Name
Abstract | ||
|---|---|---|
Fast and accurate landmark location and bounding box detection are important steps in 3D medical imaging. In this paper, we propose a novel multi-task learning framework, for real-time, simultaneous landmark location and bounding box detection in 3D space. Our method extends the famous single-shot multibox detector (SSD) from single-task learning to multi-task learning and from 2D to 3D. Furthermore, we propose a post-processing approach to refine the network landmark output, by averaging the candidate landmarks. Owing to these settings, the proposed framework is fast and accurate. For 3D cardiac magnetic resonance (MR) images with size 224x224x 64, our framework runs -128 volumes per second (VPS) on GPU and achieves 6.75mm average point-to-point distance error for landmark location, which outperforms both state-of-the-art and baseline methods. We also show that segmenting the 31) image cropped with the bounding box results in both improved performance and efficiency. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICPR48806.2021.9412087 | 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) |
DocType | ISSN | Citations |
Conference | 1051-4651 | 0 |
PageRank | References | Authors |
0.34 | 0 | 8 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Weizeng Lu | 1 | 0 | 1.35 |
| Xi Jia | 2 | 19 | 4.97 |
| Wei Chen | 3 | 9 | 2.82 |
| Nicoló Savioli | 4 | 0 | 1.01 |
| Antonio de Marvao | 5 | 60 | 4.27 |
| Linlin Shen | 6 | 1351 | 90.25 |
| Declan P. O'Regan | 7 | 258 | 16.33 |
| Jinming Duan | 8 | 130 | 19.92 |