DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Jihoon | ko |
dc.contributor.author | Kang, Inha | ko |
dc.contributor.author | Park, Jinah | ko |
dc.date.accessioned | 2022-04-28T07:00:52Z | - |
dc.date.available | 2022-04-28T07:00:52Z | - |
dc.date.created | 2022-03-24 | - |
dc.date.created | 2022-03-24 | - |
dc.date.created | 2022-03-24 | - |
dc.date.created | 2022-03-24 | - |
dc.date.created | 2022-03-24 | - |
dc.date.issued | 2021-10-01 | - |
dc.identifier.citation | 24th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2021 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10203/296333 | - |
dc.description.abstract | The Medical Out-Of-Distribution analysis challenge(MOOD) has the goal to build an anomaly detection algorithm when only normal CT images of the brain and abdomen are given. It performs both a sample level task to detect an abnormal image (i.e., an Out-of Distribution (OOD) image), and a pixel(voxel)-level task to locate the abnormal position. Since these tasks have dependency that partial abnormality of the image causes the image-level anomaly, we design the model to perform both tasks at once. We use U-Net [2] as a reference network that receives 3D patches as inputs. The pixel-level task is performed through the decoder of U-Net, and the sample-level task is performed by attaching a classication module to the bottom of the network. | - |
dc.language | English | - |
dc.publisher | Springer Science and Business Media Deutschland GmbH | - |
dc.title | Self-supervised Robust Anomaly Detection with Hard Augmentation | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 24th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2021 | - |
dc.identifier.conferencecountry | FR | - |
dc.identifier.conferencelocation | Strasbourg | - |
dc.contributor.localauthor | Park, Jinah | - |
dc.contributor.nonIdAuthor | Kang, Inha | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.