Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
R2U++: a multiscale recurrent residual U-Net with dense skip connections for medical image segmentation
Department of Electrical and Computer Engineering, COMSATS University Islamabad, Abbottabad Campus, Abbottabad, Pakistan.
Umeå University, Faculty of Medicine, Department of Radiation Sciences, Radiation Physics. Department of Electrical and Computer Engineering, COMSATS University Islamabad, Abbottabad Campus, Abbottabad, Pakistan.ORCID iD: 0000-0003-3058-5794
Umeå University, Faculty of Medicine, Department of Radiation Sciences, Radiation Physics.ORCID iD: 0000-0003-4288-1208
Department of Electrical and Computer Engineering, COMSATS University Islamabad, Abbottabad Campus, Abbottabad, Pakistan.
2022 (English)In: Neural Computing & Applications, ISSN 0941-0643, E-ISSN 1433-3058, Vol. 34, no 20, p. 17723-17739Article in journal (Refereed) Published
Abstract [en]

U-Net is a widely adopted neural network in the domain of medical image segmentation. Despite its quick embracement by the medical imaging community, its performance suffers on complicated datasets. The problem can be ascribed to its simple feature extracting blocks: encoder/decoder, and the semantic gap between encoder and decoder. Variants of U-Net (such as R2U-Net) have been proposed to address the problem of simple feature extracting blocks by making the network deeper, but it does not deal with the semantic gap problem. On the other hand, another variant UNET++ deals with the semantic gap problem by introducing dense skip connections but has simple feature extraction blocks. To overcome these issues, we propose a new U-Net based medical image segmentation architecture R2U++. In the proposed architecture, the adapted changes from vanilla U-Net are: (1) the plain convolutional backbone is replaced by a deeper recurrent residual convolution block. The increased field of view with these blocks aids in extracting crucial features for segmentation which is proven by improvement in the overall performance of the network. (2) The semantic gap between encoder and decoder is reduced by dense skip pathways. These pathways accumulate features coming from multiple scales and apply concatenation accordingly. The modified architecture has embedded multi-depth models, and an ensemble of outputs taken from varying depths improves the performance on foreground objects appearing at various scales in the images. The performance of R2U++ is evaluated on four distinct medical imaging modalities: electron microscopy, X-rays, fundus, and computed tomography. The average gain achieved in IoU score is 1.5 ± 0.37% and in dice score is 0.9 ± 0.33% over UNET++, whereas, 4.21 ± 2.72 in IoU and 3.47 ± 1.89 in dice score over R2U-Net across different medical imaging segmentation datasets.

Place, publisher, year, edition, pages
Springer Nature, 2022. Vol. 34, no 20, p. 17723-17739
Keywords [en]
Convolutional neural networks, Medical imaging, R2U-Net, Semantic segmentation, U-Net, U-Net++
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:umu:diva-203248DOI: 10.1007/s00521-022-07419-7ISI: 000805719500003PubMedID: 35694048Scopus ID: 2-s2.0-85131336212OAI: oai:DiVA.org:umu-203248DiVA, id: diva2:1727814
Available from: 2023-01-17 Created: 2023-01-17 Last updated: 2023-05-04Bibliographically approved

Open Access in DiVA

fulltext(2853 kB)167 downloads
File information
File name FULLTEXT01.pdfFile size 2853 kBChecksum SHA-512
6af9a478b3d056bf76f4dc5b4e44d3e4bdf0dc13dd5f6d7d89361ccaf8db24cbfd4da4d41031f64eb199da42eabe73125ad6fc9f2983400ee65d2e11371a6f2f
Type fulltextMimetype application/pdf

Other links

Publisher's full textPubMedScopus

Authority records

Ali, HazratGrönlund, Christer

Search in DiVA

By author/editor
Ali, HazratGrönlund, Christer
By organisation
Radiation Physics
In the same journal
Neural Computing & Applications
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 168 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 540 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf