CCLS Inaugural Research Symposium

AI for Biology and Medicine (AI4BM)

October 30, 2025

Gateway Center (Room 42/43/47), University of North Texas

 

Join us for the CCLS Inaugural Research Symposium, AI for Biology & Medicine (AI4BM). This one-day event explores how AI is revolutionizing biological research, precision medicine, and healthcare technology through distinguished keynote speaker, research talks, poster sessions and a panel discussion.

We invite our research community to submit abstracts for posters and talks at AI4BM.

• Who: Open to all students, post-doctoral researchers, and faculty/staff.
• What: We are looking for submissions that highlight ongoing, innovative, and high-impact research in AI for biology and medicine.
• Why: Showcase your work, and foster new collaborations.

Registration to AI4BM is free. Please click the button above to register.

Keynote Speaker

Artificial Intelligence and Foundation Models for Reproductive Medicine: From Embryo to Ovary

Recent advances in self-supervised learning and foundation model architectures have opened new frontiers in reproductive medicine by enabling scalable, standardized interpretation of complex imaging data. In this talk, I will present a series of efforts in my lab toward developing generalizable AI systems that enhance both embryology and pelvic imaging workflows.

Following an overview of deep learning applications for embryo imaging, I will introduce FEMI (Foundational IVF Model for Imaging)—a large-scale foundation model trained on 18 million embryo images that unifies multiple IVF tasks, including ploidy prediction, blastocyst quality scoring, component segmentation, and developmental stage assessment, within a single framework. I will then describe ARIA (Automated Reproductive Intelligence Agents), a multi-agent AI system that leverages FEMI and vision-language reasoning to automate continuous embryo monitoring and real-time reporting, achieving high accuracy across key embryology tasks. Finally, I will discuss the development of self-supervised foundation models for pelvic ultrasonography, trained on over 1.7 million unlabeled frames to standardize ovarian and follicular measurements and reduce operator variability.

Together, these efforts illustrate how AI and foundation models can unify reproductive imaging tasks, minimize subjectivity, and lay the groundwork for AI-based, clinically integrated tools in reproductive medicine.

Dr. Iman Hajirasouliha is an Associate Professor of Systems and Computational Biomedicine at Weill Cornell Medicine of Cornell University. He is a member of the Englander Institute for Precision Medicine and the Meyer Cancer Center in New York. He is also the Co-Director of the Tri-I Computational Biology and Medicine Ph.D. program. He completed a Postdoctoral Scholarship at Stanford University's Computer Science Department and a Simons Research Fellowship at the University of California, Berkeley. He earned his B.Sc. in Computer Engineering from Sharif University, an M.Sc. in Computing Science from Simon Fraser University (SFU), and a Ph.D. with Exceptional Recognition from SFU, followed by a postdoctoral appointment at Brown University. Dr. Hajirasouliha has received several prestigious awards, including the Simons-Berkeley Research Fellowship, an NIGMS Maximizing Investigators' Research Award, and an Irma T. Hirschl Career Scientist Award. Website: www.imanh.org.

Call for Abstracts

We invite submissions for oral presentations and posters from academic, industry, and clinical researchers working in areas related to AI, computational biology, and biomedical applications.

We invite abstracts in the areas including but not limited to:

1. Predictive Models trained on multi-omics datasets – AI for genomics, transcriptomics, metabolomics, lipidomics; biomarker discovery; network modeling.
2. Precision Medicine & Computational Drug Discovery – Virtual screening, molecular docking, predictive modeling for therapeutics and devices.
3. Biomedical AI, Vision & Robotics – Medical imaging, surgical robotics, wearable and sensor-based healthcare AI.
4. Machine Learning Foundations for Life Sciences – Active learning, model adaptation, domain transfer for biomedical datasets.
5. Responsible AI, Security, & Fairness – Privacy-preserving AI, bias mitigation, explainability in clinical AI systems.
6. Computational Plant Biology, Ecology & Environmental Health – AI applications in plant systems, environmental exposure, and health.
7. Industry & Translational Innovation – Case studies and applied solutions from biotech, pharma, and med-tech companies.

Please click the button above to submit your abstract.

For all inquiries, please email serdar.bozdag@unt.edu