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
4228 - Clinical Evaluation of Drug-Eluting Bead Transcatheter Arterial Chemoembolization(D-TACE) versus Conventional TACE in Treatment of unresectable Hepatocellular Carcinoma
Presenter: Yi Chen
Session: Poster Display session 1
Resources:
Abstract
3930 - Safety profile of tepotinib in patients with advanced solid tumors: pooled analysis of phase I and II data
Presenter: Thomas Decaens
Session: Poster Display session 1
Resources:
Abstract
5373 - Drug-drug interaction profile of tepotinib with CYP3A and P-gp substrates
Presenter: Juergen Heuer
Session: Poster Display session 1
Resources:
Abstract
5455 - Bioavailability of tepotinib: impact of omeprazole and food
Presenter: Juergen Heuer
Session: Poster Display session 1
Resources:
Abstract
2618 - Tislelizumab Exposure-Response Analyses of Efficacy and Safety in Patients with Advanced Tumors
Presenter: Chi-Yuan Wu
Session: Poster Display session 1
Resources:
Abstract
2563 - Population Pharmacokinetics of Tislelizumab in Patients with Advanced Tumors
Presenter: Chi-Yuan Wu
Session: Poster Display session 1
Resources:
Abstract
2021 - The Addition of Metformin to Systemic Anticancer Therapy
Presenter: Jung Han Kim
Session: Poster Display session 1
Resources:
Abstract
5243 - Growth modulation index (GMI) as a comparative measure of clinical activity of larotrectinib versus prior systemic treatments in adult and pediatric TRK fusion cancer patients
Presenter: Antoine Italiano
Session: Poster Display session 1
Resources:
Abstract
598 - Analysis of the overall survival and main surrogates used for FDA approvals in solid and hematological malignancies.
Presenter: Maria Kleniewska-Wieczor
Session: Poster Display session 1
Resources:
Abstract
5381 - Comparison of intratumoral docetaxel exposure in cancer patients between nanoparticle entrapped docetaxel (CPC634) and conventional docetaxel (Cd): the CriTax study
Presenter: Ruben Van Eerden
Session: Poster Display session 1
Resources:
Abstract