar Vertebrae - diagnostic imaging

Male

Neural Networks, Computer

Thoracic Vertebrae - diagnostic imaging

Tomography, X-Ray Computed - methods

Details

Title: Subtitle: Lumbar and Thoracic Vertebrae Segmentation in CT Scans Using a 3D Multi-Object Localization and Segmentation CNN
Creators: Xiaofan Xiong - University of Iowa
Stephen A Graves - University of Iowa
Brandie A Gross - Department of Radiation Oncology, University of Iowa Hospitals and Clinics, Iowa City, IA 52242, USA
John M Buatti - University of Iowa Hospitals and Clinics
Reinhard R Beichel - University of Iowa
Resource Type: Journal article
Publication Details: Tomography (Ann Arbor), Vol.10(5), pp.738-760
DOI: 10.3390/tomography10050057
PMID: 38787017
PMCID: PMC11125921
ISSN: 2379-1381
eISSN: 2379-139X
Grant note: U01CA140206 / NIH/NCI
Language: English
Date published: 05/13/2024
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Radiation Oncology; Neurosurgery; Otolaryngology
Record Identifier: 9984630659002771

Metrics

5 Record Views

2 Times Cited - Web of Science

See more details