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
4811 - Comprehensive genomic profiling of thymic carcinoma in a sample Chinese population
Presenter: Baohui Han
Session: Poster Display session 1
Resources:
Abstract
2045 - The analysis of treatment sequences and clinical outcomes of thymic carcinoma
Presenter: Arakaki Motoko
Session: Poster Display session 1
Resources:
Abstract
4785 - Transcriptomic Difference of Thymoma and Thymic Carcinoma
Presenter: Naixin Liang
Session: Poster Display session 1
Resources:
Abstract
2864 - A Phase II Trial of Preoperative Chemoradiotherapy and Pembrolizumab for Locally Advanced Esophageal Squamous Cell Carcinoma (ESCC)
Presenter: Seoyoung Lee
Session: Poster Display session 1
Resources:
Abstract
5015 - The study of tumor associated exosomes in crosstalk between esophageal carcinoma and lymphatic endothelial cells
Presenter: Weimin Mao
Session: Poster Display session 1
Resources:
Abstract
1339 - Up-regulation of IBSP expression predicts poor prognosis of Esophageal Squamous Cell Carcinoma patients
Presenter: Mingyue Wang
Session: Poster Display session 1
Resources:
Abstract
4083 - PD-L1 expression in primary tumour vs metastatic samples in the Phase 3 MYSTIC study in first-line metastatic (m) NSCLC
Presenter: Niels Reinmuth
Session: Poster Display session 1
Resources:
Abstract
5113 - Assessing the impact of subsequent checkpoint inhibitor (CPI) treatment on overall survival: post hoc analyses from the phase 3 JAVELIN Lung 200 study of avelumab vs docetaxel in platinum-treated locally advanced/metastatic non-small cell lung cancer (NSCLC)
Presenter: Fabrice Barlesi
Session: Poster Display session 1
Resources:
Abstract
4256 - Long-term avelumab treatment in patients with advanced non-small cell lung cancer (NSCLC): post hoc analyses from JAVELIN Solid Tumor
Presenter: Borys Hrinczenko
Session: Poster Display session 1
Resources:
Abstract
4305 - Effectiveness and safety of nivolumab in the treatment of lung cancer patients in France: Updated survival and subgroup analysis from the real-world EVIDENS study
Presenter: Fabrice Barlesi
Session: Poster Display session 1
Resources:
Abstract