TY - JOUR
T1 - Automatic multi-modal MR tissue classification for the assessment of response to bevacizumab in patients with glioblastoma
AU - Liberman, Gilad
AU - Louzoun, Yoram
AU - Aizenstein, Orna
AU - Blumenthal, Deborah T.
AU - Bokstein, Felix
AU - Palmon, Mika
AU - Corn, Benjamin W.
AU - Ben Bashat, Dafna
PY - 2013/2
Y1 - 2013/2
N2 - 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.
AB - 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.
KW - Anti-angiogenic treatment
KW - Automatic classification
KW - Glioblastoma
KW - MRI
UR - http://www.scopus.com/inward/record.url?scp=84871920938&partnerID=8YFLogxK
U2 - 10.1016/j.ejrad.2012.09.001
DO - 10.1016/j.ejrad.2012.09.001
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
C2 - 23017192
AN - SCOPUS:84871920938
SN - 0720-048X
VL - 82
SP - e87-e94
JO - European Journal of Radiology
JF - European Journal of Radiology
IS - 2
ER -