MRI radiomics-based machine learning classification of atypical cartilaginous tumour and grade II chondrosarcoma of long bones.
Artificial intelligence
bone neoplasms
chondrosarcoma
machine learning
magnetic resonance imaging
Journal
EBioMedicine
ISSN: 2352-3964
Titre abrégé: EBioMedicine
Pays: Netherlands
ID NLM: 101647039
Informations de publication
Date de publication:
Jan 2022
Jan 2022
Historique:
received:
25
09
2021
revised:
24
11
2021
accepted:
30
11
2021
pubmed:
22
12
2021
medline:
1
4
2022
entrez:
21
12
2021
Statut:
ppublish
Résumé
Atypical cartilaginous tumour (ACT) and grade II chondrosarcoma (CS2) of long bones are respectively managed with watchful waiting or curettage and wide resection. Preoperatively, imaging diagnosis can be challenging due to interobserver variability and biopsy suffers from sample errors. The aim of this study is to determine diagnostic performance of MRI radiomics-based machine learning in differentiating ACT from CS2 of long bones. One-hundred-fifty-eight patients with surgically treated and histology-proven cartilaginous bone tumours were retrospectively included at two tertiary bone tumour centres. The training cohort consisted of 93 MRI scans from centre 1 (n=74 ACT; n=19 CS2). The external test cohort consisted of 65 MRI scans from centre 2 (n=45 ACT; n=20 CS2). Bidimensional segmentation was performed on T1-weighted MRI. Radiomic features were extracted. After dimensionality reduction and class balancing in centre 1, a machine-learning classifier (Extra Trees Classifier) was tuned on the training cohort using 10-fold cross-validation and tested on the external test cohort. In centre 2, its performance was compared with an experienced musculoskeletal oncology radiologist using McNemar's test. After tuning on the training cohort (AUC=0.88), the machine-learning classifier had 92% accuracy (60/65, AUC=0.94) in identifying the lesions in the external test cohort. Its accuracies in correctly classifying ACT and CS2 were 98% (44/45) and 80% (16/20), respectively. The radiologist had 98% accuracy (64/65) with no difference compared to the classifier (p=0.134). Machine learning showed high accuracy in classifying ACT and CS2 of long bones based on MRI radiomic features. ESSR Young Researchers Grant.
Sections du résumé
BACKGROUND
BACKGROUND
Atypical cartilaginous tumour (ACT) and grade II chondrosarcoma (CS2) of long bones are respectively managed with watchful waiting or curettage and wide resection. Preoperatively, imaging diagnosis can be challenging due to interobserver variability and biopsy suffers from sample errors. The aim of this study is to determine diagnostic performance of MRI radiomics-based machine learning in differentiating ACT from CS2 of long bones.
METHODS
METHODS
One-hundred-fifty-eight patients with surgically treated and histology-proven cartilaginous bone tumours were retrospectively included at two tertiary bone tumour centres. The training cohort consisted of 93 MRI scans from centre 1 (n=74 ACT; n=19 CS2). The external test cohort consisted of 65 MRI scans from centre 2 (n=45 ACT; n=20 CS2). Bidimensional segmentation was performed on T1-weighted MRI. Radiomic features were extracted. After dimensionality reduction and class balancing in centre 1, a machine-learning classifier (Extra Trees Classifier) was tuned on the training cohort using 10-fold cross-validation and tested on the external test cohort. In centre 2, its performance was compared with an experienced musculoskeletal oncology radiologist using McNemar's test.
FINDINGS
RESULTS
After tuning on the training cohort (AUC=0.88), the machine-learning classifier had 92% accuracy (60/65, AUC=0.94) in identifying the lesions in the external test cohort. Its accuracies in correctly classifying ACT and CS2 were 98% (44/45) and 80% (16/20), respectively. The radiologist had 98% accuracy (64/65) with no difference compared to the classifier (p=0.134).
INTERPRETATION
CONCLUSIONS
Machine learning showed high accuracy in classifying ACT and CS2 of long bones based on MRI radiomic features.
FUNDING
BACKGROUND
ESSR Young Researchers Grant.
Identifiants
pubmed: 34933178
pii: S2352-3964(21)00551-X
doi: 10.1016/j.ebiom.2021.103757
pmc: PMC8688587
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
103757Informations de copyright
Copyright © 2021 The Authors. Published by Elsevier B.V. All rights reserved.
Déclaration de conflit d'intérêts
Declaration of interests The authors declare no potential conflict of interest related to this work.