Dataset Information

Radiomics approach to distinguish between well differentiated liposarcomas and lipomas on MRI.

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.

SUBMITTER: Vos M

PROVIDER: S-EPMC6899528 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Radiomics approach to distinguish between well differentiated liposarcomas and lipomas on MRI.

Vos M M Starmans M P A MPA Timbergen M J M MJM van der Voort S R SR Padmos G A GA Kessels W W Niessen W J WJ van Leenders G J L H GJLH Grünhagen D J DJ Sleijfer S S Verhoef C C Klein S S Visser J J JJ

The British journal of surgery 20191201 13

<h4>Background</h4>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.<h4>Methods</h4>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 a ...[more]

PMID: 31747074

Similar Datasets

Project description:Background To develop a machine learning model based on tumor-to-bone distance and radiomic features derived from preoperative MRI images to distinguish intramuscular (IM) lipomas and atypical lipomatous tumors/well-differentiated liposarcomas (ALTs/WDLSs) and compared with radiologists. Methods The study included patients with IM lipomas and ALTs/WDLSs diagnosed between 2010 and 2022, and with MRI scans (sequence/field strength: T1-weighted (T1W) imaging at 1.5 or 3.0 Tesla MRI). Manual segmentation of tumors based on the three-dimensional T1W images was performed by two observers to appraise the intra- and interobserver variability. After radiomic features and tumor-to-bone distance were extracted, it was used to train a machine learning model to distinguish IM lipomas and ALTs/WDLSs. Both feature selection and classification steps were performed using Least Absolute Shrinkage and Selection Operator logistic regression. The performance of the classification model was assessed using a tenfold cross-validation strategy and subsequently evaluated using the receiver operating characteristic curve (ROC) analysis. The classification agreement of two experienced musculoskeletal (MSK) radiologists was assessed using the kappa statistics. The diagnosis accuracy of each radiologist was evaluated using the final pathological results as the gold standard. Additionally, we compared the performance of the model and two radiologists in terms of the area under the receiver operator characteristic curves (AUCs) using the Delong’s test. Results There were 68 tumors (38 IM lipomas and 30 ALTs/WDLSs). The AUC of the machine learning model was 0.88 [95% CI 0.72–1] (sensitivity, 91.6%; specificity, 85.7%; and accuracy, 89.0%). For Radiologist 1, the AUC was 0.94 [95% CI 0.87–1] (sensitivity, 97.4%; specificity, 90.9%; and accuracy, 95.0%), and as to Radiologist 2, the AUC was 0.91 [95% CI 0.83–0.99] (sensitivity, 100%; specificity, 81.8%; and accuracy, 93.3%). The classification agreement of the radiologists was 0.89 of kappa value (95% CI 0.76–1). Although the AUC of the model was lower than of two experienced MSK radiologists, there was no statistically significant difference between the model and two radiologists (all P > 0.05). Conclusions The novel machine learning model based on tumor-to-bone distance and radiomic features is a noninvasive procedure that has the potential for distinguishing IM lipomas from ALTs/WDLSs. The predictive features that suggested malignancy were size, shape, depth, texture, histogram, and tumor-to-bone distance. Supplementary Information The online version contains supplementary material available at 10.1186/s13018-023-03718-4.

Project description:Myxoid liposarcoma (LS), the most common subtype of LS, is known to be characterized by the specific t(12;16) resulting in a TLS-CHOP fusion in almost all cases. We wished to address the following questions: (i) Is this genetic hallmark also present in other types of LS with predominant myxoid change? (ii) What is the proportion of cases with the variant EWS-CHOP fusion? (iii) What is the optimal approach for Southern blot detection of TLS breakpoints? We identified 59 LS characterized histologically by >90% myxoid component, in which frozen tissue tumor was available for DNA extraction. These 59 LS with myxoid features were divided into 2 groups: 42 LS with classic myxoid/round cell appearance (myxoid LS) and 17 well-differentiated LS (WDLS) with a predominant (>90%) myxoid component. Within the myxoid LS group, 29 tumors were low grade and 13 high grade (>20% round cell component). Among the 17 predominantly myxoid WDLS, there were 15 low grade and 2 focally high grade tumors. In addition, we selected as control group, 20 LS of other histological types with minimal or no myxoid change (17 WDLS and 3 pleomorphic LS) and 13 myxofibrosarcomas. Southern blot analysis was performed in all cases using a CHOP cDNA probe, and in all CHOP rearranged cases using a TLS cDNA probe. Probe/enzyme combinations for Southern blot analysis were CHOP exon 3-4 cDNA probe with BamHI or SacI, TLS exon 3-6 cDNA probe with BclI. All 42 cases of myxoid LS showed a CHOP rearrangement and 38 of them also had a TLS rearrangement. Among the 4 myxoid LS without Southern blot evidence of TLS rearrangement, 1 showed an EWS-CHOP fusion by Southern blotting and reverse transcriptase-polymerase chain reaction and in another case, reverse transcriptase-polymerase chain reaction detected a TLS-CHOP fusion transcript. None of the predominantly myxoid WDLS and none of the tumors included in the control group showed rearranegements with CHOP probe. In addition, 12 predominantly myxoid WDLS, 10 other LS, and 5 myxofibrosarcoma from the control group were also tested for TLS rearrangement; all were negative. The TLS-CHOP fusion is highly sensitive and specific for the entity of classic myxoid/round cell LS. Other types of LS, even with a predominant myxoid component, lack the TLS-CHOP rearrangement, confirming that they represent a genetically distinct group of LS. The prevalence of the EWS-CHOP variant fusion was approximately 2% in this series. The optimal enzyme for TLS genomic breakpoint detection is BclI.

Dataset Information

Radiomics approach to distinguish between well differentiated liposarcomas and lipomas on MRI.

Background

Methods

Results

Conclusion

Publications

Radiomics approach to distinguish between well differentiated liposarcomas and lipomas on MRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets