Differential diagnosis and mutation stratification of desmoid-type fibromatosis on MRI using radiomics

• Published in: European journal of radiology Vol. 131; p. 109266
• Main Authors: Timbergen, Milea J.M., Starmans, Martijn P.A., Padmos, Guillaume A., Grünhagen, Dirk J., van Leenders, Geert J.L.H., Hanff, D.F., Verhoef, Cornelis, Niessen, Wiro J., Sleijfer, Stefan, Klein, Stefan, Visser, Jacob J.
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01-10-2020
• Subjects: Adult; Aggressive; Beta catenin; beta Catenin - analysis; beta Catenin - genetics; Diagnosis, Differential; DNA Mutational Analysis; Female; Fibromatosis; Fibromatosis, Aggressive - diagnostic imaging; Fibromatosis, Aggressive - genetics; Humans; Imaging Genomics; Immunohistochemistry; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Middle Aged; Mutation; Radiomics; Retrospective Studies; Sarcoma - diagnostic imaging; Magnetic resonance imaging; Aggressive; Beta catenin; Machine learning; Fibromatosis; Radiomics
• ISSN: 0720-048X; 1872-7727
• DOI: 10.1016/j.ejrad.2020.109266

•Radiomics can distinguish between desmoid-type fibromatotis (DTF) and soft tissue sarcomas (STS).•Radiomics performs similar to radiologists in distinguishing DTF from STS.•Radiomics cannot stratify the CTNNB1 mutation of DTF.•Radiomics for DTF can handle variations in the MRI imaging protocols.
Diagnosing desmoid-type fibromatosis (DTF) requires an invasive tissue biopsy with β-catenin staining and CTNNB1 mutational analysis, and is challenging due to its rarity. The aim of this study was to evaluate radiomics for distinguishing DTF from soft tissue sarcomas (STS), and in DTF, for predicting the CTNNB1 mutation types.
Patients with histologically confirmed extremity STS (non-DTF) or DTF and at least a pretreatment T1-weighted (T1w) MRI scan were retrospectively included. Tumors were semi-automatically annotated on the T1w scans, from which 411 features were extracted. Prediction models were created using a combination of various machine learning approaches. Evaluation was performed through a 100x random-split cross-validation. The model for DTF vs. non-DTF was compared to classification by two radiologists on a location matched subset.
The data included 203 patients (72 DTF, 131 STS). The T1w radiomics model showed a mean AUC of 0.79 on the full dataset. Addition of T2w or T1w post-contrast scans did not improve the performance. On the location matched cohort, the T1w model had a mean AUC of 0.88 while the radiologists had an AUC of 0.80 and 0.88, respectively. For the prediction of the CTNNB1 mutation types (S45 F, T41A and wild-type), the T1w model showed an AUC of 0.61, 0.56, and 0.74.
Our radiomics model was able to distinguish DTF from STS with high accuracy similar to two radiologists, but was not able to predict the CTNNB1 mutation status.