Registration of multiple stained histological sections

Borovec, Jiří; Kybic, Jan; Bušta, Michal; Ortiz‐de‐Solórzano, Carlos; Muñoz-Barrutia, Arrate

doi:10.1109/isbi.2013.6556654

Cited by 16 publications

(10 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Registration methods developed for other modalities might therefore not work optimally and need to be modified for microscopy images. Changes in appearance can be handled by color normalization [39] or deconvolution [40], focusing on the parts or stains common to both images [33], segmentation [41], [42] or probabilistic segmentation [43], or using multimodal similarity features such as structural probability maps [29]. While most algorithms are intensity-based, some use keypoint features [44] or edge features [45], and some combine the two approaches [22].…”

Section: Histology Image Registrationmentioning

confidence: 99%

ANHIR: Automatic Non-Rigid Histological Image Registration Challenge

Borovec

Kybic

Arganda‐Carreras

et al. 2020

IEEE Trans. Med. Imaging

Self Cite

113

114

View full text Add to dashboard Cite

Automatic Non-rigid Histological Image Registration (ANHIR) challenge was organized to compare the performance of image registration algorithms on several kinds of microscopy histology images in a fair and independent manner. We have assembled 8 datasets, containing 355 images with 18 different stains, resulting in 481 image pairs to be registered. Registration accuracy was evaluated using manually placed landmarks. In total, 256 teams registered for the challenge, 10 submitted the results, and 6 participated in the workshop. Here, we present the results of 7 wellperforming methods from the challenge together with 6 well-known existing methods. The best methods used coarse but robust initial alignment, followed by non-rigid registration, used multiresolution, and were carefully tuned for the data at hand. They outperformed off-the-shelf methods, mostly by being more robust. The best methods could successfully register over 98% of all landmarks and their mean landmark registration accuracy (TRE) was 0.44% of the image diagonal. The challenge remains open to submissions and all images are available for download.

show abstract

Section: Histology Image Registrationmentioning

confidence: 99%

ANHIR: Automatic Non-Rigid Histological Image Registration Challenge

Borovec

Kybic

Arganda‐Carreras

et al. 2020

IEEE Trans. Med. Imaging

Self Cite

113

114

View full text Add to dashboard Cite

show abstract

“…The publicly available 1 CIMA dataset [3], [4], [10] consists of histological sections from 9 anatomical regions (3 lung lesions, 4 lung lobes and 2 mammary glands). Five slices were extracted from each region and a different stain was applied to each slice, leading to a total of 9 inter-modality registration problems with 5 modalities each.…”

Section: ) Intermodal Registration In Histology (Cima Dataset)mentioning

confidence: 99%

“…Dimensionality Deformation Available ground truth Target set Annotation uncertainty CoBrA Lab [42] 3D Synthetic All pixels Brain structure Fixed CIMA [3], [4], [10] 2D Real Sparse All pixels User-specified ellipses Nissl / OCM [25] 2D Real Dense All pixels Fixed COPDgene [6] 3D Real Dense All pixels Fusion of multiple annotations TABLE I: Properties of the four considered datasets. Each dataset allows the evaluation of some properties of our approach.…”

Section: Datasetmentioning

confidence: 99%

Uncertainty-Aware Annotation Protocol to Evaluate Deformable Registration Algorithms

Peter

Alexander

Magnain

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Landmark correspondences are a widely used type of gold standard in image registration. However, the manual placement of corresponding points is subject to high inter-user variability in the chosen annotated locations and in the interpretation of visual ambiguities. In this paper, we introduce a principled strategy for the construction of a gold standard in deformable registration. Our framework: (i) iteratively suggests the most informative location to annotate next, taking into account its redundancy with previous annotations; (ii) extends traditional pointwise annotations by accounting for the spatial uncertainty of each annotation, which can either be directly specified by the user, or aggregated from pointwise annotations from multiple experts; and (iii) naturally provides a new strategy for the evaluation of deformable registration algorithms. Our approach is validated on four different registration tasks. The experimental results show the efficacy of suggesting annotations according to their informativeness, and an improved capacity to assess the quality of the outputs of registration algorithms. In addition, our approach yields, from sparse annotations only, a dense visualization of the errors made by a registration method. The source code of our approach supporting both 2D and 3D data is publicly available at https://github.com/LoicPeter/ evaluation-deformable-registration.

show abstract

“…There are also feature-based registration methods, which extract descriptive features using mostly Scale-Invariant Feature Transform (SIFT) or Speeded-Up Robust Features (SURF) and estimate an optimal transformation using RANdom SAmple and Consensus (RANSAC) (feature-based registration). Feature- and intensity-based methods mix both previous approaches by using the feature method for the estimation of a rough initial alignment and then optimize the alignment using intensity metrics for similarity (feature-based+Elastix [ 13 ]). Landmark-based algorithms try to minimize the distance between two sets of landmarks.…”

Section: State-of-the-artmentioning

confidence: 99%

Nonlinear Image Registration and Pixel Classification Pipeline for the Study of Tumor Heterogeneity Maps

Nicolás-Sáenz

Guerrero-Aspizúa

Pascau

et al. 2020

Entropy

View full text Add to dashboard Cite

We present a novel method to assess the variations in protein expression and spatial heterogeneity of tumor biopsies with application in computational pathology. This was done using different antigen stains for each tissue section and proceeding with a complex image registration followed by a final step of color segmentation to detect the exact location of the proteins of interest. For proper assessment, the registration needs to be highly accurate for the careful study of the antigen patterns. However, accurate registration of histopathological images comes with three main problems: the high amount of artifacts due to the complex biopsy preparation, the size of the images, and the complexity of the local morphology. Our method manages to achieve an accurate registration of the tissue cuts and segmentation of the positive antigen areas.

show abstract

Registration of multiple stained histological sections

Cited by 16 publications

References 7 publications

ANHIR: Automatic Non-Rigid Histological Image Registration Challenge

ANHIR: Automatic Non-Rigid Histological Image Registration Challenge

Uncertainty-Aware Annotation Protocol to Evaluate Deformable Registration Algorithms

Nonlinear Image Registration and Pixel Classification Pipeline for the Study of Tumor Heterogeneity Maps

Contact Info

Product

Resources

About