Selected Funded Projects
This page summarizes selected previously funded research projects, including documented collaborations, student involvement, and research outcomes.
Trustworthy Weakly Supervised Breast Cancer Detection in Ultrasound Imaging
Funding: Students Partnering with Faculty (SpF) program at Kean University
Period: Summer 2024 | Role: Principal Investigator
This project investigated trustworthy weakly supervised breast cancer detection in breast ultrasound imaging. It focused on BUSwiNet, a weakly supervised framework using image-level labels to identify breast tumor bounding boxes and classify tumors, and on Bayesian neural networks for quantitative trustworthiness evaluation.
People
- Principal Investigator: Dr. Meng Xu
- Co-Principal Investigator: Dr. Kuan Huang
- Undergraduate Student Researchers: Maryam Ahmed, Joanna Loja, Armando Mendez
Selected Outcomes
- Maryam Ahmed, Joanna Loja, Kuan Huang, Meng Xu. “Benchmarking the Robustness of Segmentation Methods Against Adversarial Attacks in Breast Ultrasound Segmentation.” International Conference on Computational Science and Computational Intelligence, 2024. [link]
- Armando Mendez, Meng Xu, Kuan Huang. “Multimodal Breast Ultrasound Segmentation: Combining Visual and Clinical Data.” International Conference on Computational Science and Computational Intelligence, 2024. [link]
- Cesar Marte, Meng Xu, Kuan Huang. “Text-Guided Weakly Supervised Segmentation for COVID-19 Detection in X-ray Images.” International Conference on Computational Science and Computational Intelligence, 2024. [link]
Building a Trustworthy Deep Learning Model for Urban-Scene Image Segmentation: Robustness and Uncertainty Analysis
Funding: CAHSI-Google Institutional Research program
Period: 9/1/2024 to 8/31/2025 | Role: Principal Investigator
This project examined trustworthy deep learning for urban-scene image segmentation, with attention to robustness and uncertainty analysis. It focused on evaluating segmentation models under adversarial perturbations and developing ContraDiff, a contrastive learning diffusion model for trustworthy urban-scene image segmentation.
People
- Principal Investigator: Dr. Meng Xu
- Co-Principal Investigator: Dr. Yuyin Zhou (University of California, Santa Cruz)
- Undergraduate Student Researchers: Cesar Marte