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
3020 - Circulating tumor DNA (ctDNA) analysis depicts mechanisms of resistance and tumor response to BRAF inhibitors in BRAF-mutant non-small cell lung cancer (NSCLC)
Presenter: Sandra Ortiz - Cuaran
Session: Poster Display session 1
Resources:
Abstract
1271 - A large scale prospective concordance study of oncogene driver detection between plasma- and tissue-based NGS analysis in advanced non-small cell lung cancer (NSCLC).
Presenter: Ryo Itotani
Session: Poster Display session 1
Resources:
Abstract
1132 - Biomarker status as a mediator of age-related overall survival (OS) in advanced non-small cell lung cancer (aNSCLC)
Presenter: Aaron Cohen
Session: Poster Display session 1
Resources:
Abstract
1502 - An exploratory analysis of on-treatment ctDNA measurement as a potential surrogate for overall survival for atezolizumab benefit in the OAK Study
Presenter: David Gandara
Session: Poster Display session 1
Resources:
Abstract
3912 - Disease monitoring of EGFR mutation-positive NSCLC patients via circulating tumor DNA
Presenter: Wei Fang Hsu
Session: Poster Display session 1
Resources:
Abstract
3856 - Incidence of T790M in NSCLC patients progressed to gefitinib, erlotinib, and afatinib: a study on circulating tumor DNA
Presenter: Romano Danesi
Session: Poster Display session 1
Resources:
Abstract
1330 - Folate receptor-positive circulating tumor cells as a predictive biomarker for the efficacy of first-line pemetrexed-based therapy in patients with non-squamous non-small cell lung cancer
Presenter: Xiaoxia Chen
Session: Poster Display session 1
Resources:
Abstract
3512 - Carcinoembryonic Antigen of Cerebrospinal Fluid Predict Prognosis of Leptomeningeal Metastasis from Non-Small Cell Lung Cancer
Presenter: Junjie Zhen
Session: Poster Display session 1
Resources:
Abstract
3852 - Liquid biopsy in clinical pratice of Non-Small-Cell-Lung Cancer (NSCLC): a multi-institutional experience
Presenter: Giovanna De Maglio
Session: Poster Display session 1
Resources:
Abstract
1205 - A Phase III Study Comparing SB8, a Proposed Bevacizumab Biosimilar, and Reference Bevacizumab in Patients with Metastatic or Recurrent Non-squamous NSCLC
Presenter: Martin Reck
Session: Poster Display session 1
Resources:
Abstract