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
4925 - Prognostic role of CD73 in metastatic Non Small Cell Lung Cancer according to the presence of driver alterations
Presenter: Giulia Galli
Session: Poster Display session 1
Resources:
Abstract
785 - JAK-STAT inhibitor overcomes interferon γ-reduced, NK cell-mediated cytotoxicity in non-small-cell lung cancer cells
Presenter: Riki Okita
Session: Poster Display session 1
Resources:
Abstract
2326 - Low LATS2 expression is associated with poor prognosis in non small cell lung cancer
Presenter: Si-hyong Jang
Session: Poster Display session 1
Resources:
Abstract
5960 - Application of ESCAT and OncoKB scales in Liquid biopsy (LB) in Advanced NSCLC patients (pts): Is it feasible and reliable?
Presenter: Michael McCusker
Session: Poster Display session 1
Resources:
Abstract
4855 - IDH1R132H mutation induces a less aggressive phenotype of glioma cells and affects the radiosensitivity by interacting with Wnt/β-catenin signaling
Presenter: Xuetao Han
Session: Poster Display session 1
Resources:
Abstract
2641 - Impact of Angiopoietin-2 on glioblastoma response to combined chemo-radiotherapy
Presenter: Charly Helaine
Session: Poster Display session 1
Resources:
Abstract
5743 - The Discovery of RNA-aptamers That Selectively Bind and Inhibit Glioblastoma Stem Cells by targeting EphA2
Presenter: Alessandra Affinito
Session: Poster Display session 1
Resources:
Abstract
4160 - Impact of tumor reoxygenation by nanoparticles on Tumor Associated Macrophages (TAMs)
Presenter: Aurélie Ferré
Session: Poster Display session 1
Resources:
Abstract
2474 - Prognostic significance of c-Rel/p50 heterodimer in the tumor microenvironment of uveal melanoma
Presenter: Seema Kashyap
Session: Poster Display session 1
Resources:
Abstract
1769 - Synergistic role of BAP1 and DNA damage response pathway in uveal melanoma and its prognostic significance.
Presenter: JAYANTI JHA
Session: Poster Display session 1
Resources:
Abstract