Details

Autor(en) / Beteiligte

• Xue, Wufeng
• Cao, Chunyan
• Liu, Jie
• Duan, Yilian
• Cao, Haiyan
• Wang, Jian
• Tao, Xumin
• Chen, Zejian
• Wu, Meng
• Zhang, Jinxiang
• Sun, Hui
• Jin, Yang
• Yang, Xin
• Huang, Ruobing
• Xiang, Feixiang
• Song, Yue
• You, Manjie
• Zhang, Wen
• Jiang, Lili
• Zhang, Ziming
• Kong, Shuangshuang
• Tian, Ying
• Zhang, Li
• Ni, Dong
• Xie, Mingxing

Titel

Modality alignment contrastive learning for severity assessment of COVID-19 from lung ultrasound and clinical information

Ist Teil von

• Medical image analysis, 2021-04, Vol.69, p.101975-101975, Article 101975

Ort / Verlag

Netherlands: Elsevier B.V

Erscheinungsjahr

2021

Link zum Volltext

Quelle

Elsevier ScienceDirect Journals Complete

Beschreibungen/Notizen

• •We conducted the first large scale research for AI-based LUS analysis of COVID-19 and built an effective framework for COVID-19 diagnosis.•We designed a DSA-MIL module to combine the heterogeneous LUS images and videos.•We proposed a MA-CLR module to align the feature of LUS data and clinical information for patient severity prediction.•We learned the framework following an SRT pipeline to explore discriminative features gradually from different level. [Display omitted] The outbreak of COVID-19 around the world has caused great pressure to the health care system, and many efforts have been devoted to artificial intelligence (AI)-based analysis of CT and chest X-ray images to help alleviate the shortage of radiologists and improve the diagnosis efficiency. However, only a few works focus on AI-based lung ultrasound (LUS) analysis in spite of its significant role in COVID-19. In this work, we aim to propose a novel method for severity assessment of COVID-19 patients from LUS and clinical information. Great challenges exist regarding the heterogeneous data, multi-modality information, and highly nonlinear mapping. To overcome these challenges, we first propose a dual-level supervised multiple instance learning module (DSA-MIL) to effectively combine the zone-level representations into patient-level representations. Then a novel modality alignment contrastive learning module (MA-CLR) is presented to combine representations of the two modalities, LUS and clinical information, by matching the two spaces while keeping the discriminative features. To train the nonlinear mapping, a staged representation transfer (SRT) strategy is introduced to maximumly leverage the semantic and discriminative information from the training data. We trained the model with LUS data of 233 patients, and validated it with 80 patients. Our method can effectively combine the two modalities and achieve accuracy of 75.0% for 4-level patient severity assessment, and 87.5% for the binary severe/non-severe identification. Besides, our method also provides interpretation of the severity assessment by grading each of the lung zone (with accuracy of 85.28%) and identifying the pathological patterns of each lung zone. Our method has a great potential in real clinical practice for COVID-19 patients, especially for pregnant women and children, in aspects of progress monitoring, prognosis stratification, and patient management.