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
5239 - Treatment patterns and outcomes for patients (pts) with anaplastic lymphoma kinase-positive (ALK+) advanced non-small-cell lung cancer (NSCLC) in US clinical practice
Presenter: Matthew Krebs
Session: Poster Display session 1
Resources:
Abstract
5595 - Is there any prognostic significance in pleural involvement and/or effusion (Ple-I/E) in patients with ALK-positive NSCLC?
Presenter: Saadettin Kilickap
Session: Poster Display session 1
Resources:
Abstract
5840 - Crizotinib in patients with advanced or metastatic ROS1-rearranged lung cancer (EUCROSS): A European phase 2 clinical trial – Updated progression-free survival, overall survival and mechanisms of resistance
Presenter: Sebastian Michels
Session: Poster Display session 1
Resources:
Abstract
1905 - NTRK1-3 Genomic Fusions in Non-Small Cell Lung Cancer (NSCLC) Determined by Comprehensive Genomic Profiling
Presenter: Sai-Hong Ou
Session: Poster Display session 1
Resources:
Abstract
3016 - Preferential expression of the affected MET allele in lung carcinomas with heterozygous MET exon 14 skipping mutations: implications for clinical testing
Presenter: Evgeny Imyanitov
Session: Poster Display session 1
Resources:
Abstract
4120 - Brain metastases, treatment patterns and outcomes in ROS1-positive NSCLC patients from US oncology community centers
Presenter: Matthew G Krebs
Session: Poster Display session 1
Resources:
Abstract
3764 - Patients with metastatic non-small cell lung cancer and targetable molecular alterations in Germany. Treatment and first outcome data from the prospective German Registry Platform CRISP (AIO-TRK-0315)
Presenter: Frank Griesinger
Session: Poster Display session 1
Resources:
Abstract
4070 - Crizotinib vs Platinum-based Chemotherapy as First-line Treatment for Advanced Non-small Cell Lung Cancer with Different ROS1 Fusion Variants
Presenter: Haiyan Xu
Session: Poster Display session 1
Resources:
Abstract
5528 - Genomic and clinical characterization of Non-small cell lung cancer (NSCLC) patients harboring mutations in FGFR2 and FGFR3
Presenter: Matthias Scheffler
Session: Poster Display session 1
Resources:
Abstract
3779 - The expression of HER2-gene polymorphisms -1985G>T and P1170A C>G and their association with the risk of development of lung adenocarcinoma
Presenter: Ivan Aleric
Session: Poster Display session 1
Resources:
Abstract