Registration with probabilistic correspondences — Accurate and robust registration for pathological and inhomogeneous medical data

Krüger, Julia; Schultz, Sandra; Handels, Heinz; Ehrhardt, Jan

doi:10.1016/j.cviu.2019.102839

Cited by 5 publications

(13 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are currently working on finding missing correspondences automatically during the registration. This can be done by building probabilistic correspondence maps [ 32 ] or using geometrical constraints [ 33 ].…”

Section: Discussionmentioning

confidence: 99%

Esmraldi: efficient methods for the fusion of mass spectrometry and magnetic resonance images

et al. 2021

View full text Add to dashboard Cite

Background Mass spectrometry imaging (MSI) is a family of acquisition techniques producing images of the distribution of molecules in a sample, without any prior tagging of the molecules. This makes it a very interesting technique for exploratory research. However, the images are difficult to analyze because the enclosed data has high dimensionality, and their content does not necessarily reflect the shape of the object of interest. Conversely, magnetic resonance imaging (MRI) scans reflect the anatomy of the tissue. MRI also provides complementary information to MSI, such as the content and distribution of water. Results We propose a new workflow to merge the information from 2D MALDI–MSI and MRI images. Our workflow can be applied to large MSI datasets in a limited amount of time. Moreover, the workflow is fully automated and based on deterministic methods which ensures the reproducibility of the results. Our methods were evaluated and compared with state-of-the-art methods. Results show that the images are combined precisely and in a time-efficient manner. Conclusion Our workflow reveals molecules which co-localize with water in biological images. It can be applied on any MSI and MRI datasets which satisfy a few conditions: same regions of the shape enclosed in the images and similar intensity distributions.

show abstract

Section: Discussionmentioning

confidence: 99%

Esmraldi: efficient methods for the fusion of mass spectrometry and magnetic resonance images

et al. 2021

View full text Add to dashboard Cite

show abstract

“…ICP algorithms find closest points iteratively and for the k th iteration of an ICP variant two steps given as follows are solved: On the other hand, three corresponding points (m j(i,1) , m j(i,2) and m j(i,3) ) are necessary to find the tangent plane of a surface in 3D space. These correspondences can be determined using the previous transformation (A k−1 , t k−1 ) via many methods available in the literature such as Delaunay tessellation of [43], k-d trees of [44], probabilistic correspondence method of [5]. In this study, the k-d trees approach is applied to assign corresponding points of p i in the model set.…”

Section: Computation Of Affine Transformationmentioning

confidence: 99%

“…Today, point set/cloud registration is a noteworthy problem since it contributes to various fields such as computer vision, pattern recognition, image processing and classification (see in [1][2][3][4]), medical imaging and diagnosis (see in [5]), 3D modeling and construction (see in [6][7][8]), machine learning (see in [9]) and other engineering fields. The point cloud registration problem can be defined as finding the spatial transformation between two point sets by aligning them in a space.…”

Section: Introductionmentioning

confidence: 99%

Robust affine registration method using line/surface normals and correntropy criterion

Yïlmaz

Temeltaş

2022

Complex Intell. Syst.

View full text Add to dashboard Cite

The problem of matching point clouds is an efficient way of registration, which is significant for many research fields including computer vision, machine learning, and robotics. There may be linear or non-linear transformation between point clouds, but determining the affine relation is more challenging among linear cases. Various methods have been presented to overcome this problem in the literature and one of them is the affine variant of the iterative closest point (ICP) algorithm. However, traditional affine ICP variants are highly sensitive to effects such as noises, deformations, and outliers; the least-square metric is substituted with the correntropy criterion to increase the robustness of ICPs to such effects. Correntropy-based robust affine ICPs available in the literature use point-to-point metric to estimate transformation between point clouds. Conversely, in this study, a line/surface normal that examines point-to-curve or point-to-plane distances is employed together with the correntropy criterion for affine point cloud registration problems. First, the maximum correntropy criterion measure is built for line/surface normal conditions. Then, the closed-form solution that maximizes the similarity between point sets is achieved for 2D registration and extended for 3D registration. Finally, the application procedure of the developed robust affine ICP method is given and its registration performance is examined through extensive experiments on 2D and 3D point sets. The results achieved highlight that our method can align point clouds more robustly and precisely than the state-of-the-art methods in the literature, while the registration time of the process remains at reasonable levels.

show abstract

“…Works detecting non-correspondences during the optimization process, e.g. [3][4][5][6][7][8], overcome this limitation. Chen et al detect non-corresponding regions based on outlier detection in the distance measure combined with regularization [3].…”

Section: Introductionmentioning

confidence: 99%

“…Krüger et al estimate correspondence probabilities between sparse image representations to weight the image distance during registration. The correspondence probabilities are further used to segment pathologies in medical images [5,6]. Metamorphoses models such as [9][10][11][12] model both spatial deformations and appearance changes to match moving and fixed image.…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based simultaneous registration and unsupervised non-correspondence segmentation of medical images with pathologies

et al. 2022

Self Cite

View full text Add to dashboard Cite

Purpose The registration of medical images often suffers from missing correspondences due to inter-patient variations, pathologies and their progression leading to implausible deformations that cause misregistrations and might eliminate valuable information. Detecting non-corresponding regions simultaneously with the registration process helps generating better deformations and has been investigated thoroughly with classical iterative frameworks but rarely with deep learning-based methods. Methods We present the joint non-correspondence segmentation and image registration network (NCR-Net), a convolutional neural network (CNN) trained on a Mumford–Shah-like functional, transferring the classical approach to the field of deep learning. NCR-Net consists of one encoding and two decoding parts allowing the network to simultaneously generate diffeomorphic deformations and segment non-correspondences. The loss function is composed of a masked image distance measure and regularization of deformation field and segmentation output. Additionally, anatomical labels are used for weak supervision of the registration task. No manual segmentations of non-correspondences are required. Results The proposed network is evaluated on the publicly available LPBA40 dataset with artificially added stroke lesions and a longitudinal optical coherence tomography (OCT) dataset of patients with age-related macular degeneration. The LPBA40 data are used to quantitatively assess the segmentation performance of the network, and it is shown qualitatively that NCR-Net can be used for the unsupervised segmentation of pathologies in OCT images. Furthermore, NCR-Net is compared to a registration-only network and state-of-the-art registration algorithms showing that NCR-Net achieves competitive performance and superior robustness to non-correspondences. Conclusion NCR-Net, a CNN for simultaneous image registration and unsupervised non-correspondence segmentation, is presented. Experimental results show the network’s ability to segment non-correspondence regions in an unsupervised manner and its robust registration performance even in the presence of large pathologies.

show abstract

Registration with probabilistic correspondences — Accurate and robust registration for pathological and inhomogeneous medical data

Cited by 5 publications

References 44 publications

Esmraldi: efficient methods for the fusion of mass spectrometry and magnetic resonance images

Esmraldi: efficient methods for the fusion of mass spectrometry and magnetic resonance images

Robust affine registration method using line/surface normals and correntropy criterion

Deep learning-based simultaneous registration and unsupervised non-correspondence segmentation of medical images with pathologies

Contact Info

Product

Resources

About