43 Computer Vision News enhance tag contrast and alleviate into tag fading is also something that he intends to explore in the future. Could that constitute a sneak peek at the winning paper for next year? “Yeah, hopefully!” he laughs. “I’m just trying to do my best.” Zhangxing, originally from China, has been in the US for around five years. He studied for his master’s in computer vision at the University of Michigan before moving into medical imaging. “Before doing any research or publication, I like to have a deeper understanding of the problem at hand instead of just applying any other approach,” he says. “I like to explore. I do a lot of sports, like snowboarding and climbing. I consider myself an adventurous person.” He is still considering his next move after his PhD. While he has not made any firm decisions regarding a choice between academia and industry, he is leaning in one direction. “Right now, I prefer industry,” he reveals. “Probably going to a pharmaceutical or medical imaging device company to do real applications and solve real-life problems.” Different methods are evaluated on a tagged-MRI of a motionless gel phantom, where the ground truth motion is zero. Left panel shows the acquired horizontal (h-tag) and vertical (v-tag) tagging images for three timeframes. Right panel shows the color-coded maximum principal strain map and zoomed-in motion field of four methods. The first and second row show the registration results of ref-to-8th and ref-to-40th frame. Zhangxing Bian
RkJQdWJsaXNoZXIy NTc3NzU=