SBIR-STTR Award

The overall goal of this application is to develop an automated and quantitative analysis tool for brain MR images. The technology is based on the MriStudio program developed by Drs. Mori and Miller, which is characterized by accurate multi-modal diffeomorphic mapping and deformable atlases with extensive anatomical definitions of gray and white matter structures. The program has been extensively tested for accuracy in normal and various patient groups. This Phase I grant will support the integration of existing programs into an automated pipeline and generate data for FDA approval. Currently, daily radiological diagnosis of MRI is almost exclusively based on qualitative examination. However, the availability of quantitative analysis results, such as volumes of various brain structures, would provide a variety of benefits for clinical diagnosis and subsequent patient care. If quantitative reporting of anatomical status were available, it could be readily compared with results from normals to estimate the degree of abnormalities. Compared to the current free-text format, quantitative reporting could be correlated with clinical functions more easily. Quantitativ data could be stored as a part of clinical database (PACS), which is fully searchable, and, thus, past cases with similar anatomical status could be readily retrieved and the functional outcomes and final diagnosis in past cases could be used to enrich current diagnosis. If serial scans were available, longitudinal changes could also be appreciated readily. Our specific aims are; Aim 1: Build a pipeline for full automation and test the parcellation accuracy the newly designed tools will be based on the MriStudio platform (www.mristudio.org). This software is designed for research use, with full access to parameters and results at each analysis step. We need to convert it to a fully automated pipeline in a platform-independent manner. This new pipeline then must be rigorously tested for accuracy Dr. Mori's lab has 30 training image datasets with full manual segmentation for 12 basal ganglia and 16 core white matter structures. We will use these datasets to test the accuracy of the automated segmentation. Aim 2: Apply the pipeline to normal data and establish normal ranges of values for each age we will use the pediatric, young adult, and elderly normal databases in Dr. Mori's lab to establish normal values and the degree of anatomical variability at each age. We will quantify volumes, T2 intensity, and DTI- derived indices for each parcellated structure. The age-dependency of the quantified values and confidence levels will be characterized. This data will provide information about the statistical power to detect abnormalities. The database contains variability in imaging parameters, the impact of which on the measured values will be characterized. This information, as well as the existing clinical data for various brain diseases, will be used to evaluate the efficacy of the proposed tool in the Phase II study and in the future FDA application.

Public Health Relevance:
We will develop software for automated analysis of brain MR images. This software provides quantitative assessment of brain anatomical status of various brain disease patients.

Public Health Relevance Statement:
We will develop software for automated analysis of brain MR images. This software provides quantitative assessment of brain anatomical status of various brain disease patients.

NIH Spending Category:
Bioengineering; Diagnostic Radiology; Neurosciences; Pediatric

Project Terms:
4 year old; Age; Atlases; Atrophic; Automation; Basal Ganglia; base; Brain; Brain Diseases; Childhood; Clinical; clinical application; Clinical Data; clinical Diagnosis; Communities; Computer software; Data; Data Set; Databases; Dementia; Dependency (Psychology); design; Diagnosis; Elderly; FDA approved; flexibility; functional outcomes; Future; Goals; Gold; Grant; gray matter; Image; indexing; interest; Location; Magnetic Resonance Imaging; Manuals; Maps; Measures; Medical Imaging; Modality; Morus (plant); Neuroanatomy; neuroimaging; Neurology; Noise; Normal Range; Patient Care; Patients; Phase; phase 2 study; platform-independent; programs; Radiology Specialty; Reporting; Research; Research Design; Scanning; software development; Structure; Technology; Testing; Text; Time; tool; Training; Universities; Weight; white matter; young adult

In this project, we will develop a commercial resource for the automated analysis of brain anatomy, based on MRI. This product is based on the whole-brain parcellation algorithm with the following unique features. First, it is based on a cutting-edge multi-atlas approach, in which we will incorporate rich atlas resources from Dr. Mori's lab at the Johns Hopkins University (JHU). Second, our multi-atlas approach is based on advanced diffeomorphic image transformation and multi-atlas probability fusion, recently developed by Dr. Miller at JHU. These CPU-intensive algorithms, combined with a large atlas inventory, require highly parallelized computational resources. We, therefore, will develop a fully portable and scalable cloud-based architecture, such that many users can have access at minimum costs. Third, we will develop a flexible architecture to define brain structures with multiple anatomical criteria, providing a very unique multi-granularity analysis, which provides an anatomy-centric and intuitive interface for clinical use. Fourth, we extend the analysis to diffusion tensor imaging (DTI) by incorporating a unique approach to multi-contrast image transformation and probability fusion. Last but not least, these algorithms can convert a set of multiple MR images to a quantitative and standardized Anatomical Matrix, which allows us to perform image data structurization, searching, and individualized analysis of anatomical phenotypes. Aim 1: To establish a cloud-based servicing architecture: We will develop a scalable and portable architecture for cloud-based computation. Parallel processing is required to achieve fast computation for the multi-atlas calculations. The algorithms accept DICOM data from four major vendors and apply a parcellation tool that identifies 254 brain structures. Aim 2: To establish a web-based interface for non-corporate users: To make our advanced image analysis tools widely available for research communities, we will create a web-based interface and provide the service at a minimum cost ($20/data). Aim 3: To implement a data visualization interface with ontology-based multi-granularity analysis: Our image analysis pipeline is a departure from conventional voxel-based automated analysis. Our structure-based analysis reduces the anatomical dimension to much lower scales. However, there are multiple ways to perform the structure-based information reduction. The ontology-based analysis provides a novel way to perform hierarchical anatomical interpretation of the structure-based analysis. Aim 4: To increase the number of atlases and cases in the database for interpretation support: Through the collaboration with JHU, we have access to a large inventory of research and clinical data, including controls and various patient groups. To create reference data, we will process these data and establish a background database, against which users can compare and interpret their data.

Public Health Relevance Statement:


Public Health Relevance:
We will develop software for automated analysis of brain MR images. This software provides quantitative assessment of brain anatomical status of various brain disease patients.

Project Terms:
Adopted; Algorithms; Anatomy; Architecture; Atlases; Automation; base; Beds; Brain; Brain Diseases; Clinical; Clinical Data; clinical practice; cloud based; Collaborations; Communities; computer cluster; Computer software; computerized data processing; computing resources; cost; Data; Databases; Development; Diffusion Magnetic Resonance Imaging; Dimensions; Equipment and supply inventories; Fees; flexibility; Image; Image Analysis; Imagery; improved; Location; Magnetic Resonance Imaging; Manuals; Modeling; Morus (plant); novel; Online Systems; Ontology; Operating System; PACS (Radiology); parallel processing; Pathology; Patients; Performance; Phase; phase 1 study; phase 2 study; Phenotype; Population; Probability; programs; Protocols documentation; public health relevance; Reproducibility; Research; Resolution; Resources; Running; Science; Services; software development; Source; Structure; System; Technology; Testing; Time; tool; Universities; Vendor; web based interface; web interface; Weight