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
5314 - Spirituality and religious coping for Cancer patients and providers: An ‘Almighty’ belief for palliative care
Presenter: Vibhay Pareek
Session: Poster Display session 1
Resources:
Abstract
5519 - Is there a difference of Palliative care problems and needs between cancer and non-cancer hospitalized elderly patients?
Presenter: Ioanna Chatzi
Session: Poster Display session 1
Resources:
Abstract
2505 - There is a lack of clinical research for patients with cancer in palliative care
Presenter: Marie Vinches
Session: Poster Display session 1
Resources:
Abstract
5273 - Specialist Palliative Care (SPC) in Haematological Malignancy: Establishing practices in a UK Tertiary Cancer Centre (TCC)
Presenter: Emma Kedgley
Session: Poster Display session 1
Resources:
Abstract
5864 - Evaluation of the relationship between the attachment styles and psychological resilience of cancer patients receiving chemotherapy
Presenter: Fatma Bugdayci Basal
Session: Poster Display session 1
Resources:
Abstract
770 - Gefitinib along with Methotrexate as palliative therapy in PS 3 and above in metastatic squamous cell carcinoma head and neck cancer patients
Presenter: Vidya Dusi
Session: Poster Display session 1
Resources:
Abstract
4232 - High intensity end-of-life care in pediatrics, adolescent and young adult patients with cancer using an administrative database.
Presenter: Seiko Bun
Session: Poster Display session 1
Resources:
Abstract
4845 - Embedded outpatient palliative care service within the oncology clinic: Preliminary experience in Hacettepe Oncology Hospital
Presenter: Deniz Can Guven
Session: Poster Display session 1
Resources:
Abstract
3270 - Internet-based stepped care for individuals with cancer and concurrent anxiety or depression symptoms – results from a randomized controlled trial
Presenter: Birgitta Johansson
Session: Poster Display session 1
Resources:
Abstract
5503 - Impact of Cognitive-Behavioral-Therapy (CBT) on levels of anxiety, depression and distress in cancer patients (pts)
Presenter: Daniela Tregnago
Session: Poster Display session 1
Resources:
Abstract