UCSF Center for Intelligent Imaging (@UCSF_Ci2) header
UCSF Center for Intelligent Imaging (@UCSF_Ci2) profile picture

The Center for Intelligent Imaging (Ci2) is focused on applications of artificial intelligence and image analysis tools in medical imaging. @UCSFImaging

San Francisco, CA
Joined February 2020
Photo by UCSF Center for Intelligent Imaging (@UCSF_Ci2)Photo by UCSF Center for Intelligent Imaging (@UCSF_Ci2)Photo by UCSF Center for Intelligent Imaging (@UCSF_Ci2)Photo by UCSF Center for Intelligent Imaging (@UCSF_Ci2)Photo by UCSF Center for Intelligent Imaging (@UCSF_Ci2)Photo by UCSF Center for Intelligent Imaging (@UCSF_Ci2)Photo by UCSF Center for Intelligent Imaging (@UCSF_Ci2)Photo by UCSF Center for Intelligent Imaging (@UCSF_Ci2)Photo by UCSF Center for Intelligent Imaging (@UCSF_Ci2)Photo by UCSF Center for Intelligent Imaging (@UCSF_Ci2)
A new study of 1,715 participants over 48 months in @OAC_Open by @UCSF_Ci2's Dr. Alexandra Gersing found thigh muscle loss was associated with greater tendon damage & decline in physical performance. oarsiopenjournal.com/article…
1
139
Hospital archives offer anatomy & pathology diversity at scale, but their images are magnitude-only. @UCSFimaging #postdoc Nikhil Deveshwar shares how a generative model helps create synthetic multicoil MRI training data. ➡️ intelligentimaging.ucsf.edu/…
1
148
Join us for our next SRG Pillar Meeting with @washumedicine's Dr. Daniel Marcus on XNAT 2. After over 2 decades supporting medical researchers, XNAT is adding agentic AI to research & extending its reach to enable responsible AI translation to the clinic. intelligentimaging.ucsf.edu/…
2
125
What role does the infrapatellar fat pad play in knee OA? A study of 4,257 OAI participants by @UCSF_Ci2's Dr. @ThomasMLink1 & colleagues used DL-based automatic volumetric segmentation to investigate subregion-specific associations. More in @OACJournal: oarsijournal.com/article/S10…
3
3
216
Thigh muscle gain over 48 months was associated with less progression in ligamentous damage, bone marrow edema-like lesions, & pain in knee osteoarthritis. New study in @OAC_Open led by @UCSF_Ci2's Dr. Alexandra Gersing. oarsiopenjournal.com/article…
3
125
In @OACJournal, @UCSF_Ci2's Dr. @ThomasMLink1 & colleagues used a deep learning algorithm for automatic IPFP segmentation to analyze 4,257 knees from the Osteoarthritis Initiative. oarsijournal.com/article/S10…
1
90
Can #DeepLearning close the gap between low-field and conventional MRI? A study in @EJR_official_ led by @UCSF_Ci2's Dr. Alexandra S. Gersing found DL-based denoising of 0.55T knee MRI achieved excellent agreement with 3T (CCC of 0.94). doi.org/10.1016/j.ejrad.2026…
1
113
Routinely acquired radiography, CT & MRI scans may hold more bone health information than we're currently using. A new narrative review in #CalcifiedTissueInternational explores #AI methods for extracting those markers. doi.org/10.1007/s00223-026-0…
1
47
A new comparative study led by @UCSF_Ci2's Dr. Alexandra Gersing in @EJR_official_ found that deep learning-based denoising of low-field 0.55T knee MRI improved diagnostic accuracy from 0.83 to 0.98, achieving results comparable to conventional 3T. doi.org/10.1016/j.ejrad.2026…
1
110
Join us Monday, October 12 from 3–4 pm for our next SRG Pillar Meeting! Nikhil Deveshwar, Postdoctoral Scholar in the Larson lab, will present "Deep Generative and Hardware Accelerated MRI." bit.ly/4rTKRlx
2
82
New narrative review from @UCSF_Ci2's Dr. Sharmila Majumdar & postdoc Dr. Katharina Ziegeler examines how AI can opportunistically assess bone mineral density & bone microarchitecture from routinely acquired imaging across radiography, CT & MRI. doi.org/10.1007/s00223-026-0…
67
Finding a deep pediatric brain tumor's subtype usually means a biopsy. Emma Duprat tested whether AI uncertainty could flag it noninvasively. Louan Bardou tackled detecting white matter lesions in adolescents without FLAIR. Learn more about their research: intelligentimaging.ucsf.edu/…
1
98
Meet the #postdoc making sense of breast cancer MRIs from more than 30 sites. Pouya Metanat studies how scanner & software variability affects the reading of treatment response, so care can be personalized. Happy #PostdocAppreciationWeek! #UCSFProud
1
3
240
We're recognizing Atlas Haddadi Avval this #PostdocAppreciationWeek. Her research uses #AI to compare a patient's MRI scans over time & quantify how a pediatric brain tumor is changing. The aim is a more objective, reproducible way to track disease & inform treatment. #UCSFProud
3
19
482
Most tools that segment white matter lesions rely on FLAIR imaging. Louan Bardou reached comparable accuracy without it. Emma Duprat used AI segmentation uncertainty to read pediatric brain tumor subtypes. Learn more: intelligentimaging.ucsf.edu/…
1
84
Building tools to read prostate MRIs takes data with reliable answers attached. @UCSF_Ci2's UCSF-ProstateMR dataset pairs 973 prostate scans with the biopsy results that show what was truly there, giving researchers a solid basis to test their work. imagingdatasets.ucsf.edu/dat…
1
1
211
Primary CNS lymphoma is a rare brain cancer that is easily mistaken for other conditions, which delays care. @UCSF_Ci2 has released the first public imaging dataset for it, covering 150 patients, to help researchers build better tools to spot it. imagingdatasets.ucsf.edu/dat…
3
2
290
Not every kidney tumor is dangerous, but telling risky ones apart often means surgery or biopsy. @UCSF_Ci2's UCSF RMaC dataset offers 831 CT scans of kidney masses, each linked to its surgical result, to help build tools that gauge risk from imaging alone. imagingdatasets.ucsf.edu/dat…
1
88
Could disk imaging help target back pain treatment? In @JorSpine, @UCSF_Ci2's Dr. @sharmilamajumda & colleagues show quantitative disk hydration markers add information beyond standard grading for the disk-endplate unit. doi.org/10.1002/jsp2.70188
86