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
860 - Dose differential modulation of the autophagic behavior of estrogen expressing breast carcinoma cells
Presenter: Mariam Fouad
Session: Poster Display session 1
Resources:
Abstract
2304 - Synthetic peptide of tumor–associated antigen L6 formulated with polymer-based adjuvant enhances anti-tumor effects in mice
Presenter: Shih-jen Liu
Session: Poster Display session 1
Resources:
Abstract
4419 - Improving detection level of somatic mosaicism in neurofibromatosis type 1
Presenter: Kristina Karandasheva
Session: Poster Display session 1
Resources:
Abstract
5283 - Preclinical pharmacokinetic/pharmacodynamic (PK/PD) relationship of ABN401, a highly selective Met inhibitor, in gastric and non-small-cell lung cancer models
Presenter: JooSeok Kim
Session: Poster Display session 1
Resources:
Abstract
5488 - Transcription factors of Snail family in the regulation of resistance of breast cancer cells to hypoxic conditions
Presenter: Alvina Khamidullina
Session: Poster Display session 1
Resources:
Abstract
5417 - Metastasis is impaired by endothelial-specific Dll4 loss-of-function through inhibition of epithelial-to-mesenchymal transition and reduction of cancer stem cells and circulating tumour cells
Presenter: Liliana Mendonça
Session: Poster Display session 1
Resources:
Abstract
5494 - Identification of novel and known FGFR gene fusions in Chinese non-small cell lung cancer
Presenter: Weixin Zhao
Session: Poster Display session 1
Resources:
Abstract
3412 - WNT pathway mutations (APC/CTNNB1) and immune checkpoint inhibitors (ICI) response in metastatic non-small cell lung cancer (NSCLC) patients.
Presenter: Francisco Javier Ros Montana
Session: Poster Display session 1
Resources:
Abstract
1815 - Leukocytosis as a negative prognostic factor in patients with lung cancer: Which subpopulation of leukocytes is responsible?
Presenter: Filip Kohutek
Session: Poster Display session 1
Resources:
Abstract
5022 - Identification of MET gene amplifications using next-generation sequencing in non-small cell lung cancer patients
Presenter: Sergi Clavé
Session: Poster Display session 1
Resources:
Abstract