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
2023 - Patients with brain metastases treated with afatinib in clinical practice – results from the prospective non-interventional study GIDEON
Presenter: Eckart Laack
Session: Poster Display session 1
Resources:
Abstract
1613 - Lerociclib (G1T38), an oral CDK4/6 inhibitor, dosed continuously in combination with osimertinib for EGFRmut non-small cell lung cancer: initial Phase 1b results
Presenter: David Berz
Session: Poster Display session 1
Resources:
Abstract
2853 - Real-world implementation of sequential targeted therapies for EGFR-mutated NSCLC
Presenter: Petros Christopoulos
Session: Poster Display session 1
Resources:
Abstract
1974 - A Phase II Open-Label, Multicentre Study to Assess the Anti-tumour Activity of Afatinib in Patients with Activating Epidermal Growth Factor Receptor mutation (EGFRm) from Circulating Tumor DNA (CtDNA)
Presenter: Young-Chul Kim
Session: Poster Display session 1
Resources:
Abstract
3370 - Influence of cow’s milk on the absorption and exposure of erlotinib in NSCLC patients
Presenter: Geerten Veerman
Session: Poster Display session 1
Resources:
Abstract
5900 - PTEN loss as Predictor of Tumor Heterogeneity (TH) and Poor Prognosis in EGFR-mutant Advanced Non-Small Cell Lung Cancer (ANSCLC) Patients (pts) Receiving Tyrosine-Kinase Inhibitors (TKIs).
Presenter: Miriam Ferrara
Session: Poster Display session 1
Resources:
Abstract
1302 - Safety of lorlatinib in subgroups of patients from a phase 1/2 trial
Presenter: Enriqueta Felip
Session: Poster Display session 1
Resources:
Abstract
1497 - Brigatinib (BRG) in Asian vs non-Asian patients (pts) with crizotinib (CRZ)-refractory ALK+ NSCLC in the phase 2 ALTA trial
Presenter: Dae Ho Lee
Session: Poster Display session 1
Resources:
Abstract
2349 - The safety assessment of crizotinib and alectinib from real world data of 840 ALK-inhibitor naïve patients with NSCLC harboring ALK-rearrangement (WJOG9516L).
Presenter: Kei Kunimasa
Session: Poster Display session 1
Resources:
Abstract
1120 - Brigatinib in ALK TKI-pretreated ALK+ metastatic non-small cell lung cancer (mNSCLC): the Use Via Expanded Access to Brigatinib (UVEA-Brig) study
Presenter: Silvia Novello
Session: Poster Display session 1
Resources:
Abstract