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
3409 - Effect and safety of immune checkpoint inhibitors for brain metastases from non-small cell lung cancer
Presenter: Toshihiko Iuchi
Session: Poster Display session 1
Resources:
Abstract
3683 - Impact of Radiotherapy on efficacy of anti-programmed death 1 (PD-1) antibodies in metastatic NSCLC
Presenter: Evangeline Samuel
Session: Poster Display session 1
Resources:
Abstract
3924 - Pembrolizumab frontline monotherapy in patients with NSCLC and high PD-L1 expression: Real World Data from a European Cohort with focus on subgroups of interest
Presenter: Giannis Mountzios
Session: Poster Display session 1
Resources:
Abstract
3970 - Patients with metastatic non-small cell lung cancer and PD-L1 expression in Germany. Treatment and first outcome from the prospective German Registry Platform CRISP (AIO-TRK-0315)
Presenter: Martin Sebastian
Session: Poster Display session 1
Resources:
Abstract
5350 - The efficacy and safety of pembrolizumab as a first-line therapy in PD-L1 50% positive advanced NSCLC (HOPE-001)
Presenter: Motohiro Tamiya
Session: Poster Display session 1
Resources:
Abstract
3832 - Osimertinib in epidermal growth factor receptor (EGFR) T790M advanced non-small cell lung cancer (NSCLC): analysis of patients with central nervous system (CNS) metastases in a real-world study (ASTRIS)
Presenter: Giulio Metro
Session: Poster Display session 1
Resources:
Abstract
4082 - Real-world (RW) treatment patterns and outcomes for second-line (2L) therapy and beyond in patients (pts) with epidermal growth factor receptor-mutated (EGFRm) advanced NSCLC receiving a first-line (1L) first- or second-generation (1G/2G) EGFR tyrosine kinase inhibitor (TKI)
Presenter: Riyaz Shah
Session: Poster Display session 1
Resources:
Abstract
2855 - Impact of ramucirumab (RAM) + erlotinib (ERL) on EGFR mutations in circulating tumor DNA – The 1st report of a biomarker study in Japanese patients from RELAY: Global Ph3 study of ERL + RAM or placebo (PL) in 1L metastatic NSCLC with EGFR activating mutations
Presenter: Kazuto Nishio
Session: Poster Display session 1
Resources:
Abstract
2911 - Apatinib combined with EGFR - TKI in treating advanced non-small cell lung cancer with EGFR - TKI resistance
Presenter: Ruifen Tian
Session: Poster Display session 1
Resources:
Abstract
2100 - Updated analysis of a phase I trial of afatinib (Afa) and bevacizumab (Bev) in chemo-naïve patients (pts) with advanced non-small-cell lung cancer (NSCLC) harboring EGFR-mutations: OLCSG1404
Presenter: Takashi Ninomiya
Session: Poster Display session 1
Resources:
Abstract