A label-free and data-free training strategy for vasculature segmentation in serial sectioning OCT data

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chollet, Etienne, Balbastre, Yael, Magnain, Caroline, Fischl, Bruce, Wang, Hui
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916257367851008
author Chollet, Etienne
Balbastre, Yael
Magnain, Caroline
Fischl, Bruce
Wang, Hui
author_facet Chollet, Etienne
Balbastre, Yael
Magnain, Caroline
Fischl, Bruce
Wang, Hui
contents Serial sectioning Optical Coherence Tomography (sOCT) is a high-throughput, label free microscopic imaging technique that is becoming increasingly popular to study post-mortem neurovasculature. Quantitative analysis of the vasculature requires highly accurate segmentation; however, sOCT has low signal-to-noise-ratio and displays a wide range of contrasts and artifacts that depend on acquisition parameters. Furthermore, labeled data is scarce and extremely time consuming to generate. Here, we leverage synthetic datasets of vessels to train a deep learning segmentation model. We construct the vessels with semi-realistic splines that simulate the vascular geometry and compare our model with realistic vascular labels generated by constrained constructive optimization. Both approaches yield similar Dice scores, although with very different false positive and false negative rates. This method addresses the complexity inherent in OCT images and paves the way for more accurate and efficient analysis of neurovascular structures.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13757
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A label-free and data-free training strategy for vasculature segmentation in serial sectioning OCT data
Chollet, Etienne
Balbastre, Yael
Magnain, Caroline
Fischl, Bruce
Wang, Hui
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
I.4.6; I.2.10; I.2.1; I.2.6; I.6.5; J.3
Serial sectioning Optical Coherence Tomography (sOCT) is a high-throughput, label free microscopic imaging technique that is becoming increasingly popular to study post-mortem neurovasculature. Quantitative analysis of the vasculature requires highly accurate segmentation; however, sOCT has low signal-to-noise-ratio and displays a wide range of contrasts and artifacts that depend on acquisition parameters. Furthermore, labeled data is scarce and extremely time consuming to generate. Here, we leverage synthetic datasets of vessels to train a deep learning segmentation model. We construct the vessels with semi-realistic splines that simulate the vascular geometry and compare our model with realistic vascular labels generated by constrained constructive optimization. Both approaches yield similar Dice scores, although with very different false positive and false negative rates. This method addresses the complexity inherent in OCT images and paves the way for more accurate and efficient analysis of neurovascular structures.
title A label-free and data-free training strategy for vasculature segmentation in serial sectioning OCT data
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
I.4.6; I.2.10; I.2.1; I.2.6; I.6.5; J.3
url https://arxiv.org/abs/2405.13757