JointViT: Modeling Oxygen Saturation Levels with Joint Supervision on Long-Tailed OCTA
This work addresses the challenge of diagnosing sleep-related disorders using OCTA imaging, representing an incremental advancement in medical AI applications.
The paper tackles the problem of continuous oxygen saturation monitoring by proposing JointViT, a Vision Transformer model with joint supervision and balancing augmentation, which achieves up to 12.28% improvement in accuracy on an OCTA dataset.
The oxygen saturation level in the blood (SaO2) is crucial for health, particularly in relation to sleep-related breathing disorders. However, continuous monitoring of SaO2 is time-consuming and highly variable depending on patients' conditions. Recently, optical coherence tomography angiography (OCTA) has shown promising development in rapidly and effectively screening eye-related lesions, offering the potential for diagnosing sleep-related disorders. To bridge this gap, our paper presents three key contributions. Firstly, we propose JointViT, a novel model based on the Vision Transformer architecture, incorporating a joint loss function for supervision. Secondly, we introduce a balancing augmentation technique during data preprocessing to improve the model's performance, particularly on the long-tail distribution within the OCTA dataset. Lastly, through comprehensive experiments on the OCTA dataset, our proposed method significantly outperforms other state-of-the-art methods, achieving improvements of up to 12.28% in overall accuracy. This advancement lays the groundwork for the future utilization of OCTA in diagnosing sleep-related disorders. See project website https://steve-zeyu-zhang.github.io/JointViT