Deep learning strategies for ultrasound in pregnancy
Ultrasound is one of the most ubiquitous imaging modalities in clinical practice. It is cheap, does not require ionizing radiation and can be performed at the bedside, making it the most commonly utilized imaging technique in pregnancy. Despite these advantages, it does have some drawbacks such as r...
| Main Authors: | , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
European Medical Group
2020
|
| _version_ | 1797068977654988800 |
|---|---|
| author | Bandeira Diniz, P Yin, Y Collins, S |
| author_facet | Bandeira Diniz, P Yin, Y Collins, S |
| author_sort | Bandeira Diniz, P |
| collection | OXFORD |
| description | Ultrasound is one of the most ubiquitous imaging modalities in clinical practice. It is cheap, does not require ionizing radiation and can be performed at the bedside, making it the most commonly utilized imaging technique in pregnancy. Despite these advantages, it does have some drawbacks such as relatively low imaging quality, low contrast, and high variability. With these constraints, automating the interpretation of ultrasound images is challenging. However, successful automated identification of structures within 3D ultrasound volumes has the potential to revolutionize clinical practice. For example, a small placental volume in the first trimester has been shown to be correlated to adverse outcome later in pregnancy. If the placenta could be segmented reliably and automatically from a static 3D ultrasound volume, it would facilitate the use of its estimated volume, and other morphological metrics, as part of a screening test for increased risk of pregnancy complications potentially improving clinical outcomes.
Recently, deep learning has emerged, achieving state-of-the-art performance in various research fields, notably medical image analysis involving classification, segmentation, object detection, and tracking tasks. Due to its increased performance with large datasets, it has gained great interest in medical imaging applications. In this review, we present an overview of deep learning methods applied to ultrasound in pregnancy, introducing their architectures and analyzing their strategies. We then present some common problems and provide some perspectives into potential future research. |
| first_indexed | 2024-03-06T22:17:47Z |
| format | Journal article |
| id | oxford-uuid:54013b9b-aaad-456f-a828-9c58abb218f5 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T22:17:47Z |
| publishDate | 2020 |
| publisher | European Medical Group |
| record_format | dspace |
| spelling | oxford-uuid:54013b9b-aaad-456f-a828-9c58abb218f52022-03-26T16:35:07ZDeep learning strategies for ultrasound in pregnancyJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:54013b9b-aaad-456f-a828-9c58abb218f5EnglishSymplectic ElementsEuropean Medical Group2020Bandeira Diniz, PYin, YCollins, SUltrasound is one of the most ubiquitous imaging modalities in clinical practice. It is cheap, does not require ionizing radiation and can be performed at the bedside, making it the most commonly utilized imaging technique in pregnancy. Despite these advantages, it does have some drawbacks such as relatively low imaging quality, low contrast, and high variability. With these constraints, automating the interpretation of ultrasound images is challenging. However, successful automated identification of structures within 3D ultrasound volumes has the potential to revolutionize clinical practice. For example, a small placental volume in the first trimester has been shown to be correlated to adverse outcome later in pregnancy. If the placenta could be segmented reliably and automatically from a static 3D ultrasound volume, it would facilitate the use of its estimated volume, and other morphological metrics, as part of a screening test for increased risk of pregnancy complications potentially improving clinical outcomes. Recently, deep learning has emerged, achieving state-of-the-art performance in various research fields, notably medical image analysis involving classification, segmentation, object detection, and tracking tasks. Due to its increased performance with large datasets, it has gained great interest in medical imaging applications. In this review, we present an overview of deep learning methods applied to ultrasound in pregnancy, introducing their architectures and analyzing their strategies. We then present some common problems and provide some perspectives into potential future research. |
| spellingShingle | Bandeira Diniz, P Yin, Y Collins, S Deep learning strategies for ultrasound in pregnancy |
| title | Deep learning strategies for ultrasound in pregnancy |
| title_full | Deep learning strategies for ultrasound in pregnancy |
| title_fullStr | Deep learning strategies for ultrasound in pregnancy |
| title_full_unstemmed | Deep learning strategies for ultrasound in pregnancy |
| title_short | Deep learning strategies for ultrasound in pregnancy |
| title_sort | deep learning strategies for ultrasound in pregnancy |
| work_keys_str_mv | AT bandeiradinizp deeplearningstrategiesforultrasoundinpregnancy AT yiny deeplearningstrategiesforultrasoundinpregnancy AT collinss deeplearningstrategiesforultrasoundinpregnancy |