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
5751 - Phase 3 ALTA-3 study of brigatinib (BRG) vs alectinib (ALC) in patients (pts) with advanced anaplastic lymphoma kinase (ALK)−positive non–small cell lung cancer (NSCLC) that progressed on crizotinib (CRZ)
Presenter: Sanjay Popat
Session: Poster Display session 1
Resources:
Abstract
5103 - CANOPY phase 3 program: Three studies evaluating canakinumab in patients with non-small cell lung cancer (NSCLC)
Presenter: Luis Paz-Ares
Session: Poster Display session 1
Resources:
Abstract
3666 - The Elderly Patient Individualized Chemotherapy (EPIC) trial, a study for an aged population of non-small cell lung cancer.
Presenter: Francesco Passiglia
Session: Poster Display session 1
Resources:
Abstract
4799 - KEYNOTE-495/KeyImPaCT: A Randomized, Biomarker-Directed, Phase 2 Trial of Pembrolizumab-Based Therapy for Non–Small Cell Lung Cancer (NSCLC)
Presenter: Martin Gutierrez
Session: Poster Display session 1
Resources:
Abstract
6035 - Safety, tolerability and activity of autologous T cells with enhanced T-cell receptors specific to NY ESO 1/LAGE 1a (GSK3377794) alone, or in combination with pembrolizumab, in advanced non small cell lung cancer: A Phase 1b/2a randomised pilot study
Presenter: Karen Reckamp
Session: Poster Display session 1
Resources:
Abstract
2176 - IFCT-1701 DICIPLE: a randomized phase 3 trial comparing continuation Nivolumab-Ipilimumab doublet immunotherapy until progression versus observation in patients with PDL1-positive stage IV Non-Small Cell Lung Cancer (NSCLC) after Nivolumab-Ipilimumab induction treatment
Presenter: Gerard Zalcman
Session: Poster Display session 1
Resources:
Abstract
2352 - ATALANTE-1 randomized phase 3 trial, OSE-2101 versus standard treatment as second or third line in HLA-A2 positive advanced non-small cell lung cancer (NSCLC) patients
Presenter: Enriqueta Felip
Session: Poster Display session 1
Resources:
Abstract
2451 - Phase Ib dose-escalation/expansion study of BI 836880, a VEGF/Ang2-blocking nanobody®, in combination with BI 754091, an anti-PD-1 antibody, in patients with advanced solid tumours
Presenter: Nicolas Girard
Session: Poster Display session 1
Resources:
Abstract
4285 - Radiosurgery followed by Tumor Treating Fields (TTFields) for brain metastases (1-10) from NSCLC in the phase 3 METIS trial
Presenter: Minesh Mehta
Session: Poster Display session 1
Resources:
Abstract
4909 - Nivolumab plus ipilimumab (NI) versus chemotherapy plus nivolumab (CN) in squamous cell lung cancer (SqCLC): the SQUINT trial
Presenter: Lorenza Landi
Session: Poster Display session 1
Resources:
Abstract