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
1728 - A phase III trial evaluating olanzapine 5 mg for the prevention of chemotherapy-induced nausea and vomiting in patients receiving cisplatin: J-FORCE Study
Presenter: Hironobu Hashimoto
Session: Poster Display session 1
Resources:
Abstract
920 - Efficacy of intravenous (IV) NEPA, a fixed NK1/5-HT3 receptor antagonist (RA) combination, for prevention of CINV following cisplatin- and anthracycline cyclophosphamide (AC)-based chemotherapy (CT)
Presenter: Lee Schwartzberg
Session: Poster Display session 1
Resources:
Abstract
5146 - Efficacy of olanzapine combination in prevention of nausea & vomiting in highly emetogenic chemotherapy
Presenter: Smitha Saldanha
Session: Poster Display session 1
Resources:
Abstract
1947 - Patient-reported outcome data during real-world use of NEPA for prevention of chemotherapy-induced nausea and vomiting in high-risk platin-receiving patients - A prospective multicenter trial
Presenter: Meinolf Karthaus
Session: Poster Display session 1
Resources:
Abstract
6163 - A study evaluating steroid induced metabolic syndrome after antiemetic dexamethasone therapy in patients received high emetic risk chemotherapy
Presenter: Hee Jun Kim
Session: Poster Display session 1
Resources:
Abstract
2154 - High incidence of nausea during initial and repeated courses if intravenous chemotherapy in patients receiving guideline consistent antiemetic prophylaxis - a prospective, observational, real world study.
Presenter: Teresa Smit
Session: Poster Display session 1
Resources:
Abstract
1637 - "Randomised controlled trial of Scalp Cooling (SC) for the prevention of Chemotherapy Induced Alopecia (CIA)”
Presenter: Jyoti Bajpai
Session: Poster Display session 1
Resources:
Abstract
5351 - Performance of the ‘4S rule’ to predict short-term outcomes in cancer outpatients with unsuspected pulmonary embolism.
Presenter: David Pesántez Coronel
Session: Poster Display session 1
Resources:
Abstract
1189 - Prevalence of venous thromboembolism based on intensive screening for patients with advanced solid tumor in prospective observational study
Presenter: Shota Omori
Session: Poster Display session 1
Resources:
Abstract
4340 - Short-term outcomes of cancer patients with pulmonary embolism according to the setting (hospital-acquired vs. outpatient) at diagnosis.
Presenter: Diego Muñoz Guglielmetti
Session: Poster Display session 1
Resources:
Abstract