Development and validation of a semi-automated and unsupervised method for femur segmentation from CT
Abstract Quantitative computed tomography (QCT)-based in silico models have demonstrated improved accuracy in predicting hip fractures with respect to the current gold standard, the areal bone mineral density. These models require that the femur bone is segmented as a first step. This task can be ch...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-03-01
|
Series: | Scientific Reports |
Subjects: | |
Online Access: | https://doi.org/10.1038/s41598-024-57618-6 |
_version_ | 1797233566655971328 |
---|---|
author | Alessandra Aldieri Riccardo Biondi Antonino A. La Mattina Julia A. Szyszko Stefano Polizzi Daniele Dall’Olio Nico Curti Gastone Castellani Marco Viceconti |
author_facet | Alessandra Aldieri Riccardo Biondi Antonino A. La Mattina Julia A. Szyszko Stefano Polizzi Daniele Dall’Olio Nico Curti Gastone Castellani Marco Viceconti |
author_sort | Alessandra Aldieri |
collection | DOAJ |
description | Abstract Quantitative computed tomography (QCT)-based in silico models have demonstrated improved accuracy in predicting hip fractures with respect to the current gold standard, the areal bone mineral density. These models require that the femur bone is segmented as a first step. This task can be challenging, and in fact, it is often almost fully manual, which is time-consuming, operator-dependent, and hard to reproduce. This work proposes a semi-automated procedure for femur bone segmentation from CT images. The proposed procedure is based on the bone and joint enhancement filter and graph-cut algorithms. The semi-automated procedure performances were assessed on 10 subjects through comparison with the standard manual segmentation. Metrics based on the femur geometries and the risk of fracture assessed in silico resulting from the two segmentation procedures were considered. The average Hausdorff distance (0.03 ± 0.01 mm) and the difference union ratio (0.06 ± 0.02) metrics computed between the manual and semi-automated segmentations were significantly higher than those computed within the manual segmentations (0.01 ± 0.01 mm and 0.03 ± 0.02). Besides, a blind qualitative evaluation revealed that the semi-automated procedure was significantly superior (p < 0.001) to the manual one in terms of fidelity to the CT. As for the hip fracture risk assessed in silico starting from both segmentations, no significant difference emerged between the two (R 2 = 0.99). The proposed semi-automated segmentation procedure overcomes the manual one, shortening the segmentation time and providing a better segmentation. The method could be employed within CT-based in silico methodologies and to segment large volumes of images to train and test fully automated and supervised segmentation methods. |
first_indexed | 2024-04-24T16:18:13Z |
format | Article |
id | doaj.art-f5835009f36d4f0e9445596a195788b7 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-24T16:18:13Z |
publishDate | 2024-03-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-f5835009f36d4f0e9445596a195788b72024-03-31T11:21:06ZengNature PortfolioScientific Reports2045-23222024-03-0114111310.1038/s41598-024-57618-6Development and validation of a semi-automated and unsupervised method for femur segmentation from CTAlessandra Aldieri0Riccardo Biondi1Antonino A. La Mattina2Julia A. Szyszko3Stefano Polizzi4Daniele Dall’Olio5Nico Curti6Gastone Castellani7Marco Viceconti8PolitoBIOMedLab, Department of Mechanical and Aerospace Engineering, Politecnico di TorinoIRCCS Bologna - Istituto delle Scienze Neurologiche di BolognaMedical Technology Lab, IRCCS Istituto Ortopedico RizzoliMedical Technology Lab, IRCCS Istituto Ortopedico RizzoliDepartment of Medical and Surgical Sciences, Alma Mater Studiorum - University of BolognaIRCCS Bologna - Istituto delle Scienze Neurologiche di BolognaIRCCS Bologna - Istituto delle Scienze Neurologiche di BolognaDepartment of Medical and Surgical Sciences, Alma Mater Studiorum - University of BolognaMedical Technology Lab, IRCCS Istituto Ortopedico RizzoliAbstract Quantitative computed tomography (QCT)-based in silico models have demonstrated improved accuracy in predicting hip fractures with respect to the current gold standard, the areal bone mineral density. These models require that the femur bone is segmented as a first step. This task can be challenging, and in fact, it is often almost fully manual, which is time-consuming, operator-dependent, and hard to reproduce. This work proposes a semi-automated procedure for femur bone segmentation from CT images. The proposed procedure is based on the bone and joint enhancement filter and graph-cut algorithms. The semi-automated procedure performances were assessed on 10 subjects through comparison with the standard manual segmentation. Metrics based on the femur geometries and the risk of fracture assessed in silico resulting from the two segmentation procedures were considered. The average Hausdorff distance (0.03 ± 0.01 mm) and the difference union ratio (0.06 ± 0.02) metrics computed between the manual and semi-automated segmentations were significantly higher than those computed within the manual segmentations (0.01 ± 0.01 mm and 0.03 ± 0.02). Besides, a blind qualitative evaluation revealed that the semi-automated procedure was significantly superior (p < 0.001) to the manual one in terms of fidelity to the CT. As for the hip fracture risk assessed in silico starting from both segmentations, no significant difference emerged between the two (R 2 = 0.99). The proposed semi-automated segmentation procedure overcomes the manual one, shortening the segmentation time and providing a better segmentation. The method could be employed within CT-based in silico methodologies and to segment large volumes of images to train and test fully automated and supervised segmentation methods.https://doi.org/10.1038/s41598-024-57618-6Bone and joint enhancement filterCTFemur segmentationFinite element modelGraph-cutSemi-automated segmentation |
spellingShingle | Alessandra Aldieri Riccardo Biondi Antonino A. La Mattina Julia A. Szyszko Stefano Polizzi Daniele Dall’Olio Nico Curti Gastone Castellani Marco Viceconti Development and validation of a semi-automated and unsupervised method for femur segmentation from CT Scientific Reports Bone and joint enhancement filter CT Femur segmentation Finite element model Graph-cut Semi-automated segmentation |
title | Development and validation of a semi-automated and unsupervised method for femur segmentation from CT |
title_full | Development and validation of a semi-automated and unsupervised method for femur segmentation from CT |
title_fullStr | Development and validation of a semi-automated and unsupervised method for femur segmentation from CT |
title_full_unstemmed | Development and validation of a semi-automated and unsupervised method for femur segmentation from CT |
title_short | Development and validation of a semi-automated and unsupervised method for femur segmentation from CT |
title_sort | development and validation of a semi automated and unsupervised method for femur segmentation from ct |
topic | Bone and joint enhancement filter CT Femur segmentation Finite element model Graph-cut Semi-automated segmentation |
url | https://doi.org/10.1038/s41598-024-57618-6 |
work_keys_str_mv | AT alessandraaldieri developmentandvalidationofasemiautomatedandunsupervisedmethodforfemursegmentationfromct AT riccardobiondi developmentandvalidationofasemiautomatedandunsupervisedmethodforfemursegmentationfromct AT antoninoalamattina developmentandvalidationofasemiautomatedandunsupervisedmethodforfemursegmentationfromct AT juliaaszyszko developmentandvalidationofasemiautomatedandunsupervisedmethodforfemursegmentationfromct AT stefanopolizzi developmentandvalidationofasemiautomatedandunsupervisedmethodforfemursegmentationfromct AT danieledallolio developmentandvalidationofasemiautomatedandunsupervisedmethodforfemursegmentationfromct AT nicocurti developmentandvalidationofasemiautomatedandunsupervisedmethodforfemursegmentationfromct AT gastonecastellani developmentandvalidationofasemiautomatedandunsupervisedmethodforfemursegmentationfromct AT marcoviceconti developmentandvalidationofasemiautomatedandunsupervisedmethodforfemursegmentationfromct |