1
|
Verma R, Hill VB, Statsevych V, Bera K, Correa R, Leo P, Ahluwalia M, Madabhushi A, Tiwari P. Stable and Discriminatory Radiomic Features from the Tumor and Its Habitat Associated with Progression-Free Survival in Glioblastoma: A Multi-Institutional Study. AJNR Am J Neuroradiol 2022; 43:1115-1123. [PMID: 36920774 PMCID: PMC9575418 DOI: 10.3174/ajnr.a7591] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2021] [Accepted: 06/13/2022] [Indexed: 11/07/2022]
Abstract
BACKGROUND AND PURPOSE Glioblastoma is an aggressive brain tumor, with no validated prognostic biomarkers for survival before surgical resection. Although recent approaches have demonstrated the prognostic ability of tumor habitat (constituting necrotic core, enhancing lesion, T2/FLAIR hyperintensity subcompartments) derived radiomic features for glioblastoma survival on treatment-naive MR imaging scans, radiomic features are known to be sensitive to MR imaging acquisitions across sites and scanners. In this study, we sought to identify the radiomic features that are both stable across sites and discriminatory of poor and improved progression-free survival in glioblastoma tumors. MATERIALS AND METHODS We used 150 treatment-naive glioblastoma MR imaging scans (Gadolinium-T1w, T2w, FLAIR) obtained from 5 sites. For every tumor subcompartment (enhancing tumor, peritumoral FLAIR-hyperintensities, necrosis), a total of 316 three-dimensional radiomic features were extracted. The training cohort constituted studies from 4 sites (n = 93) to select the most stable and discriminatory radiomic features for every tumor subcompartment. These features were used on a hold-out cohort (n = 57) to evaluate their ability to discriminate patients with poor survival from those with improved survival. RESULTS Incorporating the most stable and discriminatory features within a linear discriminant analysis classifier yielded areas under the curve of 0.71, 0.73, and 0.76 on the test set for distinguishing poor and improved survival compared with discriminatory features alone (areas under the curve of 0.65, 0.54, 0.62) from the necrotic core, enhancing tumor, and peritumoral T2/FLAIR hyperintensity, respectively. CONCLUSIONS Incorporating stable and discriminatory radiomic features extracted from tumors and associated habitats across multisite MR imaging sequences may yield robust prognostic classifiers of patient survival in glioblastoma tumors.
Collapse
Affiliation(s)
- R Verma
- From the Department of Biomedical Engineering (R.V., K.B., R.C., P.L.), Case Western Reserve University, Cleveland, Ohio .,Alberta Machine Intelligence Institute (R.V.), Edmonton, Alberta
| | - V B Hill
- Department of Neuroradiology (V.B.H.), Feinberg School of Medicine, Northwestern University, Chicago, Illinois
| | - V Statsevych
- Brain Tumor and Neuro-Oncology Center (V.S.), Cleveland Clinic, Cleveland, Ohio
| | - K Bera
- From the Department of Biomedical Engineering (R.V., K.B., R.C., P.L.), Case Western Reserve University, Cleveland, Ohio
| | - R Correa
- From the Department of Biomedical Engineering (R.V., K.B., R.C., P.L.), Case Western Reserve University, Cleveland, Ohio
| | - P Leo
- From the Department of Biomedical Engineering (R.V., K.B., R.C., P.L.), Case Western Reserve University, Cleveland, Ohio
| | - M Ahluwalia
- Miami Cancer Institute (M.A.), Miami, FL and Herbert Wertheim College of Medicine, Florida International University, Florida
| | - A Madabhushi
- Department of Biomedical Engineering (A.M.), Emory University, Atlanta Veterans Administration Medical Center
| | - P Tiwari
- Departments of Radiology and Biomedical Engineering (P.T.), University of Wisconsin Madison, Wisconsin
| |
Collapse
|
2
|
Ismail M, Hill V, Statsevych V, Huang R, Prasanna P, Correa R, Singh G, Bera K, Beig N, Thawani R, Madabhushi A, Aahluwalia M, Tiwari P. Shape Features of the Lesion Habitat to Differentiate Brain Tumor Progression from Pseudoprogression on Routine Multiparametric MRI: A Multisite Study. AJNR Am J Neuroradiol 2018; 39:2187-2193. [PMID: 30385468 DOI: 10.3174/ajnr.a5858] [Citation(s) in RCA: 48] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2018] [Accepted: 09/06/2018] [Indexed: 11/07/2022]
Abstract
BACKGROUND AND PURPOSE Differentiating pseudoprogression, a radiation-induced treatment effect, from tumor progression on imaging is a substantial challenge in glioblastoma management. Unfortunately, guidelines set by the Response Assessment in Neuro-Oncology criteria are based solely on bidirectional diametric measurements of enhancement observed on T1WI and T2WI/FLAIR scans. We hypothesized that quantitative 3D shape features of the enhancing lesion on T1WI, and T2WI/FLAIR hyperintensities (together called the lesion habitat) can more comprehensively capture pathophysiologic differences across pseudoprogression and tumor recurrence, not appreciable on diametric measurements alone. MATERIALS AND METHODS A total of 105 glioblastoma studies from 2 institutions were analyzed, consisting of a training (n = 59) and an independent test (n = 46) cohort. For every study, expert delineation of the lesion habitat (T1WI enhancing lesion and T2WI/FLAIR hyperintense perilesional region) was obtained, followed by extraction of 30 shape features capturing 14 "global" contour characteristics and 16 "local" curvature measures for every habitat region. Feature selection was used to identify most discriminative features on the training cohort, which were evaluated on the test cohort using a support vector machine classifier. RESULTS The top 2 most discriminative features were identified as local features capturing total curvature of the enhancing lesion and curvedness of the T2WI/FLAIR hyperintense perilesional region. Using top features from the training cohort (training accuracy = 91.5%), we obtained an accuracy of 90.2% on the test set in distinguishing pseudoprogression from tumor progression. CONCLUSIONS Our preliminary results suggest that 3D shape attributes from the lesion habitat can differentially express across pseudoprogression and tumor progression and could be used to distinguish these radiographically similar pathologies.
Collapse
Affiliation(s)
- M Ismail
- From the Department of Biomedical Engineering (M.I., P.P., R.C., G.S., K.B., N.B., R.T., A.M., P.T.), Case Western Reserve University, Cleveland, Ohio
| | - V Hill
- Department of Neuroradiology (V.H., V.S.), Imaging Institute
| | - V Statsevych
- Department of Neuroradiology (V.H., V.S.), Imaging Institute
| | - R Huang
- Department of Radiology (R.H.), Brigham and Women's Hospital, Dana-Farber/Harvard Cancer Center, Boston, Massachusetts
| | - P Prasanna
- From the Department of Biomedical Engineering (M.I., P.P., R.C., G.S., K.B., N.B., R.T., A.M., P.T.), Case Western Reserve University, Cleveland, Ohio
| | - R Correa
- From the Department of Biomedical Engineering (M.I., P.P., R.C., G.S., K.B., N.B., R.T., A.M., P.T.), Case Western Reserve University, Cleveland, Ohio
| | - G Singh
- From the Department of Biomedical Engineering (M.I., P.P., R.C., G.S., K.B., N.B., R.T., A.M., P.T.), Case Western Reserve University, Cleveland, Ohio
| | - K Bera
- From the Department of Biomedical Engineering (M.I., P.P., R.C., G.S., K.B., N.B., R.T., A.M., P.T.), Case Western Reserve University, Cleveland, Ohio
| | - N Beig
- From the Department of Biomedical Engineering (M.I., P.P., R.C., G.S., K.B., N.B., R.T., A.M., P.T.), Case Western Reserve University, Cleveland, Ohio
| | - R Thawani
- From the Department of Biomedical Engineering (M.I., P.P., R.C., G.S., K.B., N.B., R.T., A.M., P.T.), Case Western Reserve University, Cleveland, Ohio
| | - A Madabhushi
- From the Department of Biomedical Engineering (M.I., P.P., R.C., G.S., K.B., N.B., R.T., A.M., P.T.), Case Western Reserve University, Cleveland, Ohio
| | - M Aahluwalia
- Brain Tumor and Neuro-Oncology Center (M.A.), Cleveland Clinic, Cleveland, Ohio
| | - P Tiwari
- From the Department of Biomedical Engineering (M.I., P.P., R.C., G.S., K.B., N.B., R.T., A.M., P.T.), Case Western Reserve University, Cleveland, Ohio
| |
Collapse
|
3
|
Arakawa Y, Fujimoto KI, Murata D, Nakamoto Y, Okada T, Miyamoto S, Bahr O, Harter PN, Weise L, You SJ, Ronellenfitsch MW, Rieger J, Steinbach JP, Hattingen E, Bahr O, Jurcoane A, Daneshvar K, Pilatus U, Mittelbronn M, Steinbach JP, Hattingen E, Carrillo J, Bota D, Handwerker J, Su LMY, Chen T, Stathopoulos A, Yu H, Chang JH, Kim EH, Kim SH, Mi, Yun J, Pytel P, Collins J, Choi Y, Lukas R, Nicholas M, Colen R, Jafrani R, Zinn P, Colen R, Ashour O, Zinn P, Colen R, Vangel M, Gutman D, Hwang S, Wintermark M, Jain R, Jilwan-Nicolas M, Chen J, Raghavan P, Holder C, Rubin D, Huang E, Kirby J, Freymann J, Jaffe C, Flanders A, Zinn P, Colen R, Ashour O, Zinn P, Colen R, Zinn P, Dahiya S, Statsevych V, Elson P, Xie H, Chao S, Peereboom D, Stevens G, Barnett G, Ahluwalia M, Daras M, Karimi S, Abrey L, Sanchez J, Beal K, Gutin P, Kaley T, Grommes C, Correa D, Reiner A, Briggs S, Omuro A, Verburg N, Hoefnagels F, Pouwels P, Boellaard R, Barkhof F, Hoekstra O, Wesseling P, Reijneveld J, Heimans J, Vandertop P, Zwinderman K, Hamer HDW, Elinzano H, Kadivar F, Yadav PO, Breese VL, Jackson CL, Donahue JE, Boxerman JL, Ellingson B, Pope W, Lai A, Nghiemphu P, Cloughesy T, Ellingson B, Pope W, Chen W, Czernin J, Phelps M, Lai A, Nghiemphu P, Liau L, Cloughesy T, Ellingson B, Leu K, Tran A, Pope W, Lai A, Nghiemphu P, Harris R, Woodworth D, Cloughesy T, Ellingson B, Pope W, Leu K, Chen W, Czernin J, Phelps M, Lai A, Nghiemphu P, Liau L, Cloughesy T, Ellingson B, Enzmann D, Pope W, Lai A, Nghiemphu P, Liau L, Cloughesy T, Eoli M, Di Stefano AL, Aquino D, Scotti A, Anghileri E, Cuppini L, Prodi E, Finocchiaro G, Bruzzone MG, Fujimoto K, Arakawa Y, Murata D, Nakamoto Y, Okada T, Miyamoto S, Galldiks N, Stoffels G, Filss C, Dunkl V, Rapp M, Sabel M, Ruge MI, Goldbrunner R, Shah NJ, Fink GR, Coenen HH, Langen KJ, Guha-Thakurta N, Langford L, Collet S, Valable S, Constans JM, Lechapt-Zalcman E, Roussel S, Delcroix N, Bernaudin M, Abbas A, Ibazizene E, Barre L, Derlon JM, Guillamo JS, Harris R, Bookheimer S, Cloughesy T, Kim H, Pope W, Yang K, Lai A, Nghiemphu P, Ellingson B, Huang R, Rahman R, Hamdan A, Kane C, Chen C, Norden A, Reardon D, Mukundan S, Wen P, Jafrani R, Zinn P, Colen R, Jafrani R, Zinn P, Colen R, Jancalek R, Bulik M, Kazda T, Jensen R, Salzman K, Kamson D, Lee T, Varadarajan K, Robinette N, Muzik O, Chakraborty P, Barger G, Mittal S, Juhasz C, Kamson D, Barger G, Robinette N, Muzik O, Chakraborty P, Kupsky W, Mittal S, Juhasz C, Kinoshita M, Sasayama T, Narita Y, Kawaguchi A, Yamashita F, Chiba Y, Kagawa N, Tanaka K, Kohmura E, Arita H, Okita Y, Ohno M, Miyakita Y, Shibui S, Hashimoto N, Yoshimine T, Ronan LK, Eskey C, Hampton T, Fadul C, LaMontagne P, Milchenko M, Sylvester P, Benzinger T, Marcus D, Fouke SJ, Lupo J, Bian W, Anwar M, Banerjee S, Hess C, Chang S, Nelson S, Mabray M, Sanchez L, Valles F, Barajas R, Rubenstein J, Cha S, Miyake K, Ogawa D, Hatakeyama T, Kawai N, Tamiya T, Mori K, Ishikura R, Tomogane Y, Ando K, Izumoto S, Nelson S, Lieberman F, Lupo J, Viziri S, Nabors LB, Crane J, Wen P, Cote A, Peereboom D, Wen Q, Cloughesy T, Robins HI, Fisher J, Desideri S, Grossman S, Ye X, Blakeley J, Nonaka M, Nakajima S, Shofuda T, Kanemura Y, Nowosielski M, Wiestler B, Gobel G, Hutterer M, Schlemmer H, Stockhammer G, Wick W, Bendszus M, Radbruch A, Perreault S, Yeom K, Ramaswamy V, Shih D, Remke M, Luu B, Schubert S, Fisher P, Partap S, Vogel H, Poussaint TY, Taylor M, Cho YJ, Piludu F, Pace A, Fabi A, Anelli V, Villani V, Carapella C, Marzi S, Vidiri A, Pungavkar S, Tanawde P, Epari S, Patkar D, Lawande M, Moiyadi A, Gupta T, Jalali R, Rahman R, Akgoz A, You H, Hamdan A, Seethamraju R, Wen P, Young G, Rao A, Rao G, Flanders A, Ghosh P, Rao G, Martinez J, Rao A, Roh TH, Kim EH, Chang JH, Kushnirsky M, Katz J, Knisely J, Schulder M, Steinklein J, Rosen L, Warshall C, Nguyen V, Tiwari P, Rogers L, Wolansky L, Sloan A, Barnholtz-Sloan J, Tatsauka C, Cohen M, Madabhushi A, Rachinger W, Thon N, Haug A, Schuller U, Schichor C, Tonn JC, Tran A, Lai A, Li S, Pope W, Teixeira S, Harris R, Woodworth D, Nghiemphu P, Cloughesy T, Ellingson B, Villanueva-Meyer J, Barajas R, Mabray M, Barani I, Chen W, Shankaranarayanan A, Koon P, Cha S, Wen Q, Elkhaled A, Essock-Burns E, Molinaro A, Phillips J, Chang S, Cha S, Nelson S, Wolf D, Ye X, Lim M, Zhu H, Wang M, Quinones-Hinojosa A, Weingart J, Olivi A, van Zijl P, Laterra J, Zhou J, Blakeley J, Zakaria R, Das K, Sluming V, Bhojak M, Walker C, Jenkinson MD, (Tiger) Yuan S, Tao R, Yang G, Chen Z, Mu D, Zhao S, Fu Z, Li W, Yu J. RADIOLOGY. Neuro Oncol 2013; 15:iii191-iii205. [PMCID: PMC3823904 DOI: 10.1093/neuonc/not189] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/14/2023] Open
|