Segmentation of the thoracolumbar fascia in ultrasound imaging: a deep learning approach

Abstract Background Only in recent years it has been demonstrated that the thoracolumbar fascia is involved in low back pain (LBP), thus highlighting its implications for treatments. Furthermore, an easily accessible and non-invasive way to investigate the fascia in real time is the ultrasound exami...

Full description

Saved in:
Bibliographic Details
Main Authors: Lorenza Bonaldi, Carmelo Pirri, Federico Giordani, Chiara Giulia Fontanella, Carla Stecco, Francesca Uccheddu
Format: Article
Language:English
Published: BMC 2025-05-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01720-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850154774581739520
author Lorenza Bonaldi
Carmelo Pirri
Federico Giordani
Chiara Giulia Fontanella
Carla Stecco
Francesca Uccheddu
author_facet Lorenza Bonaldi
Carmelo Pirri
Federico Giordani
Chiara Giulia Fontanella
Carla Stecco
Francesca Uccheddu
author_sort Lorenza Bonaldi
collection DOAJ
description Abstract Background Only in recent years it has been demonstrated that the thoracolumbar fascia is involved in low back pain (LBP), thus highlighting its implications for treatments. Furthermore, an easily accessible and non-invasive way to investigate the fascia in real time is the ultrasound examination, which to be reliable as is, it must overcome the challenges related to the configuration of the machine and the experience of the operator. Therefore, the lack of a clear understanding of the fascial system combined with the penalty related to the setting of the ultrasound acquisition has generated a gap that makes its effective evaluation difficult during clinical routine. The aim of the present work is to fill this gap by investigating the effectiveness of using a deep learning approach to segment the thoracolumbar fascia from ultrasound imaging. Methods A total of 538 ultrasound images of the thoracolumbar fascia of LBP subjects were finally used to train and test a deep learning network. An additional test set (so-called Test set 2) was collected from another center, operator, machine manufacturer, patient cohort, and protocol to improve the generalizability of the study. Results A U-Net-based architecture was demonstrated to be able to segment these structures with a final training accuracy of 0.99 and a validation accuracy of 0.91. The accuracy of the prediction computed on a test set (87 images not included in the training set) reached the 0.94, with a mean intersection over union index of 0.82 and a Dice-score of 0.76. These latter metrics were outperformed by those in Test set 2. The validity of the predictions was also verified and confirmed by two expert clinicians. Conclusions Automatic identification of the thoracolumbar fascia has shown promising results to thoroughly investigate its alteration and target a personalized rehabilitation intervention based on each patient-specific scenario.
format Article
id doaj-art-c0a8f6210fa74ee78f3f7ef196dd9db7
institution OA Journals
issn 1471-2342
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-c0a8f6210fa74ee78f3f7ef196dd9db72025-08-20T02:25:12ZengBMCBMC Medical Imaging1471-23422025-05-012511710.1186/s12880-025-01720-2Segmentation of the thoracolumbar fascia in ultrasound imaging: a deep learning approachLorenza Bonaldi0Carmelo Pirri1Federico Giordani2Chiara Giulia Fontanella3Carla Stecco4Francesca Uccheddu5Department of Civil, Environmental and Architectural Engineering, University of PadovaCenter for Mechanics of Biological Materials, University of PadovaNeurological Rehabilitation CentreCenter for Mechanics of Biological Materials, University of PadovaCenter for Mechanics of Biological Materials, University of PadovaCenter for Mechanics of Biological Materials, University of PadovaAbstract Background Only in recent years it has been demonstrated that the thoracolumbar fascia is involved in low back pain (LBP), thus highlighting its implications for treatments. Furthermore, an easily accessible and non-invasive way to investigate the fascia in real time is the ultrasound examination, which to be reliable as is, it must overcome the challenges related to the configuration of the machine and the experience of the operator. Therefore, the lack of a clear understanding of the fascial system combined with the penalty related to the setting of the ultrasound acquisition has generated a gap that makes its effective evaluation difficult during clinical routine. The aim of the present work is to fill this gap by investigating the effectiveness of using a deep learning approach to segment the thoracolumbar fascia from ultrasound imaging. Methods A total of 538 ultrasound images of the thoracolumbar fascia of LBP subjects were finally used to train and test a deep learning network. An additional test set (so-called Test set 2) was collected from another center, operator, machine manufacturer, patient cohort, and protocol to improve the generalizability of the study. Results A U-Net-based architecture was demonstrated to be able to segment these structures with a final training accuracy of 0.99 and a validation accuracy of 0.91. The accuracy of the prediction computed on a test set (87 images not included in the training set) reached the 0.94, with a mean intersection over union index of 0.82 and a Dice-score of 0.76. These latter metrics were outperformed by those in Test set 2. The validity of the predictions was also verified and confirmed by two expert clinicians. Conclusions Automatic identification of the thoracolumbar fascia has shown promising results to thoroughly investigate its alteration and target a personalized rehabilitation intervention based on each patient-specific scenario.https://doi.org/10.1186/s12880-025-01720-2SegmentationDeep learningDeep fasciaThoracolumbarLow back pain
spellingShingle Lorenza Bonaldi
Carmelo Pirri
Federico Giordani
Chiara Giulia Fontanella
Carla Stecco
Francesca Uccheddu
Segmentation of the thoracolumbar fascia in ultrasound imaging: a deep learning approach
BMC Medical Imaging
Segmentation
Deep learning
Deep fascia
Thoracolumbar
Low back pain
title Segmentation of the thoracolumbar fascia in ultrasound imaging: a deep learning approach
title_full Segmentation of the thoracolumbar fascia in ultrasound imaging: a deep learning approach
title_fullStr Segmentation of the thoracolumbar fascia in ultrasound imaging: a deep learning approach
title_full_unstemmed Segmentation of the thoracolumbar fascia in ultrasound imaging: a deep learning approach
title_short Segmentation of the thoracolumbar fascia in ultrasound imaging: a deep learning approach
title_sort segmentation of the thoracolumbar fascia in ultrasound imaging a deep learning approach
topic Segmentation
Deep learning
Deep fascia
Thoracolumbar
Low back pain
url https://doi.org/10.1186/s12880-025-01720-2
work_keys_str_mv AT lorenzabonaldi segmentationofthethoracolumbarfasciainultrasoundimagingadeeplearningapproach
AT carmelopirri segmentationofthethoracolumbarfasciainultrasoundimagingadeeplearningapproach
AT federicogiordani segmentationofthethoracolumbarfasciainultrasoundimagingadeeplearningapproach
AT chiaragiuliafontanella segmentationofthethoracolumbarfasciainultrasoundimagingadeeplearningapproach
AT carlastecco segmentationofthethoracolumbarfasciainultrasoundimagingadeeplearningapproach
AT francescauccheddu segmentationofthethoracolumbarfasciainultrasoundimagingadeeplearningapproach