BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Pathology News - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.pathologynews.com
X-WR-CALDESC:Events for Pathology News
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:20241027T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:20261025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/London:20251117T140000
DTEND;TZID=Europe/London:20251117T150000
DTSTAMP:20260829T215239
CREATED:20251111T142519Z
LAST-MODIFIED:20251111T142519Z
UID:100116750-1763388000-1763391600@www.pathologynews.com
SUMMARY:TIA Centre Seminar Series – Too Many Models\, Too Few Benchmarks: Addressing the benchmarking crisis in AI for pathology
DESCRIPTION:The Tissue Image Analytics (TIA) Centre hosts a seminar series for those interested in computational pathology. The series invites researchers and leaders in computational pathology and related fields to present their work and foster thought-provoking discussions. \nThis seminar features Professor Jana Lipkova from the University of California\, Irvine\, USA. \nAbstract\nThe field of AI in pathology is experiencing a benchmarking crisis. New models emerge weekly\, each claiming superiority over predecessors\, yet the community lacks rigorous\, reproducible tools to validate these claims. In this talk\, I will present two open benchmarks from our group to address this gap. The first benchmark systematically evaluates state-of-the-art pathology foundation models (FMs) for survival prediction in oncology. We assess model generalization across multiple external cohorts\, compare architectural paradigms (patch- vs. slide-level\, uni- vs. multimodal)\, probe model interpretability and investigate weather FM allow to build pan-cancer generalists model that replace disease-specific models and generalize to rare cancers and conditions not seen during the model training? The second benchmark introduces a framework for safe AI deployment in pathology\, focusing on out-of-distribution (OOD) detection and model “guardrails.” We propose a new taxonomy for OOD scenarios in pathology and a public benchmark that stress-tests existing OOD models across diverse data shifts and real-world variability. Both benchmarks\, including all datasets\, standardized splits\, and evaluation protocols\, are publicly released to serve as standards for model evaluation and comparison\, thereby accelerate further advances and deployment of AI in pathology. \nRegister NowBio\nJana is an Assistant Professor at the University of California\, Irvine\, with joint appointments in the School of Medicine\, School of Biomedical Engineering\, and the School of Computer Science. She completed her postdoctoral fellowship in the AI for Pathology group at Harvard Medical School\, under the mentorship of Dr. Faisal Mahmood. Prior to that\, she earned her Ph.D. in computer-aided medical procedures from the Department of Radiology at the Technical University of Munich. Jana leads the OctoPath Lab (http://octopath.org/)\, which develops AI methods for diagnosis\, prognosis\, and treatment optimization in histopathology and beyond.
URL:https://www.pathologynews.com/event/tia-centre-seminar-series-too-many-models-too-few-benchmarks-addressing-the-benchmarking-crisis-in-ai-for-pathology/
LOCATION:Online
CATEGORIES:Live Online Webinar
ATTACH;FMTTYPE=image/png:https://www.pathologynews.com/wp-content/uploads/2025/11/TIA-Centre-Seminar-Series-–-Too-Many-Models-Too-Few-Benchmarks-Addressing-the-benchmarking-crisis-in-AI-for-pathology-1.png
END:VEVENT
END:VCALENDAR