Whole slide image registration via multi-stained feature matching

Hoque, Md Ziaul; Keskinarkaus, Anja; Nyberg, Pia; Mattila, Taneli T.; Seppänen, Tapio

doi:10.1016/j.compbiomed.2022.105301

Cited by 15 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we adopt Dice Similarity Coefficient (DSC), 53 Hausdorff Distance (HD), 54 SSIM, and NCC for WSI block registration accuracy evaluation. 55 For DSC and HD evaluation, 8 region of interest (ROI) pairs are manually annotated from the testing and validation WSI blocks. The complete evaluation process is presented in Supplemental Figure S7 and the quantitative results are shown in Table 4 .…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning based registration of serial whole-slide histopathology images in different stains

Roy¹,

Wang²,

Teodoro³

et al. 2023

Journal of Pathology Informatics

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

“… 19 Moreover, a modified SIFT method is applied to image registration with color interpolation. 20 WSIReg is another method for WSI registration based on elastix. 21 However, all these methods require feature matching that highly depends on feature engineering and parameter tuning.…”

Section: Introductionmentioning

confidence: 99%

Deep learning based registration of serial whole-slide histopathology images in different stains

Roy¹,

Wang²,

Teodoro³

et al. 2023

Journal of Pathology Informatics

View full text Add to dashboard Cite

“…After individual image patch registrations, they are spatially assembled to generate the registered WSI blocks. In this study, we adopt Dice Similarity Coefficient (DSC) [38], Hausdorff Distance (HD) [39], SSIM, and NCC for WSI block registration accuracy evaluation [40]. For DSC and HD evaluation, eight Region of Interest (ROI) pairs are manually annotated from the testing and validation WSI blocks.…”

Section: Evaluation Of Wsi Block Registrationmentioning

confidence: 99%

“…In a study on multi-stained histology image registration, a method is developed by the feature-based affine registration, rotation alignment followed by nonrigid alignment with Demons algorithm [4]. Moreover, a modified SIFT method is applied to image registration with color interpolation [5]. WSIReg is another method for WSI registration based on elastix [6].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Registration of Serial Whole-slide Histopathology Images in Different Stains

Roy

Wang

Teodoro

et al. 2022

Preprint

View full text Add to dashboard Cite

Whole-slide image (WSI) analysis has been largely performed in a 2D tissue space to support routine pathology diagnosis and imaging based biomedical research. For a more definitive representation and characterization of the tissue spatial space, it is critical to extend such tissue based investigations to a 3D space by spatially aligning 2D serial sections, which are often stained differently, such as Hematoxylin and Eosin (H\&E) and Immunohistochemistry (IHC) stains. However, registration of whole slide images is challenged by the overwhelmingly scale of images, the complexity of local histology structure changes across slides, and significant variations of tissue appearance between staining methods. We propose a novel translation based registration network CycGANRegNet using deep learning for serial WSI images in different stains, which requires no prior deformation field information for deep model training. We first generate synthetic IHC slides from H\&E slides through a robust image synthesis algorithm. The synthetic IHC images and the real IHC images are then registered through a Fully Convolutional Network with multi-scale based deformable vector fields and a joint loss optimization for enhancing image alignment. We perform the registration at original image resolution with a patch-wide approach, thus tissue details at the highest resolution are retained in the results. CycGANRegNet outperforms both the state-of-the-art conventional and deep learning-based registration methods based on the evaluation using a serial WSI image dataset in H\&E stain and IHC stain with two biomarkers from 76 breast cancer patients. The experimental and comparison results demonstrate that CycGANRegNet can produce promising registration results with serial WSIs in different stains, suggesting its potential for integrative 3D tissue-based biomedical investigations.

show abstract

“…Although this method has high precision and perfect registration performance, it is relatively time-consuming. Hoque et al 20 proposed an automatic histological image registration, and a joint distance was used to eliminate position transformation error and add match keypoints. And this method has been well applied in the medical field.…”

Section: Introductionmentioning

confidence: 99%

Hybrid double branch image registration algorithm

et al. 2022

View full text Add to dashboard Cite

High-quality image registration is the basis of multimodal fusion in the field of industrial welds. Due to the influence of contrast, scale, and illumination, the registration accuracy and robustness of existing algorithms are not high enough for the industrial weld field, and registration performance still needs further improvement. In this case, we propose a hybrid double branch image registration (HDBR) algorithm for multisource images, which has a parallel composite structure. The experimental result demonstrates that compared with the radiation invariant feature transformation and histogram of absolute phase consistency gradients algorithms, HDBR algorithm has higher matching accuracy and lower registration loss, and the registration performance is improved by 1.12% and 15.55%. The composite structure registration algorithm we proposed is mainly applied to the multiview weld image field, and finally high-quality multiview weld data set is obtained.

show abstract

Whole slide image registration via multi-stained feature matching

Cited by 15 publications

References 37 publications

Deep learning based registration of serial whole-slide histopathology images in different stains

Deep learning based registration of serial whole-slide histopathology images in different stains

Deep Learning Based Registration of Serial Whole-slide Histopathology Images in Different Stains

Hybrid double branch image registration algorithm

Contact Info

Product

Resources

About