Computer scientists from the Johns Hopkins University Computational Cognition, Vision, and Learning (CCVL) research group will present their work at the 2025 Annual Meeting of the Radiological Society of North America (RSNA): Imaging the Individual, taking place November 30 through December 4 in Chicago.
The meeting is the world’s premier conference in medical imaging, attracting over 40,000 radiologists, clinicians, researchers, and industry leaders to present the latest advances in imaging science and AI.
The CCVL group had 18 abstracts accepted to this year’s event, with half chosen for oral presentations—a distinction afforded to only 7% of submissions. These include:
- “Early Pancreatic Cancer Detection via Prediagnostic CT and Artificial Intelligence” by Wenxuan Li, Pedro Ricardo Ariel Salvador Bassi, Xinze Zhou, Qi Chen, Tianyu Lin, Xiaoxi Chen, Shanshan Jiang, Chandana G. Lall, Zheren Zhu, Yang Yang, Kai Ding, Heng Li, Kang Wang, Alan Yuille, and Zongwei Zhou
- “A Touchstone of Medical Artificial Intelligence” by Pedro Ricardo Ariel Salvador Bassi, Wenxuan Li, Alan Yuille, and Zongwei Zhou, also covered here
- “Rewinding Late-Stage CT Scans to Train AI for Early Pancreatic Cancer Detection” by Wenxuan Li, Qi Chen, Kang Wang, Heng Li, Yang Yang, Alan Yuille, and Zongwei Zhou
- “How Many Annotations are Enough? Real-and-Synthetic Data Plateaus for <2 cm PDAC Detection on CT” by Qi Chen, Wenxuan Li, Xinze Zhou, Alan Yuille, and Zongwei Zhou
- “Are Pixel-Wise Metrics Reliable for Computerized Tomography Reconstruction?” by Tianyu Lin, Xinran Li, Qi Chen, Yuanhao Cai, Kai Ding, Alan Yuille, and Zongwei Zhou
- “AbdomenAtlas X: A Large-Scale, Semi-Synthetic Dataset for Abdominal Tumor Segmentation in Solid and Tubular Organs” by Qi Chen, Alan Yuille, and Zongwei Zhou
- “Turning CT Slices into A Story: How Video-Inspired AI is Helping Us Train Smarter Cancer Detectors” by Qi Chen, Wenxuan Li, Xinze Zhou, Alan Yuille, and Zongwei Zhou
- “AI Algorithms Can Assist Radiologists in Detection and Segmentation of Tumors in Uterus and Esophagus Through Non-Contrast Enhanced CT Images” by Qi Chen, Zekun Jiang, Wenxuan Li, Alan Yuille, and Zongwei Zhou
- “AI-Powered Image-to-Image Translation Tool to Enhance Non-Contrast CT Scans” by Junqi Liu, Tianyu Lin, Kai Ding, Alan Yuille, and Zongwei Zhou
CCVL researchers will additionally present the following posters:
- “Using Generative Simulation to Predict Tumor Response for Treatment” by Yijun Yang, Alan Yuille, Zongwei Zhou, Kang Wang, Yang Yang, and Jieneng Chen
- “AI-Powered Map of the Abdomen Could Help Find Cancer Early On” by Wenxuan Li, Yucheng Tang, Alan Yuille, and Zongwei Zhou, also covered here
- “16 Readily Available Radiology Reports Are Worth 1 Time-Consuming Voxel-Wise Annotation for Whole-Body CT Tumor Detection” by Pedro Ricardo Ariel Salvador Bassi, Wenxuan Li, Sergio Decherchi, Andrea Cavalli, Kang Wang, Yang Yang, Alan Yuille, and Zongwei Zhou, also covered here
- “ChatGPT-Guided Diffusion Generates Realistic Synthetic Tumors, Boosting Early CT Detection of Liver, Pancreas, and Kidney Cancers” by Xinran Li, Wenxuan Li, Kang Wang, Yang Yang, Alan Yuille, and Zongwei Zhou
- “CancerVerse: Robust Segmentation of 16 Major Cancers in Computed Tomography” by Wenxuan Li, Xinze Zhou, Qi Chen, Pedro Ricardo Ariel Salvador Bassi, Xiaoxi Chen, Zheren Zhu, Yang Yang, Kang Wang, Alan Yuille, and Zongwei Zhou
- “Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Images” by Wenxuan Li, Alan Yuille, and Zongwei Zhou
- “Multicenter, Multiorgan Pretraining Helps PDAC, Cyst, and PNet Recognition in Contrast Enhanced Computed Tomography” by Xinze Zhou, Alan Yuille, and Zongwei Zhou
- “Creating Triplet Datasets for Multiomic and Multicenter Radiology AI Exploiting CT Images, Anatomical Shapes, and Radiology Reports” by Pedro Ricardo Ariel Salvador Bassi, Alan Yuille, and Zongwei Zhou
- “AbdomenAtlas 2.0: Comprehensive Lesion Annotations in Liver, Pancreas, Kidney, and Colon for 9,901 Three-Dimensional Computed Tomography” by Xinze Zhou, Yuxuan Zhao, Qi Chen, Wenxuan Li, Dexin Yu, Alan Yuille, and Zongwei Zhou