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
2041 - Efficacy results of selective AXL inhibitor bemcentinib with pembrolizumab following chemo in patients with NSCLC
Presenter: Jose Trigo Perez
Session: Poster Display session 1
Resources:
Abstract
5444 - Analysis of the tumor microenvironment and tumor genotype through different stages of lung adenocarcinoma
Presenter: Peter Zink
Session: Poster Display session 1
Resources:
Abstract
3124 - Does Progress achieved in the Treatment of Patients with Metastatic Non-Small-Cell Lung Cancer (NSCLC) reach the Elderly Population?
Presenter: Jorune Suipyte
Session: Poster Display session 1
Resources:
Abstract
5142 - Prognostic factors for non-small cell lung cancer patients with driver mutation negative and brain metastases (HOT 1701)
Presenter: Yoshihito Ohhara
Session: Poster Display session 1
Resources:
Abstract
1580 - A novel risk classification system based on nomogram scores to predict survival of patients presenting with brain metastases at the first diagnosis of NSCLC
Presenter: Pengfei Cui
Session: Poster Display session 1
Resources:
Abstract
4442 - Comparison of real-world response rate (rwRR) to RECIST-based response rate in patients with advanced non-small cell lung cancer (aNSCLC)
Presenter: Xinran Ma
Session: Poster Display session 1
Resources:
Abstract
5405 - Estimating the cost and survival impact of new aNSCLC therapies in Canada with the iTEN model
Presenter: Parneet Kaur Cheema
Session: Poster Display session 1
Resources:
Abstract
1893 - SMARCA4 Deficient Non-Small Cell Lung Cancer (NSCLC): A Comprehensive Genomic Profiling (CGP) Study
Presenter: Stephen Graziano
Session: Poster Display session 1
Resources:
Abstract
5582 - Exploring Resistance to Nivolumab [NIV] applying an Immune Genomic Signature (IGS) in advanced pretreated NSCLC [PRINCiPe study]
Presenter: Sara Pilotto
Session: Poster Display session 1
Resources:
Abstract
1408 - DNA damage repair deficiency is associated with early resistance to crizotinib: whole-genome analysis in non-small cell lung cancer patients with ALK-fusion
Presenter: Dongyun He
Session: Poster Display session 1
Resources:
Abstract