Diffeomorphic Registration With Intensity Transformation and Missing Data: Application to 3D Digital Pathology of Alzheimer's Disease
This paper examines the problem of diffeomorphic image registration in the presence of differing image intensity profiles and sparsely sampled, missing, or damaged tissue. Our motivation comes from the problem of aligning 3D brain MRI with 100-micron isotropic resolution to histology sections at 1 ×...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-02-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fnins.2020.00052/full |
| _version_ | 1818444069402050560 |
|---|---|
| author | Daniel Tward Daniel Tward Timothy Brown Yusuke Kageyama Jaymin Patel Zhipeng Hou Susumu Mori Marilyn Albert Juan Troncoso Michael Miller Michael Miller |
| author_facet | Daniel Tward Daniel Tward Timothy Brown Yusuke Kageyama Jaymin Patel Zhipeng Hou Susumu Mori Marilyn Albert Juan Troncoso Michael Miller Michael Miller |
| author_sort | Daniel Tward |
| collection | DOAJ |
| description | This paper examines the problem of diffeomorphic image registration in the presence of differing image intensity profiles and sparsely sampled, missing, or damaged tissue. Our motivation comes from the problem of aligning 3D brain MRI with 100-micron isotropic resolution to histology sections at 1 × 1 × 1,000-micron resolution with multiple varying stains. We pose registration as a penalized Bayesian estimation, exploiting statistical models of image formation where the target images are modeled as sparse and noisy observations of the atlas. In this injective setting, there is no assumption of symmetry between atlas and target. Cross-modality image matching is achieved by jointly estimating polynomial transformations of the atlas intensity. Missing data is accommodated via a multiple atlas selection procedure where several atlas images may be of homogeneous intensity and correspond to “background” or “artifact.” The two concepts are combined within an Expectation-Maximization algorithm, where atlas selection posteriors and deformation parameters are updated iteratively and polynomial coefficients are computed in closed form. We validate our method with simulated images, examples from neuropathology, and a standard benchmarking dataset. Finally, we apply it to reconstructing digital pathology and MRI in standard atlas coordinates. By using a standard convolutional neural network to detect tau tangles in histology slices, this registration method enabled us to quantify the 3D density distribution of tauopathy throughout the medial temporal lobe of an Alzheimer's disease postmortem specimen. |
| first_indexed | 2024-12-14T19:10:04Z |
| format | Article |
| id | doaj.art-659bd3452e8b464fa4026fd37fdc6398 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-14T19:10:04Z |
| publishDate | 2020-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-659bd3452e8b464fa4026fd37fdc63982022-12-21T22:50:45ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2020-02-011410.3389/fnins.2020.00052478330Diffeomorphic Registration With Intensity Transformation and Missing Data: Application to 3D Digital Pathology of Alzheimer's DiseaseDaniel Tward0Daniel Tward1Timothy Brown2Yusuke Kageyama3Jaymin Patel4Zhipeng Hou5Susumu Mori6Marilyn Albert7Juan Troncoso8Michael Miller9Michael Miller10Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, United StatesCenter for Imaging Science, Johns Hopkins University, Baltimore, MD, United StatesCenter for Imaging Science, Johns Hopkins University, Baltimore, MD, United StatesDepartment of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, United StatesDepartment of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, United StatesDepartment of Radiology, Johns Hopkins University School of Medicine, Baltimore, MD, United StatesDepartment of Radiology, Johns Hopkins University School of Medicine, Baltimore, MD, United StatesDepartment of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, United StatesDepartment of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, United StatesDepartment of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, United StatesCenter for Imaging Science, Johns Hopkins University, Baltimore, MD, United StatesThis paper examines the problem of diffeomorphic image registration in the presence of differing image intensity profiles and sparsely sampled, missing, or damaged tissue. Our motivation comes from the problem of aligning 3D brain MRI with 100-micron isotropic resolution to histology sections at 1 × 1 × 1,000-micron resolution with multiple varying stains. We pose registration as a penalized Bayesian estimation, exploiting statistical models of image formation where the target images are modeled as sparse and noisy observations of the atlas. In this injective setting, there is no assumption of symmetry between atlas and target. Cross-modality image matching is achieved by jointly estimating polynomial transformations of the atlas intensity. Missing data is accommodated via a multiple atlas selection procedure where several atlas images may be of homogeneous intensity and correspond to “background” or “artifact.” The two concepts are combined within an Expectation-Maximization algorithm, where atlas selection posteriors and deformation parameters are updated iteratively and polynomial coefficients are computed in closed form. We validate our method with simulated images, examples from neuropathology, and a standard benchmarking dataset. Finally, we apply it to reconstructing digital pathology and MRI in standard atlas coordinates. By using a standard convolutional neural network to detect tau tangles in histology slices, this registration method enabled us to quantify the 3D density distribution of tauopathy throughout the medial temporal lobe of an Alzheimer's disease postmortem specimen.https://www.frontiersin.org/article/10.3389/fnins.2020.00052/fullneuroimagingdigital pathologyhistologybrain mappingimage registrationmissing data |
| spellingShingle | Daniel Tward Daniel Tward Timothy Brown Yusuke Kageyama Jaymin Patel Zhipeng Hou Susumu Mori Marilyn Albert Juan Troncoso Michael Miller Michael Miller Diffeomorphic Registration With Intensity Transformation and Missing Data: Application to 3D Digital Pathology of Alzheimer's Disease Frontiers in Neuroscience neuroimaging digital pathology histology brain mapping image registration missing data |
| title | Diffeomorphic Registration With Intensity Transformation and Missing Data: Application to 3D Digital Pathology of Alzheimer's Disease |
| title_full | Diffeomorphic Registration With Intensity Transformation and Missing Data: Application to 3D Digital Pathology of Alzheimer's Disease |
| title_fullStr | Diffeomorphic Registration With Intensity Transformation and Missing Data: Application to 3D Digital Pathology of Alzheimer's Disease |
| title_full_unstemmed | Diffeomorphic Registration With Intensity Transformation and Missing Data: Application to 3D Digital Pathology of Alzheimer's Disease |
| title_short | Diffeomorphic Registration With Intensity Transformation and Missing Data: Application to 3D Digital Pathology of Alzheimer's Disease |
| title_sort | diffeomorphic registration with intensity transformation and missing data application to 3d digital pathology of alzheimer s disease |
| topic | neuroimaging digital pathology histology brain mapping image registration missing data |
| url | https://www.frontiersin.org/article/10.3389/fnins.2020.00052/full |
| work_keys_str_mv | AT danieltward diffeomorphicregistrationwithintensitytransformationandmissingdataapplicationto3ddigitalpathologyofalzheimersdisease AT danieltward diffeomorphicregistrationwithintensitytransformationandmissingdataapplicationto3ddigitalpathologyofalzheimersdisease AT timothybrown diffeomorphicregistrationwithintensitytransformationandmissingdataapplicationto3ddigitalpathologyofalzheimersdisease AT yusukekageyama diffeomorphicregistrationwithintensitytransformationandmissingdataapplicationto3ddigitalpathologyofalzheimersdisease AT jayminpatel diffeomorphicregistrationwithintensitytransformationandmissingdataapplicationto3ddigitalpathologyofalzheimersdisease AT zhipenghou diffeomorphicregistrationwithintensitytransformationandmissingdataapplicationto3ddigitalpathologyofalzheimersdisease AT susumumori diffeomorphicregistrationwithintensitytransformationandmissingdataapplicationto3ddigitalpathologyofalzheimersdisease AT marilynalbert diffeomorphicregistrationwithintensitytransformationandmissingdataapplicationto3ddigitalpathologyofalzheimersdisease AT juantroncoso diffeomorphicregistrationwithintensitytransformationandmissingdataapplicationto3ddigitalpathologyofalzheimersdisease AT michaelmiller diffeomorphicregistrationwithintensitytransformationandmissingdataapplicationto3ddigitalpathologyofalzheimersdisease AT michaelmiller diffeomorphicregistrationwithintensitytransformationandmissingdataapplicationto3ddigitalpathologyofalzheimersdisease |