Cargando…

Deep Learning for Automated Measurement of Patellofemoral Anatomic Landmarks

Background: Patellofemoral anatomy has not been well characterized. Applying deep learning to automatically measure knee anatomy can provide a better understanding of anatomy, which can be a key factor in improving outcomes. Methods: 483 total patients with knee CT imaging (April 2017–May 2022) from...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Zelong, Zhou, Alexander, Fauveau, Valentin, Lee, Justine, Marcadis, Philip, Fayad, Zahi A., Chan, Jimmy J., Gladstone, James, Mei, Xueyan, Huang, Mingqian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10376187/
https://www.ncbi.nlm.nih.gov/pubmed/37508842
http://dx.doi.org/10.3390/bioengineering10070815
_version_ 1785079208738816000
author Liu, Zelong
Zhou, Alexander
Fauveau, Valentin
Lee, Justine
Marcadis, Philip
Fayad, Zahi A.
Chan, Jimmy J.
Gladstone, James
Mei, Xueyan
Huang, Mingqian
author_facet Liu, Zelong
Zhou, Alexander
Fauveau, Valentin
Lee, Justine
Marcadis, Philip
Fayad, Zahi A.
Chan, Jimmy J.
Gladstone, James
Mei, Xueyan
Huang, Mingqian
author_sort Liu, Zelong
collection PubMed
description Background: Patellofemoral anatomy has not been well characterized. Applying deep learning to automatically measure knee anatomy can provide a better understanding of anatomy, which can be a key factor in improving outcomes. Methods: 483 total patients with knee CT imaging (April 2017–May 2022) from 6 centers were selected from a cohort scheduled for knee arthroplasty and a cohort with healthy knee anatomy. A total of 7 patellofemoral landmarks were annotated on 14,652 images and approved by a senior musculoskeletal radiologist. A two-stage deep learning model was trained to predict landmark coordinates using a modified ResNet50 architecture initialized with self-supervised learning pretrained weights on RadImageNet. Landmark predictions were evaluated with mean absolute error, and derived patellofemoral measurements were analyzed with Bland–Altman plots. Statistical significance of measurements was assessed by paired t-tests. Results: Mean absolute error between predicted and ground truth landmark coordinates was 0.20/0.26 cm in the healthy/arthroplasty cohort. Four knee parameters were calculated, including transepicondylar axis length, transepicondylar-posterior femur axis angle, trochlear medial asymmetry, and sulcus angle. There were no statistically significant parameter differences (p > 0.05) between predicted and ground truth measurements in both cohorts, except for the healthy cohort sulcus angle. Conclusion: Our model accurately identifies key trochlear landmarks with ~0.20–0.26 cm accuracy and produces human-comparable measurements on both healthy and pathological knees. This work represents the first deep learning regression model for automated patellofemoral annotation trained on both physiologic and pathologic CT imaging at this scale. This novel model can enhance our ability to analyze the anatomy of the patellofemoral compartment at scale.
format Online
Article
Text
id pubmed-10376187
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-103761872023-07-29 Deep Learning for Automated Measurement of Patellofemoral Anatomic Landmarks Liu, Zelong Zhou, Alexander Fauveau, Valentin Lee, Justine Marcadis, Philip Fayad, Zahi A. Chan, Jimmy J. Gladstone, James Mei, Xueyan Huang, Mingqian Bioengineering (Basel) Article Background: Patellofemoral anatomy has not been well characterized. Applying deep learning to automatically measure knee anatomy can provide a better understanding of anatomy, which can be a key factor in improving outcomes. Methods: 483 total patients with knee CT imaging (April 2017–May 2022) from 6 centers were selected from a cohort scheduled for knee arthroplasty and a cohort with healthy knee anatomy. A total of 7 patellofemoral landmarks were annotated on 14,652 images and approved by a senior musculoskeletal radiologist. A two-stage deep learning model was trained to predict landmark coordinates using a modified ResNet50 architecture initialized with self-supervised learning pretrained weights on RadImageNet. Landmark predictions were evaluated with mean absolute error, and derived patellofemoral measurements were analyzed with Bland–Altman plots. Statistical significance of measurements was assessed by paired t-tests. Results: Mean absolute error between predicted and ground truth landmark coordinates was 0.20/0.26 cm in the healthy/arthroplasty cohort. Four knee parameters were calculated, including transepicondylar axis length, transepicondylar-posterior femur axis angle, trochlear medial asymmetry, and sulcus angle. There were no statistically significant parameter differences (p > 0.05) between predicted and ground truth measurements in both cohorts, except for the healthy cohort sulcus angle. Conclusion: Our model accurately identifies key trochlear landmarks with ~0.20–0.26 cm accuracy and produces human-comparable measurements on both healthy and pathological knees. This work represents the first deep learning regression model for automated patellofemoral annotation trained on both physiologic and pathologic CT imaging at this scale. This novel model can enhance our ability to analyze the anatomy of the patellofemoral compartment at scale. MDPI 2023-07-08 /pmc/articles/PMC10376187/ /pubmed/37508842 http://dx.doi.org/10.3390/bioengineering10070815 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Liu, Zelong
Zhou, Alexander
Fauveau, Valentin
Lee, Justine
Marcadis, Philip
Fayad, Zahi A.
Chan, Jimmy J.
Gladstone, James
Mei, Xueyan
Huang, Mingqian
Deep Learning for Automated Measurement of Patellofemoral Anatomic Landmarks
title Deep Learning for Automated Measurement of Patellofemoral Anatomic Landmarks
title_full Deep Learning for Automated Measurement of Patellofemoral Anatomic Landmarks
title_fullStr Deep Learning for Automated Measurement of Patellofemoral Anatomic Landmarks
title_full_unstemmed Deep Learning for Automated Measurement of Patellofemoral Anatomic Landmarks
title_short Deep Learning for Automated Measurement of Patellofemoral Anatomic Landmarks
title_sort deep learning for automated measurement of patellofemoral anatomic landmarks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10376187/
https://www.ncbi.nlm.nih.gov/pubmed/37508842
http://dx.doi.org/10.3390/bioengineering10070815
work_keys_str_mv AT liuzelong deeplearningforautomatedmeasurementofpatellofemoralanatomiclandmarks
AT zhoualexander deeplearningforautomatedmeasurementofpatellofemoralanatomiclandmarks
AT fauveauvalentin deeplearningforautomatedmeasurementofpatellofemoralanatomiclandmarks
AT leejustine deeplearningforautomatedmeasurementofpatellofemoralanatomiclandmarks
AT marcadisphilip deeplearningforautomatedmeasurementofpatellofemoralanatomiclandmarks
AT fayadzahia deeplearningforautomatedmeasurementofpatellofemoralanatomiclandmarks
AT chanjimmyj deeplearningforautomatedmeasurementofpatellofemoralanatomiclandmarks
AT gladstonejames deeplearningforautomatedmeasurementofpatellofemoralanatomiclandmarks
AT meixueyan deeplearningforautomatedmeasurementofpatellofemoralanatomiclandmarks
AT huangmingqian deeplearningforautomatedmeasurementofpatellofemoralanatomiclandmarks