Abstract
Studies have proved that the number of B-lines in lung ultrasound images has a strong statistical link to the amount of extravascular lung water, which is significant for hemodialysis treatment. Manual inspection of B-lines requires experts and is time-consuming, whilst designing automatic methods is currently problematic because of the lack of ground truth. Therefore, in this paper, we propose a novel semi-supervised learning method for the B-line detection task based on contrastive learning. Through multi-level unsupervised learning on unlabelled lung ultrasound images, the features of the arte-facts are learnt. In the downstream task, we introduce a fine-tuning process on a small number of labelled images using the EIoU-based loss function. Apart from reducing the data labelling workload, the proposed method shows a superior performance compared to model-based methods with the recall of 91.43%, the accuracy of 84.21% and the F1 score of 91.43%.
Original language | English |
---|---|
Title of host publication | 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023 |
Publisher | IEEE Computer Society |
ISBN (Electronic) | 9781665473583 |
DOIs | |
Publication status | Published - 2023 |
Event | 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023 - Cartagena, Colombia Duration: 18 Apr 2023 → 21 Apr 2023 https://biomedicalimaging.org/2023/ |
Publication series
Name | Proceedings - International Symposium on Biomedical Imaging |
---|---|
Volume | 2023-April |
ISSN (Print) | 1945-7928 |
ISSN (Electronic) | 1945-8452 |
Conference
Conference | 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023 |
---|---|
Country/Territory | Colombia |
City | Cartagena |
Period | 18/04/23 → 21/04/23 |
Internet address |
Bibliographical note
Publisher Copyright:© 2023 IEEE.
Keywords
- B-line detection
- Contrastive learning
- EIoU loss
- lung ultrasound
- unsupervised learning