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
1357 - Upfront atezolizumab chemoimmunotherapy-associated Immune-related adverse events in patients with advanced non-small cell lung cancer
Presenter: Francis Mogollon-Duffo
Session: Poster Display session 1
Resources:
Abstract
1851 - Nivolumab-induced and radiation recall pneumonitis in patients with non-small cell lung cancer: a multicenter real world analysis of 669 patients
Presenter: Nobuaki Mamesaya
Session: Poster Display session 1
Resources:
Abstract
851 - Retrospective analysis of immunotherapy prognostic scores in advanced NSCLC at Nottingham University Hospitals (UK)
Presenter: Cristina Lopez Escola
Session: Poster Display session 1
Resources:
Abstract
3639 - Applicability of lung immune prognostic index (LIPI) to predict efficacy of first-line pembrolizumab in advanced non-small-cell lung cancer (NSCLC)
Presenter: Xabier Mielgo Rubio
Session: Poster Display session 1
Resources:
Abstract
2950 - Delayed Onset Immune Related Adverse Effects (IRAEs) of Pembrolizumab in Non-Small Cell Lung Cancer
Presenter: Haixi Yan
Session: Poster Display session 1
Resources:
Abstract
3659 - Clinical implication of multiplex IHC and serologic biomarkers on Hyperprogression in NSCLC patients receiving Immune checkpoint blockers in real world.
Presenter: Joori Kim
Session: Poster Display session 1
Resources:
Abstract
4882 - Local ablative treatment and treatment beyond progression for oligo-progression in stage IV non-small cell lung cancer after tumor response to anti-PD1 treatment
Presenter: Florian Guisier
Session: Poster Display session 1
Resources:
Abstract
1358 - Atezolizumab in combination with chemotherapy for first-line treatment of advanced non-small cell lung cancer: A systematic review and meta-analysis of randomized controlled trials (RCTs)
Presenter: Francis Mogollon-Duffo
Session: Poster Display session 1
Resources:
Abstract
2170 - Prognostic Impact of Metastatic Sites for Pembrolizumab Efficacy as First-line therapy in Patients with PD-L1 tumor proportion score (TPS) ≥ 50% Advanced Non–Small Cell Lung Cancer: A Retrospective Multicenter Study
Presenter: Hayato Kawachi
Session: Poster Display session 1
Resources:
Abstract
3051 - Impact of visceral fat area as independent predictive factor in patients with advanced non-small cell lung cancer treated with nivolumab
Presenter: Yuki Sato
Session: Poster Display session 1
Resources:
Abstract