The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index; 4 of the 52 sources its claims cite were checked for support.
Deep Learning Strategies for Ultrasound in Pregnancy
Open accessAbstract
Ultrasound is one of the most ubiquitous imaging modalities in clinical practice. It is cheap, does not require ionising radiation, and can be performed at the bedside, making it the most commonly used 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, successfully automated identification of structures within three-dimensional ultrasound volumes has the potential to revolutionise clinical practice. For example, a small placental volume in the first trimester is correlated to adverse outcome later in pregnancy. If the placenta could be segmented reliably and automatically from a static three-dimensional 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, deep learning has garnered great interest relating to medical imaging applications. In this review, the authors present an overview of deep learning methods applied to ultrasound in pregnancy, introducing their architectures and analysing strategies. Some common problems are presented and some perspectives into potential future research are provided.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This review surveys deep learning methods applied to pregnancy ultrasound, focusing on fetal and placental segmentation, and reports state-of-the-art performance across several CNN/FCNN approaches. It concludes that the field is promising but limited by heterogeneous, small, non-public datasets and a lack of direct comparability and clinical translation.
Key findings
Deep learning has been applied to fetal brain alignment, fetal head segmentation, fetal cardiac annulus segmentation, and placental/vascular segmentation in 2D and 3D ultrasound. For first-trimester placental segmentation, Looney et al.’s DeepMedic CNN achieved median Dice Similarity Coefficient (DSC) of 0.73 (Q1, Q3: 0.66, 0.76) and median Hausdorff distance of 27 mm (Q1, Q3: 18 mm, 36 mm), while their OxNNet FCNN achieved median DSC of 0.84 (IQR 0.09) on 2,393 first-trimester 3D volumes. Other reported results include Oguz et al.’s mean Dice coefficient of 0.8686.3 (±0.05), Torrents-Barrena et al.’s mean Dice of 0.75±0.12 for placenta and 0.70±0.14 for vessels, and Zimmer et al.’s Dice of 0.81±0.05 for placental volume segmentation. The review also notes that OxNNet-segmented placental volumes correlated with birth weight to predict small-for-gestational-age babies, with almost identical clinical conclusions to validated semi-automated tools.
Methods
Narrative review of deep learning applications in pregnancy ultrasound; papers were identified through a broad free-text search of medical databases including PubMed and Google Scholar, augmented by reviewing references in identified papers. Included papers were assessed by the authors and filtered for perceived novelty, impact in the field, and publication date (2017–2020). The review describes architectures and strategies for tasks including classification, object detection, and tissue segmentation, without a quantitative meta-analysis.
Limitations
The paper states that direct comparison between methods is not currently possible because they use different datasets and measurements; datasets are often small and not widely available, and models trained on one dataset may fail on another from a different manufacturer’s machine. It also states that large, public, quality-controlled ultrasound datasets are needed, and that few papers translate algorithms into broader practical clinical solutions. Evident from the text: the review is not a systematic review, its search and selection are broad and partly subjective, and it reports heterogeneous performance metrics without pooled analysis.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
14 Not checked yet · 8 Own interpretation · 5 Sources not found · 2 Supported · 1 Supported so far · 1 No basis given
Every source the paper cites for this claim was checked and supports it.
In the paper
“They also demonstrated that increasing the size of the training set improves the performance of the FCNN.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Supportedcites [29] Looney P Fully automated, real-time 3d ultrasound segmentation to estimate first trimester placental volume using deep learning. JCI insight. 2018; 3(11). PMC6124436 29875312 source
The Discussion reports that the FCNN’s segmentation performance improved as its training set grew: the Dice similarity coefficient rose from 0.73 with 100 cases to 0.81 with 1,200 cases. This directly supports the attributed claim for the model studied. (LLM, conf=0.94)
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
In the paper
“Thus ultrasound examination results are highly dependent on the training, experience and skill of the sonographer [23].”
§ Deep Learning strategies for Ultrasound in Pregnancy > Introduction
What the sources say
- Not checked yetcites [23] Sarris I Intra-and interobserver variability in fetal ultrasound measurements. Ultrasound in obstetrics & gynecology. 2012; 39(3): 266– 273. 22535628 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“A study of the prenatal detection of malformations using ultrasound images demonstrated that the performance sensitivity ranged from 27.5% to 96% among different medical institutions [24].”
§ Deep Learning strategies for Ultrasound in Pregnancy > Introduction
What the sources say
- Not checked yetcites [24] Salomon L A score-based method for quality control of fetal images at routine second-trimester ultrasound examination. Prenatal Diagnosis: Published in Affiliation with the International Society for Prenatal Diagnosis. 2008; 28(9): 822– 827. 18646244 source
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Poor vascularity of the first-trimester placenta has also been demonstrated to increase the risk of developing pre-eclampsia later in pregnancy [40].”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Not checked yetcites [40] Mathewlynn S, Collins S. Volume and vascularity: Using ultrasound to unlock the secrets of the first trimester placenta. Placenta. 2019. PMC7586067 31279487 source
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, it’s not currently possible to compare these methods directly, even if designed for the same task, because they all use different datasets and measurements.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Discussion
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“The best results of placental volume segmentation were comparable to corresponding volumes extracted from MRI, achieving Dice coefficient of 0.81±0.05.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Not matchedcites [34] Zimmer VA Towards whole placenta segmentation at late gestation using multi-view ultrasound images. In: International Conference on Medical Image Computing and Computer Assisted Intervention. Springer. 2019; 628– 636.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainn = 30- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Most of the presented methods cannot be independently evaluated as their datasets are small and not widely available.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Discussion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Their results demonstrated that a combination of 10 selected radiomic features led to the highest tissue segmentation performance.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Fetal Segmentation
What the sources say
- Not checked yetcites [25] Torrents-Barrena J Assessment of radiomics and deep learning for the segmentation of fetal and maternal anatomy in magnetic resonance imaging and ultrasound. Academic Radiology. Elsevier. 2019. 31879159 source
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“This demonstrated the feasibility of using this technique for automated segmentation of the fetal annulus.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Fetal Segmentation
What the sources say
- Not matchedcites [26] Philip ME Convolutional neural networks for automated fetal cardiac assessment using 4d b-mode ultrasound. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). IEEE. 2019; 824– 828.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
boostedn = 250- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
- It may state two separate claims as one. 14
- Probably not a substantial claim. 10
- The quote only partly states this claim. 3
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Compared to classical machine learning algorithms, CNNs have enabled the development of numerous solutions not previously achievable because they do not need a human operator to identify an initial set of features: they can find relevant features within the data itself.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Introduction
What the sources say
- Supportedcites [1] Simonyan K, Zisserman A. Very deep convolutional networks for largescale image recognition. arXiv preprint arXiv 1409.1556 2014. source
In “Generalisation of Very Deep Features” (p. 11), the paper describes image representations learned by ConvNets and contrasts them with hand-crafted representations. Its use of trained ConvNets as feature extractors (p. 12) supports the attributed point that relevant features need not be selected by a human operator. (LLM, conf=0.88)
- Not matchedcites [2] Szegedy C Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015; 1– 9.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [3] He K Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016; 770– 778.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [4] Huang G Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017; 4700– 4708.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [5] Hu J Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018; 7132– 7141.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [6] Wang D Exploring linear relationship in feature map subspace for convnets compression. arXiv preprint arXiv:1803.05729 2018. source
- Not matchedcites [7] Ren S Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems. 2015; 91– 99.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites [8] He K Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE transactions on pattern analysis and machine intelligence. 2015; 37(9): 1904– 1916. 26353135 source
Section 2.1 (p. 3) describes CNN feature maps whose filters respond to shapes in input images and contrasts them with features extracted in traditional methods. This supports the attributed point that CNNs identify relevant features from data without a person specifying an initial feature set. (LLM, conf=0.85)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Experimental results demonstrated that the proposed method achieved high recognition accuracy, and could localize complex anatomical structures around the placenta.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Supportedcites [27] Qi H Weakly supervised learning of placental ultrasound images with residual networks. In: Annual Conference on Medical Image Understanding and Analysis. Springer. 2017; 98– 108. PMC6816799 31660542 source
The Introduction describes the proposed CNN and reports accurate classification alongside good localization of placental anatomical structures. The Experiments section describes weakly supervised localization results, and the Conclusion reports good detection accuracy and reasonable localization without explicit localization training. (LLM, conf=0.95)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Supported
In the paper
“Ultrasound is the most commonly used medical imaging modality for diagnosis and screening in clinical practice [18].”
§ Deep Learning strategies for Ultrasound in Pregnancy > Introduction
What the sources say
- Not checked yetcites [18] Noble JA, Boukerroui D. Ultrasound image segmentation: a survey. IEEE Transactions on medical imaging. 2006; 25(8): 987– 1010. 16894993 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“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.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“However, ultrasound has its disadvantages. It often has relatively low imaging quality, is prone to artifacts, is highly dependent on operator experience, and has high inter- and intra-observer variability across different manufacturers’ machines [10].”
§ Deep Learning strategies for Ultrasound in Pregnancy > Introduction
What the sources say
- Not matchedcites [10] Liu S Deep learning in medical ultrasound analysis: a review. Engineering. 2019.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
None of the sources cited for this claim have been checked yet.
In the paper
“In medical imaging, the most commonly employed deep learning methods are convolutional neural networks (CNNs) [1–8].”
§ Deep Learning strategies for Ultrasound in Pregnancy > Introduction
What the sources say
- Not checked yetcites [1] Simonyan K, Zisserman A. Very deep convolutional networks for largescale image recognition. arXiv preprint arXiv 1409.1556 2014. source
- Not matchedcites [2] Szegedy C Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015; 1– 9.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [3] He K Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016; 770– 778.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [4] Huang G Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017; 4700– 4708.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [5] Hu J Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018; 7132– 7141.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [6] Wang D Exploring linear relationship in feature map subspace for convnets compression. arXiv preprint arXiv:1803.05729 2018. source
- Not matchedcites [7] Ren S Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems. 2015; 91– 99.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [8] He K Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE transactions on pattern analysis and machine intelligence. 2015; 37(9): 1904– 1916. 26353135 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Even when undertaken correctly by an expert, manual interrogation of ultrasound images is still time-consuming which limits its use as a population-based screening tool.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Introduction
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“The placental volume as early as 11 to 13 weeks’ gestation has long been known to correlate with birth weight at term [39].”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Not checked yetcites [39] Salafia CM Placenta and fetal growth restriction. Clinical obstetrics and gynecology. 2006; 49(2) 236– 256. 16721104 source
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Placental insufficiency is associated with adverse pregnancy outcomes like fetal growth restriction (FGR), caused by insufficient transport of nutrients and oxygen through the placenta [38].”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Not checked yetcites [38] Salavati N The possible role of placental morphometry in the detection of fetal growth restriction. Frontiers in physiology. 2019; 9: 1884. 30670983 PMC6331677 source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“In medical imaging, deep learning is increasingly used for tasks such as automated lesion detection, segmentation and registration to assist clinicians in disease diagnosis and surgical planning.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Introduction
What the sources say
- Not checked yetcites [9] Namburete AI Fully automated alignment of 3d fetal brain ultrasound to a canonical reference space using multi-task learning. Medical image analysis. Elsevier. 2018; 46: 1– 14. 29499436 source
- Not matchedcites [10] Liu S Deep learning in medical ultrasound analysis: a review. Engineering. 2019.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [11] Al-Bander B Improving fetal head contour detection by object localisation with deep learning. In: Annual Conference on Medical Image Understanding and Analysis. Springer. 2019; 142– 150.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [12] Sa R Intervertebral disc detection in x-ray images using faster r-cnn. In: 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE. 2017; 564– 567. 29059935 source
- Not matchedcites [13] Li Q Medical image classification with convolutional neural network. In: 13th international conference on control automation robotics & vision (ICARCV). IEEE. 2014; 844– 848.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [14] Miao S Real-time 2d/3d registration via cnn regression. In: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). IEEE. 2016; 1430– 1434.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [15] Diniz JO Spinal cord detection in planning CT for radiotherapy through adaptive template matching, IMSLIC and convolutional neural networks. Computer methods and programs in biomedicine. 2019; 170: 53– 67. 30712604 source
- Not checked yetcites [16] Diniz PH Detection of white matter lesion regions in MRI using SLIC0 and convolutional neural network. Computer methods and programs in biomedicine. 2018; 167: 49– 63. 29706405 source
- Not checked yetcites [17] Diniz JO Detection of mass regions in mammograms by bilateral analysis adapted to breast density using similarity indexes and convolutional neural networks. Computer methods and programs in biomedicine. 2018; 156: 191– 207. 29428071 source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Deep learning techniques have the potential to create new screening tools, predict diseases, improve diagnostic accuracy and accelerate clinical tasks, whilst also reducing costs and human error [9–17].”
§ Deep Learning strategies for Ultrasound in Pregnancy > Introduction
What the sources say
- Not checked yetcites [9] Namburete AI Fully automated alignment of 3d fetal brain ultrasound to a canonical reference space using multi-task learning. Medical image analysis. Elsevier. 2018; 46: 1– 14. 29499436 source
- Not matchedcites [10] Liu S Deep learning in medical ultrasound analysis: a review. Engineering. 2019.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [11] Al-Bander B Improving fetal head contour detection by object localisation with deep learning. In: Annual Conference on Medical Image Understanding and Analysis. Springer. 2019; 142– 150.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [12] Sa R Intervertebral disc detection in x-ray images using faster r-cnn. In: 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE. 2017; 564– 567. 29059935 source
- Not matchedcites [13] Li Q Medical image classification with convolutional neural network. In: 13th international conference on control automation robotics & vision (ICARCV). IEEE. 2014; 844– 848.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [14] Miao S Real-time 2d/3d registration via cnn regression. In: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). IEEE. 2016; 1430– 1434.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [15] Diniz JO Spinal cord detection in planning CT for radiotherapy through adaptive template matching, IMSLIC and convolutional neural networks. Computer methods and programs in biomedicine. 2019; 170: 53– 67. 30712604 source
- Not checked yetcites [16] Diniz PH Detection of white matter lesion regions in MRI using SLIC0 and convolutional neural network. Computer methods and programs in biomedicine. 2018; 167: 49– 63. 29706405 source
- Not checked yetcites [17] Diniz JO Detection of mass regions in mammograms by bilateral analysis adapted to breast density using similarity indexes and convolutional neural networks. Computer methods and programs in biomedicine. 2018; 156: 191– 207. 29428071 source
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
In the paper
“In addition, the placental volumes segmented by OxNNet were correlated with birth weight to predict small-for-gestational-age babies, showing almost identical clinical conclusions to those produced by the validated semi-automated tools.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Not checked yetcites [29] Looney P Fully automated, real-time 3d ultrasound segmentation to estimate first trimester placental volume using deep learning. JCI insight. 2018; 3(11). PMC6124436 29875312 source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In addition, models trained on one dataset might fail on another generated by a different manufacturer’s machine.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Discussion
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Lack of sufficient high-quality data and practical clinical solutions are some of the key barriers.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Discussion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The performance of deep learning methods usually depends on the number of samples.
- Rests on an assumption: Full automation of placental segmentation is challenging due to heterogeneity of ultrasound images, indistinct boundaries and the placenta’s highly variable shape and position.
- Rests on an assumption: Manual placental segmentation is relatively accurate but extremely time-consuming.
- Rests on an assumption: Semi-automated image analysis tools are faster but still time-consuming and typically require the operator to manually identify the placenta.
- Rests on an assumption: CNNs need large amounts of data to automatically find the right features.
- Rests on an assumption: Processing large datasets is computationally costly and takes time.
- Rests on an assumption: Ultrasound scans are typically useful only in the early stages of pregnancy because a limited field of view only permits the complete capture of small placentas.
In the paper
“A 4-fold cross-validation was performed and the proposed method reportedly achieved a mean Dice coefficient of 0.8686.3 (±0.05) for the test folds.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Not matchedcites [30] Oguz B Combining deep learning and multi-atlas label fusion for automated placenta segmentation from 3dus. In: Data Driven Treatment Response Assessment and Preterm, Perinatal, and Pediatric Image Analysis. Springer. 2018; 138– 148.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The quote only partly states this claim.
- Not matched
In the paper
“The results achieved a mean Dice coefficient of 0.75±0.12 for the placenta and 0.70±0.14 for its vessels on images that had been pre-processed by down-sampling and cropping.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Not matchedcites [33] Torrents-Barrena J Automatic segmentation of the placenta and its peripheral vasculature in volumetric ultrasound for ttts fetal surgery. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). IEEE. 2019; 772– 775.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The quote only partly states this claim.
- Not matched
In the paper
“The results of the DeepMedic CNN were compared against semi-automated segmentation, achieving median Dice Similarity Coefficient (DSC) of 0.73 (first Quartile, third Quartile: 0.66, 0.76) and median Hausdorff distance of 27 mm (first Quartile, third Quartile:18 mm, 36 mm).”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Not checked yetcites [28] Looney P Automatic 3d ultrasound segmentation of the first trimester placenta using deep learning. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). IEEE. 2017; 279– 282. source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“An accurate and fully automated technique for placental segmentation that provided measurements such as placental volume and vascularity would permit population-based screening for pregnancies at risk of adverse outcomes.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Very few papers translate the simple application of algorithms to a broader, practical solution that could be widely used in clinical practice.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Discussion
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
In the paper
“The OxNNet FCNN obtained placental segmentation with state-of-the-art accuracy (median DSC of 0.84 (Interquartile range 0.09).”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Not checked yetcites [29] Looney P Fully automated, real-time 3d ultrasound segmentation to estimate first trimester placental volume using deep learning. JCI insight. 2018; 3(11). PMC6124436 29875312 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Reliable placental segmentation is the basis of further measurement and analysis which has the ability to predict adverse outcomes.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“In both cases, the acoustic shadow detection scheme was proven to be able to improve segmentation accuracy.”
§ Deep Learning strategies for Ultrasound in Pregnancy > Deep Learning Applications in Pregnancy Ultrasound > Placental Segmentation
What the sources say
- Not checked yetcites [32] Hu R Rohling. Automated placenta segmentation with a convolutional neural network weighted by acoustic shadow detection. In: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE. 2019; 6718– 6723. 31947383 source
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The quote only partly states this claim.
The paper relies on this without support.
The performance of deep learning methods usually depends on the number of samples.
“The performance of deep learning methods usually depends on the number of samples.”
The paper relies on this without support.
Full automation of placental segmentation is challenging due to heterogeneity of ultrasound images, indistinct boundaries and the placenta’s highly variable shape and position.
“However, full automation of this is a challenging task due to the heterogeneity of ultrasound images, indistinct boundaries and them placenta’s highly variable shape and position.”
The paper relies on this without support.
Manual placental segmentation is relatively accurate but extremely time-consuming.
“Manual segmentation is relatively accurate but is extremely time-consuming.”
The paper relies on this without support.
Semi-automated image analysis tools are faster but still time-consuming and typically require the operator to manually identify the placenta.
“Semi-automated image analysis tools are faster but are still time consuming and typically require the operator to manually identify the placenta within the image.”
The paper relies on this without support.
CNNs need large amounts of data to automatically find the right features.
“CNNs have some disadvantages however; they need large amounts of data in order to automatically find the right features and processing large datasets is both computationally costly and takes time.”
The paper relies on this without support.
Processing large datasets is computationally costly and takes time.
“CNNs have some disadvantages however; they need large amounts of data in order to automatically find the right features and processing large datasets is both computationally costly and takes time.”
The paper relies on this without support.
Ultrasound scans are typically useful only in the early stages of pregnancy because a limited field of view only permits the complete capture of small placentas.
“Ultrasound scans are typically useful only in the early stages of pregnancy because a limited field of view only permits the complete capture of small placentas.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In particular, the subspecialty of obstetrics is profoundly dependent on the diagnostic imaging tool of US because of its non-invasive, cost-effective, real-time, and low-radiation characteristics for fetal scanning [3,4].”
From Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology (2023) · cites this paper as [4]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“However, US imaging has limitations regarding its comparability and reproducibility.”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2389824 · Cited by 11,971
Radiomics: extracting more information from medical images using advanced feature analysis
Lambin, P., Rios-Velazquez, E., Leijenaar, R., Carvalho, S., van Stiphout, R. G. P. M., Granton, P., Zegers, C. M. L., Gillies, R., Boellard, R., Dekker, A., et al. (2012) · European Journal of Cancer · doi:10.1016/j.ejca.2011.11.036 · Cited by 6,084
Random Walks for Image Segmentation
Grady, L. (2006) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2006.233 · Cited by 2,624
Ultrasound image segmentation: a survey
Noble, J. A., & Boukerroui, D. (2006) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2006.877092 · Cited by 1,157
Medical image classification with convolutional neural network
Li, Q., Cai, W., Wang, X., Zhou, Y., Feng, D. D., & Chen, M. (2014) · 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV) · doi:10.1109/icarcv.2014.7064414 · Cited by 880
Deep Learning in Medical Ultrasound Analysis: A Review
Liu, S., Wang, Y., Yang, X., Lei, B., Liu, L., Li, S. X., Ni, D., & Wang, T. (2019) · Engineering · doi:10.1016/j.eng.2018.11.020 · Cited by 798
Gauss and the Invention of Least Squares
Stigler, S. M. (1981) · The Annals of Statistics · doi:10.1214/aos/1176345451 · Cited by 418
DeepMedic for Brain Tumor Segmentation
Kamnitsas, K., Ferrante, E., Parisot, S., Ledig, C., Nori, A. V., Criminisi, A., Rueckert, D., & Glocker, B. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-55524-9_14 · Cited by 346
Machine learning for medical ultrasound: status, methods, and future opportunities
Brattain, L. J., Telfer, B. A., Dhyani, M., Grajo, J. R., & Samir, A. E. (2018) · Abdominal Radiology · doi:10.1007/s00261-018-1517-0 · Cited by 262
Placenta and Fetal Growth Restriction
SALAFIA, C. M., CHARLES, A. K., & MAAS, E. M. (2006) · Clinical Obstetrics and Gynecology · doi:10.1097/00003081-200606000-00007 · Cited by 235
Intra‐ and interobserver variability in fetal ultrasound measurements
Sarris, I., Ioannou, C., Chamberlain, P., Ohuma, E., Roseman, F., Hoch, L., Altman, D. G., Papageorghiou, A. T., & for the International Fetal and Newborn Growth Consortium for the 21 Century (INTERGROWTH‐21) (2012) · Ultrasound in Obstetrics & Gynecology · doi:10.1002/uog.10082 · Cited by 195
Rueda, S., Fathima, S., Knight, C. L., Yaqub, M. K., Papageorghiou, A. T., Rahmatullah, B., Foi, A., Maggioni, M., Pepe, A., Tohka, J., et al. (2013) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2013.2276943 · Cited by 177
Reddy, U. M., Filly, R. A., & Copel, J. A. (2008) · Obstetrics and Gynecology · doi:10.1097/01.aog.0000318871.95090.d9 · Cited by 152
Looney, P., Stevenson, G. N., Nicolaides, K. H., Plasencia, W., Molloholli, M., Natsis, S., & Collins, S. L. (2018) · JCI Insight · doi:10.1172/jci.insight.120178 · Cited by 112 · cited 2×
“A transfer learning technique was applied to initialize the model using parameters optimized by a single-class model [29] trained on 1200 labelled placental volumes.”
BackgroundMethodSelf-citationThe Possible Role of Placental Morphometry in the Detection of Fetal Growth Restriction
Salavati, N., Smies, M., Ganzevoort, W., CHARLES, A. K., Erwich, J. J., Plösch, T., & Gordijn, S. J. (2019) · Frontiers in Physiology · doi:10.3389/fphys.2018.01884 · Cited by 109
Real-time 2D/3D registration via CNN regression
Miao, S., Wang, Z. J., Zheng, Y., & Liao, R. (2016) · 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2016.7493536 · Cited by 101
Namburete, A. I. L., Xie, W., Yaqub, M., Zisserman, A., & Noble, J. A. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.02.006 · Cited by 95
Intervertebral disc detection in X-ray images using faster R-CNN
Sa, R., Owens, W., Wiegand, R., Studin, M., Capoferri, D., Barooha, K., Greaux, A., Rattray, R., Hutton, A., Cintineo, J., et al. (2017) · 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2017.8036887 · Cited by 90
Salomon, L. J., Winer, N., Bernard, J. P., & Ville, Y. (2008) · Prenatal Diagnosis · doi:10.1002/pd.2016 · Cited by 85
Bandeira Diniz, J. O., Bandeira Diniz, P. H., Azevedo Valente, T. L., Corrêa Silva, A., de Paiva, A. C., & Gattass, M. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.01.007 · Cited by 74
Automatic 3D ultrasound segmentation of the first trimester placenta using deep learning
Looney, P., Stevenson, G. N., Nicolaides, K. H., Plasencia, W., Molloholli, M., Natsis, S., & Collins, S. L. (2017) · 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) · doi:10.1109/isbi.2017.7950519 · Cited by 47
Self-citationImproving Fetal Head Contour Detection by Object Localisation with Deep Learning
Al-Bander, B., Alzahrani, T., Alzahrani, S., Williams, B. M., & Zheng, Y. (2020) · Communications in Computer and Information Science · doi:10.1007/978-3-030-39343-4_12 · Cited by 44
Torrents-Barrena, J., Monill, N., Piella, G., Gratacós, E., Eixarch, E., Ceresa, M., & González Ballester, M. A. (2021) · Academic Radiology · doi:10.1016/j.acra.2019.11.006 · Cited by 42
Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression
Wang, D., Zhou, L., Zhang, X., Bai, X., & Zhou, J. (2018) · arXiv · doi:10.48550/arxiv.1803.05729 · Cited by 42
Stevenson, G. N., Collins, S. L., Welsh, A. W., Impey, L. W., & Noble, J. A. (2015) · Radiology · doi:10.1148/radiol.14132363 · Cited by 38
Self-citationAutomatic Segmentation of Human Placenta Images With U-Net
Han, M., Bao, Y., Sun, Z., Wen, S., Xia, L., Zhao, J., Du, J., & Yan, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2958133 · Cited by 37
Detection of white matter lesion regions in MRI using SLIC0 and convolutional neural network
Diniz, P. H. B., Valente, T. L. A., Diniz, J. O. B., Silva, A. C., Gattass, M., Ventura, N., Muniz, B. C., & Gasparetto, E. L. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.04.011 · Cited by 34
Self-citationDiniz, J. O. B., Diniz, P. H. B., Valente, T. L. A., Silva, A. C., & Paiva, A. C. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.01.005 · Cited by 34
Self-citationVolume and vascularity: Using ultrasound to unlock the secrets of the first trimester placenta
Mathewlynn, S., & Collins, S. L. (2019) · Placenta · doi:10.1016/j.placenta.2019.06.379 · Cited by 30
Self-citationHu, R., Singla, R., Yan, R., Mayer, C., & Rohling, R. N. (2019) · 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2019.8857448 · Cited by 27
Towards Whole Placenta Segmentation at Late Gestation Using Multi-view Ultrasound Images
Zimmer, V. A., Gomez, A., Skelton, E., Toussaint, N., Zhang, T., Khanal, B., Wright, R., Noh, Y., Ho, A., Matthew, J., et al. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-32254-0_70 · Cited by 20
Roy‐Lacroix, M., Moretti, F., Ferraro, Z. M., et al. (2017) · Journal of Perinatology · doi:10.1038/jp.2016.212 · Cited by 18
Convolutional Neural Networks for Automated Fetal Cardiac Assessment using 4D B-Mode Ultrasound
Philip, M. E., Sowmya, A., Avnet, H., Ferreira, A., Stevenson, G., & Welsh, A. (2019) · 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) · doi:10.1109/isbi.2019.8759377 · Cited by 18
Weakly Supervised Learning of Placental Ultrasound Images with Residual Networks
Qi, H., Collins, S., & Noble, A. (2017) · Communications in computer and information science · doi:10.1007/978-3-319-60964-5_9 · Cited by 17
Self-citationCombining Deep Learning and Multi-atlas Label Fusion for Automated Placenta Segmentation from 3DUS
Oguz, B. U., Wang, J., Yushkevich, N., Pouch, A., Gee, J., Yushkevich, P. A., Schwartz, N., & Oguz, I. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00807-9_14 · Cited by 13
Torrents-Barrena, J., Piella, G., Masoller, N., Gratacos, E., Eixarch, E., Ceresa, M., & Ballester, M. A. G. (2019) · 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) · doi:10.1109/isbi.2019.8759296 · Cited by 9
Yin, Y., Looney, P., & Collins, S. L. (2020) · Medical Imaging 2020: Computer-Aided Diagnosis · doi:10.1117/12.2549349 · Cited by 4
Self-citation
Research works printed but not linked: 1
- Simonyan K, Zisserman A. Very deep convolutional networks for largescale image recognition. arXiv preprint arXiv. 2014;1409.1556.
Cited by
Sorted by citations
Jost, E., Kosian, P., Jimenez Cruz, J., Albarqouni, S., Gembruch, U., Strizek, B., & Recker, F. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12216833 · Cited by 44
“In particular, the subspecialty of obstetrics is profoundly dependent on the diagnostic imaging tool of US because of its non-invasive, cost-effective, real-time, and low-radiation characteristics for fetal scanning [3,4].”
Background
Metadata
- Authors
- Diniz, P. H. B., Yin, Y., & Collins, S.
- Affiliations
- University of Oxford (GB)
- John Radcliffe Hospital (GB)
- Venue
- EMJ Reproductive Health
- Publisher
- European Medical Group
- Published
- 2020-08-25
- Volume
- 6
- Issue
- 1
- Pages
- 73-80
- ISSN
- 2059-450X (ISSN-L)
- PMC
- PMC7590498
- OpenAlex
- W4210288949
- Semantic Scholar
- 5278f8fee9e4865c472608d1e564a391e74b09b3
- Cited by
- 32
- References
- 43
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 9 · 2023: 10 · 2022: 4 · 2021: 4
- FWCI
- 1.75
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by-nc
- Locations
- EMJ Reproductive Health (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- PubMed
- Funders
- National Institutes of Health
- National Institute of Child Health and Human Development (UO1-HD087209)
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (UO1 HD 087209, U01HD087209)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- deep learning, prenatal ultrasound, 3D ultrasound, placental volume, first trimester, pregnancy complications, automated image interpretation, medical image segmentation, prenatal screening
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
