Computer Vision News - May 2022

35 Pallavi Tiwari radiation they’ve received? The only definitive diagnosis comes from surgical resection. Some of these patients, who have already undergone chemoradiation treatment, must undergo another surgery only to realize it was a benign condition and could have been avoided. That affects their quality of life, overall outcomes, and survival. How do you solve it? We use AI and machine learning on routinely acquired MRI scans. We don’t look at any fancy imaging. That has allowed us to collaborate with institutions globally to obtain MRI scans. We’re close to 90% Can you tell us about your work? My lab is developing AI and machine learning-driven approaches for the diagnosis, prediction, and treatment evaluation of neurological disorders, particularly brain tumors. Recently we’ve been looking at post-treatment response assessment. Glioblastoma, one of the most aggressive and highly malignant forms of brain tumor, has a median survival rate of 15 months. Patients know there will be recurrence at some point after treatment. They’re asked to come back for follow-up MRI scans, and if a suspicious lesion is seen, the question is, is it tumor recurrence, or is it just a side effect of the aggressive Work from Tiwari’s group published in IEEE Transactions of Medical Imaging (Ismail et al, 2022). Top row shows a GBM patient with an overall survival of 30 days, while the bottom row shows a GBM patient with an overall survival of 691 days.  (b), (f) demonstrate the COLLAGE heatmaps generated for each of the two subjects, with higher values (red) being more prevalent in the patient with poor survival, compared to the patient with prolonged survival. (c), (g) illustrate the extracted deformation field magnitudes respectively for each of the two patients. For the patient with poor survival (d), higher magnitude values (represented in red) were observed in close proximity of the tumor, whereas lower values were observed (blue) for the patient with prolonged survival (h).