Hi /你好，
I'm Degan Hao,
a PhD candidate from the University of Pittsburgh.
I am dedicated to life changing medicine through the development of trusthworthy artificial intelligence. My research efforts are centered on advancing both algorithmic innovation and clinical applications to ensure better patient outcomes.
Current questions
1. Deep learning are vulnerable to adversarial attacks. How to make safer AI for healthcare?
See our recent work on "Adversarially Robust Feature Learning for Breast Cancer Diagnosis"[link]
See our recent work on "Adversarially Robust Feature Learning for Breast Cancer Diagnosis"[link]
2. With the surge of generative AI, more synthetic data are produced. How do we mitigate the impact of biased synthetic data on model training?
Past questions
1.When working in the field of medicine, where labeled data can be scarce, what are the effective approaches to implementing machine learning?
Hao, Degan, et al. "A self-training teacher-student model with an automatic label grader for abdominal skeletal muscle segmentation." Artificial Intelligence in Medicine 132 (2022): 102366. [link]
2.Inaccurate labels are common in medicine. How can deep learning be effectively applied in the existance of weak supervision?
Hao, Degan, et al. "Inaccurate labels in weakly-supervised deep learning: Automatic identification and correction and their impact on classification performance." IEEE journal of biomedical and health informatics 24.9 (2020): 2701-2710. [link]
3.Censored data often occur during patient follow-ups. How to handle censored data for patient outcome prediction?
Hao, Degan, et al. "Identifying Prognostic Markers From Clinical, Radiomics, and Deep Learning Imaging Features for Gastric Cancer Survival Prediction." Frontiers in oncology 11 (2021): 725889-725889. [link]
Hao, Degan, et al. "SurvivalCNN: A deep learning-based method for gastric cancer survival prediction using radiological imaging data and clinicopathological variables." Artificial Intelligence in Medicine (2022): 102424. [link]
Hao, Degan, et al. (2023). Predicting Outcomes in Long COVID Patients with Spatiotemporal Attention. Eleventh IEEE International Conference on Healthcare Informatics (ICHI). 2023 IEEE 11th International Conference on Healthcare Informatics (ICHI), Houston, TX, USA, 2023 pp. 162-167. [link]
4.Can we incorporate medical knowledge and behaviors into deep learning?
Hao, Degan, et al. (2022). Incorporate radiograph-reading behavior and knowledge into deep reinforcement learning for lesion localization. Medical Imaging 2022: Computer-Aided Diagnosis, 12033, 244-249. [link]
Hao, Degan, et al. (2024). Medical Knowledge-Enabled Multi-Task Learning for Gastric Cancer Survival Prediction. International Symposium on Biomedical Imaging, Athens, Greece, 2024.