@ModHabes

Director Biggs Institute Neuroimaging Core, Associate Prof. of Radiology, UT Health San Antonio.

 USA
Joined July 2016
  • Tweets261
  • Following558
  • Followers357
47Media
Can AI for dementia work equally well across populations? In our new @NatureComms study of 9,007 participants, we found important performance differences across racial and ethnic groups and showed that fairness-aware learning can reduce them. nature.com/articles/s41467-0… #AI #Dementia
1
4
8
250
Can better blood pressure control protect the brain? In our new EClinicalMedicine study using SPRINT data, intensive systolic BP control was linked to less progression of cerebral small vessel disease, with greater BP reductions linked to greater benefit. doi.org/10.1016/j.eclinm.202…
1
1
4
135
more replies
Congratulations to Sokratis Charisis, who led this work, and to our outstanding SPRINT collaborators. A message that continues to emerge across this field: Protecting cardiovascular health may also help protect the brain.
1
4
@UTHealthSARad @UTHSAResearch
2
Congratulations to Ngoc-Huynh Ho, who led this work from our lab, and to the entire collaborative team. Very proud of this study and of the broader goal behind it: developing AI that is not only accurate, but also more reliable across the populations it is intended to serve.
1
1
1
17
@UTHealthSARad @UTHSAResearch
1
16
@UTHealthSARad @UTHSAResearch
1
14
@NatureComms
1
Deeply grateful to share our manuscript, now published in @Radiology_RSNA and featured by @RSNA. We used deep learning to measure vertebral bone mineral density on chest CT in MESA. Lower bone density was associated with modestly accelerated regional white matter injury and faster cognitive decline, particularly among participants with diabetes. Since chest CT is done so often, this could be an opportunistic way to detect accelerated brain aging. Thank you to the MESA participants for their years of commitment. @Hopkins_Rad @RadiologyEditor 📢 Press release: rsna.org/news/2026/september… 📄 Paper: pubs.rsna.org/doi/10.1148/ra…
5
3
48
1,665
Everything new is also old. This from my 1984 PhD thesis: "AI is an experimental science, yet the complexity of its programs and problem domains often makes the interpretation of results very difficult. Programs often contain so many components and parameters that limitations on computer time and the sheer number of possibilities make it impossible to experimentally evaluate how each contributes to performance." Then I argued, just as I do today, for careful empirical studies in simplified settings that enable better scientific understanding.
19
88
5
711
51,846
Congrats to Dr. Di Wang @jieyoushen on successfully defending his PhD! One of the committee members remarked that it was among the best PhD theses he had seen in the past 30 years—a true testament to your hard work, innovation, and dedication.Excited to see the impact you’ll make
1
4
513
Organizing @MLCNworkshop alongside Yimming @xiaobird, @ThomasWolfers, #NichaDvorek, and many others was an incredible pleasure. Grateful for the teamwork and for the outstanding research that made this program a success. Here's to many more milestones together! @MICCAI_Society
1
4
584
Load more