TY - GEN
T1 - MTA-Net
T2 - 20th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2024
AU - Liang, Zhaohai
AU - Wu, Jiayi
AU - Chai, Siyi
AU - Wang, Yingkai
AU - Li, Chengdong
AU - Shen, Cong
AU - Xin, Jingmin
N1 - Publisher Copyright:
© IFIP International Federation for Information Processing 2024.
PY - 2024
Y1 - 2024
N2 - Lymphoma treatment planning and prognosis assessment require accurate segmentation of lymphoma lesions. Positron emission tomography (PET) /computed tomography (CT) is widely used for lymphoma segmentation. Many methods do automatic segmentation of lymphoma based on PET/CT. However, a significant challenge that limits the effectiveness of the segmentation method is the large and imbalance variation in size of whole-body lymphoma lesions. For example, a small percentage of images contain large lesions, while most images contain only small lesions or even no lesions, which results in inaccurate segmentation. In this paper, we propose a Multi-task Assisted Network (MTA-Net) for whole-body lymphoma segmentation. First, we design a novel Multi-task Cross-scale Transformer (MCT) block, which combines the pixels regression task and the whole image classification task at multiple scales. Second, we design a Classification Dynamic Convolution (CDC) whose parameters are additionally controlled by the classification task to assist the segmentation task. In our private whole-body lymphoma dataset, experiments show that MTA-Net achieves the best result among state-of-the-art methods on Dice, HD (Hausdorff Distance), Recall, and Precision.
AB - Lymphoma treatment planning and prognosis assessment require accurate segmentation of lymphoma lesions. Positron emission tomography (PET) /computed tomography (CT) is widely used for lymphoma segmentation. Many methods do automatic segmentation of lymphoma based on PET/CT. However, a significant challenge that limits the effectiveness of the segmentation method is the large and imbalance variation in size of whole-body lymphoma lesions. For example, a small percentage of images contain large lesions, while most images contain only small lesions or even no lesions, which results in inaccurate segmentation. In this paper, we propose a Multi-task Assisted Network (MTA-Net) for whole-body lymphoma segmentation. First, we design a novel Multi-task Cross-scale Transformer (MCT) block, which combines the pixels regression task and the whole image classification task at multiple scales. Second, we design a Classification Dynamic Convolution (CDC) whose parameters are additionally controlled by the classification task to assist the segmentation task. In our private whole-body lymphoma dataset, experiments show that MTA-Net achieves the best result among state-of-the-art methods on Dice, HD (Hausdorff Distance), Recall, and Precision.
KW - lymphoma
KW - multi-task learning
KW - PET/CT
KW - semantic segmentation
UR - https://www.scopus.com/pages/publications/85197338252
U2 - 10.1007/978-3-031-63211-2_14
DO - 10.1007/978-3-031-63211-2_14
M3 - 会议稿件
AN - SCOPUS:85197338252
SN - 9783031632105
T3 - IFIP Advances in Information and Communication Technology
SP - 174
EP - 186
BT - Artificial Intelligence Applications and Innovations - 20th IFIP WG 12.5 International Conference, AIAI 2024, Proceedings
A2 - Maglogiannis, Ilias
A2 - Iliadis, Lazaros
A2 - Papaleonidas, Antonios
A2 - Macintyre, John
A2 - Avlonitis, Markos
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 27 June 2024 through 30 June 2024
ER -