Erschienen:
Springer Science and Business Media LLC, 2022
Erschienen in:European Radiology Experimental
Sprache:
Englisch
DOI:
10.1186/s41747-022-00295-9
ISSN:
2509-9280
Entstehung:
Anmerkungen:
Beschreibung:
<jats:title>Abstract</jats:title><jats:sec>
<jats:title>Objectives</jats:title>
<jats:p>Malignancy of lipomatous soft-tissue tumours diagnosis is suspected on magnetic resonance imaging (MRI) and requires a biopsy. The aim of this study is to compare the performances of MRI radiomic machine learning (ML) analysis with deep learning (DL) to predict malignancy in patients with lipomas oratypical lipomatous tumours.</jats:p>
</jats:sec><jats:sec>
<jats:title>Methods</jats:title>
<jats:p>Cohort include 145 patients affected by lipomatous soft tissue tumours with histology and fat-suppressed gadolinium contrast-enhanced T1-weighted MRI pulse sequence. Images were collected between 2010 and 2019 over 78 centres with non-uniform protocols (three different magnetic field strengths (1.0, 1.5 and 3.0 T) on 16 MR systems commercialised by four vendors (General Electric, Siemens, Philips, Toshiba)).</jats:p>
<jats:p>Two approaches have been compared: (i) ML from radiomic features with and without batch correction; and (ii) DL from images. Performances were assessed using 10 cross-validation folds from a test set and next in external validation data.</jats:p>
</jats:sec><jats:sec>
<jats:title>Results</jats:title>
<jats:p>The best DL model was obtained using ResNet50 (resulting into an area under the curve (AUC) of 0.87 ± 0.11 (95% CI 0.65−1). For ML/radiomics, performances reached AUCs equal to 0.83 ± 0.12 (95% CI 0.59−1) and 0.99 ± 0.02 (95% CI 0.95−1) on test cohort using gradient boosting without and with batch effect correction, respectively. On the external cohort, the AUC of the gradient boosting model was equal to 0.80 and for an optimised decision threshold sensitivity and specificity were equal to 100% and 32% respectively.</jats:p>
</jats:sec><jats:sec>
<jats:title>Conclusions</jats:title>
<jats:p>In this context of limited observations, batch-effect corrected ML/radiomics approaches outperformed DL-based models.</jats:p>
</jats:sec>