On the uncertainty in the segmentation of ultrasound images reconstructed with the total focusing method
Article Highlights This study uses neural networks to probabilistically segment TFM images and investigate uncertainty. The probabilistic U-Net outperforms other models, and high uncertainty is found in the shadow zone, reflections, and small defects. Three different defect types are investigated.
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer
2023-03-01
|
Series: | SN Applied Sciences |
Subjects: | |
Online Access: | https://doi.org/10.1007/s42452-023-05342-7 |
_version_ | 1797863888500293632 |
---|---|
author | Simon Schmid Haoyu Wei Christian U. Grosse |
author_facet | Simon Schmid Haoyu Wei Christian U. Grosse |
author_sort | Simon Schmid |
collection | DOAJ |
description | Article Highlights This study uses neural networks to probabilistically segment TFM images and investigate uncertainty. The probabilistic U-Net outperforms other models, and high uncertainty is found in the shadow zone, reflections, and small defects. Three different defect types are investigated. |
first_indexed | 2024-04-09T22:42:53Z |
format | Article |
id | doaj.art-aaf48e09e1074120beec2a5548ab83e4 |
institution | Directory Open Access Journal |
issn | 2523-3963 2523-3971 |
language | English |
last_indexed | 2024-04-09T22:42:53Z |
publishDate | 2023-03-01 |
publisher | Springer |
record_format | Article |
series | SN Applied Sciences |
spelling | doaj.art-aaf48e09e1074120beec2a5548ab83e42023-03-22T12:03:01ZengSpringerSN Applied Sciences2523-39632523-39712023-03-015411110.1007/s42452-023-05342-7On the uncertainty in the segmentation of ultrasound images reconstructed with the total focusing methodSimon Schmid0Haoyu Wei1Christian U. Grosse2Chair of Non-Destructive Testing, Technical University of MunichChair of Non-Destructive Testing, Technical University of MunichChair of Non-Destructive Testing, Technical University of MunichArticle Highlights This study uses neural networks to probabilistically segment TFM images and investigate uncertainty. The probabilistic U-Net outperforms other models, and high uncertainty is found in the shadow zone, reflections, and small defects. Three different defect types are investigated.https://doi.org/10.1007/s42452-023-05342-7Probabilistic image segmentationDeep learningTotal focusing methodUltrasound |
spellingShingle | Simon Schmid Haoyu Wei Christian U. Grosse On the uncertainty in the segmentation of ultrasound images reconstructed with the total focusing method SN Applied Sciences Probabilistic image segmentation Deep learning Total focusing method Ultrasound |
title | On the uncertainty in the segmentation of ultrasound images reconstructed with the total focusing method |
title_full | On the uncertainty in the segmentation of ultrasound images reconstructed with the total focusing method |
title_fullStr | On the uncertainty in the segmentation of ultrasound images reconstructed with the total focusing method |
title_full_unstemmed | On the uncertainty in the segmentation of ultrasound images reconstructed with the total focusing method |
title_short | On the uncertainty in the segmentation of ultrasound images reconstructed with the total focusing method |
title_sort | on the uncertainty in the segmentation of ultrasound images reconstructed with the total focusing method |
topic | Probabilistic image segmentation Deep learning Total focusing method Ultrasound |
url | https://doi.org/10.1007/s42452-023-05342-7 |
work_keys_str_mv | AT simonschmid ontheuncertaintyinthesegmentationofultrasoundimagesreconstructedwiththetotalfocusingmethod AT haoyuwei ontheuncertaintyinthesegmentationofultrasoundimagesreconstructedwiththetotalfocusingmethod AT christianugrosse ontheuncertaintyinthesegmentationofultrasoundimagesreconstructedwiththetotalfocusingmethod |