Samir Harake

Med Student @UMichMedSchool | @UMich '19 @MichiganRoss '20

[Samir Harake @SamirHarake]

@Aditya_S_Pandey @UMichMedSchool @ToddCHollon @umichneuro Thank you @Aditya_S_Pandey ! I appreciate your kind words, and I am incredibly grateful for the support I have received from you, @ToddCHollon , and the department as a whole. I can't wait to continue the journey in residency at @umichneuro

[Eric Topol @EricTopol]

How to read a brain MRI and make a diagnosis in seconds, along with urgent triage, with very high accuracy? A vision language AI model from @umichmedicine @natBME tested in real world medicine
https://t.co/aCTgcrATDT

[Nature Biomedical Engineering @natBME]

Learning neuroimaging models from health system-scale data https://t.co/cJTRKano9v

[Todd Hollon @ToddCHollon]

We present Prima, the first medical foundation model for neuroimaging that supports full real-world, clinical MRI studies: the whole MRI in >>> diagnosis out!
Thanks to @umichmedicine, @umichneuro, and our @mlins_lab.

https://t.co/VKZBqtbZPW

[Kennedy S. Miller @kennedymiller37]

Grateful for the opportunity to present my #SurgeryOlympics team's research on spinal cord stimulator revisions at the #AANS2025 meeting in Boston @umichneuro @AANSneuro @UMichSCRUBS

[Samir Harake @SamirHarake]

@KHolsteMD @umichmedicine @UMich @umichneuro @NeenaMarupudi Thank you for your mentorship and support!

[CNSResidents @CNSResidents]

Congratulations to Dr. Alon Kashanian (@AlonKashanian @NorthwellNsurg) and Dr. Rushikesh Joshi (@RushiSJoshi7 @umichneuro) on being named our new CNS Resident Committee Membership Co-Chairs!

[Todd Hollon @ToddCHollon]

@mlins_lab PhD all-star, Yiwei Lyu, presenting his paper at @RealAAAI on Restorative Step-Calibrated Diffusion. His paper solves the problem of restoring biomedical images with variable and unknown amounts of data degradation.

Checkout the preprint: https://t.co/AfsoPZHwai

[Michigan Neurosurgery @umichneuro]

🌟 Attention #SpineSummit2025 attendees! 🌟 As you plan your schedule, make sure to note the sessions featuring @umichneuro residents. Their contributions are insightful and inspiring, so plan accordingly and don’t miss out on their sessions! 📅 #GoBlue @spinesection

[Todd Hollon @ToddCHollon]

Big thanks to @NIHDirector for covering #FastGlioma in her latest post.

[Todd Hollon @ToddCHollon]

🚀 Proud to introduce #FastGlioma: the first foundation model enabling rapid, accurate detection of brain tumor infiltration during surgery, in under 10 seconds. With FastGlioma, we’re minimizing the risk of residual tumor and enhancing outcomes for glioma patients. This work sets a new standard in real-time, microscopic-level detection, powered by AI in healthcare. Kudos to the incredible team @mlins, @HerveyJumper, @DanOrringerMD, @InvenioImaging, @CameloPiragua!
Read the full paper in @Nature: https://t.co/gJ3dCPYod4

[Todd Hollon @ToddCHollon]

@__chengjia__ presenting at UM Bioinformatics BISTRO conference. Great talk on single cell optical phenotyping! @mlins_lab

[Armin Mortazavi @arminm870]

We recently published a paper in @EditorNeuro that highlights the importance of tumor biology and interactions with the surrounding brain, in this case, seizures. https://t.co/cHSWLlRxEJ

[Max Lu @MYLu97]

4/7 📊 Hou & Jiang et al. present SPT, a framework for learning self-supervised slide representations, which is consistently able to learn strong slide-level features across a variety of encoders, including UNI. arXiv: https://t.co/2FEQ9Kcaau

⚡️This is the first work to investigate slide pretraining across a diverse variety of ROI encoders. The analyses in Hou & Jiang et al. suggest that slide pretraining provide the biggest performance gains in less powerful ROI encoders, with least benefit in HiDisc and UNI. They also show the importance of further finetuning as well, which can yield as big of an improvement as slide pretraining.

💭 We believe more development needs to happen in self-supervised slide encoders than ROI encoders. Few works in this area, and where most of the technical advancements need to be made 🔥

[Todd Hollon @ToddCHollon]

@__chengjia__ giving his awesome talk at @CVPR on 3D super-resolution. So proud of him and the @mlins_lab!

[emerse @projectEMERSE]

EMERSE identified patients who underwent whole-spine radiography for study, "Development and validation of an artificial intelligence model..."
@SamirHarake @joseph_linzey @__chengjia__ @RushiSJoshi7 @MarkZaki24 @SiriKhalsaMD @ZWilseckMD @ToddCHollon
https://t.co/Bu7CFIYbTK

[Samir Harake @SamirHarake]

Very excited to share our most recent work out of the @mlins_lab - SpinePose is a novel deep learning model that predicts spinopelvic parameters. Special thanks to @ToddCHollon , Dr. Paul Park, @joseph_linzey @__chengjia__ https://t.co/t2DQifUjY3

[Samir Harake @SamirHarake]

@ToddCHollon @mlins_lab @ToddCHollon Thank you for the constant support and guidance on this effort!

[Samir Harake @SamirHarake]

@joseph_linzey @umichneuro @ToddCHollon @mlins_lab @SRS_org Thank you for your mentorship and help in making this project possible! @joseph_linzey Looking forward to what we have in store next!