Multi-atlas label fusion (MALF) is a powerful new technology that can automatically detect and label anatomical structures in biomedical images. It is arguably the most successful general-purpose automatic image segmentation technique ever developed. Automatic segmentation is in high demand in clinical and research applications of medical imaging, since segmentation forms a crucial step towards extracting quantitative information from imaging data, and since manual and semi-automatic approaches are ill suited for today's increasingly large and complex imaging datasets. Despite a number of papers that demonstrated outstanding performance of MALF methods across a range of biomedical imaging applications, the broader biomedical imaging research community has been slow to adopt this technique. This can be explained by multiple factors, including the technique's high computational demands, lack of a turnkey software implementation, as well as scarcity of validation in clinical imaging datasets and in the presence of extensive pathology. The present application seeks to remove these barriers and to enable a broad range of clinicians and biomedical researchers to take advantage of MALF technology. It builds on our strong track record of innovation in the MALF field, including a novel redundancy-correcting MALF technique that led in segmentation grand challenges in the past two years.
Aim 1 seeks to improve the computational performance of MALF by replacing dense deformable image registration, by far the most time consuming component of MALF, with faster and less constrained sparse registration strategies. We hypothesize that this will not only reduce the computational cost of MALF, but will also make it more robust to anatomical variability, in particular enabling its use for tumor and lesion segmentation.
Aim 2 proposes algorithmic extensions to MALF that support automatic segmentation of dynamic and multi-modality imaging datasets, which have been largely overlooked in the MALF literature.
Aim 3 will develop a turnkey open-source implementation of MALF methodology. Taking advantage of cloud computing technology, this software will allow users with minimal image processing expertise to take full advantage of MALF segmentation on their desktop.
Aim 3 will also provide a set of publicly available atlases and the means for users to build new custom atlas sets from their own data.
Aim 4 will perform extensive evaluation of the new methods and software in challenging real-world clinical imaging data, including brain and cardiac imaging. As part of this evaluation, we will quantify how well our MALF approach and competing techniques generalize to novel imaging datasets with heterogeneity in acquisition parameters and clinical phenotypes.

Public Health Relevance

This research will make it possible for a wide community of researchers who collect and analyze medical imaging data to take advantage of a new class of computer algorithms that very accurately label and measure anatomical structures and pathological formations in medical images. By offering more accurate image-derived measurements, the project promises to improve the accuracy of diagnosis, reduce the costs of biomedical re- search studies and pharmaceutical trials, and accelerate scientific discovery.

Agency
National Institute of Health (NIH)
Institute
National Institute of Biomedical Imaging and Bioengineering (NIBIB)
Type
Research Project (R01)
Project #
5R01EB017255-04
Application #
9350173
Study Section
Biodata Management and Analysis Study Section (BDMA)
Program Officer
Shabestari, Behrouz
Project Start
2014-08-01
Project End
2019-07-31
Budget Start
2017-08-01
Budget End
2018-07-31
Support Year
4
Fiscal Year
2017
Total Cost
Indirect Cost
Name
University of Pennsylvania
Department
Radiation-Diagnostic/Oncology
Type
Schools of Medicine
DUNS #
042250712
City
Philadelphia
State
PA
Country
United States
Zip Code
19104
Dworkin, J D; Sati, P; Solomon, A et al. (2018) Automated Integration of Multimodal MRI for the Probabilistic Detection of the Central Vein Sign in White Matter Lesions. AJNR Am J Neuroradiol 39:1806-1813
Valcarcel, Alessandra M; Linn, Kristin A; Vandekar, Simon N et al. (2018) MIMoSA: An Automated Method for Intermodal Segmentation Analysis of Multiple Sclerosis Brain Lesions. J Neuroimaging 28:389-398
Fleishman, Greg M; Valcarcel, Alessandra; Pham, Dzung L et al. (2018) Joint Intensity Fusion Image Synthesis Applied to Multiple Sclerosis Lesion Segmentation. Brainlesion (2017) 10670:43-54
Papinutto, Nico; Bakshi, Rohit; Bischof, Antje et al. (2018) Gradient nonlinearity effects on upper cervical spinal cord area measurement from 3D T1 -weighted brain MRI acquisitions. Magn Reson Med 79:1595-1601
Yushkevich, Paul A; Pashchinskiy, Artem; Oguz, Ipek et al. (2018) User-Guided Segmentation of Multi-modality Medical Imaging Datasets with ITK-SNAP. Neuroinformatics :
Xie, Long; Das, Sandhitsu R; Wisse, Laura E M et al. (2018) Early Tau Burden Correlates with Higher Rate of Atrophy in Transentorhinal Cortex. J Alzheimers Dis 62:85-92
Oguz, Ipek; Carass, Aaron; Pham, Dzung L et al. (2018) Dice Overlap Measures for Objects of Unknown Number: Application to Lesion Segmentation. Brainlesion (2017) 10670:3-14
Shah, Preya; Bassett, Danielle S; Wisse, Laura E M et al. (2018) Mapping the structural and functional network architecture of the medial temporal lobe using 7T MRI. Hum Brain Mapp 39:851-865
Adler, Daniel H; Wisse, Laura E M; Ittyerah, Ranjit et al. (2018) Characterizing the human hippocampus in aging and Alzheimer's disease using a computational atlas derived from ex vivo MRI and histology. Proc Natl Acad Sci U S A 115:4252-4257
Hadar, Peter N; Kini, Lohith G; Coto, Carlos et al. (2018) Clinical validation of automated hippocampal segmentation in temporal lobe epilepsy. Neuroimage Clin 20:1139-1147

Showing the most recent 10 out of 34 publications