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
3909 - Spectrum of pathogenic germline mutations in Chinese lung cancer patients through next-generation sequencing
Presenter: Ying Huang
Session: Poster Display session 1
Resources:
Abstract
3061 - Poor prognostic impact of NTRK2 gene variation in Esophageal Squamous Cell Carcinoma
Presenter: Ye Chen
Session: Poster Display session 1
Resources:
Abstract
4735 - Mutation profile of Tibetan lung cancer revealed by Whole Exome Sequencing
Presenter: Xin Wang
Session: Poster Display session 1
Resources:
Abstract
5236 - Synergistic activity between niraparib and chemotherapy in colorectal cancer: molecular determinants from a preclinical model
Presenter: Pietro Paolo Vitiello
Session: Poster Display session 1
Resources:
Abstract
4051 - cRGDfK (cRGD) conjugated Pyropheophor¬bide-a (Pyro), a new tumor photodynamic agent, is highly accumulated and specific in tumor cell killing
Presenter: Fengwei Wang
Session: Poster Display session 1
Resources:
Abstract
859 - The expression of MMR, CD133 and the presence of p53 wt predict the response to Cabazitaxel in malignant neural tumors cell lines.
Presenter: Kevin Doello
Session: Poster Display session 1
Resources:
Abstract
2497 - IKS01, a next generation antibody drug conjugate (ADC) designed to be efficacious in tumors with low and moderate levels of folate receptor expression
Presenter: Jenny Thirlway
Session: Poster Display session 1
Resources:
Abstract
1636 - Novel Non-Camptothecin Compounds with Antiproliferative Activities against Breast Cancer Cells
Presenter: Wen-shan Li
Session: Poster Display session 1
Resources:
Abstract
3443 - Sensitization of estrogen receptor-positive breast cancer cells to tamoxifen by novel epi-oligomycin A
Presenter: Margarita Yastrebova
Session: Poster Display session 1
Resources:
Abstract
840 - Autophagy inhibition enhances leflunomide-induced cytotoxicity in human bladder cancer cells
Presenter: Li Cheng
Session: Poster Display session 1
Resources:
Abstract