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
3317 - Circulating tumor DNA (ctDNA) analysis in patients (pts) with non-small cell lung cancer (NSCLC) treated with telisotuzumab vedotin (teliso-v), an antibody-drug conjugate targeting c-Met
Presenter: Rebecca Heist
Session: Poster Display session 1
Resources:
Abstract
3887 - First Real Life Data on Durvalumab after definitive concomitant ChemoRadiotherapy (cCRT) in unresectable Stage (St) III Non-Small Cell Lung Cancer (NSCLC) in France: Analysis of 591 patients (pts) enrolled in the French cohort (c) Temporary Authorization of Use (ATU)
Presenter: Virginie Avrillon
Session: Poster Display session 1
Resources:
Abstract
682 - EGFR Inhibitor Versus Chemotherapy as Adjuvant Treatment for Locally-advanced EGFR-mutant Non-Small Cell Lung Cancer
Presenter: Peng Xie
Session: Poster Display session 1
Resources:
Abstract
2509 - Afatinib in EGFR TKI-naïve patients with EGFR mutation-positive (EGFRm+) NSCLC: interim analysis of a Phase IIIb, multi-national, open-label study
Presenter: Filippo de Marinis
Session: Poster Display session 1
Resources:
Abstract
3300 - First-line ceritinib versus chemotherapy in patients (pts) with advanced ALK rearranged (ALK+) non-small cell lung cancer (NSCLC): ASCEND-4 Asian subgroup analysis
Presenter: Daniel SW Tan
Session: Poster Display session 1
Resources:
Abstract
2653 - A combined analysis of two Phase IIIb studies of afatinib in EGFR TKI-naïve patients (pts) with EGFR mutation-positive (EGFRm+) NSCLC
Presenter: Filippo de Marinis
Session: Poster Display session 1
Resources:
Abstract
3663 - Impact of plasma EGFR mutation fractions on response to first generation tyrosine-kinase inhibitor in treatment of naïve non-small cell lung cancer patients
Presenter: Xiaohong Wang
Session: Poster Display session 1
Resources:
Abstract
5921 - Definition of an afatinib trough concentration threshold in the treatment of NSCLC
Presenter: Stephane Bouchet
Session: Poster Display session 1
Resources:
Abstract
2852 - A Phase Ib Trial of Neoadjuvant Chemoradiotherapy and Durvalumab(MEDI4736) for Potentially Resectable stage III Non-Small Cell Lung Cancer (NSCLC)
Presenter: Beung chul AHN
Session: Poster Display session 1
Resources:
Abstract
3273 - Low expression of Notch1 and combined Notch1/HES1 are associated with adverse survival factor for limited stage small cell lung cancer
Presenter: Jinsoo Lee
Session: Poster Display session 1
Resources:
Abstract