National Alliance for Medical Image Computing (NA-MIC) has matured into the national biomedical computing infrastructure for medical image analysis that we envisioned at the start of our first funding cycle six years ago. Through this alliance, we have demonstrated that coordinated innovation in algorithms, software engineering, and outreach processes can enable innovation in biomedical research to address a range of clinical needs. As in the first cycle, Brigham &Women's Hospital (BWH), acting as the prime contractor, has put together a stellar group of experts in both computer science and biomedical sciences consisting of 13 leading institutions across the country and 18 PIs. The Computer Science Core, addressing algorithms and software engineering, work to implement solutions for Core 2 (Driving Biological Projects or DBPs). Core 3 provides technology service. Core 4 provides training and Core 5 provides dissemination of the NA-MIC deliverables. Core 6 (or Admin Core) will coordinate between various Cores, institutions and the science and finance and project management aspects. As per the RFA, Core IA and IB together constitute 50% of our proposed budget and Core 2 constitutes 25%, while Cores 3-6 constitute 25%. All four DBPs address personalized medicine: adapting radiotherapy to accommodate patient changes;guiding cardiac catheters for targeted ablation;assessing consequences of brain trauma;and predicting future neurodegeneration and treatment response from genetic, clinical, and imaging biomarkers. Building on powerful accepted technologies, our deliverable, the NA-MIC Kit, consists of software, documentation, methodology, license policy, training materials, and data. This free open-source software (FOSS) platform features novel image analysis algorithms, smooth interoperability between its components, ease of integration with third party software, and multi-pronged outreach mechanisms to facilitate end use, thus supporting basic science.
The overarching topic of this competitive renewal is the use of medical image computing for enabling personalized medicine. Computer science and biomedical experts collaborate as part of this project to put immediately usable tools with free open-source software (FOSS) license so that others may extend the goal of using medical imaging for personalized medicine.
|Liu, Sidong; Cai, Weidong; Pujol, Sonia et al. (2016) Cross-View Neuroimage Pattern Analysis in Alzheimer's Disease Staging. Front Aging Neurosci 8:23|
|Kapur, Tina; Pieper, Steve; Fedorov, Andriy et al. (2016) Increasing the impact of medical image computing using community-based open-access hackathons: The NA-MIC and 3D Slicer experience. Med Image Anal 33:176-80|
|Luo, Xinchao; Zhu, Lixing; Zhu, Hongtu (2016) Single-index varying coefficient model for functional responses. Biometrics 72:1275-1284|
|Roth, Robert M; Garlinghouse, Matthew A; Flashman, Laura A et al. (2016) Apathy Is Associated With Ventral Striatum Volume in Schizophrenia Spectrum Disorder. J Neuropsychiatry Clin Neurosci 28:191-4|
|Herrick, Rick; Horton, William; Olsen, Timothy et al. (2016) XNAT Central: Open sourcing imaging research data. Neuroimage 124:1093-6|
|Sadeghi, Neda; Gilmore, John H; Gerig, Guido (2016) Twin-singleton developmental study of brain white matter anatomy. Hum Brain Mapp :|
|Wang, Bo; Prastawa, Marcel; Irimia, Andrei et al. (2016) Modeling 4D Pathological Changes by Leveraging Normative Models. Comput Vis Image Underst 151:3-13|
|Li, Bolun; Shi, Jie; Gutman, Boris A et al. (2016) Influence of APOE Genotype on Hippocampal Atrophy over Time - An N=1925 Surface-Based ADNI Study. PLoS One 11:e0152901|
|Ruellas, Antonio Carlos de Oliveira; Yatabe, Marilia Sayako; Souki, Bernardo Quiroga et al. (2016) 3D Mandibular Superimposition: Comparison of Regions of Reference for Voxel-Based Registration. PLoS One 11:e0157625|
|Oguz, Ipek; Cates, Josh; Datar, Manasi et al. (2016) Entropy-based particle correspondence for shape populations. Int J Comput Assist Radiol Surg 11:1221-32|
Showing the most recent 10 out of 625 publications