TY - GEN
T1 - Multi-view Contrastive Learning with Additive Margin for Adaptive Nasopharyngeal Carcinoma Radiotherapy Prediction
AU - Sheng, Jiabao
AU - Lam, Sai Kit
AU - Li, Zhe
AU - Zhang, Jiang
AU - Teng, Xinzhi
AU - Zhang, Yuanpeng
AU - Cai, Jing
N1 - Funding Information:
This work was supported in part by the Project of RISA (P0043001) of The Hong Kong Polytechnic University, Shenzhen-Hong Kong-Macau S&T Program (Category C) (SGDX20201103095002019), Shen-zhen Basic Research Program (JCYJ20210324130209023) of Shen-zhen Science and Technology Innovation Committee, Project of Strategic Importance (P0035421), the NSF of Jiangsu Province (No.
Funding Information:
This work was supported in part by the Project of RISA (P0043001) of The Hong Kong Polytechnic University, Shenzhen-Hong KongMacau S&T Program (Category C) (SGDX20201103095002019), Shenzhen Basic Research Program (JCYJ20210324130209023) of Shenzhen Science and Technology Innovation Committee, Project of Strategic Importance (P0035421), the NSF of Jiangsu Province (No. BK20201441), Jiangsu Post-doctoral Research Funding Program (No. 2020Z020), and the NSFC (Grant No. 82072019).
Funding Information:
BK20201441), Jiangsu Post-doctoral Research Funding Program (No. 2020Z020), and the NSFC (Grant No. 82072019).
Publisher Copyright:
© 2023 ACM.
PY - 2023/6/12
Y1 - 2023/6/12
N2 - The accurate prediction of adaptive radiation therapy (ART) for nasopharyngeal carcinoma (NPC) patients before radiation therapy (RT) is crucial for minimizing toxicity and enhancing patient survival rates. Owing to the complexity of the tumor micro-environment, a single high-resolution image offers only limited insight. Furthermore, the traditional softmax-based loss falls short in quantifying a model's discriminative power. To address these challenges, we introduce a supervised multi-view contrastive learning approach with an additive margin (MMCon). For each patient, we consider four medical images to form multi-view positive pairs, which supply supplementary information and bolster the representation of medical images. We employ supervised contrastive learning to determine the embedding space, ensuring that NPC samples from the same patient or with the same labels stay in close proximity while NPC samples with different labels are distant. To enhance the discriminative ability of the loss function, we incorporate a margin into the contrastive learning process. Experimental results show that this novel learning objective effectively identifies an embedding space with superior discriminative abilities for NPC images.
AB - The accurate prediction of adaptive radiation therapy (ART) for nasopharyngeal carcinoma (NPC) patients before radiation therapy (RT) is crucial for minimizing toxicity and enhancing patient survival rates. Owing to the complexity of the tumor micro-environment, a single high-resolution image offers only limited insight. Furthermore, the traditional softmax-based loss falls short in quantifying a model's discriminative power. To address these challenges, we introduce a supervised multi-view contrastive learning approach with an additive margin (MMCon). For each patient, we consider four medical images to form multi-view positive pairs, which supply supplementary information and bolster the representation of medical images. We employ supervised contrastive learning to determine the embedding space, ensuring that NPC samples from the same patient or with the same labels stay in close proximity while NPC samples with different labels are distant. To enhance the discriminative ability of the loss function, we incorporate a margin into the contrastive learning process. Experimental results show that this novel learning objective effectively identifies an embedding space with superior discriminative abilities for NPC images.
KW - Contrastive Learning
KW - Medical Image Analysis
KW - Multi-view
KW - Nasopharyngeal Carcinoma
UR - http://www.scopus.com/inward/record.url?scp=85163665924&partnerID=8YFLogxK
U2 - 10.1145/3591106.3592261
DO - 10.1145/3591106.3592261
M3 - Conference article published in proceeding or book
AN - SCOPUS:85163665924
T3 - ICMR 2023 - Proceedings of the 2023 ACM International Conference on Multimedia Retrieval
SP - 555
EP - 559
BT - ICMR 2023 - Proceedings of the 2023 ACM International Conference on Multimedia Retrieval
PB - Association for Computing Machinery, Inc
T2 - 2023 ACM International Conference on Multimedia Retrieval, ICMR 2023
Y2 - 12 June 2023 through 15 June 2023
ER -