Robust Non-rigid Registration Through Agent-Based Action Learning

By Julian Krebs, Tommaso Mansi, H. Delingette, Li Zhang, Florin C. Ghesu, Shun Miao, Andreas K. Maier, Nicholas Ayache, Rui Liao, Ali Kamen. 2017

227 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Reinforcement Learning in Healthcare: A Survey (2019, methodology): “r aortic valve landmarks localization and left atrial appendage seed localization in 3D CT images. Several researchers also applied DQN methods in 3D medical image registration problems [262], [263], [264], active breast lesion detection from dynamic contrast-enhanced MRI [265], and robust vessel ce”
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].”
Deep learning in medical image registration: a review (2019, methodology): “For image processing, the Q function is often modeled as CNN, which could encode input images as states and learn the Q function via supervised training [51, 78, 92, 108].”
Weakly-supervised convolutional neural networks for multimodal image registration (2018, methodology): “Several methods have been proposed to procure large numbers of pseudo-ground-truth transformations for training, such as those from simulations (Krebs et al., 2017; Miao et al., 2016; Sokooti et al., 2017), existing registration methods (Rohé et al., 2017) or manual rigid alignment (Liao et al.,…”
Deformable Image Registration Using Cue-aware Deep Regression Network (2018, methodology): “To align the prostates in MR images, the deformation ﬁeld is estimated by a deep reinforcement learning framework [52].”
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].”
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): “[55] used a reinforcement learning-based approach to perform the deformable registration of 2D and 3D prostate MR volumes.”
Recursive Cascaded Networks for Unsupervised Medical Image Registration (2019, methodology): “Some initial works rely on the dense ground-truth flows obtained by either traditional algorithms [14, 56] or simulating intrasubject deformations [36, 53], but their performance is restricted due to the limited quality of training data.”
A Gentle Introduction to Deep Learning in Medical Image Processing (2018, background): “This approach can also be applied to nonrigid registration using a statistical deformation model [79].”
A review of multimodal image matching: Methods and applications (2021, background): “and can handle both rigid [91,92,94] and non-rigid [93] image reg-”