SoHyun Han1,2, Radka Stoyanova3, Hansol Lee1, Sean D Carlin4,5, Jason A Koutcher4,6,7,8, HyungJoon Cho1, Ellen Ackerstaff4. 1. Department of Biomedical Engineering, Ulsan National Institute of Science and Technology, Ulsan, South Korea. 2. Currently at: Center for Neuroscience Imaging Research, Institute for Basic Science (IBS), Suwon, South Korea. 3. Department of Radiation Oncology, Miller School of Medicine, University of Miami, Miami, Florida, USA. 4. Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA. 5. Currently at: Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA. 6. Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, New York, USA. 7. Sloan Kettering Institute Molecular Pharmacology Program, Memorial Sloan Kettering Cancer Center, New York, New York, USA. 8. Weill Cornell Medical College, Cornell University, New York, New York, USA.
Abstract
PURPOSE: To automate dynamic contrast-enhanced MRI (DCE-MRI) data analysis by unsupervised pattern recognition (PR) to enable spatial mapping of intratumoral vascular heterogeneity. METHODS: Three steps were automated. First, the arrival time of the contrast agent at the tumor was determined, including a calculation of the precontrast signal. Second, four criteria-based algorithms for the slice-specific selection of number of patterns (NP) were validated using 109 tumor slices from subcutaneous flank tumors of five different tumor models. The criteria were: half area under the curve, standard deviation thresholding, percent signal enhancement, and signal-to-noise ratio (SNR). The performance of these criteria was assessed by comparing the calculated NP with the visually determined NP. Third, spatial assignment of single patterns and/or pattern mixtures was obtained by way of constrained nonnegative matrix factorization. RESULTS: The determination of the contrast agent arrival time at the tumor slice was successfully automated. For the determination of NP, the SNR-based approach outperformed other selection criteria by agreeing >97% with visual assessment. The spatial localization of single patterns and pattern mixtures, the latter inferring tumor vascular heterogeneity at subpixel spatial resolution, was established successfully by automated assignment from DCE-MRI signal-versus-time curves. CONCLUSION: The PR-based DCE-MRI analysis was successfully automated to spatially map intratumoral vascular heterogeneity. Magn Reson Med 79:1736-1744, 2018.
PURPOSE: To automate dynamic contrast-enhanced MRI (DCE-MRI) data analysis by unsupervised pattern recognition (PR) to enable spatial mapping of intratumoral vascular heterogeneity. METHODS: Three steps were automated. First, the arrival time of the contrast agent at the tumor was determined, including a calculation of the precontrast signal. Second, four criteria-based algorithms for the slice-specific selection of number of patterns (NP) were validated using 109 tumor slices from subcutaneous flank tumors of five different tumor models. The criteria were: half area under the curve, standard deviation thresholding, percent signal enhancement, and signal-to-noise ratio (SNR). The performance of these criteria was assessed by comparing the calculated NP with the visually determined NP. Third, spatial assignment of single patterns and/or pattern mixtures was obtained by way of constrained nonnegative matrix factorization. RESULTS: The determination of the contrast agent arrival time at the tumor slice was successfully automated. For the determination of NP, the SNR-based approach outperformed other selection criteria by agreeing >97% with visual assessment. The spatial localization of single patterns and pattern mixtures, the latter inferring tumor vascular heterogeneity at subpixel spatial resolution, was established successfully by automated assignment from DCE-MRI signal-versus-time curves. CONCLUSION: The PR-based DCE-MRI analysis was successfully automated to spatially map intratumoral vascular heterogeneity. Magn Reson Med 79:1736-1744, 2018.
Authors: Radka Stoyanova; Mandeep Takhar; Yohann Tschudi; John C Ford; Gabriel Solórzano; Nicholas Erho; Yoganand Balagurunathan; Sanoj Punnen; Elai Davicioni; Robert J Gillies; Alan Pollack Journal: Transl Cancer Res Date: 2016-08 Impact factor: 1.241
Authors: Radka Stoyanova; Kris Huang; Kiri Sandler; Hyungjoon Cho; Sean Carlin; Pat B Zanzonico; Jason A Koutcher; Ellen Ackerstaff Journal: Transl Oncol Date: 2012-12-01 Impact factor: 4.243
Authors: M O Leach; B Morgan; P S Tofts; D L Buckley; W Huang; M A Horsfield; T L Chenevert; D J Collins; A Jackson; D Lomas; B Whitcher; L Clarke; R Plummer; I Judson; R Jones; R Alonzi; T Brunner; D M Koh; P Murphy; J C Waterton; G Parker; M J Graves; T W J Scheenen; T W Redpath; M Orton; G Karczmar; H Huisman; J Barentsz; A Padhani Journal: Eur Radiol Date: 2012-05-07 Impact factor: 5.315
Authors: HyungJoon Cho; Ellen Ackerstaff; Sean Carlin; Mihaela E Lupu; Ya Wang; Asif Rizwan; Joseph O'Donoghue; C Clifton Ling; John L Humm; Pat B Zanzonico; Jason A Koutcher Journal: Neoplasia Date: 2009-03 Impact factor: 5.715
Authors: Bruna V Jardim-Perassi; Suning Huang; William Dominguez-Viqueira; Jan Poleszczuk; Mikalai M Budzevich; Mahmoud A Abdalah; Smitha R Pillai; Epifanio Ruiz; Marilyn M Bui; Debora A P C Zuccari; Robert J Gillies; Gary V Martinez Journal: Cancer Res Date: 2019-06-11 Impact factor: 12.701
Authors: Ethan Bendau; Jason Smith; Lin Zhang; Ellen Ackerstaff; Natalia Kruchevsky; Binlin Wu; Jason A Koutcher; Robert Alfano; Lingyan Shi Journal: J Biophotonics Date: 2020-04-20 Impact factor: 3.207
Authors: Po-Hung Wu; Matthew Gibbons; Sarah C Foreman; Julio Carballido-Gamio; Misung Han; Roland Krug; Jing Liu; Thomas M Link; Galateia J Kazakia Journal: Quant Imaging Med Surg Date: 2019-06
Authors: Edward Taylor; Jitao Zhou; Patricia Lindsay; Warren Foltz; May Cheung; Iram Siddiqui; Ali Hosni; Ahmed El Amir; John Kim; Richard P Hill; David A Jaffray; David W Hedley Journal: Sci Rep Date: 2020-01-31 Impact factor: 4.379