NLM G08-LM008937



Assisted Follow-up in NeuroImaging of Therapeutic Intervention


AFINITI (Assisted Follow-up in NeuroImaging of Therapeutic Intervention) is translational image informatics system designed to enhance efficacy and reduce error in the interpretation of neuroimaging follow-up studies for several common indications, by providing the interpreting and referring physicians with automated tools and augmented information needed to allow sensitive, reproducible, quantitative assessment of longitudinal changes in brains in response to therapeutic intervention. The primary goal is to introduce the tools and techniques resulting from biomedical informatics research into real-life settings in clinical care, education and basic biomedical research of neurological diseases. The secondary goal is to design and offer a new information service to support neuroimaging follow-up studies.


PI: Stephen TC Wong, Ph.D., P.E., The Methodist Hospital Research Institute.
Co-PI: Geoffrey Young, MD, Brigham and Women's Hospital
Investigator: Fei Cao, Ph.D., Zhong Xue, Ph.D., The Methodist Hospital Research Institute.
Research Assistant: Ying Zhu, The Methodist Hospital Research Institute.
Web Administrator: Vinothini Kamalesan, The Methodist Hospital Research Institute.
Research Fellow: Hui You, Brigham and Women's Hospital
IT Administrator: John, Chow, Brigham and Women's Hospital


The current AFINITI software provides the functions for automatic/semiautomatic brain tumor segmentation, tumor grow quantification, and DICOM result generation (as shown in fig 1.). All the inputs and outputs are DICOM series to make the software easy to use with clinical workstations. We are validating the automatic segmentation performance on high resolution T1 images by comparing automatic results with gold standard manual segmentation results of 57 cases of brain tumor patients. Meanwhile, we are refining the methods for T2 hyper intense region grow follow-up and ADC tumor biomarker identification.



1. J. Nie, Z. Xue, T. Liu, G. Young, K. Setayesh, L. Guo, S. Wong, Automated brain tumor segmentation using spatial accuracy-weighted hidden Markov Random Field, Computerized Medical Imaging and Graphics,Volume 33, Issue 6, 2009, Pages 431-441

2. Zhong Xue, Dinggang Shen, A New Statistically-Constrained Deformable Registration Framework for MR Brain Images, International Journal of Medical Engineering and Informatics, Vol. 1, No.3, 2009, pp. 357-367

Conferences and Book Chapters:

3. Zhong Xue, Dinggang Shen, Stephen TC Wong, Tissue Probability Map Constrained CLASSIC for Increased Accuracy and Robustness in Serial Image Segmentation, SPIE Medical Imaging, 2009.

4. Hai Li, Zhong Xue, Jiong Xing, Lei Guo, Stephen TC Wong, Analyzing the Diffusion Patterns for Follow-Up Study of Glioblastoma Multiforme Using Diffusion Tensor Imaging, The Fourth IEEE-NIH Life Science Systems and Applications Workshop, 2009.

Software Link: