File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes

TitleH-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes
Authors
KeywordsCT
deep learning
liver tumor segmentation
hybrid features
Issue Date2018
Citation
IEEE Transactions on Medical Imaging, 2018, v. 37, n. 12, p. 2663-2674 How to Cite?
Abstract© 2018 IEEE. Liver cancer is one of the leading causes of cancer death. To assist doctors in hepatocellular carcinoma diagnosis and treatment planning, an accurate and automatic liver and tumor segmentation method is highly demanded in the clinical practice. Recently, fully convolutional neural networks (FCNs), including 2-D and 3-D FCNs, serve as the backbone in many volumetric image segmentation. However, 2-D convolutions cannot fully leverage the spatial information along the third dimension while 3-D convolutions suffer from high computational cost and GPU memory consumption. To address these issues, we propose a novel hybrid densely connected UNet (H-DenseUNet), which consists of a 2-D DenseUNet for efficiently extracting intra-slice features and a 3-D counterpart for hierarchically aggregating volumetric contexts under the spirit of the auto-context algorithm for liver and tumor segmentation. We formulate the learning process of the H-DenseUNet in an end-to-end manner, where the intra-slice representations and inter-slice features can be jointly optimized through a hybrid feature fusion layer. We extensively evaluated our method on the data set of the MICCAI 2017 Liver Tumor Segmentation Challenge and 3DIRCADb data set. Our method outperformed other state-of-the-arts on the segmentation results of tumors and achieved very competitive performance for liver segmentation even with a single model.
Persistent Identifierhttp://hdl.handle.net/10722/281963
ISSN
2023 Impact Factor: 8.9
2023 SCImago Journal Rankings: 3.703
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLi, Xiaomeng-
dc.contributor.authorChen, Hao-
dc.contributor.authorQi, Xiaojuan-
dc.contributor.authorDou, Qi-
dc.contributor.authorFu, Chi Wing-
dc.contributor.authorHeng, Pheng Ann-
dc.date.accessioned2020-04-09T09:19:15Z-
dc.date.available2020-04-09T09:19:15Z-
dc.date.issued2018-
dc.identifier.citationIEEE Transactions on Medical Imaging, 2018, v. 37, n. 12, p. 2663-2674-
dc.identifier.issn0278-0062-
dc.identifier.urihttp://hdl.handle.net/10722/281963-
dc.description.abstract© 2018 IEEE. Liver cancer is one of the leading causes of cancer death. To assist doctors in hepatocellular carcinoma diagnosis and treatment planning, an accurate and automatic liver and tumor segmentation method is highly demanded in the clinical practice. Recently, fully convolutional neural networks (FCNs), including 2-D and 3-D FCNs, serve as the backbone in many volumetric image segmentation. However, 2-D convolutions cannot fully leverage the spatial information along the third dimension while 3-D convolutions suffer from high computational cost and GPU memory consumption. To address these issues, we propose a novel hybrid densely connected UNet (H-DenseUNet), which consists of a 2-D DenseUNet for efficiently extracting intra-slice features and a 3-D counterpart for hierarchically aggregating volumetric contexts under the spirit of the auto-context algorithm for liver and tumor segmentation. We formulate the learning process of the H-DenseUNet in an end-to-end manner, where the intra-slice representations and inter-slice features can be jointly optimized through a hybrid feature fusion layer. We extensively evaluated our method on the data set of the MICCAI 2017 Liver Tumor Segmentation Challenge and 3DIRCADb data set. Our method outperformed other state-of-the-arts on the segmentation results of tumors and achieved very competitive performance for liver segmentation even with a single model.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Medical Imaging-
dc.subjectCT-
dc.subjectdeep learning-
dc.subjectliver tumor segmentation-
dc.subjecthybrid features-
dc.titleH-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TMI.2018.2845918-
dc.identifier.pmid29994201-
dc.identifier.scopuseid_2-s2.0-85048473372-
dc.identifier.volume37-
dc.identifier.issue12-
dc.identifier.spage2663-
dc.identifier.epage2674-
dc.identifier.eissn1558-254X-
dc.identifier.isiWOS:000451903400011-
dc.identifier.issnl0278-0062-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats