Literature DB >> 29044896

Support vector machine for breast cancer classification using diffusion-weighted MRI histogram features: Preliminary study.

Igor Vidić1, Liv Egnell1,2, Neil P Jerome2,3, Jose R Teruel4,5, Torill E Sjøbakk3, Agnes Østlie2, Hans E Fjøsne6,7, Tone F Bathen3, Pål Erik Goa1,2.   

Abstract

BACKGROUND: Diffusion-weighted MRI (DWI) is currently one of the fastest developing MRI-based techniques in oncology. Histogram properties from model fitting of DWI are useful features for differentiation of lesions, and classification can potentially be improved by machine learning.
PURPOSE: To evaluate classification of malignant and benign tumors and breast cancer subtypes using support vector machine (SVM). STUDY TYPE: Prospective.
SUBJECTS: Fifty-one patients with benign (n = 23) and malignant (n = 28) breast tumors (26 ER+, whereof six were HER2+). FIELD STRENGTH/SEQUENCE: Patients were imaged with DW-MRI (3T) using twice refocused spin-echo echo-planar imaging with echo time / repetition time (TR/TE) = 9000/86 msec, 90 × 90 matrix size, 2 × 2 mm in-plane resolution, 2.5 mm slice thickness, and 13 b-values. ASSESSMENT: Apparent diffusion coefficient (ADC), relative enhanced diffusivity (RED), and the intravoxel incoherent motion (IVIM) parameters diffusivity (D), pseudo-diffusivity (D*), and perfusion fraction (f) were calculated. The histogram properties (median, mean, standard deviation, skewness, kurtosis) were used as features in SVM (10-fold cross-validation) for differentiation of lesions and subtyping. STATISTICAL TESTS: Accuracies of the SVM classifications were calculated to find the combination of features with highest prediction accuracy. Mann-Whitney tests were performed for univariate comparisons.
RESULTS: For benign versus malignant tumors, univariate analysis found 11 histogram properties to be significant differentiators. Using SVM, the highest accuracy (0.96) was achieved from a single feature (mean of RED), or from three feature combinations of IVIM or ADC. Combining features from all models gave perfect classification. No single feature predicted HER2 status of ER + tumors (univariate or SVM), although high accuracy (0.90) was achieved with SVM combining several features. Importantly, these features had to include higher-order statistics (kurtosis and skewness), indicating the importance to account for heterogeneity. DATA
CONCLUSION: Our findings suggest that SVM, using features from a combination of diffusion models, improves prediction accuracy for differentiation of benign versus malignant breast tumors, and may further assist in subtyping of breast cancer. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2018;47:1205-1216.
© 2017 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  breast MR; diffusion weighted MRI; intravoxel incoherent motion; prognostic factors; support vector machine; tumor heterogeneity

Mesh:

Substances:

Year:  2017        PMID: 29044896     DOI: 10.1002/jmri.25873

Source DB:  PubMed          Journal:  J Magn Reson Imaging        ISSN: 1053-1807            Impact factor:   4.813


  13 in total

Review 1.  Machine learning in breast MRI.

Authors:  Beatriu Reig; Laura Heacock; Krzysztof J Geras; Linda Moy
Journal:  J Magn Reson Imaging       Date:  2019-07-05       Impact factor: 4.813

Review 2.  Radiomics in breast MRI: current progress toward clinical application in the era of artificial intelligence.

Authors:  Hiroko Satake; Satoko Ishigaki; Rintaro Ito; Shinji Naganawa
Journal:  Radiol Med       Date:  2021-10-26       Impact factor: 3.469

3.  Development and Validation of an MRI Radiomics-Based Signature to Predict Histological Grade in Patients with Invasive Breast Cancer.

Authors:  Shihui Wang; Yi Wei; Zhouli Li; Jingya Xu; Yunfeng Zhou
Journal:  Breast Cancer (Dove Med Press)       Date:  2022-10-14

Review 4.  Current and Emerging Magnetic Resonance-Based Techniques for Breast Cancer.

Authors:  Apekshya Chhetri; Xin Li; Joseph V Rispoli
Journal:  Front Med (Lausanne)       Date:  2020-05-12

5.  Histogram Analysis and Visual Heterogeneity of Diffusion-Weighted Imaging with Apparent Diffusion Coefficient Mapping in the Prediction of Molecular Subtypes of Invasive Breast Cancers.

Authors:  Joao V Horvat; Aditi Iyer; Elizabeth A Morris; Aditya Apte; Blanca Bernard-Davila; Danny F Martinez; Doris Leithner; Olivia M Sutton; R Elena Ochoa-Albiztegui; Dilip Giri; Katja Pinker; Sunitha B Thakur
Journal:  Contrast Media Mol Imaging       Date:  2019-11-22       Impact factor: 3.161

6.  Discrimination of Breast Cancer from Healthy Breast Tissue Using a Three-component Diffusion-weighted MRI Model.

Authors:  Maren M Sjaastad Andreassen; Ana E Rodríguez-Soto; Rebecca Rakow-Penner; Anders M Dale; Christopher C Conlin; Igor Vidić; Tyler M Seibert; Anne M Wallace; Somaye Zare; Joshua Kuperman; Boya Abudu; Grace S Ahn; Michael Hahn; Neil P Jerome; Agnes Østlie; Tone F Bathen; Haydee Ojeda-Fournier; Pål Erik Goa
Journal:  Clin Cancer Res       Date:  2020-11-04       Impact factor: 12.531

Review 7.  Perfusion-driven Intravoxel Incoherent Motion (IVIM) MRI in Oncology: Applications, Challenges, and Future Trends.

Authors:  Mami Iima
Journal:  Magn Reson Med Sci       Date:  2020-06-15       Impact factor: 2.471

8.  Development of a Novel Multiparametric MRI Radiomic Nomogram for Preoperative Evaluation of Early Recurrence in Resectable Pancreatic Cancer.

Authors:  Tian-Yu Tang; Xiang Li; Qi Zhang; Cheng-Xiang Guo; Xiao-Zhen Zhang; Meng-Yi Lao; Yi-Nan Shen; Wen-Bo Xiao; Shi-Hong Ying; Ke Sun; Ri-Sheng Yu; Shun-Liang Gao; Ri-Sheng Que; Wei Chen; Da-Bing Huang; Pei-Pei Pang; Xue-Li Bai; Ting-Bo Liang
Journal:  J Magn Reson Imaging       Date:  2019-12-23       Impact factor: 4.813

Review 9.  Application of Radiomics and Decision Support Systems for Breast MR Differential Diagnosis.

Authors:  Ioannis Tsougos; Alexandros Vamvakas; Constantin Kappas; Ioannis Fezoulidis; Katerina Vassiou
Journal:  Comput Math Methods Med       Date:  2018-09-23       Impact factor: 2.238

10.  An Efficient Feature Selection Strategy Based on Multiple Support Vector Machine Technology with Gene Expression Data.

Authors:  Ying Zhang; Qingchun Deng; Wenbin Liang; Xianchun Zou
Journal:  Biomed Res Int       Date:  2018-08-30       Impact factor: 3.411

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.