Advertisement

Performance of Machine Learning Methods Based on Multi-Sequence Textural Parameters Using Magnetic Resonance Imaging and Clinical Information to Differentiate Malignant and Benign Soft Tissue Tumors

      Rationale and Objectives

      To evaluate the performance of a machine learning method to differentiate malignant from benign soft tissue tumors based on textural features on multiparametric magnetic resonance imaging (mpMRI).

      Materials and Methods

      We enrolled 163 patients with soft tissue tumors whose diagnosis was pathologically proven (71 malignant, 92 benign). All patients underwent mpMRI. Twelve histographic and textural parameters were assessed on T1-weighted imaging (T1WI), T2-weighted imaging, diffusion-weighted imaging, apparent diffusion coefficient maps, and contrast-enhanced T1WI imaging. We compared mean signals of all sequences from the malignant and benign tumors using Welch's t-test. Prediction models were developed via a machine learning technique (support vector machine) using textural features of each sequence, clinical information (sex + age + tumor size), and the combined model incorporating all features. Areas under the receiver operating characteristic curves (AUCs) of these models were calculated using fivefold cross validation.

      Results

      The diagnostic ability of clinical information model (AUC 0.85) was not inferior to the model with textural features of each sequence (AUC 0.79–0.84). The combined model showed the highest diagnostic ability (AUC 0.89). The AUC of the combined model (0.89) was comparable to those of two board-certified radiologists (0.89 and 0.87).

      Conclusions

      Machine learning methods based on textural features on mpMRI and clinical information offer adequate diagnostic performance to differentiate between malignant and benign soft tissue tumors.

      Key Words

      Abbreviations:

      mpMRI (multiparametric magnetic resonance imaging), T1WI (T1-weighted imaging), T2WI (T2-weighted imaging), DWI (diffusion-weighted imaging), ADC (apparent diffusion coefficient), CE-T1WI (contrast-enhanced T1WI imaging), SVM (support vector machine), AUC (areas under the receiver operating characteristic curve), ITA (image texture analysis), ROC (receiver operating characteristic)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Academic Radiology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      REFERENCES

        • Dangoor A
        • Seddon B
        • Gerrand C
        • et al.
        UK guidelines for the management of soft tissue sarcomas.
        Clin Sarcoma Res. 2016; 6: 20
        • Ahlawat S
        • Fritz J
        • Morris CD
        • et al.
        Magnetic resonance imaging biomarkers in musculoskeletal soft tissue tumors: review of conventional features and focus on nonmorphologic imaging.
        J Magn Reson Imaging. 2019; 50: 11-27
        • Aga P
        • Singh R
        • Parihar A
        • et al.
        Imaging spectrum in soft tissue sarcomas.
        Indian J Surg Oncol. 2011; 2: 271-279
        • Juntu J
        • Sijbers J
        • De Backer S
        • et al.
        Machine learning study of several classifiers trained with texture analysis features to differentiate benign from malignant soft-tissue tumors in T1-MRI images.
        J Magn Reson Imaging. 2010; 31: 680-689
        • Teixeira PA
        • Gay F
        • Chen B
        • et al.
        Diffusion-weighted magnetic resonance imaging for the initial characterization of non-fatty soft tissue tumors: correlation between T2 signal intensity and ADC values.
        Skeletal Radiol. 2016; 45: 263-271
        • Bian Y
        • Jin P
        • Wang Y
        • et al.
        Clinical applications of DSC-MRI parameters assess angiogenesis and differentiate malignant from benign soft tissue tumors in limbs.
        Acad Radiol. 2020; 27: 354-360
        • Hori M
        Distinguishing benign from malignant soft tissue tumors by dynamic susceptibility contrast magnetic resonance imaging.
        Acad Radiol. 2020; 27: 361-362
        • Einarsdottir H
        • Karlsson M
        • Wejde J
        • et al.
        Diffusion-weighted MRI of soft tissue tumours.
        Eur Radiol. 2004; 14: 959-963
        • Kransdorf MJ
        Benign soft-tissue tumors in a large referral population: distribution of specific diagnoses by age, sex, and location.
        AJR Am J Roentgenol. 1995; 164: 395-402
        • Larroza A
        • Moratal D
        • Paredes-Sanchez A
        • et al.
        Support vector machine classification of brain metastasis and radiation necrosis based on texture analysis in MRI.
        J Magn Reson Imaging. 2015; 42: 1362-1368
        • Nakagawa M
        • Nakaura T
        • Namimoto T
        • et al.
        Machine learning based on multi-parametric magnetic resonance imaging to differentiate glioblastoma multiforme from primary cerebral nervous system lymphoma.
        Eur J Radiol. 2018; 108: 147-154
        • Tateishi M
        • Nakaura T
        • Kitajima M
        • et al.
        An initial experience of machine learning based on multi-sequence texture parameters in magnetic resonance imaging to differentiate glioblastoma from brain metastases.
        J Neurol Sci. 2020; 410116514
        • Yu H
        • Scalera J
        • Khalid M
        • et al.
        Texture analysis as a radiomic marker for differentiating renal tumors.
        Abdom Radiol (NY). 2017; 42: 2470-2478
        • Mayerhoefer ME
        • Schima W
        • Trattnig S
        • et al.
        Texture-based classification of focal liver lesions on MRI at 3.0 Tesla: a feasibility study in cysts and hemangiomas.
        J Magn Reson Imaging. 2010; 32: 352-359
        • Gnep K
        • Fargeas A
        • Gutierrez-Carvajal RE
        • et al.
        Haralick textural features on T2 -weighted MRI are associated with biochemical recurrence following radiotherapy for peripheral zone prostate cancer.
        J Magn Reson Imaging. 2017; 45: 103-117
        • Iyama Y
        • Nakaura T
        • Katahira K
        • et al.
        Development and validation of a logistic regression model to distinguish transition zone cancers from benign prostatic hyperplasia on multi-parametric prostate MRI.
        Eur Radiol. 2017; 27: 3600-3608
        • McLaren CE
        • Chen WP
        • Nie K
        • et al.
        Prediction of malignant breast lesions from MRI features: a comparison of artificial neural network and logistic regression techniques.
        Acad Radiol. 2009; 16: 842-851
        • Nakagawa M
        • Nakaura T
        • Namimoto T
        • et al.
        Machine learning to differentiate T2-weighted hyperintense uterine leiomyomas from uterine sarcomas by utilizing multiparametric magnetic resonance quantitative imaging features.
        Acad Radiol. 2019; 26: 1390-1399
        • Xu R
        • Kido S
        • Suga K
        • et al.
        Texture analysis on (18)F-FDG PET/CT images to differentiate malignant and benign bone and soft-tissue lesions.
        Ann Nucl Med. 2014; 28: 926-935
        • Wu JS
        • Hochman MG
        Soft-tissue tumors and tumorlike lesions: a systematic imaging approach.
        Radiology. 2009; 253: 297-316
        • Choi YJ
        • Lee IS
        • Song YS
        • et al.
        Diagnostic performance of diffusion-weighted (DWI) and dynamic contrast-enhanced (DCE) MRI for the differentiation of benign from malignant soft-tissue tumors.
        J Magn Reson Imaging. 2019; 50: 798-809
        • Song Y
        • Yoon YC
        • Chong Y
        • et al.
        Diagnostic performance of conventional MRI parameters and apparent diffusion coefficient values in differentiating between benign and malignant soft-tissue tumours.
        Clin Radiol. 2017; 72 (691 e1- e10)
        • Genovese E
        • Cani A
        • Rizzo S
        • et al.
        Comparison between MRI with spin-echo echo-planar diffusion-weighted sequence (DWI) and histology in the diagnosis of soft-tissue tumours.
        Radiol Med. 2011; 116: 644-656
        • Johnson CJ
        • Pynsent PB
        • Grimer RJ
        Clinical features of soft tissue sarcomas.
        Ann R Coll Surg Engl. 2001; 83: 203-205
        • Naylor P
        Pattern recognition and neural networks - Ripley, BD.
        Nature. 1996; 381: 206