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
5939 - Matrix metalloproteinases and their tissue inhibitors genes abnormal DNA methylation in breast cancer
Presenter: Olga Simonova
Session: Poster Display session 1
Resources:
Abstract
2703 - Uveal melanoma cell lines depend on multiple signaling pathways for survival
Presenter: John Park
Session: Poster Display session 1
Resources:
Abstract
4849 - XAF1 and ZNF313 complex stimulates ER stress-induced apoptosis via direct GRP78 inhibition.
Presenter: Sungchan Jang
Session: Poster Display session 1
Resources:
Abstract
4801 - XAF1 assembles a destructive complex to induce BRCA1-mediated apoptosis via suppressing ERa and switching estrogen function
Presenter: Seung-hun Jang
Session: Poster Display session 1
Resources:
Abstract
3416 - Cancer associated fibroblasts promote cancer progression via Wnt2 secretion in colorectal cancer
Presenter: Hideaki Karasawa
Session: Poster Display session 1
Resources:
Abstract
4273 - Paired-related homeobox 1 overexpression promotes invasion and metastasis and is a prognostic factor for worse disease-free survival in patients with lung cancer
Presenter: Jung-jyh Hung
Session: Poster Display session 1
Resources:
Abstract
4241 - LncRNA-GC1 contributes to gastric cancer chemo-resistance through inhibition of miR-551b-3p and the overexpression of dysbindin
Presenter: Xin Guo
Session: Poster Display session 1
Resources:
Abstract
5388 - GLPG 1790, a new selective EPHA2 inhibitor, is active in colorectal cancer cell lines belonging to the CMS4/mesenchymal-like subtype
Presenter: Pietro Paolo Vitiello
Session: Poster Display session 1
Resources:
Abstract
5208 - Characterisation of growth hormone signal transduction in primary melanoma cell lines
Presenter: Karla Sousa
Session: Poster Display session 1
Resources:
Abstract
3156 - LAPTM5 protein can regulate TGF-β mediated MAPK and Smad signaling pathways in ovarian cancer cell
Presenter: Yan Gao
Session: Poster Display session 1
Resources:
Abstract