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
4658 - Patient-reported outcomes associated with switching to rivaroxaban for the treatment of venous thromboembolism (VTE) in patients with active cancer
Presenter: Alexander Cohen
Session: Poster Display session 1
Resources:
Abstract
5638 - Incidence of Vascular Thromboembolism Events in Cancer Patients Receiving Immunotherapy: A Single Institution Experience.
Presenter: Laura Gutiérrez Sainz
Session: Poster Display session 1
Resources:
Abstract
5182 - High Incidence of Venous Thromboembolic Events (VTE) in Patients with Diffuse Large B-Cell Lymphoma.
Presenter: Alaa Abufara
Session: Poster Display session 1
Resources:
Abstract
1504 - Weight Loss over Time in Non-Small Cell Lung Cancer: Results from a Landmark Analysis of 800+ Prospectively-Treated Patients
Presenter: Jennifer Le-rademacher
Session: Poster Display session 1
Resources:
Abstract
3972 - The prognostic significance of preoperative nutritional status in resected pancreatic ductal adenocarcinoma (PDAC).
Presenter: Salvatore Paiella
Session: Poster Display session 1
Resources:
Abstract
2313 - Impact of Timing and Technique of Gastrostomy Placement on the Outcome of Patients (pts) with Head and Neck Cancer (HNC)
Presenter: M Julia Lostes Bardaji
Session: Poster Display session 1
Resources:
Abstract
5219 - Clinical & nutritional determinants of quality of life in patients with incurable cancer
Presenter: Louise Daly
Session: Poster Display session 1
Resources:
Abstract
4075 - Loss of skeletal muscle mass during palliative chemotherapy is a poor prognostic factor in patients with advanced gastric cancer
Presenter: In Gyu Hwang
Session: Poster Display session 1
Resources:
Abstract
4159 - Impact of nutritional derangement on treatment outcome in advanced non-small-cell lung cancer (A-NSCLC) patients (pts).
Presenter: Ilaria Trestini
Session: Poster Display session 1
Resources:
Abstract
1210 - Sarcopenia and pretreatment anemia as prognostic factors for patients with localized muscle invasive bladder cancer treated by neoadjuvant chemotherapy and radical cystectomy
Presenter: Emilien Billon
Session: Poster Display session 1
Resources:
Abstract