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
3181 - Effects of Three Products in the Prevention and Treatment of Chemotherapy and Radiation Therapy-Induced Oral Mucositis
Presenter: Francesca Zannier
Session: Poster Display session 1
Resources:
Abstract
2433 - Boiling Histotripsy-induced Mechanical Ablation Modulates Tumour Microenvironment by Promoting Immunogenic Cell Death of Cancers
Presenter: Cheol-Hee Shin
Session: Poster Display session 1
Resources:
Abstract
2663 - The bacterial receptor NOD2 mediates LGR5+ intestinal stem cells protection against irradiation via mitophagy activation
Presenter: Antonin Levy
Session: Poster Display session 1
Resources:
Abstract
3213 - Pulse mode irradiation regimen of PDT results in high progression free and overall survival in mice with model tumor
Presenter: Alexey Bogdanov
Session: Poster Display session 1
Resources:
Abstract
3722 - Proton-sensitizing effect of small molecule inhibitor of P300 histone acetyltransferase C646 in human pancreatic cancer cells.
Presenter: Sungwon Shin
Session: Poster Display session 1
Resources:
Abstract
5805 - Red-Blood-Cell-Membrane-Enveloped Magnetic Nanoclusters as a Biomimetic Theranostic Nanoplatform for Bimodal Imaging Guided Cancer Photothermal Therapy
Presenter: sheng wang
Session: Poster Display session 1
Resources:
Abstract
5251 - Urine cell-free and extracellular vesicle cargo miRNAs as biomarkers for prostate cancer diagnosis
Presenter: Ivan Zaporozhchenko
Session: Poster Display session 1
Resources:
Abstract
3657 - Parkin, APEX1 and BCL2L1 Tissue Expression in Southern Brazilian Patients with Different Breast Cancer Molecular Subtypes
Presenter: Bianca Cabral
Session: Poster Display session 1
Resources:
Abstract
2839 - Obesity and prognosis in breast cancer
Presenter: Noha Ibrahim
Session: Poster Display session 1
Resources:
Abstract
5132 - SIPA1 is a modulator of HGF induced tumor metastasis via the regulation of tight junctions in lung adenocarcinoma cells
Presenter: Chang Liu
Session: Poster Display session 1
Resources:
Abstract