| Paper ID | BIO-9.2 |
| Paper Title |
DeepNodule: Multi-task Learning of Segmentation Bootstrap for Pulmonary Nodule Detection |
| Authors |
Jingqin Li, Kun Wang, Dan Yang, Xiaohong Zhang, Chongqing University, China; Chen Liu, The First Affiliated Hospital of Army Medical University, China |
| Session | BIO-9: Medical Image Analysis |
| Location | Gather.Town |
| Session Time: | Wednesday, 09 June, 14:00 - 14:45 |
| Presentation Time: | Wednesday, 09 June, 14:00 - 14:45 |
| Presentation |
Poster
|
| Topic |
Biomedical Imaging and Signal Processing: [BIO-MIA] Medical image analysis |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Pulmonary nodule detection and segmentation are the necessary successively steps in lung cancer screening with low-dose computed tomography (CT) scans. However, the state-of-the-art models focus on solving tasks separately, thereby ignore the correlation between each task. Besides, most nodule detectors adopt anchor-based method falling to achieve good performance in low FPs per scan. To overcome those barriers, we present a novel multi-task 3D convolutional network (DeepNodule) for simultaneous nodule detection and segmentation in a shared-and-fined manner. Meanwhile, we utilize the center-point of the predicted segmentation masks to refine the bounding box coordinate and get a more precise nodule location. Furthermore, we design a 3D Gated Channel Transformation convolutional attention block for learning nodule features better. Experiments conducted on LUNA16 dataset demonstrates that DeepNodule obtains competitive performance, with the sensitivity of nodule candidate detection achieving 92.0\%, and the accuracy of nodule segmentation reaching 80.04\%. |
