Machine Learning in the Differentiation of Soft Tissue Neoplasms: Comparison of Fat-Suppressed T2WI and Apparent Diffusion Coefficient (ADC) Features-Based Models
Open Access
- 20 September 2021
- journal article
- research article
- Published by Springer Nature in Journal of Digital Imaging
- Vol. 34 (5) , 1146-1155
Abstract
Machine learning has been widely used in the characterization of tumors recently. This article aims to explore the feasibility of the whole tumor fat-suppressed (FS) T2WI and ADC features-based least absolute shrinkage and selection operator (LASSO)-logistic predictive models in the differentiation of soft tissue neoplasms (STN). The clinical and MR findings of 160 cases with 161 histologically proven STN were reviewed, retrospectively, 75 with diffusion-weighted imaging (DWI withbvalues of 50, 400, and 800 s/mm2). They were divided into benign and malignant groups and further divided into training (70%) and validation (30%) cohorts. The MR FS T2WI and ADC features-based LASSO-logistic models were built and compared. The AUC of the FS T2WI features-based LASSO-logistic regression model for benign and malignant prediction was 0.65 and 0.75 for the training and validation cohorts. The model’s sensitivity, specificity, and accuracy of the validation cohort were 55%, 96%, and 76.6%. While the AUC of the ADC features-based model was 0.932 and 0.955 for the training and validation cohorts. The model’s sensitivity, specificity, and accuracy were 83.3%, 100%, and 91.7%. The performances of these models were also validated by decision curve analysis (DCA). The AUC of the whole tumor ADC features-based LASSO-logistic regression predictive model was larger than that of FS T2WI features (p = 0.017). The whole tumor fat-suppressed T2WI and ADC features-based LASSO-logistic predictive models both can serve as useful tools in the differentiation of STN. ADC features-based LASSO-logistic regression predictive model did better than that of FS T2WI features.Keywords
Funding Information
- the Science and Technology Council of Shanghai (grant no. 15ZR1408000, grant no. 18.no.12140901302, and grant no. 18140901200)
This publication has 36 references indexed in Scilit:
- Diffusion weighted MRI for detecting and monitoring cancer: a review of current applications in body imagingDiagnostic and Interventional Radiology, 2011
- Usefulness of diffusion‐weighted imaging for differentiating between desmoid tumors and malignant soft tissue tumorsJournal of Magnetic Resonance Imaging, 2010
- Diffusion‐weighted echo‐planar magnetic resonance imaging for the assessment of tumor cellularity in patients with soft‐tissue sarcomasJournal of Magnetic Resonance Imaging, 2009
- Diffusion-Weighted MRI in the Body: Applications and Challenges in OncologyAmerican Journal of Roentgenology, 2007
- Incidence patterns of soft tissue sarcomas, regardless of primary site, in the surveillance, epidemiology and end results program, 1978–2001: An analysis of 26,758 casesInternational Journal of Cancer, 2006
- Diffusion‐weighted MRI in the characterization of soft‐tissue tumorsJournal of Magnetic Resonance Imaging, 2002
- Differentiation of benign from malignant musculoskeletal lesions using MR imaging: pitfalls in MR evaluation of lesions with a cystic appearance.American Journal of Roentgenology, 1998
- MR imaging of soft-tissue masses: diagnostic efficacy and value of distinguishing between benign and malignant lesions.American Journal of Roentgenology, 1995
- Diseases of the musculoskeletal system in children: imaging with CT, sonography, and MR.American Journal of Roentgenology, 1992
- Value of MR imaging in differentiating benign from malignant soft-tissue masses: study of 95 lesions.American Journal of Roentgenology, 1990