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
1735 - mTOR inhibition in the treatment of resistant breast cancer
Presenter: María Rodriguez
Session: Poster Display session 1
Resources:
Abstract
6068 - Study of Photodynamic therapy in vitro
Presenter: Irene Jiménez Munguía
Session: Poster Display session 1
Resources:
Abstract
3011 - The potential of neratinib plus dasatinib in overcoming and preventing neratinib resistance in HER2-positive breast cancer models
Presenter: Neil Conlon
Session: Poster Display session 1
Resources:
Abstract
2644 - Novel HDACi, MHY446, induces apoptosis via regulation of mitochondria-endoplasmic reticulum interaction in HCT116 human colorectal cancer cells
Presenter: Nam Deuk Kim
Session: Poster Display session 1
Resources:
Abstract
3085 - Dual inhibition of TGF-β and AXL as a novel treatment for colorectal cancer
Presenter: Davide Ciardiello
Session: Poster Display session 1
Resources:
Abstract
1314 - PARP inhibition enhances cisplatin sensitivity in cervical cancer by modulating β-catenin signaling
Presenter: Minakshi Mann
Session: Poster Display session 1
Resources:
Abstract
2417 - Synergistic effect of DSF combined treatment with cisplatin in atypical teratoid/rhabdoid tumors (AT/RT)
Presenter: Seung Ah Choi
Session: Poster Display session 1
Resources:
Abstract
1149 - Reactive oxygen species induced by OSU-A9 inhibit the growth of duodenal cancer and gastric cancer cells through dephosphorylating intranuclear pyruvate kinase muscle isozyme M2
Presenter: Li-Yuan Bai
Session: Poster Display session 1
Resources:
Abstract
1862 - New therapy for intrahepatic cholangiocarcinoma targeted to cancer associated fibroblasts
Presenter: Takahiro Yamanaka
Session: Poster Display session 1
Resources:
Abstract
782 - Macrophage-cancer cell fusion is mediated by Phosphatidylserine-CD36 receptor interaction and induced by ionizing radiation
Presenter: Ivan Shabo
Session: Poster Display session 1
Resources:
Abstract