A Persistent Homology-Based Topological Loss for CNN-Based Multiclass Segmentation of CMR

Byrne, Nick; Clough, James R.; Valverde, Isra; Montana, Giovanni; King, Andrew P.

doi:10.1109/tmi.2022.3203309

Cited by 15 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The densest regions of the image space are taken to be the origin point for identifiable objects, which are then constructed iteratively ( 41 ) . For 3D image analysis, this is done by ordering the intensity of each pixel across each frame, producing what is known as a filtration scheme ( 40 , 42 ) . Objects are identified by iteratively analyzing each entry in the filtration to determine local maxima, then sequentially attaching pixels to their neighbors across multiple adjacent frames ( 43 ) .…”

Section: Resultsmentioning

confidence: 99%

Three-dimensional topology-based analysis segments volumetric and spatiotemporal fluorescence microscopy

Panconi,

Tansell,

Collins

et al. 2023

Biol. Imaging

View full text Add to dashboard Cite

Image analysis techniques provide objective and reproducible statistics for interpreting microscopy data. At higher dimensions, three-dimensional (3D) volumetric and spatiotemporal data highlight additional properties and behaviors beyond the static 2D focal plane. However, increased dimensionality carries increased complexity, and existing techniques for general segmentation of 3D data are either primitive, or highly specialized to specific biological structures. Borrowing from the principles of 2D topological data analysis (TDA), we formulate a 3D segmentation algorithm that implements persistent homology to identify variations in image intensity. From this, we derive two separate variants applicable to spatial and spatiotemporal data, respectively. We demonstrate that this analysis yields both sensitive and specific results on simulated data and can distinguish prominent biological structures in fluorescence microscopy images, regardless of their shape. Furthermore, we highlight the efficacy of temporal TDA in tracking cell lineage and the frequency of cell and organelle replication.

show abstract

Section: Resultsmentioning

confidence: 99%

Three-dimensional topology-based analysis segments volumetric and spatiotemporal fluorescence microscopy

Panconi,

Tansell,

Collins

et al. 2023

Biol. Imaging

View full text Add to dashboard Cite

show abstract

“…). This contrasts with approaches based on persistent homology (PH) 10,35,36 which are advantageous in that respect. However, PH-based approaches are computationally expensive, in particular in 3D.…”

Section: Discussionmentioning

confidence: 99%

“…In other words, this method can only remove erroneous connected components and cannot cope with the missing ones. Byrne et al 36 designed a new loss function for multi-class segmentation based on PH, extending from binary setting to consider a richer set of topological priors, including hierarchical class containment and adjacency. It is an extension of the work of Clough et al 10 to the multi-class setting.…”

Section: Topology-based Loss Functions and Modelsmentioning

confidence: 99%

Projected pooling loss for red nucleus segmentation with soft topology constraints

Fu,

El Jurdi,

Chougar

et al. 2024

J. Med. Imag.

View full text Add to dashboard Cite

“…Two prominent points are found in region Y, given by τ ≥ 0.5, which correspond to the two bright objects in the original image to the stage of the binarization sequence at which it was first activated (Figure 1E). Mathematically, this is known as a filtration scheme, and each stage of the filtration will correspond to a different simplicial complex (Figure 1F-H) [19,20]. While the definition of a topological feature typically incorporates holes in the complex, we restrict our usage here to the first homology class, which represents the number of distinct connected components [21][22][23].…”

Section: Description Of the Algorithmmentioning

confidence: 99%

Topology‐based fluorescence image analysis for automated cell identification and segmentation

Panconi

Makarova

Lambert

et al. 2022

Journal of Biophotonics

View full text Add to dashboard Cite

Cell segmentation refers to the body of techniques used to identify cells in images and extract biologically relevant information from them; however, manual segmentation is laborious and subjective. We present Topological Boundary Line Estimation using Recurrence Of Neighbouring Emissions (TOBLERONE), a topological image analysis tool which identifies persistent homological image features as opposed to the geometric analysis commonly employed. We demonstrate that topological data analysis can provide accurate segmentation of arbitrarily‐shaped cells, offering a means for automatic and objective data extraction. One cellular feature of particular interest in biology is the plasma membrane, which has been shown to present varying degrees of lipid packing, or membrane order, depending on the function and morphology of the cell type. With the use of environmentally‐sensitive dyes, images derived from confocal microscopy can be used to quantify the degree of membrane order. We demonstrate that TOBLERONE is capable of automating this task.

show abstract

A Persistent Homology-Based Topological Loss for CNN-Based Multiclass Segmentation of CMR

Cited by 15 publications

References 34 publications

Three-dimensional topology-based analysis segments volumetric and spatiotemporal fluorescence microscopy

Three-dimensional topology-based analysis segments volumetric and spatiotemporal fluorescence microscopy

Projected pooling loss for red nucleus segmentation with soft topology constraints

Topology‐based fluorescence image analysis for automated cell identification and segmentation

Contact Info

Product

Resources

About