Atlas-ISTN: Joint Segmentation, Registration and Atlas Construction with Image-and-Spatial Transformer Networks

Sinclair, Matthew; Schuh, Andreas; Hahn, Karl; Petersen, Kathrine Birch; Bai, Ying; Batten, James; Schaap, Michiel; Glocker, Ben

doi:10.48550/arxiv.2012.10533

Cited by 3 publications

(11 citation statements)

References 61 publications

(134 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evan et al [18] proposed to learn a deformation map that warps a pre-specified atlas conditioned on subject-specific characteristics. Sinclair et al [43] proposed Atlas-ISTN, a deep-learning framework to jointly learn segmentation, registration and atlas construction. However, these approaches do not consider a pairwise image alignment loss to improve registration accuracy and their evaluation approaches require the annotation of the built atlas thus is not a measurement that can be easily compared among approaches.…”

Section: Background and Related Workmentioning

confidence: 99%

“…1 shows a comparison between our approach and other closely related learning-based approaches. 3 He et al [25] Dalca et al [12] Evan et al [18] Sinclair et al [43] Aladdin (Ours)…”

Section: Background and Related Workmentioning

confidence: 99%

“…We use a regularized stationary velocity field (SVF) parameterization [3,26,36,42,12,43] for our registration model. In particular, we instantiate Eq.…”

Section: Svf Based Implementationmentioning

confidence: 99%

“…Hence, if there are many images to be analyzed, efficient registration algorithms that can avoid costly numerical optimization are desirable. Such efficient approaches, based on deep learning, have recently been proposed for registration and atlas building [12,24,18,43,14]. However, these approaches use similarity measures between the fuzzy atlas and the anatomically more detailed images of the dataset.…”

Section: Introductionmentioning

confidence: 99%

“…Alternatively, one can build an un-biased atlas based on affine transformations [28]. To directly work with images which have not yet been affine aligned, Atlas-ISTN [43] simultaneously estimates a separate affine transformation before the nonparametric transformation and composes the two. Instead of separately considering affine and nonparametric transformations, we propose to predict a transformation which includes affine and nonparametric deformations.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Aladdin: Joint Atlas Building and Diffeomorphic Registration Learning with Pairwise Alignment

Ding¹,

Niethammer²

2022

Preprint

View full text Add to dashboard Cite

Atlas building and image registration are important tasks for medical image analysis. Once one or multiple atlases from an image population have been constructed, commonly (1) images are warped into an atlas space to study intra-subject or inter-subject variations or (2) a possibly probabilistic atlas is warped into image space to assign anatomical labels. Atlas estimation and nonparametric transformations are computationally expensive as they usually require numerical optimization. Additionally, previous approaches for atlas building often define similarity measures between a fuzzy atlas and each individual image, which may cause alignment difficulties because a fuzzy atlas does not exhibit clear anatomical structures in contrast to the individual images. This work explores using a convolutional neural network (CNN) to jointly predict the atlas and a stationary velocity field (SVF) parameterization for diffeomorphic image registration with respect to the atlas. Our approach does not require affine pre-registrations and utilizes pairwise image alignment losses to increase registration accuracy. We evaluate our model on 3D knee magnetic resonance images (MRI) from the OAI-ZIB dataset. Our results show that the proposed framework achieves better performance than other state-of-the-art image registration algorithms, allows for end-to-end training, and for fast inference at test time. 1

show abstract

Section: Background and Related Workmentioning

confidence: 99%

“…1 shows a comparison between our approach and other closely related learning-based approaches. 3 He et al [25] Dalca et al [12] Evan et al [18] Sinclair et al [43] Aladdin (Ours)…”

Section: Background and Related Workmentioning

confidence: 99%

“…We use a regularized stationary velocity field (SVF) parameterization [3,26,36,42,12,43] for our registration model. In particular, we instantiate Eq.…”

Section: Svf Based Implementationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Aladdin: Joint Atlas Building and Diffeomorphic Registration Learning with Pairwise Alignment

Ding¹,

Niethammer²

2022

Preprint

View full text Add to dashboard Cite

show abstract

Pancreas MRI Segmentation Into Head, Body, and Tail Enables Regional Quantitative Analysis of Heterogeneous Disease

Bagur

Aljabar²,

Ridgway³

et al. 2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background: Quantitative imaging studies of the pancreas have often targeted the three main anatomical segments, head, body, and tail, using manual region of interest strategies to assess geographic heterogeneity. Existing automated analyses have implemented whole-organ segmentation, providing overall quantification but failing to address spatial heterogeneity. Purpose: To develop and validate an automated method for pancreas segmentation into head, body, and tail subregions in abdominal MRI. Study Type: Retrospective. Subjects: One hundred and fifty nominally healthy subjects from UK Biobank (100 subjects for method development and 50 subjects for validation). A separate 390 UK Biobank triples of subjects including type 2 diabetes mellitus (T2DM) subjects and matched nondiabetics. Field strength/Sequence: A 1.5 T, three-dimensional two-point Dixon sequence (for segmentation and volume assessment) and a two-dimensional axial multiecho gradient-recalled echo sequence. Assessment: Pancreas segments were annotated by four raters on the validation cohort. Intrarater agreement and interrater agreement were reported using Dice overlap (Dice similarity coefficient [DSC]). A segmentation method based on template registration was developed and evaluated against annotations. Results on regional pancreatic fat assessment are also presented, by intersecting the three-dimensional parts segmentation with one available proton density fat fraction (PDFF) image. Statistical Test: Wilcoxon signed rank test and Mann-Whitney U-test for comparisons. DSC and volume differences for evaluation. A P value < 0.05 was considered statistically significant. Results: Good intrarater (DSC mean, head: 0.982, body: 0.940, tail: 0.961) agreement and interrater (DSC mean, head: 0.968, body: 0.905, tail: 0.943) agreement were observed. No differences (DSC, head: P = 0.4358, body: P = 0.0992, tail: P = 0.1080) were observed between the manual annotations and our method's segmentations (DSC mean, head: 0.965, body: 0.893, tail: 0.934). Pancreatic body PDFF was different between T2DM and nondiabetics matched by body mass index. Data Conclusion:The developed segmentation's performance was no different from manual annotations. Application on type 2 diabetes subjects showed potential for assessing pancreatic disease heterogeneity. Level of Evidence: 4 Technical Efficacy Stage: 3

show abstract

CAS-Net: Conditional Atlas Generation and Brain Segmentation for Fetal MRI

Li¹,

Ma²,

Sinclair³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Fetal Magnetic Resonance Imaging (MRI) is used in prenatal diagnosis and to assess early brain development. Accurate segmentation of the different brain tissues is a vital step in several brain analysis tasks, such as cortical surface reconstruction and tissue thickness measurements. Fetal MRI scans, however, are prone to motion artifacts that can affect the correctness of both manual and automatic segmentation techniques. In this paper, we propose a novel network structure that can simultaneously generate conditional atlases and predict brain tissue segmentation, called CAS-Net. The conditional atlases provide anatomical priors that can constrain the segmentation connectivity, despite the heterogeneity of intensity values caused by motion or partial volume effects. The proposed method is trained and evaluated on 253 subjects from the developing Human Connectome Project (dHCP). The results demonstrate that the proposed method can generate conditional age-specific atlas with sharp boundary and shape variance. It also segments multicategory brain tissues for fetal MRI with a high overall Dice similarity coefficient (DSC) of 85.2% for the selected 9 tissue labels.

show abstract

Atlas-ISTN: Joint Segmentation, Registration and Atlas Construction with Image-and-Spatial Transformer Networks

Cited by 3 publications

References 61 publications

Aladdin: Joint Atlas Building and Diffeomorphic Registration Learning with Pairwise Alignment

Aladdin: Joint Atlas Building and Diffeomorphic Registration Learning with Pairwise Alignment

Pancreas MRI Segmentation Into Head, Body, and Tail Enables Regional Quantitative Analysis of Heterogeneous Disease

CAS-Net: Conditional Atlas Generation and Brain Segmentation for Fetal MRI

Contact Info

Product

Resources

About