Dense-PSP-UNet: A neural network for fast inference liver ultrasound segmentation

<p dir="ltr">Liver Ultrasound (US) or sonography is popularly used because of its real-time output, low-cost, ease-ofuse, portability, and non-invasive nature. Segmentation of real-time liver US is essential for diagnosing and analyzing liver conditions (e.g., hepatocellular carcinom...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Mohammed Yusuf Ansari (16904523) (author)
مؤلفون آخرون: Yin Yang (35103) (author), Pramod Kumar Meher (17316988) (author), Sarada Prasad Dakua (14151789) (author)
منشور في: 2023
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513543618953216
author Mohammed Yusuf Ansari (16904523)
author2 Yin Yang (35103)
Pramod Kumar Meher (17316988)
Sarada Prasad Dakua (14151789)
author2_role author
author
author
author_facet Mohammed Yusuf Ansari (16904523)
Yin Yang (35103)
Pramod Kumar Meher (17316988)
Sarada Prasad Dakua (14151789)
author_role author
dc.creator.none.fl_str_mv Mohammed Yusuf Ansari (16904523)
Yin Yang (35103)
Pramod Kumar Meher (17316988)
Sarada Prasad Dakua (14151789)
dc.date.none.fl_str_mv 2023-02-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.compbiomed.2022.106478
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Dense-PSP-UNet_A_neural_network_for_fast_inference_liver_ultrasound_segmentation/24474637
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biomedical and clinical sciences
Clinical sciences
Engineering
Biomedical engineering
Information and computing sciences
Artificial intelligence
Data management and data science
Liver segmentation
Ultrasound segmentation
Multiscale features
Real-time segmentation
dc.title.none.fl_str_mv Dense-PSP-UNet: A neural network for fast inference liver ultrasound segmentation
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Liver Ultrasound (US) or sonography is popularly used because of its real-time output, low-cost, ease-ofuse, portability, and non-invasive nature. Segmentation of real-time liver US is essential for diagnosing and analyzing liver conditions (e.g., hepatocellular carcinoma (HCC)), assisting the surgeons/radiologists in therapeutic procedures. In this paper, we propose a method using a modified Pyramid Scene Parsing (PSP) module in tuned neural network backbones to achieve real-time segmentation without compromising the segmentation accuracy. Considering widespread noise in US data and its impact on outcomes, we study the impact of pre-processing and the influence of loss functions on segmentation performance. We have tested our method after annotating a publicly available US dataset containing 2400 images of 8 healthy volunteers (link to the annotated dataset is provided); the results show that the Dense-PSP-UNet model achieves a high Dice coefficient of 0.913±0.024 while delivering a real-time performance of 37 frames per second (FPS).</p><h2>Other Information</h2><p dir="ltr">Published in: Computers in Biology and Medicine<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.compbiomed.2022.106478" target="_blank">https://dx.doi.org/10.1016/j.compbiomed.2022.106478</a></p>
eu_rights_str_mv openAccess
id Manara2_ce3aa5fdd9cd929a88ae81b5cc3b0929
identifier_str_mv 10.1016/j.compbiomed.2022.106478
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24474637
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Dense-PSP-UNet: A neural network for fast inference liver ultrasound segmentationMohammed Yusuf Ansari (16904523)Yin Yang (35103)Pramod Kumar Meher (17316988)Sarada Prasad Dakua (14151789)Biomedical and clinical sciencesClinical sciencesEngineeringBiomedical engineeringInformation and computing sciencesArtificial intelligenceData management and data scienceLiver segmentationUltrasound segmentationMultiscale featuresReal-time segmentation<p dir="ltr">Liver Ultrasound (US) or sonography is popularly used because of its real-time output, low-cost, ease-ofuse, portability, and non-invasive nature. Segmentation of real-time liver US is essential for diagnosing and analyzing liver conditions (e.g., hepatocellular carcinoma (HCC)), assisting the surgeons/radiologists in therapeutic procedures. In this paper, we propose a method using a modified Pyramid Scene Parsing (PSP) module in tuned neural network backbones to achieve real-time segmentation without compromising the segmentation accuracy. Considering widespread noise in US data and its impact on outcomes, we study the impact of pre-processing and the influence of loss functions on segmentation performance. We have tested our method after annotating a publicly available US dataset containing 2400 images of 8 healthy volunteers (link to the annotated dataset is provided); the results show that the Dense-PSP-UNet model achieves a high Dice coefficient of 0.913±0.024 while delivering a real-time performance of 37 frames per second (FPS).</p><h2>Other Information</h2><p dir="ltr">Published in: Computers in Biology and Medicine<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.compbiomed.2022.106478" target="_blank">https://dx.doi.org/10.1016/j.compbiomed.2022.106478</a></p>2023-02-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.compbiomed.2022.106478https://figshare.com/articles/journal_contribution/Dense-PSP-UNet_A_neural_network_for_fast_inference_liver_ultrasound_segmentation/24474637CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/244746372023-02-01T00:00:00Z
spellingShingle Dense-PSP-UNet: A neural network for fast inference liver ultrasound segmentation
Mohammed Yusuf Ansari (16904523)
Biomedical and clinical sciences
Clinical sciences
Engineering
Biomedical engineering
Information and computing sciences
Artificial intelligence
Data management and data science
Liver segmentation
Ultrasound segmentation
Multiscale features
Real-time segmentation
status_str publishedVersion
title Dense-PSP-UNet: A neural network for fast inference liver ultrasound segmentation
title_full Dense-PSP-UNet: A neural network for fast inference liver ultrasound segmentation
title_fullStr Dense-PSP-UNet: A neural network for fast inference liver ultrasound segmentation
title_full_unstemmed Dense-PSP-UNet: A neural network for fast inference liver ultrasound segmentation
title_short Dense-PSP-UNet: A neural network for fast inference liver ultrasound segmentation
title_sort Dense-PSP-UNet: A neural network for fast inference liver ultrasound segmentation
topic Biomedical and clinical sciences
Clinical sciences
Engineering
Biomedical engineering
Information and computing sciences
Artificial intelligence
Data management and data science
Liver segmentation
Ultrasound segmentation
Multiscale features
Real-time segmentation