Building Clinically Grounded Medical AI at Scale

Foundation Models, Data Infrastructure & Agentic Systems for Clinical Translation

I am a Research Fellow at Monash University's AIM for Health Lab, advised by Prof. Zongyuan Ge. I develop scalable, clinically grounded medical AI ecosystems, spanning foundation models, data infrastructure, and real-world clinical deployment.

My work has been recognized by the Australian Museum Eureka Prize (2024), Victorian Education Award (2025), and Victorian Melanoma Researcher of the Year (2025). It has led to real-world clinical deployment through the ACEMID screening network and an NHMRC-funded national clinical trial.

I am open to collaboration and student supervision in Medical AI. Please reach out.

Email / Google Scholar / Github / LinkedIn

Research Focus

My research advances foundation models, agentic systems, and open data infrastructure to build collaborative and trustworthy systems for clinical translation:

Foundation Models, MLLMs & Agentic AI: Developing general-purpose medical AI systems for collaborative clinical decision-making, as in PanDerm (Nature Medicine), DermFM-Zero (Preprint, 2026), DermoGPT (Preprint, 2026), and MAGEN (Preprint, 2026).
Data Infrastructure & Open Science: Establishing data infrastructure and benchmarking standards to accelerate community-wide medical AI progress, as in Derm1M (ICCV Highlight), DermoGPT (Preprint, 2026), NurViD (NeurIPS), and OphNet (ECCV).
Trustworthy & Fair AI: Developing interpretable, generalizable, and fair AI algorithms ensuring reliability in high-stakes clinical applications, as in TrustDerm (CVPR), PLDG (IEEE TMI & MICCAI), and WISE (EMNLP).
Clinical Translation & Impact: Driving real-world clinical implementation and validation in oncology and precision medicine through global collaboration, with studies published in npj Digital Medicine and British Journal of Dermatology.

News

[Jan 2026] PanDerm featured by Mayo Clinic; MAGEN and DermoGPT released.
[Dec 2025] Our AI for deep phenotype and risk stratification project published in British Journal of Dermatology (IF: 11.1).
[Nov 2025] Our multi-institutional & global melanoma screening project (ISIC2024) published in npj Digital Medicine (IF: 15.1).
[Oct 2025] Successfully submitted PhD thesis and completed PhD within 3 years at Monash University.
[Jun 2025] PanDerm published in Nature Medicine (IF: 58.7) and featured by editors.
[Jun 2025] Derm1M accepted by ICCV (Highlight Paper) (full positive score).
[May 2025] MAKE early accepted by MICCAI (full positive score).

Publications

* indicates equal contribution, † indicates corresponding author

	A Vision-Language Foundation Model for Zero-shot Clinical Collaboration and Automated Concept Discovery in Dermatology *Siyuan Yan†*, Xieji Li, Dan Mo, Philipp Tschandl, Yiwen Jiang, Zhonghua Wang, Ming Hu, Lie Ju, Cristina Vico-Alonso, Yizhen Zheng, Jiahe Liu, Juexiao Zhou, Camilla Chello, Jen G. Cheung, Julien Anriot, Luc Thomas, Clare Primiero, Gin Tan, Aik Beng Ng, Simon See, Xiaoying Tang, Albert Ip, Xiaoyang Liao, Adrian Bowling, Martin Haskett, Shuang Zhao, Monika Janda, H. Peter Soyer, Victoria Mar, Harald Kittler, Zongyuan Ge† Under Review at Nature Biomedical Engineering [Preprint] / [Code]
	A multimodal vision foundation model for clinical dermatology Siyuan Yan, Zhen Yu, Clare Primiero, Cristina Vico-Alonso, Zhonghua Wang, Litao Yang, Philipp Tschandl, Ming Hu, Lie Ju, Gin Tan, Vincent Tang, Aik Beng Ng, David Powell, Paul Bonnington, Simon See, Elisabetta Magnaterra, Peter Ferguson, Jennifer Nguyen, Pascale Guitera, Jose Banuls, Monika Janda, Victoria Mar, Harald Kittler, H Peter Soyer, Zongyuan Ge Nature Medicine, 2025 \| IF: 58.7 \| Editor's Featured [Paper] / [Code] / [Mayo Clinic] / [U.S. News] / [ABC Nightlife]
	Derm1M: A million-scale vision-language dataset aligned with clinical ontology knowledge for dermatology Siyuan Yan, Ming Hu, Yiwen Jiang, Xieji Li, Hao Fei, Philipp Tschandl, Harald Kittler, Zongyuan Ge ICCV*, 2025 \| Highlight Paper (Top 2.3%) [Paper] / [Code] / [Dataset]
	MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment Siyuan Yan, Xieji Li, Ming Hu, Yiwen Jiang, Zhen Yu, Zongyuan Ge MICCAI, 2025 \| Early Accept (Top 9%) [Paper] / [Code]
	Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision Siyuan Yan, Zhen Yu, Xuelin Zhang, Dwarikanath Mahapatra, Shekhar S. Chandra, Monika Janda, H. Peter Soyer, Zongyuan Ge CVPR, 2023 [Paper]
	Prompt-driven latent domain generalization for medical image classification Siyuan Yan, Zhen Yu, Chi Liu, Lie Ju, Dwarikanath Mahapatra, Brigid Betz-Stablein, Victoria Mar, Monika Janda, Peter Soyer, Zongyuan Ge IEEE Transactions on Medical Imaging (TMI), 2024 \| IF: 10.6 [Paper] / [Code]
	Automated triage of cancer-suspicious skin lesions with 3D total-body photography Nicholas R Kurtansky, Maura C Gillis, Noel CF Codella, Brian M D'Alessandro, Zongyuan Ge, Pascale Guitera, Allan C Halpern, Harald Kittler, Josep Malvehy, Konstantinos Liopyris, Victoria J Mar, Linda K Martin, Lara Valeska Maul, Alexander Navarini, Tarlia Rajeswaran, Vin Rajeswaran, Nadia Reichman, H Peter Soyer, Jochen Weber, Siyuan Yan, Veronica Rotemberg, Kivanc Kose npj Digital Medicine, 2025 \| IF: 15.1 [Paper] / [ISIC 2024] / [Dermatology Republic] / [OncoDaily]
	Automated classification of site-specific cutaneous photodamage using a convolutional neural network and 3D total body photography Sam Kahler, Siyuan Yan, Adam Mothershaw, Francesco Leo, Chantal Rutjes, Zhen Yu, Dilki Jayasinghe, Victoria Mar, Monika Janda, Zongyuan Ge, H Peter Soyer, Brigid Betz-Stablein, Clare Primiero British Journal of Dermatology, 2025 \| IF: 11.1 [Paper]
	DermoGPT: Open Weights and Open Data for Morphology-Grounded Dermatological Reasoning MLLMs Jinghan Ru, Siyuan Yan, Yuguo Yin, Yuexian Zou, Zongyuan Ge Preprint, 2026 [Paper] / [Code] / [Dataset]
	Multi-Aspect Knowledge-Enhanced Medical Vision-Language Pretraining with Multi-Agent Data Generation Xieji Li, Siyuan Yan†, Yingsheng Liu, H Peter Soyer, Monika Janda, Victoria Mar, Zongyuan Ge Preprint, 2026 [Paper] / [Code]
	NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding Ming Hu, Lin Wang, Siyuan Yan, Don Ma, Qingli Ren, Peng Xia, Wei Feng, Peibo Duan, Lie Ju, Zongyuan Ge NeurIPS*, 2023 [Paper] / [Code]

Selected Awards

Press

Multimodal Dermatology Foundation Model (PanDerm) was featured by over 100 global media outlets, including Mayo Clinic Platform, U.S. News, FierceBiotech, ABC Nightlife, HealthDay, EurekAlert!, The Derm Digest, as well as leading Chinese outlets such as Tencent News, Sina Finance, Bioon, MedSci, and Baidu Health, among others.
AI for 3D Total-Body Photography in Melanoma Screening was covered by Dermatology Republic, OncoDaily.

Academic Service

Journal Reviewer: Nature Medicine, The Lancet Regional Health–Europe, IEEE TMI, IEEE TIP, Journal of Investigative Dermatology

Conference Reviewer: CVPR, ICCV, NeurIPS, ECCV, AAAI, MICCAI

Challenge Organizer/Co-Organizer: