TY - GEN
T1 - Robust Divergence Learning for Missing-Modality Segmentation
AU - Cheng, Runze
AU - Sun, Zhongao
AU - Zhang, Ye
AU - Li, Chun
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Multimodal Magnetic Resonance Imaging (MRI) provides essential complementary information for analyzing brain tumor subregions. While methods using four common MRI modalities for automatic segmentation have shown success, they often face challenges with missing modalities due to image quality issues, inconsistent protocols, allergic reactions, or cost factors. Thus, developing a segmentation paradigm that handles missing modalities is clinically valuable. A novel single-modality parallel processing network framework based on Hölder divergence and mutual information is introduced. Each modality is independently input into a shared network backbone for parallel processing, preserving unique information. Additionally, a dynamic sharing framework is introduced that adjusts network parameters based on modality availability. A Hölder divergence and mutual information-based loss functions are used for evaluating discrepancies between predictions and labels. Extensive testing on the BraTS 2018 and BraTS 2020 datasets demonstrates that our method outperforms existing techniques in handling missing modalities and validates each component’s effectiveness.
AB - Multimodal Magnetic Resonance Imaging (MRI) provides essential complementary information for analyzing brain tumor subregions. While methods using four common MRI modalities for automatic segmentation have shown success, they often face challenges with missing modalities due to image quality issues, inconsistent protocols, allergic reactions, or cost factors. Thus, developing a segmentation paradigm that handles missing modalities is clinically valuable. A novel single-modality parallel processing network framework based on Hölder divergence and mutual information is introduced. Each modality is independently input into a shared network backbone for parallel processing, preserving unique information. Additionally, a dynamic sharing framework is introduced that adjusts network parameters based on modality availability. A Hölder divergence and mutual information-based loss functions are used for evaluating discrepancies between predictions and labels. Extensive testing on the BraTS 2018 and BraTS 2020 datasets demonstrates that our method outperforms existing techniques in handling missing modalities and validates each component’s effectiveness.
KW - brain-tumor segmentation
KW - divergence learning
KW - knowledge distillation
KW - Missing modality learning
UR - http://www.scopus.com/inward/record.url?scp=86000726033&partnerID=8YFLogxK
U2 - 10.1109/CAC63892.2024.10865360
DO - 10.1109/CAC63892.2024.10865360
M3 - Conference contribution
AN - SCOPUS:86000726033
T3 - Proceedings - 2024 China Automation Congress, CAC 2024
SP - 2077
EP - 2083
BT - Proceedings - 2024 China Automation Congress, CAC 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 China Automation Congress, CAC 2024
Y2 - 1 November 2024 through 3 November 2024
ER -