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
5344 - Global trends in population-based survival for 303,169 adults diagnosed with glioblastoma in 44 countries during 2000-2014 (CONCORD-3)
Presenter: Fabio Girardi
Session: Poster Display session 1
Resources:
Abstract
3088 - Spanish Survey of treatment recommendations for elderley patients with glioblastoma
Presenter: María Ángeles Vaz Salgado
Session: Poster Display session 1
Resources:
Abstract
3484 - Updated analysis of the National Registry of Nervous System Tumors in Spain (RETSINE). RETSINE: National Registry of Nervous System Tumors of the Spanish Research Group in Neuro-oncology (GEINO) and Spanish Infrequent and Orphan Tumors Group (GETHI)
Presenter: Isaac Ceballos Lenza
Session: Poster Display session 1
Resources:
Abstract
4737 - Development and validation of novel nomograms predicting survival of malignant ependymoma patients: A population-based study
Presenter: Alzhraa Abbas
Session: Poster Display session 1
Resources:
Abstract
4740 - Characteristics, incidence, and survival of primary cerebral lymphoma: A population based study
Presenter: Sherief Ghozy
Session: Poster Display session 1
Resources:
Abstract
5362 - Trends in Incidence and Survival Analyses of Adult-onset Medulloblastoma
Presenter: Feifei Lin
Session: Poster Display session 1
Resources:
Abstract
3868 - Meta of classical chemotherapy compared with high-dose chemotherapy combined with autologous stem cell transplantation in newly diagnosed medulloblastoma patients after radiotherapy
Presenter: Mengting Zhang
Session: Poster Display session 1
Resources:
Abstract
4446 - Effect of cumulative dose of maintenance temozolomide on overall survival in patients with high grade glia tumors: a single institution analysis
Presenter: Marta Nerone
Session: Poster Display session 1
Resources:
Abstract
5119 - Markers of systemic inflammation correlate with survival prognosis in patients with newly diagnosed brain metastases
Presenter: Angelika Starzer
Session: Poster Display session 1
Resources:
Abstract
3882 - Venous Thromboembolism and Intracranial Hemorrhage in Patients with High-grade Glioma
Presenter: Clara Borges
Session: Poster Display session 1
Resources:
Abstract