End-to-end detection-segmentation network with ROI convolution
| dc.contributor.author | Zhang, Zichen | |
| dc.contributor.author | Tang, Min | |
| dc.contributor.author | Cobzas, Dana | |
| dc.contributor.author | Zonoobi, Dornoosh | |
| dc.contributor.author | Jagersand, Martin | |
| dc.contributor.author | Jaremko, Jacob L. | |
| dc.date.accessioned | 2020-10-05 | |
| dc.date.accessioned | 2022-05-31T01:15:23Z | |
| dc.date.available | 2022-05-31T01:15:23Z | |
| dc.date.issued | 2018 | |
| dc.description.abstract | We propose an end-to-end neural network that improves the segmentation accuracy of fully convolutional networks by incorporating a localization unit. This network performs object localization first, which is then used as a cue to guide the training of the segmentation network. We test the proposed method on a segmentation task of small objects on a clinical dataset of ultrasound images. We show that by jointly learning for detection and segmentation, the proposed network is able to improve the segmentation accuracy compared to only learning for segmentation. | |
| dc.description.uri | https://library.macewan.ca/full-record/edseee/edseee.8363859 | |
| dc.identifier.citation | Zichen Zhang, Min Tang, Dana Cobzas, Dornoosh Zonoobi, Martin Jagersand and Jacob Jaremko, End-To-End Detection-Segmentation Network with ROI Convolution, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) | |
| dc.identifier.doi | https://doi.org/10.1109/ISBI.2018.8363859 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.14078/1755 | |
| dc.language | English | |
| dc.language.iso | en | |
| dc.rights | All Rights Reserved | |
| dc.subject | segmentation | |
| dc.subject | detection | |
| dc.subject | fully convolutional neural networks | |
| dc.subject | ultrasound | |
| dc.title | End-to-end detection-segmentation network with ROI convolution | en |
| dc.type | Presentation |