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
2432 - Retrospective comparative study of the efficacy and safety in docetaxel and ramucirumab combination chemotherapy with or without previous immune checkpoint inhibitor treatment.
Presenter: Daijiro Harada
Session: Poster Display session 1
Resources:
Abstract
2791 - Efficacy of weekly paclitaxel-bevacizumab combination in advanced non squamous non-small cell lung cancer (NSCLC) : a retrospective multicentric study.
Presenter: Geoffroy Bilger
Session: Poster Display session 1
Resources:
Abstract
2916 - Post progression survival for patients treated with docetaxel/nintedanib in the SENECA trial
Presenter: Enrica Capelletto
Session: Poster Display session 1
Resources:
Abstract
1427 - Final results of randomized phase II trial of metronomic vs weekly oral vinorelbine (OV) as first-line chemotherapy (CT) in advanced NSCLC patients unfit to platinum-based CT (P-CT): Tempo-Lung EudraCT Number: 2014-003859-61
Presenter: Dariusz Kowalski
Session: Poster Display session 1
Resources:
Abstract
3789 - Pioglitazone and clarithromycin combined with metronomic low-dose chemotherapy versus nivolumab in patients with advanced non–small-cell lung cancer treated in 2nd-line and beyond: Outcomes from a randomized phase II trial (ModuLung)
Presenter: Daniel Heudobler
Session: Poster Display session 1
Resources:
Abstract
1519 - Predicting Chemotherapy Toxicity in Elderly Patients with Advanced Non-small Cell Lung Cancer: A Prospective Multicenter Study of the National Hospital Organization in Japan
Presenter: Masaki Kanazu
Session: Poster Display session 1
Resources:
Abstract
1874 - A prospective phase II trial of carboplatin (CBDCA) and nab-paclitaxel (nabPTX) for advanced non-small cell lung cancer (NSCLC) with interstitial lung disease (ILD)
Presenter: Toshiyuki Harada
Session: Poster Display session 1
Resources:
Abstract
3819 - Weekly Epirubicin as palliative treatment in elderly patients with malignant pleural mesothelioma.
Presenter: Paola Candido
Session: Poster Display session 1
Resources:
Abstract
3390 - Survival Prolongation by Rationale INnovative Genomics (SPRING): An international WIN Consortium phase I study exploring safety and efficacy of avelumab, palbociclib, and axitinib in advanced non-small cell lung cancer (NSCLC) with integrated genomic and transcriptomic correlates.
Presenter: Benjamin Solomon
Session: Poster Display session 1
Resources:
Abstract
5069 - Preliminary results from phase 1b study of spartalizumab plus chemotherapy for advanced non-small cell lung cancer (NSCLC)
Presenter: Armando Santoro
Session: Poster Display session 1
Resources:
Abstract