CoChat
Sign Up
Cited by 416Medical Image Segmentation TechniquesArtificial Intelligence in Healthcare and EducationAdvanced Neural Network Applications

The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.

SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound

Open access
Baumgartner, Christian F., Kamnitsas, Konstantinos, Matthew, Jacqueline, Fletcher, Tara P., Smith, Sandra, Koch, Lisa M., Kainz, Bernhard, Rueckert, Daniel·2017·IEEE Transactions on Medical Imaging
DOI 10.1109/tmi.2017.2712367PMC PMC6051487
Open this paper in CoChat — free account

Abstract

Identifying and interpreting fetal standard scan planes during 2-D ultrasound mid-pregnancy examinations are highly complex tasks, which require years of training. Apart from guiding the probe to the correct location, it can be equally difficult for a non-expert to identify relevant structures within the image. Automatic image processing can provide tools to help experienced as well as inexperienced operators with these tasks. In this paper, we propose a novel method based on convolutional neural networks, which can automatically detect 13 fetal standard views in freehand 2-D ultrasound data as well as provide a localization of the fetal structures via a bounding box. An important contribution is that the network learns to localize the target anatomy using weak supervision based on image-level labels only. The network architecture is designed to operate in real-time while providing optimal output for the localization task. We present results for real-time annotation, retrospective frame retrieval from saved videos, and localization on a very large and challenging dataset consisting of images and video recordings of full clinical anomaly screenings. We found that the proposed method achieved an average F1-score of 0.798 in a realistic classification experiment modeling real-time detection, and obtained a 90.09% accuracy for retrospective frame retrieval. Moreover, an accuracy of 77.8% was achieved on the localization task.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tmi.2017.2712367

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1. Overview of proposed SonoNet: (a) 2D fetal ultrasound data can be processed in real-time through our proposed convolutional neural network to determine if the current frame contains one of 13 fetal standard views (here the 4 chamber view (4CH) is shown); (b) if a standard view was detected, its location can be determined through a backward pass through the network.
Fig. 1. Overview of proposed SonoNet: (a) 2D fetal ultrasound data can be processed in real-time through our proposed convolutional neural network to determine if the current frame contains one of 13 fetal standard views (here the 4 chamber view (4CH) is shown); (b) if a standard view was detected, its location can be determined through a backward pass through the network.CC BY · PubMed Central
Fig. 7. Results of retrospective retrieval for two example subjects. The respective top rows show the ground truth (GT) saved by the sonographer. The bottom rows show the retrieved (RET) frames. For subject (a) all frames have been correctly retrieved. For subject (b) the frames marked with red have been incorrectly retrieved.
Fig. 7. Results of retrospective retrieval for two example subjects. The respective top rows show the ground truth (GT) saved by the sonographer. The bottom rows show the retrieved (RET) frames. For subject (a) all frames have been correctly retrieved. For subject (b) the frames marked with red have been incorrectly retrieved.CC BY · PubMed Central
Fig. 2. Overview of proposed network architectures. Each network consists of a feature extractor, an adaptation layer, and the final classification layer. All convolutional operations are denoted by squared brackets. Specifically, we use the following notation: [kernelsize }{}$\times $ number of kernels / stride]. The factor in front of the squared brackets indicates how many times this operation is repeated. Max-pooling is always performed with a kernel size of 2}{}$\times $2 and a stride of 2 and is denoted by MP. All convolutions are followed by a batch normalisation layer before the ReLu activation, except the SmallNet network, for which no batch normalisation was used.
Fig. 2. Overview of proposed network architectures. Each network consists of a feature extractor, an adaptation layer, and the final classification layer. All convolutional operations are denoted by squared brackets. Specifically, we use the following notation: [kernelsize }{}$\times $ number of kernels / stride]. The factor in front of the squared brackets indicates how many times this operation is repeated. Max-pooling is always performed with a kernel size of 2}{}$\times $2 and a stride of 2 and is denoted by MP. All convolutions are followed by a batch normalisation layer before the ReLu activation, except the SmallNet network, for which no batch normalisation was used.CC BY · PubMed Central
Fig. 3. Examples of saliency maps. Column (a) shows three different input frames, (b) shows the corresponding class score maps }{}${F}_{k}$ obtained in the forward pass of the network, (c) shows saliency maps obtained using the method by Springenberg et al. [32] and (d) shows the saliency maps resulting from our proposed method. Some of the unwanted saliency artefacts are highlighted with arrows in (c).
Fig. 3. Examples of saliency maps. Column (a) shows three different input frames, (b) shows the corresponding class score maps }{}${F}_{k}$ obtained in the forward pass of the network, (c) shows saliency maps obtained using the method by Springenberg et al. [32] and (d) shows the saliency maps resulting from our proposed method. Some of the unwanted saliency artefacts are highlighted with arrows in (c).CC BY · PubMed Central
Fig. 4. Examples of saliency map post-processing for two challenging views: (a) shows two input images, (b) shows the resulting confidence maps for those images, and (c) shows the resulting bounding boxes.
Fig. 4. Examples of saliency map post-processing for two challenging views: (a) shows two input images, (b) shows the resulting confidence maps for those images, and (c) shows the resulting bounding boxes.CC BY · PubMed Central
Fig. 5. Class confusion matrix for SonoNet-32.
Fig. 5. Class confusion matrix for SonoNet-32.CC BY · PubMed Central
Fig. 6. Examples of video frames labelled as background but classified as one of three standard views. The first three columns were randomly sampled from the set of false positives and are in fact correct detections. The last column shows manually selected true failure cases.
Fig. 6. Examples of video frames labelled as background but classified as one of three standard views. The first three columns were randomly sampled from the set of false positives and are in fact correct detections. The last column shows manually selected true failure cases.CC BY · PubMed Central
Fig. 8. Examples of weakly supervised localisation using the SonoNet-32. The first three columns for each view show correct bounding boxes marked in green (}{}$\textit {IOU} \geq \textsf {0.5}$), the respective last columns shows an example of an incorrect localisation marked in red (}{}$\textit {IOU} < \textsf {0.5}$). The ground truth bounding boxes are shown in white.
Fig. 8. Examples of weakly supervised localisation using the SonoNet-32. The first three columns for each view show correct bounding boxes marked in green (}{}$\textit {IOU} \geq \textsf {0.5}$), the respective last columns shows an example of an incorrect localisation marked in red (}{}$\textit {IOU} < \textsf {0.5}$). The ground truth bounding boxes are shown in white.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 34 references

Research works printed but not linked: 2

  1. 2015, Fetal Anomalie Screen Programme Handbook NHS Screening Programmes
  2. springett, 2014, British Isles Network of Congenital Anomaly Registers Congenital Anomaly Statistics 2010 England and Wales

Cited by

Sorted by citations

See all 416

Related

Metadata

Authors
Baumgartner, C. F., Kamnitsas, K., Matthew, J., Fletcher, T. P., Smith, S., Koch, L. M., Kainz, B., & Rueckert, D.
Affiliations
  • Imperial College London (GB)
  • Guy's Hospital (GB)
  • King's College London (GB)
Corresponding author
Baumgartner, Christian F.
ORCID
Venue
IEEE Transactions on Medical Imaging
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2017-11
Volume
36
Issue
11
Pages
2204-2215
ISSN
  • 0278-0062 (ISSN-L)
  • 1558-254X
DOI
10.1109/tmi.2017.2712367
PMC
PMC6051487
OpenAlex
W2735582614
Cited by
416
References
34
Citations by year
2026: 52 · 2025: 48 · 2024: 54 · 2023: 56 · 2022: 55 · 2021: 57 · 2020: 44 · 2019: 28 · 2018: 21 · 2017: 1
FWCI
10.67
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Transactions on Medical Imaging (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Research Portal (King's College London) (submittedVersion, cc-by)
  • Spiral (Imperial College London) (submittedVersion, cc-by)
  • arXiv (Cornell University)
Funders
Wellcome Trust IEH Award (102431)
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
real-time detection, weakly supervised learning, image-level labels, convolutional neural networks, bounding box localization
MeSH terms
Algorithms, Female, Humans, Image Processing, Computer-Assisted, Pregnancy, Video Recording, Ultrasonography, Prenatal, Neural Networks, Computer

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.

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