File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TENCON55691.2022.9977573
- Scopus: eid_2-s2.0-85145654404
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Enhanced U-Net for Computer-aided Diagnosis with Cetacean Postmortem CT Scan
| Title | Enhanced U-Net for Computer-aided Diagnosis with Cetacean Postmortem CT Scan |
|---|---|
| Authors | |
| Keywords | cetaceans loss function segmentation U-Net |
| Issue Date | 1-Nov-2022 |
| Publisher | IEEE |
| Abstract | Postmortem computed tomography (PMCT) scan has long been used in the postmortem examination of cetaceans on Virtopsy to find out the cause of death such as diseases on internal organs. However, manual diagnosis using PMCT scans is labour-intensive and time consuming. Driven by the recent advances in deep learning, in this project, we develop a computer-aided diagnosis system based on U-Net, a convolutional neural network, for cetaceans. In addition, we propose two loss functions to resolve the bias due to the skewed distribution of the different areas in the PMCT-scans, thereby improving the system accuracy significantly. |
| Persistent Identifier | http://hdl.handle.net/10722/357017 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Chen, Minxin | - |
| dc.contributor.author | Lee, Victor C S | - |
| dc.contributor.author | Kot, Brian Chin Wing | - |
| dc.contributor.author | Malagambae, Mar´ıa Jos´e Robles | - |
| dc.date.accessioned | 2025-06-23T08:52:56Z | - |
| dc.date.available | 2025-06-23T08:52:56Z | - |
| dc.date.issued | 2022-11-01 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/357017 | - |
| dc.description.abstract | <p>Postmortem computed tomography (PMCT) scan has long been used in the postmortem examination of cetaceans on Virtopsy to find out the cause of death such as diseases on internal organs. However, manual diagnosis using PMCT scans is labour-intensive and time consuming. Driven by the recent advances in deep learning, in this project, we develop a computer-aided diagnosis system based on U-Net, a convolutional neural network, for cetaceans. In addition, we propose two loss functions to resolve the bias due to the skewed distribution of the different areas in the PMCT-scans, thereby improving the system accuracy significantly.<br></p> | - |
| dc.language | eng | - |
| dc.publisher | IEEE | - |
| dc.relation.ispartof | 2022 IEEE Region 10 Conference (TENCON) (01/11/2022-04/11/2022, Hong Kong) | - |
| dc.subject | cetaceans | - |
| dc.subject | loss function | - |
| dc.subject | segmentation | - |
| dc.subject | U-Net | - |
| dc.title | Enhanced U-Net for Computer-aided Diagnosis with Cetacean Postmortem CT Scan | - |
| dc.type | Conference_Paper | - |
| dc.identifier.doi | 10.1109/TENCON55691.2022.9977573 | - |
| dc.identifier.scopus | eid_2-s2.0-85145654404 | - |
| dc.identifier.volume | 2022-November | - |