Automatic multi-modal MR tissue classification for the assessment of response to bevacizumab in patients with glioblastoma

Gilad Liberman, Yoram Louzoun, Orna Aizenstein, Deborah T. Blumenthal, Felix Bokstein, Mika Palmon, Benjamin W. Corn, Dafna Ben Bashat*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

26 Scopus citations

Abstract

Background: Current methods for evaluation of treatment response in glioblastoma are inaccurate, limited and time-consuming. This study aimed to develop a multi-modal MRI automatic classification method to improve accuracy and efficiency of treatment response assessment in patients with recurrent glioblastoma (GB). Materials and methods: A modification of the k-Nearest-Neighbors (kNN) classification method was developed and applied to 59 longitudinal MR data sets of 13 patients with recurrent GB undergoing bevacizumab (anti-angiogenic) therapy. Changes in the enhancing tumor volume were assessed using the proposed method and compared with Macdonald's criteria and with manual volumetric measurements. The edema-like area was further subclassified into peri- and non-peri-tumoral edema, using both the kNN method and an unsupervised method, to monitor longitudinal changes. Results: Automatic classification using the modified kNN method was applicable in all scans, even when the tumors were infiltrative with unclear borders. The enhancing tumor volume obtained using the automatic method was highly correlated with manual measurements (N = 33, r = 0.96, p < 0.0001), while standard radiographic assessment based on Macdonald's criteria matched manual delineation and automatic results in only 68% of cases. A graded pattern of tumor infiltration within the edema-like area was revealed by both automatic methods, showing high agreement. All classification results were confirmed by a senior neuro-radiologist and validated using MR spectroscopy. Conclusion: This study emphasizes the important role of automatic tools based on a multi-modal view of the tissue in monitoring therapy response in patients with high grade gliomas specifically under anti-angiogenic therapy.

Original languageEnglish
Pages (from-to)e87-e94
JournalEuropean Journal of Radiology
Volume82
Issue number2
DOIs
StatePublished - Feb 2013
Externally publishedYes

Keywords

  • Anti-angiogenic treatment
  • Automatic classification
  • Glioblastoma
  • MRI

Fingerprint

Dive into the research topics of 'Automatic multi-modal MR tissue classification for the assessment of response to bevacizumab in patients with glioblastoma'. Together they form a unique fingerprint.

Cite this