Literature DB >> 33893534

Whole-tumor 3D volumetric MRI-based radiomics approach for distinguishing between benign and malignant soft tissue tumors.

Brandon K K Fields1, Natalie L Demirjian1,2, Darryl H Hwang1,3, Bino A Varghese1,3, Steven Y Cen1,3, Xiaomeng Lei1,3, Bhushan Desai1,3, Vinay Duddalwar1,3, George R Matcuk4.   

Abstract

OBJECTIVES: Our purpose was to differentiate between malignant from benign soft tissue neoplasms using a combination of MRI-based radiomics metrics and machine learning.
METHODS: Our retrospective study identified 128 histologically diagnosed benign (n = 36) and malignant (n = 92) soft tissue lesions. 3D ROIs were manually drawn on 1 sequence of interest and co-registered to other sequences obtained during the same study. One thousand seven hundred eight radiomics features were extracted from each ROI. Univariate analyses with supportive ROC analyses were conducted to evaluate the discriminative power of predictive models constructed using Real Adaptive Boosting (Adaboost) and Random Forest (RF) machine learning approaches.
RESULTS: Univariate analyses demonstrated that 36.89% of individual radiomics varied significantly between benign and malignant lesions at the p ≤ 0.05 level. Adaboost and RF performed similarly well, with AUCs of 0.77 (95% CI 0.68-0.85) and 0.72 (95% CI 0.63-0.81), respectively, after 10-fold cross-validation. Restricting the machine learning models to only sequences extracted from T2FS and STIR sequences maintained comparable performance, with AUCs of 0.73 (95% CI 0.64-0.82) and 0.75 (95% CI 0.65-0.84), respectively.
CONCLUSION: Machine learning decision classifiers constructed from MRI-based radiomics features show promising ability to preoperatively discriminate between benign and malignant soft tissue masses. Our approach maintains applicability even when the dataset is restricted to T2FS and STIR fluid-sensitive sequences, which may bolster practicality in clinical application scenarios by eliminating the need for complex co-registrations for multisequence analysis. KEY POINTS: • Predictive models constructed from MRI-based radiomics data and machine learning-augmented approaches yielded good discriminative power to correctly classify benign and malignant lesions on preoperative scans, with AUCs of 0.77 (95% CI 0.68-0.85) and 0.72 (95% CI 0.63-0.81) for Real Adaptive Boosting (Adaboost) and Random Forest (RF), respectively. • Restricting the models to only use metrics extracted from T2 fat-saturated (T2FS) and Short-Tau Inversion Recovery (STIR) sequences yielded similar performance, with AUCs of 0.73 (95% CI 0.64-0.82) and 0.75 (95% CI 0.65-0.84) for Adaboost and RF, respectively. • Radiomics-based machine learning decision classifiers constructed from multicentric data more closely mimic the real-world practice environment and warrant additional validation ahead of prospective implementation into clinical workflows.

Entities:  

Keywords:  Benign neoplasms; Machine learning; Magnetic resonance imaging; Radiomics; Sarcoma, soft tissue

Year:  2021        PMID: 33893534     DOI: 10.1007/s00330-021-07914-w

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  44 in total

Review 1.  Soft-tissue masses: optimal imaging protocol and reporting.

Authors:  B J Manaster
Journal:  AJR Am J Roentgenol       Date:  2013-09       Impact factor: 3.959

2.  Quantitative magnetic resonance imaging (q-MRI) for the assessment of soft-tissue sarcoma treatment response: a narrative case review of technique development.

Authors:  Brandon K K Fields; Darryl Hwang; Steven Cen; Bhushan Desai; Mittul Gulati; James Hu; Vinay Duddalwar; Bino Varghese; George R Matcuk
Journal:  Clin Imaging       Date:  2020-02-28       Impact factor: 1.605

3.  Soft-tissue lesions: when can we exclude sarcoma?

Authors:  Avneesh Chhabra; Theodoros Soldatos
Journal:  AJR Am J Roentgenol       Date:  2012-12       Impact factor: 3.959

4.  Can MR imaging be used to predict tumor grade in soft-tissue sarcoma?

Authors:  Fang Zhao; Shivani Ahlawat; Sahar J Farahani; Kristy L Weber; Elizabeth A Montgomery; John A Carrino; Laura M Fayad
Journal:  Radiology       Date:  2014-03-08       Impact factor: 11.105

5.  Radiomics nomogram for differentiating between benign and malignant soft-tissue masses of the extremities.

Authors:  Hexiang Wang; Pei Nie; Yujian Wang; Wenjian Xu; Shaofeng Duan; Haisong Chen; Dapeng Hao; Jihua Liu
Journal:  J Magn Reson Imaging       Date:  2019-06-06       Impact factor: 4.813

Review 6.  Imaging of soft tissue sarcomas.

Authors:  Dakshesh B Patel; George R Matcuk
Journal:  Chin Clin Oncol       Date:  2018-08

7.  A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities.

Authors:  M Vallières; C R Freeman; S R Skamene; I El Naqa
Journal:  Phys Med Biol       Date:  2015-06-29       Impact factor: 3.609

Review 8.  Soft-tissue tumors and tumorlike lesions: a systematic imaging approach.

Authors:  Jim S Wu; Mary G Hochman
Journal:  Radiology       Date:  2009-11       Impact factor: 11.105

Review 9.  Soft-Tissue Sarcomas: An Update for Radiologists Based on the Revised 2013 World Health Organization Classification.

Authors:  Akshay D Baheti; Ryan B O'Malley; Sooah Kim; Abhishek R Keraliya; Sree Harsha Tirumani; Nikhil H Ramaiya; Carolyn L Wang
Journal:  AJR Am J Roentgenol       Date:  2016-03-21       Impact factor: 3.959

10.  Soft Tissue Sarcomas: Preoperative Predictive Histopathological Grading Based on Radiomics of MRI.

Authors:  Yu Zhang; Yifeng Zhu; Xiaomeng Shi; Juan Tao; Jingjing Cui; Yue Dai; Minting Zheng; Shaowu Wang
Journal:  Acad Radiol       Date:  2018-10-28       Impact factor: 3.173

View more
  4 in total

Review 1.  [Preoperative diagnostics and typing of abdominal soft tissue sarcomas].

Authors:  J Kirchberg; S F U Blum; J Pablik; S Herold; R T Hoffmann; G Baretton; J Weitz
Journal:  Chirurg       Date:  2021-11-10       Impact factor: 0.955

2.  Clinical-Radiomics Nomogram from T1W, T1CE, and T2FS MRI for Improving Diagnosis of Soft-Tissue Sarcoma.

Authors:  Zhibin Yue; Xiaoyu Wang; Yan Wang; Hongbo Wang; Wenyan Jiang
Journal:  Mol Imaging Biol       Date:  2022-07-07       Impact factor: 3.484

Review 3.  Applications of machine learning for imaging-driven diagnosis of musculoskeletal malignancies-a scoping review.

Authors:  Florian Hinterwimmer; Sarah Consalvo; Jan Neumann; Daniel Rueckert; Rüdiger von Eisenhart-Rothe; Rainer Burgkart
Journal:  Eur Radiol       Date:  2022-07-19       Impact factor: 7.034

4.  CT-Based Radiomics Analysis for Preoperative Diagnosis of Pancreatic Mucinous Cystic Neoplasm and Atypical Serous Cystadenomas.

Authors:  Tiansong Xie; Xuanyi Wang; Zehua Zhang; Zhengrong Zhou
Journal:  Front Oncol       Date:  2021-06-11       Impact factor: 6.244

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.