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. 1. Department of Physics, NTNU - Norwegian University of Science and Technology, Trondheim, Norway. 2. Clinic of Radiology and Nuclear Medicine, St. Olavs University Hospital, Trondheim, Norway. 3. Department of Circulation and Medical Imaging, NTNU - Norwegian University of Science and Technology, Trondheim, Norway. 4. Department of Radiology, University of California San Diego, La Jolla, California, USA. 5. Department of Radiation Oncology, NYU Langone Medical Center, New York, New York, USA. 6. Department of Cancer Research and Molecular Medicine, NTNU - Norwegian University of Science and Technology, Trondheim, Norway. 7. Department of Surgery, St. Olavs University Hospital, Trondheim, Norway.
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.
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.
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
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
Authors: Ioannis Tsougos; Alexandros Vamvakas; Constantin Kappas; Ioannis Fezoulidis; Katerina Vassiou Journal: Comput Math Methods Med Date: 2018-09-23 Impact factor: 2.238