Nonrigid Image Registration Using Multi-scale 3D Convolutional Neural Networks

By Hessam Sokooti, Bob D. de Vos, Floris F. Berendsen, Boudewijn P. F. Lelieveldt, Ivana Isgum, Marius Staring. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2017

424 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/bbee923434518e92ee9c03dcd487e7f0b6042b78

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

An Unsupervised Learning Model for Deformable Medical Image Registration (2018, methodology): “Most of these rely on ground truth warp fields or segmentations [26, 35, 39, 45], a significant drawback compared to our method, which does not require either.”
Deep learning in medical image registration: a survey (2019, methodology): “[99] (discussed previously) and Yoo et al.”
Image Matching from Handcrafted to Deep Features: A Survey (2020, background): “Sokooti et al. (2017) first designed deep regression networks to directly learn a displacement vector field from a pair of input images.”
A deep learning framework for unsupervised affine and deformable image registration (2018, background): “, 2016) and deformable image registration (Eppenhof et al., 2018; Sokooti et al., 2017), or require manual annotations (Hu et al.”
Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI (2018, methodology): “In another study [108], chest CT follow-up examinations were registered by training a CNN to predict three-dimensional displacement vector fields between the fixed and moving image pairs.”
Data Augmentation Using Learned Transformations for One-Shot Medical Image Segmentation (2019, methodology): “This mature field spans optimization-based methods [4, 7, 67, 70], and recent learning-based methods [8, 9, 20, 42, 62, 72, 80].”
Deformable Image Registration Using Cue-aware Deep Regression Network (2018, methodology): “For lung CT image registration, the displacement vector is predicted by a CNN model in [11].”
Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration (2018, background): “which can introduce a bias and necessitate significant preprocessing [23,26,28].”
TransMorph: Transformer for unsupervised medical image registration (2021, neutral): “In supervised DNN methods, the ground-truth deformation fields are either produced synthetically or generated by traditional registration methods (Yang et al., 2017b; Sokooti et al., 2017; Cao et al., 2018).”
Medical Image Computing and Computer Assisted Intervention – MICCAI 2018 (2018, neutral): “in hidden layers [25, 26, 27, 26, 25] [29, 210, 211, 210, 29] [23, 26, 26, 26, 26, 26, 26]”
CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration (2020, methodology): “Given source and target images, deep neural networks are trained to generate deformation ﬁelds corresponding to the input image pair, so that it enables signiﬁcant fast registration [9]–[14].”
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces (2019, background): “Most earlier approaches demonstrated the feasibility of deep learning based registration, and required ground truth registration fields [13, 42, 59, 64, 68].”
Recursive Cascaded Networks for Unsupervised Medical Image Registration (2019, methodology): “Super-vised methods entail much effort on the labeled data that can hardly meet the realistic demands, resulting in the limited performance [14, 56, 36, 53].”
Unsupervised End-to-end Learning for Deformable Medical Image Registration (2017, methodology): “[39] train a 3D CNN to register chest CT data using artificially generated displacement vector field.”
Recent advances and clinical applications of deep learning in medical image analysis (2021, methodology): “…ROI segmentation (Alom et al., 2018; Yu et al., 2019; Fan et al., 2020), medical object detection (Rijthoven et al., 2018; Mei et al., 2021; Nair et al., 2020; Zheng et al., 2015), and cross-modality image registration (Simonovsky et al., 2016; Sokooti et al., 2017; Balakrishnan et al., 2018).”