Computer-extracted texture features to distinguish cerebral radionecrosis from recurrent brain tumors on multiparametric mri: A feasibility study

P. Tiwari, P. Prasanna, L. Wolansky, M. Pinho, M. Cohen, A. P. Nayate, A. Gupta, G. Singh, K. J. Hatanpaa, A. Sloan, L. Rogers, A. Madabhushi

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

BACKGROUND AND PURPOSE: Despite availability of advanced imaging, distinguishing radiation necrosis from recurrent brain tumors noninvasively is a big challenge in neuro-oncology. Our aim was to determine the feasibility of radiomic (computer-extracted texture) features in differentiating radiation necrosis from recurrent brain tumors on routine MR imaging (gadolinium T1WI, T2WI, FLAIR). MATERIALS AND METHODS: A retrospective study of brain tumor MR imaging performed 9 months (or later) post-radiochemotherapy was performed from 2 institutions. Fifty-eight patient studies were analyzed, consisting of a training (n = 43) cohort from one institution and an independent test (n = 15) cohort from another, with surgical histologic findings confirmed by an experienced neuropathologist at the respective institutions. Brain lesions on MR imaging were manually annotated by an expert neuroradiologist. A set of radiomic features was extracted for every lesion on each MR imaging sequence: gadolinium T1WI, T2WI, and FLAIR. Feature selection was used to identify the top 5 most discriminating features for every MR imaging sequence on the training cohort. These features were then evaluated on the test cohort by a support vector machine classifier. The classification performance was compared against diagnostic reads by 2 expert neuroradiologists who had access to the same MR imaging sequences (gadolinium T1WI, T2WI, and FLAIR) as the classifier. RESULTS: On the training cohort, the area under the receiver operating characteristic curve was highest for FLAIR with 0.79; 95% CI, 0.77- 0.81 for primary (n = 22); and 0.79, 95% CI, 0.75- 0.83 for metastatic subgroups (n =21). Of the 15 studies in the holdout cohort, the support vector machine classifier identified 12 of 15 studies correctly, while neuroradiologist 1 diagnosed 7 of 15 and neuroradiologist 2 diagnosed 8 of 15 studies correctly, respectively. CONCLUSIONS: Our preliminary results suggest that radiomic features may provide complementary diagnostic information on routine MR imaging sequences that may improve the distinction of radiation necrosis from recurrence for both primary and metastatic brain tumors.

Original languageEnglish (US)
Pages (from-to)2231-2236
Number of pages6
JournalAmerican Journal of Neuroradiology
Volume37
Issue number12
DOIs
StatePublished - Dec 1 2016

Fingerprint

Feasibility Studies
Brain Neoplasms
Gadolinium
Necrosis
Radiation
Chemoradiotherapy
ROC Curve
Retrospective Studies
Recurrence
Brain
Support Vector Machine

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Clinical Neurology

Cite this

Computer-extracted texture features to distinguish cerebral radionecrosis from recurrent brain tumors on multiparametric mri : A feasibility study. / Tiwari, P.; Prasanna, P.; Wolansky, L.; Pinho, M.; Cohen, M.; Nayate, A. P.; Gupta, A.; Singh, G.; Hatanpaa, K. J.; Sloan, A.; Rogers, L.; Madabhushi, A.

In: American Journal of Neuroradiology, Vol. 37, No. 12, 01.12.2016, p. 2231-2236.

Research output: Contribution to journalArticle

Tiwari, P, Prasanna, P, Wolansky, L, Pinho, M, Cohen, M, Nayate, AP, Gupta, A, Singh, G, Hatanpaa, KJ, Sloan, A, Rogers, L & Madabhushi, A 2016, 'Computer-extracted texture features to distinguish cerebral radionecrosis from recurrent brain tumors on multiparametric mri: A feasibility study', American Journal of Neuroradiology, vol. 37, no. 12, pp. 2231-2236. https://doi.org/10.3174/ajnr.A4931
Tiwari, P. ; Prasanna, P. ; Wolansky, L. ; Pinho, M. ; Cohen, M. ; Nayate, A. P. ; Gupta, A. ; Singh, G. ; Hatanpaa, K. J. ; Sloan, A. ; Rogers, L. ; Madabhushi, A. / Computer-extracted texture features to distinguish cerebral radionecrosis from recurrent brain tumors on multiparametric mri : A feasibility study. In: American Journal of Neuroradiology. 2016 ; Vol. 37, No. 12. pp. 2231-2236.
@article{c8f2eb0b1c104d9d9aebf2e9d26552e3,
title = "Computer-extracted texture features to distinguish cerebral radionecrosis from recurrent brain tumors on multiparametric mri: A feasibility study",
abstract = "BACKGROUND AND PURPOSE: Despite availability of advanced imaging, distinguishing radiation necrosis from recurrent brain tumors noninvasively is a big challenge in neuro-oncology. Our aim was to determine the feasibility of radiomic (computer-extracted texture) features in differentiating radiation necrosis from recurrent brain tumors on routine MR imaging (gadolinium T1WI, T2WI, FLAIR). MATERIALS AND METHODS: A retrospective study of brain tumor MR imaging performed 9 months (or later) post-radiochemotherapy was performed from 2 institutions. Fifty-eight patient studies were analyzed, consisting of a training (n = 43) cohort from one institution and an independent test (n = 15) cohort from another, with surgical histologic findings confirmed by an experienced neuropathologist at the respective institutions. Brain lesions on MR imaging were manually annotated by an expert neuroradiologist. A set of radiomic features was extracted for every lesion on each MR imaging sequence: gadolinium T1WI, T2WI, and FLAIR. Feature selection was used to identify the top 5 most discriminating features for every MR imaging sequence on the training cohort. These features were then evaluated on the test cohort by a support vector machine classifier. The classification performance was compared against diagnostic reads by 2 expert neuroradiologists who had access to the same MR imaging sequences (gadolinium T1WI, T2WI, and FLAIR) as the classifier. RESULTS: On the training cohort, the area under the receiver operating characteristic curve was highest for FLAIR with 0.79; 95{\%} CI, 0.77- 0.81 for primary (n = 22); and 0.79, 95{\%} CI, 0.75- 0.83 for metastatic subgroups (n =21). Of the 15 studies in the holdout cohort, the support vector machine classifier identified 12 of 15 studies correctly, while neuroradiologist 1 diagnosed 7 of 15 and neuroradiologist 2 diagnosed 8 of 15 studies correctly, respectively. CONCLUSIONS: Our preliminary results suggest that radiomic features may provide complementary diagnostic information on routine MR imaging sequences that may improve the distinction of radiation necrosis from recurrence for both primary and metastatic brain tumors.",
author = "P. Tiwari and P. Prasanna and L. Wolansky and M. Pinho and M. Cohen and Nayate, {A. P.} and A. Gupta and G. Singh and Hatanpaa, {K. J.} and A. Sloan and L. Rogers and A. Madabhushi",
year = "2016",
month = "12",
day = "1",
doi = "10.3174/ajnr.A4931",
language = "English (US)",
volume = "37",
pages = "2231--2236",
journal = "American Journal of Neuroradiology",
issn = "0195-6108",
publisher = "American Society of Neuroradiology",
number = "12",

}

TY - JOUR

T1 - Computer-extracted texture features to distinguish cerebral radionecrosis from recurrent brain tumors on multiparametric mri

T2 - A feasibility study

AU - Tiwari, P.

AU - Prasanna, P.

AU - Wolansky, L.

AU - Pinho, M.

AU - Cohen, M.

AU - Nayate, A. P.

AU - Gupta, A.

AU - Singh, G.

AU - Hatanpaa, K. J.

AU - Sloan, A.

AU - Rogers, L.

AU - Madabhushi, A.

PY - 2016/12/1

Y1 - 2016/12/1

N2 - BACKGROUND AND PURPOSE: Despite availability of advanced imaging, distinguishing radiation necrosis from recurrent brain tumors noninvasively is a big challenge in neuro-oncology. Our aim was to determine the feasibility of radiomic (computer-extracted texture) features in differentiating radiation necrosis from recurrent brain tumors on routine MR imaging (gadolinium T1WI, T2WI, FLAIR). MATERIALS AND METHODS: A retrospective study of brain tumor MR imaging performed 9 months (or later) post-radiochemotherapy was performed from 2 institutions. Fifty-eight patient studies were analyzed, consisting of a training (n = 43) cohort from one institution and an independent test (n = 15) cohort from another, with surgical histologic findings confirmed by an experienced neuropathologist at the respective institutions. Brain lesions on MR imaging were manually annotated by an expert neuroradiologist. A set of radiomic features was extracted for every lesion on each MR imaging sequence: gadolinium T1WI, T2WI, and FLAIR. Feature selection was used to identify the top 5 most discriminating features for every MR imaging sequence on the training cohort. These features were then evaluated on the test cohort by a support vector machine classifier. The classification performance was compared against diagnostic reads by 2 expert neuroradiologists who had access to the same MR imaging sequences (gadolinium T1WI, T2WI, and FLAIR) as the classifier. RESULTS: On the training cohort, the area under the receiver operating characteristic curve was highest for FLAIR with 0.79; 95% CI, 0.77- 0.81 for primary (n = 22); and 0.79, 95% CI, 0.75- 0.83 for metastatic subgroups (n =21). Of the 15 studies in the holdout cohort, the support vector machine classifier identified 12 of 15 studies correctly, while neuroradiologist 1 diagnosed 7 of 15 and neuroradiologist 2 diagnosed 8 of 15 studies correctly, respectively. CONCLUSIONS: Our preliminary results suggest that radiomic features may provide complementary diagnostic information on routine MR imaging sequences that may improve the distinction of radiation necrosis from recurrence for both primary and metastatic brain tumors.

AB - BACKGROUND AND PURPOSE: Despite availability of advanced imaging, distinguishing radiation necrosis from recurrent brain tumors noninvasively is a big challenge in neuro-oncology. Our aim was to determine the feasibility of radiomic (computer-extracted texture) features in differentiating radiation necrosis from recurrent brain tumors on routine MR imaging (gadolinium T1WI, T2WI, FLAIR). MATERIALS AND METHODS: A retrospective study of brain tumor MR imaging performed 9 months (or later) post-radiochemotherapy was performed from 2 institutions. Fifty-eight patient studies were analyzed, consisting of a training (n = 43) cohort from one institution and an independent test (n = 15) cohort from another, with surgical histologic findings confirmed by an experienced neuropathologist at the respective institutions. Brain lesions on MR imaging were manually annotated by an expert neuroradiologist. A set of radiomic features was extracted for every lesion on each MR imaging sequence: gadolinium T1WI, T2WI, and FLAIR. Feature selection was used to identify the top 5 most discriminating features for every MR imaging sequence on the training cohort. These features were then evaluated on the test cohort by a support vector machine classifier. The classification performance was compared against diagnostic reads by 2 expert neuroradiologists who had access to the same MR imaging sequences (gadolinium T1WI, T2WI, and FLAIR) as the classifier. RESULTS: On the training cohort, the area under the receiver operating characteristic curve was highest for FLAIR with 0.79; 95% CI, 0.77- 0.81 for primary (n = 22); and 0.79, 95% CI, 0.75- 0.83 for metastatic subgroups (n =21). Of the 15 studies in the holdout cohort, the support vector machine classifier identified 12 of 15 studies correctly, while neuroradiologist 1 diagnosed 7 of 15 and neuroradiologist 2 diagnosed 8 of 15 studies correctly, respectively. CONCLUSIONS: Our preliminary results suggest that radiomic features may provide complementary diagnostic information on routine MR imaging sequences that may improve the distinction of radiation necrosis from recurrence for both primary and metastatic brain tumors.

UR - http://www.scopus.com/inward/record.url?scp=85006515947&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006515947&partnerID=8YFLogxK

U2 - 10.3174/ajnr.A4931

DO - 10.3174/ajnr.A4931

M3 - Article

C2 - 27633806

AN - SCOPUS:85006515947

VL - 37

SP - 2231

EP - 2236

JO - American Journal of Neuroradiology

JF - American Journal of Neuroradiology

SN - 0195-6108

IS - 12

ER -