Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
Deep Multimodal Fusion Network for the Retinogeniculate Visual Pathway Segmentation. / Xie, Lei; Yang, Lin; Zeng, Qingrun et al.
Chinese Control Conference, CCC. Institute of Electrical and Electronics Engineers (IEEE), 2023. p. 7946-7950.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
}
TY - GEN
T1 - Deep Multimodal Fusion Network for the Retinogeniculate Visual Pathway Segmentation
AU - Xie, Lei
AU - Yang, Lin
AU - Zeng, Qingrun
AU - He, Jianzhong
AU - Huang, Jiahao
AU - Feng, Yuanjing
AU - Amelina, Evgeniya
AU - Amelin, Mihail
N1 - This work is supported by the National Natural Science Foundation of China (Grant No.62002327, 61976190); Natural Science Foundation of Zhejiang Province (Grant No.LQ21F020017 and Q23F030045); The Key Technology Research and Development Program of Zhejiang Province (Grant No.2020C03070). Postdoctoral Science Preferential Funding of Zhejiang Province (Grant No.ZJ2022067). Публикация для корректировки.
PY - 2023
Y1 - 2023
N2 - The segmentation of the retinogeniculate visual pathway (RGVP) is a significant quantitative tool for analyzing the anatomy and trajectory of individual RGVP. However, due to the complex structure and elongated morphology of the RGVP, it is difficult to accurately identify the intracranial course based on a single structural MRI or diffusion MRI. In this work, we propose a novel deep multimodal fusion network for the retinogeniculate pathway segmentation, which fuses the useful information from different modalities. Specifically, the proposed fusion model uses the supervised information generated by the spatial attention mechanism module to select useful information from the master modal and the assistant modal, where the T1 weighted (T1w) images that contributes most to the final segmentation result are used as the master modal and the FA images are used as the assistant modal. The results show that our method can achieve the best performance compared with the RGVP segmentation methods presented in the paper.
AB - The segmentation of the retinogeniculate visual pathway (RGVP) is a significant quantitative tool for analyzing the anatomy and trajectory of individual RGVP. However, due to the complex structure and elongated morphology of the RGVP, it is difficult to accurately identify the intracranial course based on a single structural MRI or diffusion MRI. In this work, we propose a novel deep multimodal fusion network for the retinogeniculate pathway segmentation, which fuses the useful information from different modalities. Specifically, the proposed fusion model uses the supervised information generated by the spatial attention mechanism module to select useful information from the master modal and the assistant modal, where the T1 weighted (T1w) images that contributes most to the final segmentation result are used as the master modal and the FA images are used as the assistant modal. The results show that our method can achieve the best performance compared with the RGVP segmentation methods presented in the paper.
UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85175524454&origin=inward&txGid=9fd7c78cfaab0b20b37438c27d1ddb04
UR - https://www.mendeley.com/catalogue/6726d88a-6dfc-37fe-a19f-eb310e90fad0/
U2 - 10.23919/ccc58697.2023.10240807
DO - 10.23919/ccc58697.2023.10240807
M3 - Conference contribution
SN - 9789887581543
SP - 7946
EP - 7950
BT - Chinese Control Conference, CCC
PB - Institute of Electrical and Electronics Engineers (IEEE)
ER -
ID: 59181698