The objective of the Computer Science Core is to develop a national computing infrastructure for image analysis to be used in biomedical research and leading-edge clinical research and practice. To meet this broad objective, the Computer Science Core is organized as two scientific teams: an Algorithms team and an Engineering team. The Algorithms team develops new techniques for image analysis to address the most pressing challenges posed by clinical researchers. The Engineering team develops software applications, delivers computational platforms, and establishes software engineering practices for algorithm researchers and for clinical hypothesis formation and testing. The combined efforts of Algorithms and Engineering produce the NA-MIC Kit, an open source platform for medical image computing that includes an end-user application (the 3D Slicer), image analysis algorithms and workflows distributed as plug-ins and reusable libraries, a PACS-like image and data management platform, computational platforms for data streaming and distributed computing, and software engineering and software quality methods and tools. The two teams bring complementary skills to the technical challenges in NA-MIC. The Algorithms group is led by five senior investigators from four academic institutions. Their combined background provides renowned expertise in variational, statistical, and geometrical approaches to image analysis. The Engineering group is led by five senior investigators from two small businesses, one industrial research facility, and two academic institutions. Their combined background spans visualization, medical image analysis, information systems, scientific computing, and software engineering. Thus, the Computer Science Core of NA-MIC is uniquely positioned with the breadth and depth to deliver a national infrastructure for medical image computing. To drive the development ofthe national infrastructure for medical image computing, this renewal has selected four DBPs that focus on the analysis of images for the understanding of disease, healing processes and adaptations, and curative and palliative therapies. These clinical applications-atrial fibrillation, Huntington's disease, head and neck cancer, traumatic brain injury-emphasize the study of an individual's pathology or injury and how that pathology or injury changes over time. Image analysis in this context requires new methods and tools for image segmentation, registration, statistical analysis, and visualization. Segmentation must be objective and robust while providing efficient interactive editing. Registration must be computationally efficient, but explicltiy accommodate longitudinal data and the nonrigid or nonsmooth nature of injuries and pathology. Characterization of change needs to be succinct and yet provide statistically quantifiable results for multidimensional analysis of structure and function. The software tools to support research in these clinical applications must be flexible enough to accommodate new methods yet enforce software engineering practices to meet the performance and stability demands of clinical settings. The sections that follow describe the Algorithms and Engineering efforts in more detail, including the motivation and aims, the background and context, and the methods, with plans for collaboration between these groups and the project as a whole. Preliminary results are presented both in the methods section below as well as in the Progress Report (Section 2.4) of the proposal, as proscribed by the RFA.
| Ghayoor, Ali; Vaidya, Jatin G; Johnson, Hans J (2018) Robust automated constellation-based landmark detection in human brain imaging. Neuroimage 170:471-481 |
| Wachinger, Christian; Toews, Matthew; Langs, Georg et al. (2018) Keypoint Transfer for Fast Whole-Body Segmentation. IEEE Trans Med Imaging : |
| Lyu, Ilwoo; Perdomo, Jonathan; Yapuncich, Gabriel S et al. (2018) Group-wise Shape Correspondence of Variable and Complex Objects. Proc SPIE Int Soc Opt Eng 10574: |
| Hong, Sungmin; Fishbaugh, James; Gerig, Guido (2018) 4D CONTINUOUS MEDIAL REPRESENTATION BY GEODESIC SHAPE REGRESSION. Proc IEEE Int Symp Biomed Imaging 2018:1014-1017 |
| Swanson, Meghan R; Wolff, Jason J; Shen, Mark D et al. (2018) Development of White Matter Circuitry in Infants With Fragile X Syndrome. JAMA Psychiatry 75:505-513 |
| Swanson, Meghan R; Shen, Mark D; Wolff, Jason J et al. (2018) Naturalistic Language Recordings Reveal ""Hypervocal"" Infants at High Familial Risk for Autism. Child Dev 89:e60-e73 |
| Swanson, Meghan R; Shen, Mark D; Wolff, Jason J et al. (2017) Subcortical Brain and Behavior Phenotypes Differentiate Infants With Autism Versus Language Delay. Biol Psychiatry Cogn Neurosci Neuroimaging 2:664-672 |
| Veni, Gopalkrishna; Elhabian, Shireen Y; Whitaker, Ross T (2017) ShapeCut: Bayesian surface estimation using shape-driven graph. Med Image Anal 40:11-29 |
| Irimia, Andrei; Goh, Sheng-Yang Matthew; Wade, Adam C et al. (2017) Traumatic Brain Injury Severity, Neuropathophysiology, and Clinical Outcome: Insights from Multimodal Neuroimaging. Front Neurol 8:530 |
| Rutherford, Helena J V; Maupin, Angela N; Landi, Nicole et al. (2017) Parental reflective functioning and the neural correlates of processing infant affective cues. Soc Neurosci 12:519-529 |
Showing the most recent 10 out of 668 publications
