MICCAI Young Scientist Publication Impact Award
The Medical Image Computing and Computer-Assisted Intervention (MICCAI) Society’s Young Scientist Publication Impact Award is an annual award given by the Society and sponsored by Kitware. This $1000 award recognizes a MICCAI conference publication from the past five years that was written by a young scientist and that has had a significant impact on the field.
Multiple factors are considered in judging the significance of a MICCAI publication. The award committee considers qualitative measures such as a personal statement from the author as well as quantitative measures such as the number times the paper, and follow-on papers, have been cited. This award is intended to recognize, reward, and encourage those scientists who are early in their careers and who are shaping the MICCAI field.
The award committee consisted of Dr. Sandy Wells from BWH, Dr. Marc Niethammer from UNC, Dr. Demian Wassermann from INRIA, and Dr. Stephen Aylward from Kitware.
As announced during the Awards Ceremony at the 2016 MICCAI Conference in Athens Greece, the 2016 Young Scientist Publication Impact award goes to
Dr. Stefan Bauer
for his paper from MICCAI 2011
“Fully Automatic Segmentation of Brain Tumor Images Using Support Vector Machine Classification in Combination with Hierarchical Conditional Random Field Regularization” by Stefan Bauer, Lutz Nolte, Mauricio Reyes, MICCAI 2011
This paper has been cited over 100 times, the method for brain tumor segmentation presented in this paper has been adapted into a clinical workflow, and working on this paper inspired its authors to establish the “Multimodal Brain Tumor Segmentation (BRaTS) Challenge” that has been hosted at every annual MICCAI conference since 2012.
Congratulations Dr. Bauer!
“Fully Automatic Segmentation of Brain Tumor Images Using Support Vector Machine Classification in Combination with Hierarchical Conditional Random Field Regularization” by Stefan Bauer, Lutz Nolte, Mauricio Reyes, MICCAI 2011
Abstract
Delineating brain tumor boundaries from magnetic resonance images is an essential task for the analysis of brain cancer. We propose a fully automatic method for brain tissue segmentation, which combines Support Vector Machine classification using multispectral intensities and textures with subsequent hierarchical regularization based on Conditional Random Fields. The CRP regularization introduces spatial constraints to the powerful SVM classification, which assumes voxels to be independent from their neighbors. The approach first separates healthy and tumor tissue before both regions are subclassified into cerebrospinal fluid, white matter, gray matter and necrotic, active, edema region respectively in a novel hierarchical way. The hierarchical approach adds robustness and speed by allowing to apply different levels of regularization at different stages. The method is fast and tailored to standard clinical acquisition protocols. It was assessed on 10 multispectral patient datasets with results outperforming previous methods in terms of segmentation detail and computation times