Hiroyuki Tatekawa1,2,3, Akifumi Hagiwara1,2,4, Hiroyuki Uetani2,5, Shadfar Bahri6, Catalina Raymond1,2, Albert Lai7,8, Timothy F Cloughesy7,8, Phioanh L Nghiemphu7,8, Linda M Liau7,9, Whitney B Pope2, Noriko Salamon2, Benjamin M Ellingson10,11,12. 1. UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision and Imaging Biomarkers, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USA. 2. Department of Radiological Science, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USA. 3. Department of Diagnostic and Interventional Radiology, Osaka City University Graduate School of Medicine, Osaka, Japan. 4. Department of Radiology, Juntendo University School of Medicine, Tokyo, Japan. 5. Department of Diagnostic Radiology, Faculty of Life Sciences, Kumamoto University, Kumamoto, Japan. 6. Department of Molecular and Medical Pharmacology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USA. 7. UCLA Neuro-Oncology Program, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USA. 8. Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USA. 9. Department of Neurosurgery, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USA. 10. UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision and Imaging Biomarkers, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USA. bellingson@mednet.ucla.edu. 11. Department of Radiological Science, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USA. bellingson@mednet.ucla.edu. 12. UCLA Neuro-Oncology Program, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USA. bellingson@mednet.ucla.edu.
Abstract
BACKGROUND: The purpose of this study was to develop a voxel-wise clustering method of multiparametric magnetic resonance imaging (MRI) and 3,4-dihydroxy-6-[18F]-fluoro-L-phenylalanine (FDOPA) positron emission tomography (PET) images using an unsupervised, two-level clustering approach followed by support vector machine in order to classify the isocitrate dehydrogenase (IDH) status of gliomas. METHODS: Sixty-two treatment-naïve glioma patients who underwent FDOPA PET and MRI were retrospectively included. Contrast enhanced T1-weighted images, T2-weighted images, fluid-attenuated inversion recovery images, apparent diffusion coefficient maps, and relative cerebral blood volume maps, and FDOPA PET images were used for voxel-wise feature extraction. An unsupervised two-level clustering approach, including a self-organizing map followed by the K-means algorithm was used, and each class label was applied to the original images. The logarithmic ratio of labels in each class within tumor regions was applied to a support vector machine to differentiate IDH mutation status. The area under the curve (AUC) of receiver operating characteristic curves, accuracy, and F1-socore were calculated and used as metrics for performance. RESULTS: The associations of multiparametric imaging values in each cluster were successfully visualized. Multiparametric images with 16-class clustering revealed the highest classification performance to differentiate IDH status with the AUC, accuracy, and F1-score of 0.81, 0.76, and 0.76, respectively. CONCLUSIONS: Machine learning using an unsupervised two-level clustering approach followed by a support vector machine classified the IDH mutation status of gliomas, and visualized voxel-wise features from multiparametric MRI and FDOPA PET images. Unsupervised clustered features may improve the understanding of prioritizing multiparametric imaging for classifying IDH status.
BACKGROUND: The purpose of this study was to develop a voxel-wise clustering method of multiparametric magnetic resonance imaging (MRI) and 3,4-dihydroxy-6-[18F]-fluoro-L-phenylalanine (FDOPA) positron emission tomography (PET) images using an unsupervised, two-level clustering approach followed by support vector machine in order to classify the isocitrate dehydrogenase (IDH) status of gliomas. METHODS: Sixty-two treatment-naïve gliomapatients who underwent FDOPA PET and MRI were retrospectively included. Contrast enhanced T1-weighted images, T2-weighted images, fluid-attenuated inversion recovery images, apparent diffusion coefficient maps, and relative cerebral blood volume maps, and FDOPA PET images were used for voxel-wise feature extraction. An unsupervised two-level clustering approach, including a self-organizing map followed by the K-means algorithm was used, and each class label was applied to the original images. The logarithmic ratio of labels in each class within tumor regions was applied to a support vector machine to differentiate IDH mutation status. The area under the curve (AUC) of receiver operating characteristic curves, accuracy, and F1-socore were calculated and used as metrics for performance. RESULTS: The associations of multiparametric imaging values in each cluster were successfully visualized. Multiparametric images with 16-class clustering revealed the highest classification performance to differentiate IDH status with the AUC, accuracy, and F1-score of 0.81, 0.76, and 0.76, respectively. CONCLUSIONS: Machine learning using an unsupervised two-level clustering approach followed by a support vector machine classified the IDH mutation status of gliomas, and visualized voxel-wise features from multiparametric MRI and FDOPA PET images. Unsupervised clustered features may improve the understanding of prioritizing multiparametric imaging for classifying IDH status.
Authors: Benjamin M Ellingson; Martin Bendszus; Jerrold Boxerman; Daniel Barboriak; Bradley J Erickson; Marion Smits; Sarah J Nelson; Elizabeth Gerstner; Brian Alexander; Gregory Goldmacher; Wolfgang Wick; Michael Vogelbaum; Michael Weller; Evanthia Galanis; Jayashree Kalpathy-Cramer; Lalitha Shankar; Paula Jacobs; Whitney B Pope; Dewen Yang; Caroline Chung; Michael V Knopp; Soonme Cha; Martin J van den Bent; Susan Chang; W K Al Yung; Timothy F Cloughesy; Patrick Y Wen; Mark R Gilbert Journal: Neuro Oncol Date: 2015-08-05 Impact factor: 12.300
Authors: B M Ellingson; A Lai; R J Harris; J M Selfridge; W H Yong; K Das; W B Pope; P L Nghiemphu; H V Vinters; L M Liau; P S Mischel; T F Cloughesy Journal: AJNR Am J Neuroradiol Date: 2012-09-20 Impact factor: 3.825
Authors: Philipp Lohmann; Christoph Lerche; Elena K Bauer; Jan Steger; Gabriele Stoffels; Tobias Blau; Veronika Dunkl; Martin Kocher; Shivakumar Viswanathan; Christian P Filss; Carina Stegmayr; Maximillian I Ruge; Bernd Neumaier; Nadim J Shah; Gereon R Fink; Karl-Josef Langen; Norbert Galldiks Journal: Sci Rep Date: 2018-09-06 Impact factor: 4.379
Authors: Anne Jarstein Skjulsvik; Hans Kristian Bø; Asgeir Store Jakola; Erik Magnus Berntsen; Lars Eirik Bø; Ingerid Reinertsen; Kristin Smistad Myrmel; Kristin Sjåvik; Kristin Åberg; Thomas Berg; Hong Yan Dai; Roar Kloster; Sverre Helge Torp; Ole Solheim Journal: J Neurooncol Date: 2020-01-25 Impact factor: 4.130
Authors: David N Louis; Hiroko Ohgaki; Otmar D Wiestler; Webster K Cavenee; Peter C Burger; Anne Jouvet; Bernd W Scheithauer; Paul Kleihues Journal: Acta Neuropathol Date: 2007-07-06 Impact factor: 17.088
Authors: Andreas Stadlbauer; Franz Marhold; Stefan Oberndorfer; Gertraud Heinz; Michael Buchfelder; Thomas M Kinfe; Anke Meyer-Bäse Journal: Cancers (Basel) Date: 2022-05-10 Impact factor: 6.575
Authors: Akifumi Hagiwara; Hiroyuki Tatekawa; Jingwen Yao; Catalina Raymond; Richard Everson; Kunal Patel; Sergey Mareninov; William H Yong; Noriko Salamon; Whitney B Pope; Phioanh L Nghiemphu; Linda M Liau; Timothy F Cloughesy; Benjamin M Ellingson Journal: Sci Rep Date: 2022-01-20 Impact factor: 4.379