The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Automated summarisation of SDOCT volumes using deep learning: Transfer learning vs de novo trained networks
Open accessPublished version of a preprint
Abstract
Spectral-domain optical coherence tomography (SDOCT) is a non-invasive imaging modality that generates high-resolution volumetric images. This modality finds widespread usage in ophthalmology for the diagnosis and management of various ocular conditions. The volumes generated can contain 200 or more B-scans. Manual inspection of such large quantity of scans is time consuming and error prone in most clinical settings. Here, we present a method for the generation of visual summaries of SDOCT volumes, wherein a small set of B-scans that highlight the most clinically relevant features in a volume are extracted. The method was trained and evaluated on data acquired from age-related macular degeneration patients, and "relevance" was defined as the presence of visibly discernible structural abnormalities. The summarisation system consists of a detection module, where relevant B-scans are extracted from the volume, and a set of rules that determines which B-scans are included in the visual summary. Two deep learning approaches are presented and compared for the classification of B-scans-transfer learning and de novo learning. Both approaches performed comparably with AUCs of 0.97 and 0.96, respectively, obtained on an independent test set. The de novo network, however, was 98% smaller than the transfer learning approach, and had a run-time that was also significantly shorter.
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.
Integrity signals
Registry
Cites
Statistics
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.
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
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Quicksilver: Fast predictive image registration – A deep learning approach
Yang, X., Kwitt, R., Styner, M., & Niethammer, M. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2017.07.008 · Cited by 630
Flagged first, then by citations
Research works printed but not linked: 24
- T Liu, 2003, A novel video key-frame-extraction algorithm based on perceived motion energy model, IEEE Transactions on Circuits and Systems for Video Technology, 13, 1006, 10.1109/TCSVT.2003.816521 · DOI
- Fauvet B, Bouthemy P, Gros P, Spindler F. A geometrical key-frame selection method exploiting dominant motion estimation in video. International Conference on Image and Video Retrieval. 2004; p. 419–427. · DOI
- J Nam, 2005, Detection of gradual transitions in video sequences using B-spline interpolation, IEEE Transactions on Multimedia, 7, 667, 10.1109/TMM.2005.843362 · DOI
- Huang P, Hilton A, Starck J. Automatic 3D video summarization: key frame extraction from self-similarity. The Fourth International Symposium on 3D Data Processing, Visualization and Transmission (3DPVT’08). 2008; p. 71–78.
- C Cotsaces, 2006, Video shot detection and condensed representation: a review, IEEE Signal Processing Magazine, 23, 28, 10.1109/MSP.2006.1621446 · DOI
- D Gibson, 2004, A wavelet-based region of interest encoder for the compression of angiogram video sequences, IEEE Transactions on Information Technology in Biomedicine, 8, 103, 10.1109/TITB.2004.826722 · DOI
- Syeda-Mahmood T, Beymer D, Wang F, Mahmood A, Lundstrom RJ, Shafee N, et al. Automatic selection of keyframes from angiogram videos. Proceedings—International Conference on Pattern Recognition. 2010; p. 4008–4011. · DOI
- D Huang, 1991, Optical coherence tomography, Science, 254, 1178, 10.1126/science.1957169 · DOI
- U Chakravarthy, 2016, Automated identification of lesion activity in neovascular age-related macular degeneration, Ophthalmology, 123, 1731, 10.1016/j.ophtha.2016.04.005 · DOI
- S Farsiu, 2013, Quantitative classification of eyes with and without Intermediate age-related macular degeneration using optical coherence tomography, Ophthalmology, 1
- Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICRL); 2015. p. 1–14. Available from: http://arxiv.org/abs/1409.1556. · arXiv
- Jégou S, Drozdzal M, Vazquez D, Romero A, Bengio Y. The one hundred layers tiramisu: fully convolutional DenseNets for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops; 2016. p. 1175–1183. Available from: http://arxiv.org/abs/1611.09326. · arXiv
- Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. arXiv 160600915v2. 2016; p. 1–14.
- G Litjens, 2017, A survey on deep learning in medical image analysis, Medical Image Analysis, 42, 60, 10.1016/j.media.2017.07.005 · DOI · Paper page
- DS Kermany, 2018, Identifying medical diagnoses and treatable diseases by image-based deep learning, Cell, 172, 1122, 10.1016/j.cell.2018.02.010 · DOI · Paper page
- SK Devalla, 2018, A deep learning approach to digitally stain optical coherence tomography images of the optic nerve head, Investigative Opthalmology & Visual Science, 59, 63, 10.1167/iovs.17-22617 · DOI
- Shah A, Abramoff MD, Wu X. Simultaneous multiple surface segmentation using deep learning. arXiv preprint 170507142v1. 2017. · DOI
- He Y, Carass A, Jedynak BM, Solomon SD, Saidha S, Calabresi PA, et al. Topology guaranteed segmentation of the human retina from OCT using convolutional neural networks. arXiv preprint 180305120v1. 2018.
- BD de Vos, 2017, End-to-end unsupervised deformable image network, Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 204, 10.1007/978-3-319-67558-9_24 · DOI
- Dwarikanath M, Antony BJ, Sedai S, Garnavi R. Deformable medical image registration using generative adversarial networks. In: IEEE International Symposium on Biomedical Imaging; 2018. p. 1449–1453.
- O Russakovsky, 2015, ImageNet Large Scale Visual Recognition Challenge, International Journal of Computer Vision, 115, 211, 10.1007/s11263-015-0816-y · DOI · Paper page
- Maetschke S, Tennakoon R, Vecchiola C, Garnavi R. nuts-flow/ml: data pre-processing for deep learning. arXiv preprint 170806046v2. 2018.
- N Otsu, 1979, A threshold selection method from gray-level histograms, IEEE Transactions on Systems, Man and Cybernetics, 9, 62, 10.1109/TSMC.1979.4310076 · DOI
- Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization. In: IEEE Conference on Computer Vision and Pattern Recognition; 2015. p. 2921–2929. Available from: http://arxiv.org/abs/1512.04150. · arXiv
Metadata
- Authors
- Antony, B. J., Maetschke, S., & Garnavi, R.
- Affiliations
- IBM Research - Australia (AU)
- Corresponding author
- Antony, Bhavna Josephine
- Maetschke, Stefan
- Garnavi, Rahil
- Venue
- PLOS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2019-05-13
- Volume
- 14
- Issue
- 5
- Pages
- e0203726
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC6513047
- OpenAlex
- W2950825660
- Cited by
- 8
- References
- 5
- Citations by year
- 2024: 2 · 2023: 1 · 2022: 2 · 2021: 3
- FWCI
- 0.83
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS ONE (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Keywords
- spectral-domain optical coherence tomography, transfer learning, age-related macular degeneration, ocular imaging, automated image analysis
- MeSH terms
- Deep Learning, Algorithms, Humans, Image Processing, Computer-Assisted, Reproducibility of Results, Neural Networks, Computer, Area Under Curve, Tomography, Optical Coherence
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
