Hongyi Pan - Homepage

Hongyi Pan

I am a Postdoctoral Research Fellow at Northwestern University, Machine and Hybrid Intelligence Lab, collaborating with Prof. Ulas Bagci. I received my Ph.D. degree in Electrical and Computer Engineering from University of Illinois Chicago in 2023, where I was advised by Prof. Ahmet Enis Cetin. I am the Principal Investigator on an NIH K99/R00 Pathway to Independence Award funded by NIH/NIBIB for the Cyst-Suite project (1K99EB039097-01), developing federated foundation models for pancreatic cyst management and cancer risk stratification.

My research lies at the intersection of medical image analysis, computer vision, and machine learning. I focus on developing privacy-preserving federated foundation models, robust domain generalization and pixel-space harmonization frameworks for multi-center clinical cohorts, and frequency-inspired neural network architectures (e.g., discrete cosine and Hadamard transforms) for efficient edge computing. My work has led to widely benchmarked datasets and clinical AI frameworks—including Cyst-X for multi-center pancreatic MRI risk stratification, LUMINA for vendor-harmonized full-field digital mammography (CVPR 2026), and BreastMammo/DenseMammo for tissue-specific domain generalization (MICCAI 2026). In addition to my research, I serve as an Associate Editor for Signal, Image and Video Processing.

Email:
hongyi.pan@northwestern.edu

Google Scholar - GitHub - LinkedIn - Resume

Editorial Service

Associate Editor, Signal, Image and Video Processing

June 2023 – Present

Selected Publications (* denotes equal contribution)


	BreastMammo and DenseMammo: Benchmarks for Mammography Domain Generalization. Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas, Andrea Mia Bejar, Mustafa Ege Seker, Nebile Alibeyoglu, Rumeysa Guclu, Rana Gunoz Comert Bozkurt, Sibel Ozkan Gurdal, Neslihan Cabioglu, Beyza Ozcinar, Ravza Yilmaz, Vahit Ozmen, Erkin Aribal, Sukru Mehmet Erturk, Yalda Zafari, Mohamed Mabrok, Kayhan Batmanghelich, Mohammad Yaqub, Ziyue Xu, Ulas Bagci. MICCAI 2026 Workshop Deep-Brea3th (Best Paper Award), 2026. [Conference] [Project]

	Discrete Cosine Transform-Based Decorrelated Attention for Vision Transformers. Hongyi Pan, Emadeldeen Hamdan, Xin Zhu, Ahmet Enis Cetin, Ulas Bagci. International Joint Conference on Artificial Intelligence (IJCAI), 2026. [ArXiv] [Code]

	LUMINA: A Multi-Vendor Mammography Benchmark with Energy Harmonization Protocol. Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas, Andrea M. Bejar, Baver Tutun, Emre Uysal, Ezgi Bulbul, Mehmet Fatih Dogan, Berrin Erok, Berna Akkus Yildirim, Sukru Mehmet Erturk, Ulas Bagci. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. [Conference] [Code] [Presentation]

	Frequency-Based Federated Domain Generalization for Polyp Segmentation Hongyi Pan, Debesh Jha, Koushik Biswas, Ulas Bagci. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025. [Conference] [Code] [Presentation]

	Multi-Channel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets Hongyi Pan, Emadeldeen Hamdan, Xin Zhu, Salih Atici, Ahmet Enis Cetin. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024. [Journal] [Code]

	Domain Generalization with Fourier Transform and Soft Thresholding Hongyi Pan, Bin Wang, Zheyuan Zhang, Xin Zhu, Debesh Jha, Ahmet Enis Cetin, Concetto Spampinato, Ulas Bagci. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024. [Conference] [Code]

	A novel asymmetrical autoencoder with a sparsifying discrete cosine Stockwell transform layer for gearbox sensor data compression Xin Zhu, Daoguang Yang, Hongyi Pan, Hamid Reza Karimi, Didem Ozevin, Ahmet Enis Cetin. Engineering Applications of Artificial Intelligence (EAAI), 2024. [Journal]

	GazeGNN: A Gaze-Guided Graph Neural Network for Chest X-ray Classification Bin Wang, Hongyi Pan*, Armstrong Aboah, Zheyuan Zhang, Elif Keles, Drew Torigian, Baris Turkbey, Elizabeth Krupinski, Jayaram Udupa, Ulas Bagci. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision* (WACV), 2024. [Conference] [Code]

	Robust Array Signal Processing Using L1-Kernel-Based Principal Component Analysis Hongyi Pan, Erdem Koyuncu, Ahmet Enis Cetin. IEEE-APS Topical Conference on Antennas and Propagation in Wireless Communications (APWC), 2023. [Conference]

	Electromagnetically Unclonable Functions Generated by Non-Hermitian Absorber-Emitter Minye Yang, Zhilu Ye, Hongyi Pan, Mohamed Farhat, Ahmet Enis Cetin, Pai-Yen Chen. Science Advances, 2023 [Journal]

	A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional Layer Hongyi Pan, Xin Zhu, Salih Furkan Atici, Ahmet Cetin. International Conference on Machine Learning (ICML), 2023. [Conference] [Code] [Presentation]

	Real-Time Wireless ECG-Derived Respiration Rate Estimation using an Autoencoder with a DCT Layer Hongyi Pan, Xin Zhu, Zhilu Ye, Pai-Yen Chen, Ahmet Enis Cetin. IEEE International Conference on Acoustics, Speech and Signal Processing* (ICASSP), 2023. [Conference] [Code] [Presentation]

	Classification of the Cervical Vertebrae Maturation (CVM) Stages Using the Tripod Network Salih Atici, Hongyi Pan*, Mohammed H Elnagar, Veerasathpurush Allareddy, Omar Suhaym, Rashid Ansari, Ahmet Enis Cetin. IEEE International Conference on Acoustics, Speech and Signal Processing* (ICASSP), 2023. [Conference]

	Block Walsh–Hadamard Transform-based Binary Layers in Deep Neural Networks Hongyi Pan, Diaa Badawi, Ahmet Enis Cetin. ACM Transactions on Embedded Computing Systems (TECS), 2022. [Journal] [Code]

	Detecting Anomaly in Chemical Sensors via L1-Kernel-Based Principal Component Analysis Hongyi Pan, Diaa Badawi, Ishaan Bassi, Sule Ozev, Ahmet Enis Cetin. IEEE Sensors Letters, 2022. [Journal]

	Multiplication-avoiding variant of power iteration with applications Hongyi Pan, Diaa Badawi, Runxuan Miao, Erdem Koyuncu, Ahmet Enis Cetin. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022. [Conference] [Presentation]

	Deep Neural Network With Walsh-Hadamard Transform Layer for Ember Detection During a Wildfire Hongyi Pan, Diaa Badawi, Chang Chen, Adam Watts, Erdem Koyuncu, Ahmet Enis Cetin. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022. [Conference] [Presentation]

	Robust Principal Component Analysis Using a Novel Kernel Related with the L1-Norm Hongyi Pan, Diaa Badawi, Erdem Koyuncu, Ahmet Enis Cetin. European Signal Processing Conferences (EUSIPCO), 2021. [Conference] [Presentation]

	Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks Hongyi Pan, Diaa Badawi, Ahmet Enis Cetin. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021. [Conference]

	Computationally Efficient Wildfire Detection Method Using a Deep Convolutional Network Pruned via Fourier Analysis Hongyi Pan, Diaa Badawi, Ahmet Enis Cetin. MDPI Sensors, 2020. [Journal] [Demo]

	Fourier Domain Pruning of MobileNet-V2 with Application to Video Based Wildfire Detection Hongyi Pan, Diaa Badawi, Ahmet Enis Cetin. International Conference on Pattern Recognition (ICPR), 2020. [Conference] [Presentation]

	Additive Neural Network for Forest Fire Detection Hongyi Pan, Diaa Badawi, Xi Zhang, Ahmet Enis Cetin. Signal, Image and Video Processing (SIVP), 2020. [Journal]

	Computationally Efficient Spatio-Temporal Dynamic Texture Recognition for Volatile Organic Compound (VOC) Leakage Detection in Industrial Plants Diaa Badawi, Hongyi Pan, Sinan Cem Cetin, Ahmet Enis Cetin. IEEE Journal of Selected Topics in Signal Processing (J-STSP), 2020. [Journal]