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
3620 - Safety, efficacy, PK and PD biomarker results of the first-in-human study of mutant isocitrate dehydrogenase 1 (mIDH1) inhibitor BAY 1436032 in patients (pts) with mIDH1 advanced solid tumours
Presenter: Wolfgang Wick
Session: Poster Display session 1
Resources:
Abstract
5465 - Proof of concept clinical study by US-guided intratumor injection of VCN-01, an oncolytic adenovirus expressing hyaluronidase in patients with pancreatic cancer
Presenter: Manuel Hidalgo
Session: Poster Display session 1
Resources:
Abstract
2555 - A Phase 1a/b first-in-human, open-label, dose-escalation, safety, PK and PD study of TP-0903 in solid tumors
Presenter: John Sarantopoulos
Session: Poster Display session 1
Resources:
Abstract
3533 - First in human phase 1/2a study of PEN-866, a Heat Shock Protein 90 (HSP90) ligand – SN38 conjugate for patients with advanced solid tumors: Phase 1 results
Presenter: Johanna Bendell
Session: Poster Display session 1
Resources:
Abstract
4114 - A Phase I Open-Label, Non-Randomized Study of Recombinant Super-Compound Interferon (rSIFN-co) In Patients with Advanced Solid Tumors
Presenter: Amanda Seet
Session: Poster Display session 1
Resources:
Abstract
2537 - Evaluation of Pharmacodynamic (PD) Biomarkers in Advanced Cancer Patients Treated with Oxidative Phosphorylation (OXPHOS) Inhibitor, OPC-317 (OPC)
Presenter: Jie Qing Eu
Session: Poster Display session 1
Resources:
Abstract
5764 - Pharmacokinetic (PK) assessment of BT1718: A phase 1/2a study of BT1718, a first in class Bicycle Toxin Conjugate (BTC), in patients (pts) with advanced solid tumours
Presenter: Natalie Cook
Session: Poster Display session 1
Resources:
Abstract
2683 - A phase I open label dose escalation trial evaluating VT1021 in patients with advanced solid tumors.
Presenter: Wael Harb
Session: Poster Display session 1
Resources:
Abstract
3609 - Interim Results from Trial of SL-801, a Novel XPO-1 Inhibitor, in Patients with Advanced Solid Tumors
Presenter: Judy Wang
Session: Poster Display session 1
Resources:
Abstract
3485 - Phase 1 Trial of Fruquintinib in Patients with Advanced Solid Tumors: Results of the Dose Escalation Phase
Presenter: Andrea Wang-Gillam
Session: Poster Display session 1
Resources:
Abstract