Radiomics approach to distinguish between well differentiated liposarcomas and lipomas on MRI. Issue 13 (20th November 2019)

• Record Type: Journal Article
• Authors: Vos, M; Starmans, M P A; Timbergen, M J M; van der Voort, S R; Padmos, G A; Kessels, W; Niessen, W J; van Leenders, G J L H; Grünhagen, D J; Sleijfer, S; Verhoef, C; Klein, S; Visser, J J
• Is Part Of: British journal of surgery. Volume 106:Issue 13(2019)
• Page Start: 1800
• Page End: 1809
• Publication Date: 2019-11-20
• Subjects: Surgery -- Periodicals; 617.005
• DOI: 10.1002/bjs.11410
• Languages: English
• ISSNs: 0007-1323

Abstract

Abstract: Background: Well differentiated liposarcoma (WDLPS) can be difficult to distinguish from lipoma. Currently, this distinction is made by testing for MDM2 amplification, which requires a biopsy. The aim of this study was to develop a noninvasive method to predict MDM2 amplification status using radiomics features derived from MRI. Methods: Patients with an MDM2 -negative lipoma or MDM2 -positive WDLPS and a pretreatment T1-weighted MRI scan who were referred to Erasmus MC between 2009 and 2018 were included. When available, other MRI sequences were included in the radiomics analysis. Features describing intensity, shape and texture were extracted from the tumour region. Classification was performed using various machine learning approaches. Evaluation was performed through a 100 times random-split cross-validation. The performance of the models was compared with the performance of three expert radiologists. Results: The data set included 116 tumours (58 patients with lipoma, 58 with WDLPS) and originated from 41 different MRI scanners, resulting in wide heterogeneity in imaging hardware and acquisition protocols. The radiomics model based on T1 imaging features alone resulted in a mean area under the curve (AUC) of 0·83, sensitivity of 0·68 and specificity of 0·84. Adding the T2-weighted imaging features in an explorative analysis improved the model to a mean AUC of 0·89, sensitivity of 0·74 and specificity of 0·88. The three radiologists scored an AUC of 0·74 and 0·72 and 0·61 respectively; a sensitivity of 0·74, 0·91 and 0·64; and a specificity of 0·55, 0·36 and 0·59. Conclusion: Radiomics is a promising, non-invasive method for differentiating between WDLPS and lipoma, outperforming the scores of the radiologists. Further optimization and validation is needed before introduction into clinical practice. Graphical Abstract: The distinction between well differentiated liposarcomas and lipomas is needed in order to provide the correct treatment approach for patients with these tumours, but is difficult to make without a biopsy. This study shows that radiomics can be used to make this distinction based on routinely obtained MRI. The resulting radiomics model performed better in classifying these lipomatous tumours than three expert radiologists, thus showing potential as a non-invasive diagnostic aid.