CoChat
Sign Up
Cited by 237Medical Image Segmentation TechniquesAdvanced Neural Network ApplicationsBrain Tumor Detection and Classification

The DOI matches its Crossref record; 103 of the 103 references it cites were found in a registry or an index.

Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities

Open access
Ghafoorian, Mohsen, Karssemeijer, Nico, Heskes, Tom, van Uden, Inge W. M., Sanchez, Clara I., Litjens, Geert, de Leeuw, Frank-Erik, van Ginneken, Bram, Marchiori, Elena, Platel, Bram·2017·Scientific Reports
DOI 10.1038/s41598-017-05300-5PMC PMC5505987
Open this paper in CoChat — free accountOpen PDF

Abstract

The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).

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 · 10.1038/s41598-017-05300-5

Cites

103 of 103 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 A pattern is observable in WMHs occurrence probability map.
Figure 1 A pattern is observable in WMHs occurrence probability map.CC BY · PubMed Central
Figure 2 An example of negative (top row) and positive (bottom row) samples in three scales (from left to right) 32 × 32, 64 × 64 and 128 × 128 on the FLAIR image. The two larger scales are down sampled to 32 × 32.
Figure 2 An example of negative (top row) and positive (bottom row) samples in three scales (from left to right) 32 × 32, 64 × 64 and 128 × 128 on the FLAIR image. The two larger scales are down sampled to 32 × 32.CC BY · PubMed Central
Figure 3 Patch preparation process and different proposed CNN architectures. The links between set of convolutional layers represent a weight sharing policy among the streams.
Figure 3 Patch preparation process and different proposed CNN architectures. The links between set of convolutional layers represent a weight sharing policy among the streams.CC BY · PubMed Central
Figure 4 Integration of spatial location information fills the gap between performance of a normal CNN and human observer. (a) An ROC comparison of different CNN methods, a conventional segmentation method and independent human observer, considering observer 1 as the reference standard. (b) A comparison of different methods on Dice score as a function of binary masking threshold. The light shades around the curves indicate 95% confidence intervals with bootstrapping on patients.
Figure 4 Integration of spatial location information fills the gap between performance of a normal CNN and human observer. (a) An ROC comparison of different CNN methods, a conventional segmentation method and independent human observer, considering observer 1 as the reference standard. (b) A comparison of different methods on Dice score as a function of binary masking threshold. The light shades around the curves indicate 95% confidence intervals with bootstrapping on patients.CC BY · PubMed Central
Figure 5 Test Dice as a function of training set size.
Figure 5 Test Dice as a function of training set size.CC BY · PubMed Central
Figure 6 Two sample cases of segmentation improvement by adding location information to the network. (a) FLAIR images without annotations. (b) Segmentation by human observer 1. (c) Segmentation by SS method. (d) Segmentation by MSWS + Loc method.
Figure 6 Two sample cases of segmentation improvement by adding location information to the network. (a) FLAIR images without annotations. (b) Segmentation by human observer 1. (c) Segmentation by SS method. (d) Segmentation by MSWS + Loc method.CC BY · PubMed Central
Figure 7 Gliosis around the lacunes is a prevalent type of false positive segmentation. (a) FLAIR images without annotations. (b) Segmentation by human observer 1. (c) Segmentation by human observer 2. (d) Segmentation by MSWS + Loc method.
Figure 7 Gliosis around the lacunes is a prevalent type of false positive segmentation. (a) FLAIR images without annotations. (b) Segmentation by human observer 1. (c) Segmentation by human observer 2. (d) Segmentation by MSWS + Loc method.CC BY · PubMed Central
Figure 8 A sample case with a small lesion missed by the two human observers. (a) FLAIR image without annotations. (b) Segmentation by human observer 1. (c) Segmentation by human observer 2. (d) Segmentation by MSWS + Loc method.
Figure 8 A sample case with a small lesion missed by the two human observers. (a) FLAIR image without annotations. (b) Segmentation by human observer 1. (c) Segmentation by human observer 2. (d) Segmentation by MSWS + Loc method.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 98 references

Research works printed but not linked: 3

  1. Ghafoorian, M. et al. Transfer learning for domain adaptation in mri: Application in brain lesion segmentation. arXiv preprint arXiv:1702.07841 (2017). · arXiv
  2. Chen, H., Dou, Q., Yu, L. & Heng, P.-A. Voxresnet: Deep voxelwise residual networks for volumetric brain segmentation. arXiv preprint arXiv:1608.05895 (2016). · arXiv
  3. Maas, A. L., Hannun, A. Y. & Ng, A. Y. Rectifier nonlinearities improve neural network acoustic models. In Proc. ICML, vol. 30 (2013).

Cited by

Sorted by citations

See all 237

Related

Metadata

Authors
Ghafoorian, M., Karssemeijer, N., Heskes, T., van Uden, I. W. M., Sanchez, C. I., Litjens, G., de Leeuw, F.-E., van Ginneken, B., Marchiori, E., & Platel, B.
Affiliations
  • Radboud University Nijmegen (NL)
  • Radboud University Medical Center (NL)
Corresponding author
Ghafoorian, Mohsen
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2017-07-11
Volume
7
Issue
1
Pages
5110-5110
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-017-05300-5
PMC
PMC5505987
OpenAlex
W2532750509
Cited by
236
References
98
Citations by year
2026: 7 · 2025: 18 · 2024: 18 · 2023: 18 · 2022: 30 · 2021: 41 · 2020: 25 · 2019: 32 · 2018: 33 · 2017: 12
FWCI
11.58
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Radboud Repository (Radboud University) (submittedVersion)
  • Radboud Repository (Radboud University) (submittedVersion, other-oa)
Funders
Nederlandse Organisatie voor Wetenschappelijk Onderzoek (016‐126‐351)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Brain Tumor Detection and Classification
Keywords
white matter hyperintensities, segmentation, brain MRI, deep convolutional neural networks, medical image analysis
MeSH terms
Aged, Aged, 80 and over, Decision Making, Female, Humans, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Male, Middle Aged, Neural Networks, Computer, Neuroimaging, White Matter

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