File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Deeply supervised rotation equivariant network for lesion segmentation in dermoscopy images

TitleDeeply supervised rotation equivariant network for lesion segmentation in dermoscopy images
Authors
Issue Date2018
PublisherSpringer.
Citation
First International Workshop on OR 2.0 Context-Aware Operating Theaters (OR 2.0 2018), 5th International Workshop on Computer-Assisted and Robotic Endoscopy (CARE 2018), 7th International Workshop on Clinical Image-Based Procedures (CLIP 2018), Third International Workshop on Skin Image Analysis (ISIC 2018), Held in Conjunction with MICCAI 2018, Granada, Spain, 16 and 20 September 2018. In Stoyanov, D, Taylor, Z, Sarikaya, D, et al. (Eds.), OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis: First International Workshop, OR 2.0 2018, 5th International Workshop, CARE 2018, 7th International Workshop, CLIP 2018, Third International Workshop, ISIC 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16 and 20, 2018, Proceedings, p. 235-243. Cham, Switzerland: Springer, 2018 How to Cite?
AbstractAutomatic lesion segmentation in dermoscopy images is an essential step for computer-aided diagnosis of melanoma. The dermoscopy images exhibits rotational and reflectional symmetry, however, this geometric property has not been encoded in the state-of-the-art convolutional neural networks based skin lesion segmentation methods. In this paper, we present a deeply supervised rotation equivariant network for skin lesion segmentation by extending the recent group rotation equivariant network. Specifically, we propose the G-upsampling and G-projection operations to adapt the rotation equivariant classification network for our skin lesion segmentation problem. To further increase the performance, we integrate the deep supervision scheme into our proposed rotation equivariant segmentation architecture. The whole framework is equivariant to input transformations, including rotation and reflection, which improves the network efficiency and thus contributes to the segmentation performance. We extensively evaluate our method on the ISIC 2017 skin lesion challenge dataset. The experimental results show that our rotation equivariant networks consistently excel the regular counterparts with the same model complexity under different experimental settings. Our best model also outperforms the state-of-the-art challenging methods, which further demonstrate the effectiveness of our proposed deeply supervised rotation equivariant segmentation network.
Persistent Identifierhttp://hdl.handle.net/10722/299579
ISBN
ISSN
2023 SCImago Journal Rankings: 0.606
ISI Accession Number ID
Series/Report no.Lecture Notes in Computer Science ; 11041

 

DC FieldValueLanguage
dc.contributor.authorLi, Xiaomeng-
dc.contributor.authorYu, Lequan-
dc.contributor.authorFu, Chi Wing-
dc.contributor.authorHeng, Pheng Ann-
dc.date.accessioned2021-05-21T03:34:43Z-
dc.date.available2021-05-21T03:34:43Z-
dc.date.issued2018-
dc.identifier.citationFirst International Workshop on OR 2.0 Context-Aware Operating Theaters (OR 2.0 2018), 5th International Workshop on Computer-Assisted and Robotic Endoscopy (CARE 2018), 7th International Workshop on Clinical Image-Based Procedures (CLIP 2018), Third International Workshop on Skin Image Analysis (ISIC 2018), Held in Conjunction with MICCAI 2018, Granada, Spain, 16 and 20 September 2018. In Stoyanov, D, Taylor, Z, Sarikaya, D, et al. (Eds.), OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis: First International Workshop, OR 2.0 2018, 5th International Workshop, CARE 2018, 7th International Workshop, CLIP 2018, Third International Workshop, ISIC 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16 and 20, 2018, Proceedings, p. 235-243. Cham, Switzerland: Springer, 2018-
dc.identifier.isbn9783030012007-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/299579-
dc.description.abstractAutomatic lesion segmentation in dermoscopy images is an essential step for computer-aided diagnosis of melanoma. The dermoscopy images exhibits rotational and reflectional symmetry, however, this geometric property has not been encoded in the state-of-the-art convolutional neural networks based skin lesion segmentation methods. In this paper, we present a deeply supervised rotation equivariant network for skin lesion segmentation by extending the recent group rotation equivariant network. Specifically, we propose the G-upsampling and G-projection operations to adapt the rotation equivariant classification network for our skin lesion segmentation problem. To further increase the performance, we integrate the deep supervision scheme into our proposed rotation equivariant segmentation architecture. The whole framework is equivariant to input transformations, including rotation and reflection, which improves the network efficiency and thus contributes to the segmentation performance. We extensively evaluate our method on the ISIC 2017 skin lesion challenge dataset. The experimental results show that our rotation equivariant networks consistently excel the regular counterparts with the same model complexity under different experimental settings. Our best model also outperforms the state-of-the-art challenging methods, which further demonstrate the effectiveness of our proposed deeply supervised rotation equivariant segmentation network.-
dc.languageeng-
dc.publisherSpringer.-
dc.relation.ispartofOR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis: First International Workshop, OR 2.0 2018, 5th International Workshop, CARE 2018, 7th International Workshop, CLIP 2018, Third International Workshop, ISIC 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16 and 20, 2018, Proceedings-
dc.relation.ispartofseriesLecture Notes in Computer Science ; 11041-
dc.titleDeeply supervised rotation equivariant network for lesion segmentation in dermoscopy images-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/978-3-030-01201-4_25-
dc.identifier.scopuseid_2-s2.0-85054823433-
dc.identifier.spage235-
dc.identifier.epage243-
dc.identifier.eissn1611-3349-
dc.identifier.isiWOS:000577071600025-
dc.publisher.placeCham, Switzerland-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats