Mamta Gupta1, Abhinav Gupta1, Virendra Yadav2, Suhail P Parvaze3, Anup Singh2, Jitender Saini4, Rana Patir5, Sandeep Vaishya5, Sunita Ahlawat6, Rakesh Kumar Gupta7. 1. Department of Radiology, Fortis Memorial Research Institute, Sector 44, Gurgaon, Haryana, 122002, India. 2. Centre for Biomedical Engineering, IIT Delhi, New Delhi, India. 3. Philips Innovation Campus, Bangalore, Karnataka, India. 4. National Institute of Mental Health and Neurosciences, Bangalore, Karnataka, India. 5. Department of Neurosurgery, Fortis Memorial Research Institute, Sector 44, Gurgaon, Haryana, India. 6. SRL Diagnostics, Fortis Memorial Research Institute, Sector 44, Gurgaon, Haryana, India. 7. Department of Radiology, Fortis Memorial Research Institute, Sector 44, Gurgaon, Haryana, 122002, India. rakeshree1@gmail.com.
Abstract
PURPOSE: This retrospective study was performed on a 3T MRI to determine the unique conventional MR imaging and T1-weighted DCE-MRI features of oligodendroglioma and astrocytoma and investigate the utility of machine learning algorithms in their differentiation. METHODS: Histologically confirmed, 81 treatment-naïve patients were classified into two groups as per WHO 2016 classification: oligodendroglioma (n = 16; grade II, n = 25; grade III) and astrocytoma (n = 10; grade II, n = 30; grade III). The differences in tumor morphology characteristics were evaluated using Z-test. T1-weighted DCE-MRI data were analyzed using an in-house built MATLAB program. The mean 90th percentile of relative cerebral blood flow, relative cerebral blood volume corrected, volume transfer rate from plasma to extracellular extravascular space, and extravascular extracellular space volume values were evaluated using independent Student's t test. Support vector machine (SVM) classifier was constructed to differentiate two groups across grade II, grade III, and grade II+III based on statistically significant features. RESULTS: Z-test signified only calcification among conventional MR features to categorize oligodendroglioma and astrocytoma across grade III and grade II+III tumors. No statistical significance was found in the perfusion parameters between two groups and its subtypes. SVM trained on calcification also provided moderate accuracy to differentiate oligodendroglioma from astrocytoma. CONCLUSION: We conclude that conventional MR features except calcification and the quantitative T1-weighted DCE-MRI parameters fail to discriminate between oligodendroglioma and astrocytoma. The SVM could not further aid in their differentiation. The study also suggests that the presence of more than 50% T2-FLAIR mismatch may be considered as a more conclusive sign for differentiation of IDH mutant astrocytoma.
PURPOSE: This retrospective study was performed on a 3T MRI to determine the unique conventional MR imaging and T1-weighted DCE-MRI features of oligodendroglioma and astrocytoma and investigate the utility of machine learning algorithms in their differentiation. METHODS: Histologically confirmed, 81 treatment-naïve patients were classified into two groups as per WHO 2016 classification: oligodendroglioma (n = 16; grade II, n = 25; grade III) and astrocytoma (n = 10; grade II, n = 30; grade III). The differences in tumor morphology characteristics were evaluated using Z-test. T1-weighted DCE-MRI data were analyzed using an in-house built MATLAB program. The mean 90th percentile of relative cerebral blood flow, relative cerebral blood volume corrected, volume transfer rate from plasma to extracellular extravascular space, and extravascular extracellular space volume values were evaluated using independent Student's t test. Support vector machine (SVM) classifier was constructed to differentiate two groups across grade II, grade III, and grade II+III based on statistically significant features. RESULTS: Z-test signified only calcification among conventional MR features to categorize oligodendroglioma and astrocytoma across grade III and grade II+III tumors. No statistical significance was found in the perfusion parameters between two groups and its subtypes. SVM trained on calcification also provided moderate accuracy to differentiate oligodendroglioma from astrocytoma. CONCLUSION: We conclude that conventional MR features except calcification and the quantitative T1-weighted DCE-MRI parameters fail to discriminate between oligodendroglioma and astrocytoma. The SVM could not further aid in their differentiation. The study also suggests that the presence of more than 50% T2-FLAIR mismatch may be considered as a more conclusive sign for differentiation of IDH mutant astrocytoma.
Authors: Hikaru Sasaki; Magdalena C Zlatescu; Rebecca A Betensky; Loki B Johnk; Andrea N Cutone; J Gregory Cairncross; David N Louis Journal: J Neuropathol Exp Neurol Date: 2002-01 Impact factor: 3.685
Authors: Sohil H Patel; Laila M Poisson; Daniel J Brat; Yueren Zhou; Lee Cooper; Matija Snuderl; Cheddhi Thomas; Ana M Franceschi; Brent Griffith; Adam E Flanders; John G Golfinos; Andrew S Chi; Rajan Jain Journal: Clin Cancer Res Date: 2017-07-27 Impact factor: 12.531
Authors: Hyun Jung Yoon; Kook Jin Ahn; Song Lee; Jin Hee Jang; Hyun Seok Choi; So Lyung Jung; Bum Soo Kim; Shin Soo Jeun; Yong Kil Hong Journal: Neuroradiology Date: 2017-05-26 Impact factor: 2.804
Authors: Soonmee Cha; Tarik Tihan; Forrest Crawford; Nancy J Fischbein; Susan Chang; Andrew Bollen; Sarah J Nelson; Michael Prados; Mitchel S Berger; William P Dillon Journal: AJNR Am J Neuroradiol Date: 2005-02 Impact factor: 3.825