FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery
<p><br></p><h3>Goal</h3><p dir="ltr">FetSAM represents a cutting-edge deep learning model aimed at revolutionizing fetal head ultrasound segmentation, thereby elevating prenatal diagnostic precision. </p><h3>Methods</h3><p dir="...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , |
| منشور في: |
2024
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1864513510742949888 |
|---|---|
| author | Mahmood Alzubaidi (15740693) |
| author2 | Uzair Shah (15740699) Marco Agus (8032898) Mowafa Househ (9154124) |
| author2_role | author author author |
| author_facet | Mahmood Alzubaidi (15740693) Uzair Shah (15740699) Marco Agus (8032898) Mowafa Househ (9154124) |
| author_role | author |
| dc.creator.none.fl_str_mv | Mahmood Alzubaidi (15740693) Uzair Shah (15740699) Marco Agus (8032898) Mowafa Househ (9154124) |
| dc.date.none.fl_str_mv | 2024-03-24T15:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1109/ojemb.2024.3382487 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/FetSAM_Advanced_Segmentation_Techniques_for_Fetal_Head_Biometrics_in_Ultrasound_Imagery/26316931 |
| 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 Information and computing sciences Artificial intelligence Fetal Ultrasound Imaging Image Segmentation Prompt-based Learning Prenatal Diagnostics Ultrasound Biometrics Ultrasonic imaging Image segmentation Head Brain modeling Biological system modeling Imaging Ultrasonic variables measurement |
| dc.title.none.fl_str_mv | FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p><br></p><h3>Goal</h3><p dir="ltr">FetSAM represents a cutting-edge deep learning model aimed at revolutionizing fetal head ultrasound segmentation, thereby elevating prenatal diagnostic precision. </p><h3>Methods</h3><p dir="ltr">Utilizing a comprehensive dataset–the largest to date for fetal head metrics–FetSAM incorporates prompt-based learning. It distinguishes itself with a dual loss mechanism, combining Weighted DiceLoss and Weighted Lovasz Loss, optimized through AdamW and underscored by class weight adjustments for better segmentation balance. Performance benchmarks against prominent models such as U-Net, DeepLabV3, and Segformer highlight its efficacy. </p><h3>Results</h3><p dir="ltr">FetSAM delivers unparalleled segmentation accuracy, demonstrated by a DSC of 0.90117, HD of 1.86484, and ASD of 0.46645. Conclusion: FetSAM sets a new benchmark in AI-enhanced prenatal ultrasound analysis, providing a robust, precise tool for clinical applications and pushing the envelope of prenatal care with its groundbreaking dataset and segmentation capabilities.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Open Journal of Engineering in Medicine and Biology<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/10.1109/ojemb.2024.3382487" target="_blank">https://dx.doi.org/10.1109/ojemb.2024.3382487</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_e0e96ae48c56fb1c81d70ef2073569cb |
| identifier_str_mv | 10.1109/ojemb.2024.3382487 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/26316931 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound ImageryMahmood Alzubaidi (15740693)Uzair Shah (15740699)Marco Agus (8032898)Mowafa Househ (9154124)Biomedical and clinical sciencesClinical sciencesInformation and computing sciencesArtificial intelligenceFetal Ultrasound ImagingImage SegmentationPrompt-based LearningPrenatal DiagnosticsUltrasound BiometricsUltrasonic imagingImage segmentationHeadBrain modelingBiological system modelingImagingUltrasonic variables measurement<p><br></p><h3>Goal</h3><p dir="ltr">FetSAM represents a cutting-edge deep learning model aimed at revolutionizing fetal head ultrasound segmentation, thereby elevating prenatal diagnostic precision. </p><h3>Methods</h3><p dir="ltr">Utilizing a comprehensive dataset–the largest to date for fetal head metrics–FetSAM incorporates prompt-based learning. It distinguishes itself with a dual loss mechanism, combining Weighted DiceLoss and Weighted Lovasz Loss, optimized through AdamW and underscored by class weight adjustments for better segmentation balance. Performance benchmarks against prominent models such as U-Net, DeepLabV3, and Segformer highlight its efficacy. </p><h3>Results</h3><p dir="ltr">FetSAM delivers unparalleled segmentation accuracy, demonstrated by a DSC of 0.90117, HD of 1.86484, and ASD of 0.46645. Conclusion: FetSAM sets a new benchmark in AI-enhanced prenatal ultrasound analysis, providing a robust, precise tool for clinical applications and pushing the envelope of prenatal care with its groundbreaking dataset and segmentation capabilities.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Open Journal of Engineering in Medicine and Biology<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/10.1109/ojemb.2024.3382487" target="_blank">https://dx.doi.org/10.1109/ojemb.2024.3382487</a></p>2024-03-24T15:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/ojemb.2024.3382487https://figshare.com/articles/journal_contribution/FetSAM_Advanced_Segmentation_Techniques_for_Fetal_Head_Biometrics_in_Ultrasound_Imagery/26316931CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/263169312024-03-24T15:00:00Z |
| spellingShingle | FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery Mahmood Alzubaidi (15740693) Biomedical and clinical sciences Clinical sciences Information and computing sciences Artificial intelligence Fetal Ultrasound Imaging Image Segmentation Prompt-based Learning Prenatal Diagnostics Ultrasound Biometrics Ultrasonic imaging Image segmentation Head Brain modeling Biological system modeling Imaging Ultrasonic variables measurement |
| status_str | publishedVersion |
| title | FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery |
| title_full | FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery |
| title_fullStr | FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery |
| title_full_unstemmed | FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery |
| title_short | FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery |
| title_sort | FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery |
| topic | Biomedical and clinical sciences Clinical sciences Information and computing sciences Artificial intelligence Fetal Ultrasound Imaging Image Segmentation Prompt-based Learning Prenatal Diagnostics Ultrasound Biometrics Ultrasonic imaging Image segmentation Head Brain modeling Biological system modeling Imaging Ultrasonic variables measurement |