Dataset Information

X-rays radiomics-based machine learning classification of atypical cartilaginous tumour and high-grade chondrosarcoma of long bones.

ABSTRACT:

Background

Atypical cartilaginous tumour (ACT) and high-grade chondrosarcoma (CS) of long bones are respectively managed with active surveillance or curettage and wide resection. Our aim was to determine diagnostic performance of X-rays radiomics-based machine learning for classification of ACT and high-grade CS of long bones.

Methods

This retrospective, IRB-approved study included 150 patients with surgically treated and histology-proven lesions at two tertiary bone sarcoma centres. At centre 1, the dataset was split into training (n = 71 ACT, n = 24 high-grade CS) and internal test (n = 19 ACT, n = 6 high-grade CS) cohorts, respectively, based on the date of surgery. At centre 2, the dataset constituted the external test cohort (n = 12 ACT, n = 18 high-grade CS). Manual segmentation was performed on frontal view X-rays, using MRI or CT for preliminary identification of lesion margins. After image pre-processing, radiomic features were extracted. Dimensionality reduction included stability, coefficient of variation, and mutual information analyses. In the training cohort, after class balancing, a machine learning classifier (Support Vector Machine) was automatically tuned using nested 10-fold cross-validation. Then, it was tested on both the test cohorts and compared to two musculoskeletal radiologists' performance using McNemar's test.

Findings

Five radiomic features (3 morphology, 2 texture) passed dimensionality reduction. After tuning on the training cohort (AUC = 0.75), the classifier had 80%, 83%, 79% and 80%, 89%, 67% accuracy, sensitivity, and specificity in the internal (temporally independent) and external (geographically independent) test cohorts, respectively, with no difference compared to the radiologists (p ≥ 0.617).

Interpretation

X-rays radiomics-based machine learning accurately differentiates between ACT and high-grade CS of long bones.

Funding

AIRC Investigator Grant.

SUBMITTER: Gitto S

PROVIDER: S-EPMC10884340 | biostudies-literature | 2024 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

X-rays radiomics-based machine learning classification of atypical cartilaginous tumour and high-grade chondrosarcoma of long bones.

Gitto Salvatore S Annovazzi Alessio A Nulle Kitija K Interlenghi Matteo M Salvatore Christian C Anelli Vincenzo V Baldi Jacopo J Messina Carmelo C Albano Domenico D Di Luca Filippo F Armiraglio Elisabetta E Parafioriti Antonina A Luzzati Alessandro A Biagini Roberto R Castiglioni Isabella I Sconfienza Luca Maria LM

EBioMedicine 20240219

<h4>Background</h4>Atypical cartilaginous tumour (ACT) and high-grade chondrosarcoma (CS) of long bones are respectively managed with active surveillance or curettage and wide resection. Our aim was to determine diagnostic performance of X-rays radiomics-based machine learning for classification of ACT and high-grade CS of long bones.<h4>Methods</h4>This retrospective, IRB-approved study included 150 patients with surgically treated and histology-proven lesions at two tertiary bone sarcoma centr ...[more]

PMID: 38377797

Similar Datasets

Project description:The differentiation between the atypical cartilaginous tumor (ACT) and the enchondromas is crucial as ACTs require a curettage and clinical as well as imaging follow-ups, whereas in the majority of cases enchondromas require neither a treatment nor follow-ups. Differentiating enchondromas from ACTs radiologically remains challenging. Therefore, this study evaluated imaging criteria in a combination of computed tomography (CT) and magnetic resonance (MR) imaging for the differentiation between enchondromas and ACTs in long bones. A total of 82 patients who presented consecutively at our institution with either an ACT (23, age 52.7 ±18.8 years; 14 women) or an enchondroma (59, age 46.0 ± 11.1 years; 37 women) over a period of 10 years, who had undergone preoperative MR and CT imaging and subsequent biopsy or/and surgical removal, were included in this study. A histopathological diagnosis was available in all cases. Two experienced radiologists evaluated several imaging criteria on CT and MR images. Likelihood of an ACT was significantly increased if either edema within the bone (p = 0.049), within the adjacent soft tissue (p = 0.006) or continuous growth pattern (p = 0.077) were present or if the fat entrapment (p = 0.027) was absent on MR images. Analyzing imaging features on CT, the likelihood of the diagnosis of an ACT was significantly increased if endosteal scalloping >2/3 (p < 0.001), cortical penetration (p < 0.001) and expansion of bone (p = 0.002) were present and if matrix calcifications were observed in less than 1/3 of the tumor (p = 0.013). All other imaging criteria evaluated showed no significant influence on likelihood of ACT or enchondroma (p > 0.05). In conclusion, both CT and MR imaging show suggestive signs which can help to adequately differentiate enchondromas from ACTs in long bones and therefore can improve diagnostics and consequently patient management. Nevertheless, these features are rare and a combination of CT and MR imaging features did not improve the diagnostic performance substantially.

Dataset Information

X-rays radiomics-based machine learning classification of atypical cartilaginous tumour and high-grade chondrosarcoma of long bones.

Background

Methods

Findings

Interpretation

Funding

Publications

X-rays radiomics-based machine learning classification of atypical cartilaginous tumour and high-grade chondrosarcoma of long bones.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets