Abstract 2737
Background
Well-differentiated liposarcomas (WDLPS) can be difficult to distinguish from lipomas. Currently, this distinction is made by testing for MDM2-amplification, which requires a biopsy. The aim of this study was to non-invasively predict the MDM2-amplification status using radiomics, i.e. a combination of quantitative imaging features and machine learning techniques, thereby differentiating between lipomas and WDLPS.
Methods
Patients with a lipoma or WDLPS, a known MDM2-amplification status and a pre-treatment T1-weighted MRI scan who were referred to or diagnosed at the Erasmus MC from 2009-2018 were included. When available, other sequences, e.g. T2-weighted (fat-saturated) MRI, were included in the radiomics analysis. Imaging features describing intensity, shape, orientation and texture were extracted from the tumor segmentations; age, gender, tumor depth and tumor localization were added as semantic features. Classification was performed using an ensemble of various machine learning approaches. Evaluation was performed through 100x random-split cross-validation.
Results
We included 116 patients: 58 patients with lipoma and 58 patients with WDLPS. The dataset originated from 41 MRI-scanners, resulting in large heterogeneity in imaging hardware and acquisition protocols. The best performing radiomics approach to differentiate between WDLPS and lipomas, based on T1-weighted imaging only, resulted in a mean [95% confidence interval] AUC of 0.75 [0.65-0.86], accuracy of 0.68 [0.59-0.77], sensitivity of 0.63 [0.48-0.78] and specificity of 0.73 [0.59-0.87]. A model based on the combination of imaging and semantic featured showed only a minor and non-significant improvement in performance.
Conclusions
There is a significant relationship between a radiomics signature, consisting of a combination of quantitative MRI features, and the MDM2-amplification status. Although further optimization and validation is needed for the transition to clinical practice, radiomics has appeared to be a promising, non-invasive approach for the classification of WDLPS and lipomas.
Clinical trial identification
Editorial acknowledgement
M.Vos and M.P.A. Starmans contributed equally to this study.
Legal entity responsible for the study
The authors.
Funding
Stichting Coolsingel, Netherlands Organisation for Scientific Research, Dutch Cancer Society.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
4325 - Multiple synchronous mechanisms may contribute to osimertinib resistance in non-small cell lung cancer (NSCLC) patients: insights of the MATCH-R study
Presenter: Diego Enrico
Session: Poster Display session 1
Resources:
Abstract
2185 - Sequential treatment with afatinib followed by 3rd generation EGFR-TKI – subgroup analysis of the GIDEON trial: a prospective non-interventional study (NIS) in EGFR mutated NSCLC patients in Germany
Presenter: Wolfgang Brückl
Session: Poster Display session 1
Resources:
Abstract
1524 - Effectiveness of sequencing TKIs in patients with EGFR mutation-positive Non-small-Cell Lung Cancer (NSCLC): A French National medico administrative claim database analysis
Presenter: Nicolas Girard
Session: Poster Display session 1
Resources:
Abstract
5733 - Phase II study of osimertinib in NSCLC patients with EGFR exon 20 insertion mutation: A multicenter trial of the Korean Cancer Study Group (LU17-19)
Presenter: Tae Min Kim
Session: Poster Display session 1
Resources:
Abstract
5440 - Different stories for different EGFR exon 19 deletion variants
Presenter: Chao Zhao
Session: Poster Display session 1
Resources:
Abstract
2982 - Safety and activity of alflutinib in patients with advanced EGFR T790M mutation non-small cell lung cancer who progressed after EGFR-TKI therapy
Presenter: Yuan-Kai Shi
Session: Poster Display session 1
Resources:
Abstract
4002 - Afatinib followed by osimertinib in patients with EGFR mutation-positive (EGFRm+) advanced NSCLC: updated data from the GioTag real-world study
Presenter: Maximilian Hochmair
Session: Poster Display session 1
Resources:
Abstract
2941 - Treatment patterns of EGFR mt+ NSCLC IV pts: Real world data of the NOWEL network
Presenter: Julia Roeper
Session: Poster Display session 1
Resources:
Abstract
4154 - TP53 mutations predicts worse prognosis in EGFR-mutated NSCLC patients receiving TKIs in first- or further line of treatment
Presenter: Matteo Canale
Session: Poster Display session 1
Resources:
Abstract
1175 - HER3 ligand heregulin expression and clinical implication in patients with epidermal growth factor receptor (EGFR)-mutant non-small cell lung cancer treated with EGFR-tyrosine kinase inhibitors
Presenter: Kimio Yonesaka
Session: Poster Display session 1
Resources:
Abstract