Evaluation Protocol of Skeletonization Applied to Grayscale Curvilinear Structures

Youssef, Rabaa; Ricordeau, Anne; Sevestre, Patrick; Benazza-Benyahya, Amel

doi:10.1109/dicta.2015.7371256

Cited by 5 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a comparison to the segmented image leverages the methods from the segmentation field used to create gold-standard segmentations, and provides a fixed point against which to assess a new skeletonised network in all cases. A number of other researchers have also sought to validate skeletons by comparison to binary images, (23; 5; 35), but these only consider one or two metrics in isolation, rather than formulating it as a collective. For example Table 4 shows comparison between the STAPLE segmentation and the skeletons for the medulla and FaDu Tumour datasets, across four different measures: Volume, number of connected components, Euler characteristic of the largest subnetwork (connected component), DICE score for bifircation points, and cl-sensitivity(33).…”

Section: A Metric For Skeleton Validationmentioning

confidence: 99%

“…Some metrics for comparison of the raw image data (or segmentation) and skeleton have been proposed, including bifurcation position and number, connectivity, homology etc. (24; 33; 23; 34; 35), however there is no clarity as to which of these metrics is most important or how differences in these metrics translate into differences in the networks functional properties.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reconstructing microvascular network skeletons from 3D images: what is the ground truth?

Walsh,

Berg,

West

et al. 2024

Preprint

View full text Add to dashboard Cite

Structural changes to microvascular networks are increasingly highlighted as markers of pathogenesis in a wide range of disease, e.g. Alzheimer’s disease, vascular dementia and tumour growth. This has motivated the development of dedicated 3D imaging techniques, alongside the creation of computational modelling frameworks capable of using 3D reconstructed networks to simulate functional behaviours such as blood flow or transport processes. Extraction of 3D networks from imaging data broadly consists of two image processing steps: segmentation followed by skeletonisation. Much research effort has been devoted to segmentation field, and there are standard and widely-applied methodologies for creating and assessing gold standards or ground truths produced by manual annotation or automated algorithms.The Skeletonisation field, however, lacks widely applied, simple to compute metrics for the validation or optimisation of the numerous algorithms that exist to extract skeletons from binary images. This is particularly problematic as 3D imaging datasets increase in size and visual inspection becomes an insufficient validation approach. In this work, we first demonstrate the extent of the problem by applying 4 widely-used skeletonisation algorithms to 3 different imaging datasets. In doing so we show significant variability between reconstructed skeletons of the same segmented imaging dataset. Moreover, we show that such a structural variability propagates to simulated metrics such as blood flow. To mitigate this variability we introduce a new, fast and easy to compute super-metric that compares the volume, connectivity, medialness, correct bifurcation point identification and homology of the reconstructed skeletons to the original segmented data. We then show that such a metric can be used to select the best performing skeletonisation algorithm for a given dataset, as well as to optimize its parameters. Finally, we demonstrate that the super-metric can also be used to quickly identify how a particular skeletonisation algorithm could be improved, becoming a powerful tool in understanding the complex implication of small structural changes in a network.

show abstract

Section: A Metric For Skeleton Validationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Reconstructing microvascular network skeletons from 3D images: what is the ground truth?

Walsh,

Berg,

West

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Standard metrics that are often used in semantic segmentation like precision, recall or the Dice coefficient are not well suited to be directly used with skeletons due to their sparseness: a shift by a single pixel can have a large impact on the result. Therefore, our main metrics for the identification of roots are skeleton completeness C p and correctness C r , which are discussed in more detail in [12] and defined as:…”

Section: Metricsmentioning

confidence: 99%

Identification and Measurement of Individual Roots in Minirhizotron Images of Dense Root Systems

Gillert

Peters

Lukas

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

Semantic segmentation networks are prone to oversegmentation in areas where objects are tightly clustered. In minirhizotron images with densely packed plant root systems this can lead to a failure to separate individual roots, thereby skewing the root length and width measurements.We propose to deal with this problem by adding additional output heads to the segmentation model, one of which is used with a ridge detection algorithm as an intermediate step and a second one that directly estimates root width. With this method we are able to improve detection and width measurements in densely packed roots systems without negative effects on sparse root systems.

show abstract

“…We then compare each predicted pixel to the ground truth labels to calculate true positive rates (TPR) versus false positive rates (FPR). Specifically, for the evaluation of microvasculature, we follow a similar evaluation method mentioned in [95,96]. Dilation with disk structuring element of radius 1 is used create a buffered truth and TPR vs FPR is calculated.…”

Section: Network Setupmentioning

confidence: 99%

Measurements of retinal microvasculature in mice and humans with deep learning

Deng¹

View full text Add to dashboard Cite

Retinal diseases such as diabetic retinopathies (DR) and radiation retinopathies (RR) show changes in the microvasculature as early symptoms. Therefore, automatically segmenting and analyzing retinal microvasculature may help diagnose and understand the underlying mechanisms of ocular diseases. However, due to the limitations of the image quality, as well as the difficulties of evaluation, very few studies address automated segmentations of microvascular networks. A commonly used imaging modality to record retinal vasculature is fluorescein angiography (FA). It is an invasive technique and uses fluorescein dyes to provide information of blood flow in the retina. Another relevant technology is optical coherence tomography angiography (OCTA). It is a newly developed non-invasive technique that captures regions with blood flow in the retina in 3D. Better ways to generate automated quantification for these modalities could potentially enhance clinical studies and help in the diagnosis and understanding of retinal diseases. In this work, automated approaches are developed to accurately quantify retinal microvasculature in mouse FA and human OCTA images. First, we develop an automated approach to simultaneously segment retinal structures including the optic nerve head (ONH), main vessels, and the microvascular network in mouse FA images. By combining traditional approaches and deep learning, we can automatically segment these structures with minimal human effort. Then, multiple methods are developed to automatically analyze the microvasculature in human OCTA projection images. The key novelties in these approaches are by using deep-learning based approaches, we can not only segment the microvasculature, but also directly find regions with different microvascular status. Furthermore, we investigated and analyzed the clinical significance of our region-based OCTA projection segmentations. In order to achieve this goal, we first analyzed the effectiveness of regional vascular measurements as an indication of RR disease. Additionally, the microvascular differences between affected and unaffected eyes of the RR patients were also studied and compared to v healthy subjects. The proposed approaches are expected to provide more accurate and reliable automated measurements to analyze retinal microvasculature. vi

show abstract

Evaluation Protocol of Skeletonization Applied to Grayscale Curvilinear Structures

Cited by 5 publications

References 19 publications

Reconstructing microvascular network skeletons from 3D images: what is the ground truth?

Reconstructing microvascular network skeletons from 3D images: what is the ground truth?

Identification and Measurement of Individual Roots in Minirhizotron Images of Dense Root Systems

Measurements of retinal microvasculature in mice and humans with deep learning

Contact Info

Product

Resources

About