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
2935 - Correlation of progression free survival-2 and overall survival in solid tumors
Presenter: Paul Mainwaring
Session: Poster Display session 1
Resources:
Abstract
2273 - High performance of serial tumor biopsies in first in human (FIH) phase I trials.
Presenter: Jun Sato
Session: Poster Display session 1
Resources:
Abstract
5933 - Response rates and lesion-level progression patterns of solid tumor patients in an academic phase 1 program: implications for tumor heterogeneity
Presenter: Christopher Chen
Session: Poster Display session 1
Resources:
Abstract
3569 - Clinical Benefit and Response Rate in Early Phase Clinical Trials: First Report from a Single-Institution Study
Presenter: Antonio Marra
Session: Poster Display session 1
Resources:
Abstract
4139 - Patient (pt) selection for immunotherapeutic early-phase clinical trials (ieCTs): a single Phase I Unit experience
Presenter: Matteo Simonelli
Session: Poster Display session 1
Resources:
Abstract
4451 - Improving patient selection for immuno-oncology phase 1 trials: an external validation of five prognostic scores at Claudius Regaud Institute of Toulouse, Oncopôle (IUCT-O).
Presenter: Ghassan Al Darazi
Session: Poster Display session 1
Resources:
Abstract
1696 - Demonstrating the Changing Trends in Phase 1 Clinical Trials
Presenter: Christina Guo
Session: Poster Display session 1
Resources:
Abstract
3202 - Participation of Women in phase 1 oncology clinical trials
Presenter: Laura Vidal
Session: Poster Display session 1
Resources:
Abstract
4518 - Predictors for early trial discontinuation of patients with cancer participating in phase I clinical trials
Presenter: Joeri Douma
Session: Poster Display session 1
Resources:
Abstract
4368 - Safety of Tumor Treating Fields delivery to the torso: Meta analysis from TTFields clinical trials
Presenter: Federica Grosso
Session: Poster Display session 1
Resources:
Abstract