Vasculature Segmentation in 3D Hierarchical Phase-contrast Tomography Images of Human Kidneys

Overview

Journal bioRxiv

Date 2024 Sep 10

PMID 39253466

Authors

Yashvardhan Jain

Claire L Walsh

Ekin Yagis

Shahab Aslani

Sonal Nandanwar

Yang Zhou

Juhyung Ha

Katherine S Gustilo

Joseph Brunet

Shahrokh Rahmani

Paul Tafforeau

Alexandre Bellier

Griffin M Weber

Peter D Lee

Katy Borner

Affiliations

Soon will be listed here.

Abstract

Efficient algorithms are needed to segment vasculature in new three-dimensional (3D) medical imaging datasets at scale for a wide range of research and clinical applications. Manual segmentation of vessels in images is time-consuming and expensive. Computational approaches are more scalable but have limitations in accuracy. We organized a global machine learning competition, engaging 1,401 participants, to help develop new deep learning methods for 3D blood vessel segmentation. This paper presents a detailed analysis of the top-performing solutions using manually curated 3D Hierarchical Phase-Contrast Tomography datasets of the human kidney, focusing on the segmentation accuracy and morphological analysis, thereby establishing a benchmark for future studies in blood vessel segmentation within phase-contrast tomography imaging.

References

Maier-Hein L, Eisenmann M, Reinke A, Onogur S, Stankovic M, Scholz P . Why rankings of biomedical image analysis competitions should be interpreted with care. Nat Commun. 2018; 9(1):5217. PMC: 6284017. DOI: 10.1038/s41467-018-07619-7. View

Borner K, Teichmann S, Quardokus E, Gee J, Browne K, Osumi-Sutherland D . Anatomical structures, cell types and biomarkers of the Human Reference Atlas. Nat Cell Biol. 2021; 23(11):1117-1128. PMC: 10079270. DOI: 10.1038/s41556-021-00788-6. View

Le T, Winsnes C, Axelsson U, Xu H, Kaimal J, Mahdessian D . Analysis of the Human Protein Atlas Weakly Supervised Single-Cell Classification competition. Nat Methods. 2022; 19(10):1221-1229. PMC: 9550622. DOI: 10.1038/s41592-022-01606-z. View

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View

. The human body at cellular resolution: the NIH Human Biomolecular Atlas Program. Nature. 2019; 574(7777):187-192. PMC: 6800388. DOI: 10.1038/s41586-019-1629-x. View

Sefidgar M, Soltani M, Raahemifar K, Sadeghi M, Bazmara H, Bazargan M . Numerical modeling of drug delivery in a dynamic solid tumor microvasculature. Microvasc Res. 2015; 99:43-56. DOI: 10.1016/j.mvr.2015.02.007. View

. NIH SenNet Consortium to map senescent cells throughout the human lifespan to understand physiological health. Nat Aging. 2023; 2(12):1090-1100. PMC: 10019484. DOI: 10.1038/s43587-022-00326-5. View

Virtanen P, Gommers R, Oliphant T, Haberland M, Reddy T, Cournapeau D . SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods. 2020; 17(3):261-272. PMC: 7056644. DOI: 10.1038/s41592-019-0686-2. View

Isensee F, Jaeger P, Kohl S, Petersen J, Maier-Hein K . nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2020; 18(2):203-211. DOI: 10.1038/s41592-020-01008-z. View

10.

Boppana A, Lee S, Malhotra R, Halushka M, Gustilo K, Quardokus E . Anatomical structures, cell types, and biomarkers of the healthy human blood vasculature. Sci Data. 2023; 10(1):452. PMC: 10356915. DOI: 10.1038/s41597-023-02018-0. View

11.

Sweeney P, Walsh C, Walker-Samuel S, Shipley R . A three-dimensional, discrete-continuum model of blood pressure in microvascular networks. Int J Numer Method Biomed Eng. 2024; 40(8):e3832. DOI: 10.1002/cnm.3832. View

12.

Jain Y, Godwin L, Ju Y, Sood N, Quardokus E, Bueckle A . Segmentation of human functional tissue units in support of a Human Reference Atlas. Commun Biol. 2023; 6(1):717. PMC: 10356924. DOI: 10.1038/s42003-023-04848-5. View

13.

Nikolov S, Blackwell S, Zverovitch A, Mendes R, Livne M, De Fauw J . Clinically Applicable Segmentation of Head and Neck Anatomy for Radiotherapy: Deep Learning Algorithm Development and Validation Study. J Med Internet Res. 2021; 23(7):e26151. PMC: 8314151. DOI: 10.2196/26151. View

14.

Jain Y, Godwin L, Joshi S, Mandarapu S, Le T, Lindskog C . Segmenting functional tissue units across human organs using community-driven development of generalizable machine learning algorithms. Nat Commun. 2023; 14(1):4656. PMC: 10400613. DOI: 10.1038/s41467-023-40291-0. View

15.

Carass A, Roy S, Gherman A, Reinhold J, Jesson A, Arbel T . Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis. Sci Rep. 2020; 10(1):8242. PMC: 7237671. DOI: 10.1038/s41598-020-64803-w. View

16.

Weber G, Ju Y, Borner K . Considerations for Using the Vasculature as a Coordinate System to Map All the Cells in the Human Body. Front Cardiovasc Med. 2020; 7:29. PMC: 7082726. DOI: 10.3389/fcvm.2020.00029. View

17.

Ouyang W, Winsnes C, Hjelmare M, Cesnik A, Akesson L, Xu H . Analysis of the Human Protein Atlas Image Classification competition. Nat Methods. 2019; 16(12):1254-1261. PMC: 6976526. DOI: 10.1038/s41592-019-0658-6. View

18.

Spangenberg P, Hagemann N, Squire A, Forster N, Krauss S, Qi Y . Rapid and fully automated blood vasculature analysis in 3D light-sheet image volumes of different organs. Cell Rep Methods. 2023; 3(3):100436. PMC: 10088239. DOI: 10.1016/j.crmeth.2023.100436. View

19.

Borner K, Blood P, Silverstein J, Ruffalo M, Satija R, Teichmann S . Human BioMolecular Atlas Program (HuBMAP): 3D Human Reference Atlas construction and usage. Nat Methods. 2025; . DOI: 10.1038/s41592-024-02563-5. View

20.

Brunet J, Walsh C, Wagner W, Bellier A, Werlein C, Marussi S . Preparation of large biological samples for high-resolution, hierarchical, synchrotron phase-contrast tomography with multimodal imaging compatibility. Nat Protoc. 2023; 18(5):1441-1461. DOI: 10.1038/s41596-023-00804-z. View