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
5683 - Prevention of chemoradiation-related mucositis in patients with head and neck cancer using dexamethasone-based mouthwash: A phase II randomized double-blind, placebo-controlled study
Presenter: Naiyarat Prasongsook
Session: Poster Display session 1
Resources:
Abstract
5437 - Salivary cytokines and oral mucosa cells apoptosis in patients during hematopoietic cell transplantation: possible relationship with oral mucositis
Presenter: Luciana Corrêa
Session: Poster Display session 1
Resources:
Abstract
1483 - A randomized trial of sodium alginate prevention of radiation-induced esophagitis in patients with locally advanced NSCLC receiving concurrent chemoradiotherapy: OLCSG1401
Presenter: Toshihide Yokoyama
Session: Poster Display session 1
Resources:
Abstract
2047 - Taste and smell alterations (TSAs) in patients (pts) with stage II-III colon cancer (CC): a pilot within the PROTECT study
Presenter: Jeroen Derksen
Session: Poster Display session 1
Resources:
Abstract
5984 - Clinical characteristics are associated with acupuncture treatment response for xerostomia in cancer patients
Presenter: Wenli Liu
Session: Poster Display session 1
Resources:
Abstract
2845 - Psychosocial Distress of Adolescent and Young Adults with Cancer at Diagnosis: A Case-Matched Retrospective Cohort of 2045 Patients in British Columbia.
Presenter: Alannah Smrke
Session: Poster Display session 1
Resources:
Abstract
724 - Accuracy of distress thermometer to measure cancer-related mood disorders in Chinese patients with cancer
Presenter: Sudip Thapa
Session: Poster Display session 1
Resources:
Abstract
2357 - Modalities of biosimilar filgrastim use in clinical practice in >1000 patients receiving chemotherapy regimens with a rest period of ≤14 days: the TOPAZE study
Presenter: Jean Marc Phelip
Session: Poster Display session 1
Resources:
Abstract
1426 - The Effect of Increasing Doses of Pegfilgrastim (Peg) on Thrombocytopenia (T) in Breast Cancer (BC) Patients (pts) Receiving Taxotere (Doc), Doxorubicin, Cyclophosphamide (TAC) and Plinabulin (Plin)
Presenter: Douglas Blayney
Session: Poster Display session 1
Resources:
Abstract
712 - The use of intravenous ferric carboxymaltose without erythropoiesis-stimulating agents in the treatment of anemia in cancer patients undergoing chemotherapy with or without radiotherapy
Presenter: Hikmat Abdel-Razeq
Session: Poster Display session 1
Resources:
Abstract