pk

Praitayini Kanakaraj (she/her)
Medical Imaging, Yoga

Roots - Coimbatore

[pk @praitayini]

https://t.co/VmIRINdmtT
#AIResearch #ScientificDiscovery #GoogleDeepMind #ResearchRead

[pk @praitayini]

An AI that proposes ideas, and other AIs that poke holes in them? That's a lab meeting I'd join.

[pk @praitayini]

The question I keep coming back to: we can verify a math proof. How do we validate a hypothesis from a system whose reasoning we can't fully trace? The tournament selects for internal consistency, but consistency isn't truth.

[kurt.schilling @kurtschilling5]

(1/3) Are you left-brained or right-brained??!?

Turns out...your both!

*at least in the white matter*

Check out our latest "white matter asymmetry" lifespan reference charts, led by Sam Bogdanov and @praitayini from @MASI_Lab

https://t.co/SYsO4DnpMm

[pk @praitayini]

@JiantaoJ I’m very interested in the LLM/DLM post-training and systems optimization. My background spans 3D vision models, generative/self-supervised training, and scaling PyTorch on HPC/GPUs, along with 40+ publications in AI/ML. CV: https://t.co/6H5j5fu1Nd

[Francois Rheault (8$™) @FrancoisRheault]

Hey everyone in diffusion MRI and tractography, if you have a cool project too complex for a 1-page abstract, consider submitting a paper to @CD_MRI workshop at MICCAI (deadline by the end of June)!

🇨🇦🧠👨‍🔬👩‍🔬💻🧮🔥

[Francois Rheault (8$™) @FrancoisRheault]

For those of you interested in the @CD_MRI workshop at MICCAI: if you want to submit your work on dMRI and Tractography, the submission process is open on CMT!

You can search for "MICCAI 2023 Workshop on Computational Diffusion MRI".

[Leon Y. Cai, MD, PhD @LeonCai]

1/3 Out of #GPU space in #medical #imaging #AI bc your data's too big? Those days may be over soon! @luke_remedios and I show we can use #AppleSilicon's shared CPU/GPU memory to train a #neural #network with gigapixel med images! That's >1 BILLON pixels! https://t.co/9spx4DfASt

[Leon Y. Cai, MD, PhD @LeonCai]

Ever wanted to do #tractography but didn't have #diffusion #MRI? Check out our preprint using #AI to propagate streamlines directly on T1w MRI, no diffusion needed! https://t.co/abRqZqfFbC Big thanks to @grahamwjohnson @dc_moyer @kurtschilling5 @FrancoisRheault & @MASI_Lab team!

[VISEVanderbilt @ViseVanderbilt]

Congratulations Dr. Leon Cai! Dr. Cai presented his final defense in front of friends and colleagues last week.
Help us congratulate Dr Cai in the comments below. @MASI_Lab #phdone

[pk @praitayini]

Thanks to everyone you made this possible @MASI_Lab @kurtschilling5 @baxpr @FangChengYeh @LeonCai @FrancoisRheault

[pk @praitayini]

1/4 Our manuscript is out!
“Mapping the impact of nonlinear gradient fields with noise on diffusion MRI”
https://t.co/qXjDjyA1io

[pk @praitayini]

4/4 The performance of the approximate gradient nonlinearity correction [https://t.co/DNjvEfSbAu] was similar to the traditional voxelwise correction [https://t.co/eDApSha0HP] for SNR below 30.

[pk @praitayini]

@baxpr Thank you so much!

[pk @praitayini]

This was a great way to celebrate #Diwali2022! Thanks to everyone at the @vuiis retreat for voting us. And, I have the best coauthors @baxpr @LeonCai @kurtschilling5 @FrancoisRheault and the best lab @MASI_Lab!

[Bennett Landman (Vanderbilt MASI Lab) @MASI_Lab]

Congratulations to @praitayini for her win as Audience Choice Best Poster at the @vuiis 2023 Retreat. Great to see @EceVanderbilt and @VanderbiltCS engaged in impactful interdisciplinary research with @VUMCradiology / @VUEngineering. I can't wait to see the journal version!

[Bennett Landman (Vanderbilt MASI Lab) @MASI_Lab]

@praitayini, great job presenting your work on correcting nonlinear gradient fields for diffusion mri at the @vuiis retreat. I'm super excited about your new toolkit that will make these ideas accessible for everyone in PreQual.