Mosaicing of Dynamic Mesentery Video with Gradient Blending

Aktar, Rumana; Huxley, Virginia H.; Guidoboni, Giovanna; Aliakbarpour, Hadi; Bunyak, Filiz; Palaniappan, Kannappan

doi:10.1109/icip40778.2020.9191045

Cited by 6 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The microscopy videos collected in situ can be mosaiced manually or semi-automatically (Aktar et al 2020) for extracting the microvascular network architecture (Bunyak & Palaniappan, 2009a, 2009b and red blood cell flow velocities in vessel segments (Nath et al 2006;Palaniappan et al 2009;Ersoy et al 2012). In the present study, the vessel segmentation traces and flows shown in Fig.…”

Section: Estimation Of Tissue Perfusion Areasmentioning

confidence: 99%

Fluid and protein exchange in microvascular networks: Importance of modelling heterogeneity in geometrical and biophysical properties

Guidoboni

Marazzi

Fraser

et al. 2021

The Journal of Physiology

View full text Add to dashboard Cite

support-information-section). Key pointsr Microvascular network architecture defines coupling of fluid and protein exchange. r Network arrangements markedly reduce capillary hydrostatic pressures and resting fluid movement at the same time as increasing the capacity for change r The presence of vascular remodelling or angiogenesis puts constraints of network behaviour r The sites of fluid and protein exchange can be segregated to different portions of the network r Although there is a net filtration of fluid from a network of exchange vessels, there are specific areas where fluid moves into the circulation (reabsorption) and, when protein is moving into tissue, the amount is insufficient under basal conditions to result in changes in oncotic pressure.

show abstract

Section: Estimation Of Tissue Perfusion Areasmentioning

confidence: 99%

Fluid and protein exchange in microvascular networks: Importance of modelling heterogeneity in geometrical and biophysical properties

Guidoboni

Marazzi

Fraser

et al. 2021

The Journal of Physiology

View full text Add to dashboard Cite

show abstract

“…FIGURE 5.10: Showing the resulting mosaic from Frog Mesentery Sequence3 dataset using the four different blending algorithms. The mosaic marked as A is generated using Rumana Aktar's DNCC algorithm [5] As can be seen from the image above, Center-Weighing method eliminates the rapid shift in the illumination by smoothing the intensity of the overlapped part, but still the illumination changes are visible from the mosaic and we can also see that the resultant mosaic is less sharp than the other three mosaic results.…”

Section: Results For Illumination-matchingmentioning

confidence: 99%

“…• Proposed Illumination Matched blending As the paper [5] clearly demonstrates that due to the deformable nature of the structure in the video sequences, the Gradientresponse Ratio (GRR) method helps selecting sharper images from a video sequence, which ultimately results in an overall sharper mosaic, I've incorporated the GRR condition with the blending techniques for generating the final mosaic result. As mentioned earlier, GRR is the ratio that is computed from the edge-response between the current frame and the current mosaic, if that ratio has a value of greater than 1 then it means that the structure in the current frame being processed is sharper than the mosaic, and vice-versa.…”

Section: Proposed Blending Methodsmentioning

confidence: 99%

Section: Previous Work On Mini-mosaic Generation Considered Reducingmentioning

confidence: 99%

“…Significant research efforts are ongoing to encounter these challenges [5], to establish a robust registration algorithm. Featurebased registration was replaced in [5] with a Correlation-based registration method. Multiple blending techniques are compared in the paper [23] demonstrating that feather blending, Laplacian pyramid blending affects the illumination of the merged images better than the alpha blending, but this might cause blurring due to deformable structure for biomedical video sequences.…”

Section: Previous Work On Mini-mosaic Generation Considered Reducingmentioning

confidence: 99%

See 2 more Smart Citations

Fast VMZ : code enhancements for video mosaicing and summarization

Ahmed¹

View full text Add to dashboard Cite

Video Mosaicing and Summarization (VMZ) is a novel image processing pipeline that summarizes the content of a long sequence of geospatial or biomedical videos using a few coverage maps or mini mosaics. The existing VMZ algorithm uses Normalized Cross-Correlation (NCC), Structure Tensor (ST), Affine-Invariant SIFT (ASIFT), Speeded up robust features for its feature matching and homography estimation pipeline, which are the most computationally expensive modules in the VMZ pipeline. Due to these long-running compute-intensive modules, the VMZ pipeline is not suitable for real-time mosaic formation in drones or UAVs. For instance, VMZ takes around 4 hours to generate mini-mosaics from an image sequence containing 9291 image frames. The blending algorithms used for mini-mosaic generation suffer from illumination variation due to the illumination difference in image frames. Such illumination inconsistency causes severe problems for biomedical scene understanding where curvilinear or tiny biological structures are present. VMZ pipeline is also dependent on 3rd party libraries not aligned with the flow of VMZ, which introduces redundant computation. One of the main reasons for the slow processing of the VMZ pipeline is not leveraging any parallel processing techniques and available graphics processing hardware. Therefore, the objective of this thesis is mainly three-fold: (i) speeding up the computeintensive and long-running modules in the VMZ pipeline, (ii) modifying the existing libraries and interfaces for better alignment with VMZ workflow, and (iii) resolving the illumination difference problem of the blending algorithms. Selected longrunning modules with the most impact on the overall run-time have been improved using CPU-based Multi-Threading, GPU-based Parallelization, and better integration with the existing VMZ pipeline. An illumination-matched blending algorithm has been proposed to improve the illumination problem. Besides, to evaluate the performance of different blending algorithms, a novel metric named Maximum Overall Illumination Difference (MOID) has been proposed. The improvement of VMZ modules has resulted in more than 100x speed-up in certain modules, with a 4.4x speed-up for the total VMZ run-time. The novel illumination matched blending resulted in a better MOID value for image sequences not having illumination variance in a single frame.

show abstract

Improving protein function prediction by learning and integrating representations of protein sequences and function labels

Boadu,

Cheng

2024

Preprint

View full text Add to dashboard Cite

Motivation: As fewer than 1% of proteins have protein function information determined experimentally, computationally predicting the function of proteins is critical for obtaining functional information for most proteins and has been a major challenge in protein bioinformatics. Despite the significant progress made in protein function prediction by the community in the last decade, the general accuracy of protein function prediction is still not high, particularly for rare function terms associated with few proteins in the protein function annotation database such as the UniProt. Results: We introduce TransFew, a new transformer model, to learn the representations of both protein sequences and function labels (Gene Ontology (GO) terms) to predict the function of proteins. TransFew leverages a large pre-trained protein language model (ESM2-t48) to learn function relevant representations of proteins from raw protein sequences and uses a biological natural language model (BioBert) and a graph convolutional neural network-based autoencoder to generate semantic representations of GO terms from their textual definition and hierarchical relationships, which are combined together to predict protein function via the cross-attention. Integrating the protein sequence and label representations not only enhances overall function prediction accuracy over the existing methods, but substantially improves the accuracy of predicting rare function terms with limited annotations by facilitating annotation transfer between GO terms. Availability: https://github.com/BioinfoMachineLearning/TransFew Supplementary information: Supplementary data are available.

show abstract

Mosaicing of Dynamic Mesentery Video with Gradient Blending

Cited by 6 publications

References 16 publications

Fluid and protein exchange in microvascular networks: Importance of modelling heterogeneity in geometrical and biophysical properties

Fluid and protein exchange in microvascular networks: Importance of modelling heterogeneity in geometrical and biophysical properties

Fast VMZ : code enhancements for video mosaicing and summarization

Improving protein function prediction by learning and integrating representations of protein sequences and function labels

Contact Info

Product

Resources

About