Topology-preserving contourwise shape fusion

Abstract The preservation of morphological features, such as protrusions and concavities, and of the topology of input shapes is important when establishing reference data for benchmarking segmentation algorithms or when constructing a mean or median shape. We present a contourwise topology-preservi...

Full description

Saved in:
Bibliographic Details
Main Authors: Aleksandra Melnikova, Martin Maška, Petr Matula
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-94977-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849392326175096832
author Aleksandra Melnikova
Martin Maška
Petr Matula
author_facet Aleksandra Melnikova
Martin Maška
Petr Matula
author_sort Aleksandra Melnikova
collection DOAJ
description Abstract The preservation of morphological features, such as protrusions and concavities, and of the topology of input shapes is important when establishing reference data for benchmarking segmentation algorithms or when constructing a mean or median shape. We present a contourwise topology-preserving fusion method, called shape-aware topology-preserving means (SATM), for merging complex simply connected shapes. The method is based on key point matching and piecewise contour averaging. Unlike existing pixelwise and contourwise fusion methods, SATM preserves topology and does not smooth morphological features. We also present a detailed comparison of SATM with state-of-the-art fusion techniques for the purpose of benchmarking and median shape construction. Our experiments show that SATM outperforms these techniques in terms of shape-related measures that reflect shape complexity, manifesting itself as a reliable method for both establishing a consensus of segmentation annotations and for computing mean shapes.
format Article
id doaj-art-a765f5f249d1459cb85f59fad1b3fef3
institution Kabale University
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-a765f5f249d1459cb85f59fad1b3fef32025-08-20T03:40:47ZengNature PortfolioScientific Reports2045-23222025-03-0115111210.1038/s41598-025-94977-0Topology-preserving contourwise shape fusionAleksandra Melnikova0Martin Maška1Petr Matula2Masaryk UniversityMasaryk UniversityMasaryk UniversityAbstract The preservation of morphological features, such as protrusions and concavities, and of the topology of input shapes is important when establishing reference data for benchmarking segmentation algorithms or when constructing a mean or median shape. We present a contourwise topology-preserving fusion method, called shape-aware topology-preserving means (SATM), for merging complex simply connected shapes. The method is based on key point matching and piecewise contour averaging. Unlike existing pixelwise and contourwise fusion methods, SATM preserves topology and does not smooth morphological features. We also present a detailed comparison of SATM with state-of-the-art fusion techniques for the purpose of benchmarking and median shape construction. Our experiments show that SATM outperforms these techniques in terms of shape-related measures that reflect shape complexity, manifesting itself as a reliable method for both establishing a consensus of segmentation annotations and for computing mean shapes.https://doi.org/10.1038/s41598-025-94977-0Average shapeMean shapeMedian shapeShape analysisSegmentation mask fusion
spellingShingle Aleksandra Melnikova
Martin Maška
Petr Matula
Topology-preserving contourwise shape fusion
Scientific Reports
Average shape
Mean shape
Median shape
Shape analysis
Segmentation mask fusion
title Topology-preserving contourwise shape fusion
title_full Topology-preserving contourwise shape fusion
title_fullStr Topology-preserving contourwise shape fusion
title_full_unstemmed Topology-preserving contourwise shape fusion
title_short Topology-preserving contourwise shape fusion
title_sort topology preserving contourwise shape fusion
topic Average shape
Mean shape
Median shape
Shape analysis
Segmentation mask fusion
url https://doi.org/10.1038/s41598-025-94977-0
work_keys_str_mv AT aleksandramelnikova topologypreservingcontourwiseshapefusion
AT martinmaska topologypreservingcontourwiseshapefusion
AT petrmatula topologypreservingcontourwiseshapefusion