P Chang1, J Grinband2, B D Weinberg3, M Bardis4, M Khy4, G Cadena5, M-Y Su4, S Cha1, C G Filippi6, D Bota7, P Baldi8, L M Poisson9, R Jain10, D Chow11. 1. From the Department of Radiology (P.C., S.C.), University of California, San Francisco, San Francisco, California. 2. Department of Radiology (J.G.), Columbia University, New York, New York. 3. Department of Radiology (B.D.W.), Emory University School of Medicine, Atlanta, Georgia. 4. Departments of Radiology (M.B., M.K., M.-Y.S., D.C.). 5. Neurosurgery (G.C.). 6. Department of Radiology (C.G.F.), North Shore University Hospital, Long Island, New York. 7. Neuro-Oncology (D.B.). 8. School of Information and Computer Sciences (P.B.), University of California, Irvine, Irvine, California. 9. Department of Public Health Sciences (L.M.P.), Henry Ford Health System, Detroit, Michigan. 10. Departments of Radiology and Neurosurgery (R.J.), New York University, New York, New York. 11. Departments of Radiology (M.B., M.K., M.-Y.S., D.C.) chowd3@uci.edu.
Abstract
BACKGROUND AND PURPOSE: The World Health Organization has recently placed new emphasis on the integration of genetic information for gliomas. While tissue sampling remains the criterion standard, noninvasive imaging techniques may provide complimentary insight into clinically relevant genetic mutations. Our aim was to train a convolutional neural network to independently predict underlying molecular genetic mutation status in gliomas with high accuracy and identify the most predictive imaging features for each mutation. MATERIALS AND METHODS: MR imaging data and molecular information were retrospectively obtained from The Cancer Imaging Archives for 259 patients with either low- or high-grade gliomas. A convolutional neural network was trained to classify isocitrate dehydrogenase 1 (IDH1) mutation status, 1p/19q codeletion, and O6-methylguanine-DNA methyltransferase (MGMT) promotor methylation status. Principal component analysis of the final convolutional neural network layer was used to extract the key imaging features critical for successful classification. RESULTS: Classification had high accuracy: IDH1 mutation status, 94%; 1p/19q codeletion, 92%; and MGMT promotor methylation status, 83%. Each genetic category was also associated with distinctive imaging features such as definition of tumor margins, T1 and FLAIR suppression, extent of edema, extent of necrosis, and textural features. CONCLUSIONS: Our results indicate that for The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas. We show that relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human-directed training.
BACKGROUND AND PURPOSE: The World Health Organization has recently placed new emphasis on the integration of genetic information for gliomas. While tissue sampling remains the criterion standard, noninvasive imaging techniques may provide complimentary insight into clinically relevant genetic mutations. Our aim was to train a convolutional neural network to independently predict underlying molecular genetic mutation status in gliomas with high accuracy and identify the most predictive imaging features for each mutation. MATERIALS AND METHODS: MR imaging data and molecular information were retrospectively obtained from The Cancer Imaging Archives for 259 patients with either low- or high-grade gliomas. A convolutional neural network was trained to classify isocitrate dehydrogenase 1 (IDH1) mutation status, 1p/19q codeletion, and O6-methylguanine-DNA methyltransferase (MGMT) promotor methylation status. Principal component analysis of the final convolutional neural network layer was used to extract the key imaging features critical for successful classification. RESULTS: Classification had high accuracy: IDH1 mutation status, 94%; 1p/19q codeletion, 92%; and MGMT promotor methylation status, 83%. Each genetic category was also associated with distinctive imaging features such as definition of tumor margins, T1 and FLAIR suppression, extent of edema, extent of necrosis, and textural features. CONCLUSIONS: Our results indicate that for The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas. We show that relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human-directed training.
Authors: Brian J Gill; David J Pisapia; Hani R Malone; Hannah Goldstein; Liang Lei; Adam Sonabend; Jonathan Yun; Jorge Samanamud; Jennifer S Sims; Matei Banu; Athanassios Dovas; Andrew F Teich; Sameer A Sheth; Guy M McKhann; Michael B Sisti; Jeffrey N Bruce; Peter A Sims; Peter Canoll Journal: Proc Natl Acad Sci U S A Date: 2014-08-11 Impact factor: 11.205
Authors: Kenneth Clark; Bruce Vendt; Kirk Smith; John Freymann; Justin Kirby; Paul Koppel; Stephen Moore; Stanley Phillips; David Maffitt; Michael Pringle; Lawrence Tarbox; Fred Prior Journal: J Digit Imaging Date: 2013-12 Impact factor: 4.056
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: Thierry Gorlia; Martin J van den Bent; Monika E Hegi; René O Mirimanoff; Michael Weller; J Gregory Cairncross; Elizabeth Eisenhauer; Karl Belanger; Alba A Brandes; Anouk Allgeier; Denis Lacombe; Roger Stupp Journal: Lancet Oncol Date: 2007-12-21 Impact factor: 41.316
Authors: Andreas Kleppe; Ole-Johan Skrede; Sepp De Raedt; Knut Liestøl; David J Kerr; Håvard E Danielsen Journal: Nat Rev Cancer Date: 2021-01-29 Impact factor: 60.716
Authors: Y W Lui; P D Chang; G Zaharchuk; D P Barboriak; A E Flanders; M Wintermark; C P Hess; C G Filippi Journal: AJNR Am J Neuroradiol Date: 2020-07-30 Impact factor: 3.825
Authors: Chandan Ganesh Bangalore Yogananda; Bhavya R Shah; Maryam Vejdani-Jahromi; Sahil S Nalawade; Gowtham K Murugesan; Frank F Yu; Marco C Pinho; Benjamin C Wagner; Bruce Mickey; Toral R Patel; Baowei Fei; Ananth J Madhuranthakam; Joseph A Maldjian Journal: Neuro Oncol Date: 2020-03-05 Impact factor: 12.300