Unsupervised learning for large motion thoracic CT follow-up registration

Hering, Alessa; Heldmann, Stefan

doi:10.1117/12.2506962

Cited by 11 publications

(16 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unsupervised, weakly supervised, and strongly supervised neural networks have been used to estimate deformation vector fields directly from two images. Unsupervised methods learn the deformation directly from pairs of images without a ground truth deformation vector field by maximizing a similarity metric . Strongly supervised methods use a ground truth deformation vector field, usually by applying known transformations to a set of images during training .…”

Section: Introductionmentioning

confidence: 99%

“…Unsupervised methods learn the deformation directly from pairs of images without a ground truth deformation vector field by maximizing a similarity metric. [21][22][23][24][25][26][27] Strongly supervised methods use a ground truth deformation vector field, usually by applying known transformations to a set of images during training. [28][29][30][31][32][33][34] Weakly supervised methods are a variant of unsupervised methods, in which the similarity metric is replaced by learning an auxiliary task, such as maximizing the overlap of known segmentations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast contour propagation for MR‐guided prostate radiotherapy using convolutional neural networks

et al. 2020

View full text Add to dashboard Cite

Purpose To quickly and automatically propagate organ contours from pretreatment to fraction images in magnetic resonance (MR)‐guided prostate external‐beam radiotherapy. Methods Five prostate cancer patients underwent 20 fractions of image‐guided external‐beam radiotherapy on a 1.5 T MR‐Linac system. For each patient, a pretreatment T2‐weighted three‐dimensional (3D) MR imaging (MRI) scan was used to delineate the clinical target volume (CTV) contours. The same scan was repeated during each fraction, with the CTV contour being manually adapted if necessary. A convolutional neural network (CNN) was trained for combined image registration and contour propagation. The network estimated the propagated contour and a deformation field between the two input images. The training set consisted of a synthetically generated ground truth of randomly deformed images and prostate segmentations. We performed a leave‐one‐out cross‐validation on the five patients and propagated the prostate segmentations from the pretreatment to the fraction scans. Three variants of the CNN, aimed at investigating supervision based on optimizing segmentation overlap, optimizing the registration, and a combination of the two were compared to results of the open‐source deformable registration software package Elastix. Results The neural networks trained on segmentation overlap or the combined objective achieved significantly better Hausdorff distances between predicted and ground truth contours than Elastix, at the much faster registration speed of 0.5 s. The CNN variant trained to optimize both the prostate overlap and deformation field, and the variant trained to only maximize the prostate overlap, produced the best propagation results. Conclusions A CNN trained on maximizing prostate overlap and minimizing registration errors provides a fast and accurate method for deformable contour propagation for prostate MR‐guided radiotherapy.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fast contour propagation for MR‐guided prostate radiotherapy using convolutional neural networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Hereby, a coarse level alignment is obtained first that typically captures the large motion components and which is later improved on finer levels for the alignment of more local details. Most of the recently presented deep learning based approaches also make use of a multilevel strategy as they are based on the U-Net architecture [2,6,7,13]. Thereby, the first half of the "U" is used to generate features on different scales starting at the highest resolution and reducing the resolution through pooling operations.…”

Section: Introductionmentioning

confidence: 99%

mlVIRNET: Multilevel Variational Image Registration Network

Hering

Ginneken

Heldmann

2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

We present a novel multilevel approach for deep learning based image registration. Recently published deep learning based registration methods have shown promising results for a wide range of tasks. However, these algorithms are still limited to relatively small deformations. Our method addresses this shortcoming by introducing a multilevel framework, which computes deformation fields on different scales, similar to conventional methods. Thereby, a coarse-level alignment is obtained first, which is subsequently improved on finer levels. We demonstrate our method on the complex task of inhale-to-exhale lung registration. We show that the use of a deep learning multilevel approach leads to significantly better registration results.

show abstract

“…Image similarity metrics can have multiple strong local optima, that do not necessarily coincide with a correct registration [2]. Examples of unsupervised registration include [3], [4], [5], [6], [7], [8], [9].…”

Section: Introductionmentioning

confidence: 99%

Progressively Trained Convolutional Neural Networks for Deformable Image Registration

Eppenhof

Lafarge

Veta

et al. 2020

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

DOI to the publisher's website. • The final author version and the galley proof are versions of the publication after peer review. • The final published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal. If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User Agreement:

show abstract

Unsupervised learning for large motion thoracic CT follow-up registration

Cited by 11 publications

References 7 publications

Fast contour propagation for MR‐guided prostate radiotherapy using convolutional neural networks

Fast contour propagation for MR‐guided prostate radiotherapy using convolutional neural networks

mlVIRNET: Multilevel Variational Image Registration Network

Progressively Trained Convolutional Neural Networks for Deformable Image Registration

Contact Info

Product

Resources

About