Anthony A. Gatti
@aagatti.bsky.social
Dad | Husband | @McMasterU PhD | @StanfordRad & @WuTsaiAlliance Postdoc | @CIHR_IRSC Fellow | Runner. Biker. Adventurer. Big science geek. http://anthonygattiphd.com
Pinned
Anthony A. Gatti
@aagatti.bsky.social
· Nov 25
I'm excited to share that our work on #deeplearning based shape modeling is finally out in #ieee.
🧵 for info about Data, Benchmarks, and Models!
@akshay-chaudhari.bsky.social @stanfordmedicine.bsky.social
www.medrxiv.org/content/10.1...
ieeexplore.ieee.org/document/107...
🧵 for info about Data, Benchmarks, and Models!
@akshay-chaudhari.bsky.social @stanfordmedicine.bsky.social
www.medrxiv.org/content/10.1...
ieeexplore.ieee.org/document/107...
Reposted by Anthony A. Gatti
Watch the @mobilizecenter.bsky.social/Restore Center webinar with @aclouthier.bsky.social and Erin Lee entitled “Integrating Bone and Joint Geometry into Musculoskeletal Models”
Research presentation: youtu.be/QtqDx3_uK9I
Tutorial: youtu.be/wqxQl3Dm9lc
Research presentation: youtu.be/QtqDx3_uK9I
Tutorial: youtu.be/wqxQl3Dm9lc
Webinar: Integrating Bone and Joint Geometry into Musculoskeletal Models, Part 1 of 2
YouTube video by Mobilize Center
youtu.be
November 10, 2025 at 5:52 PM
Watch the @mobilizecenter.bsky.social/Restore Center webinar with @aclouthier.bsky.social and Erin Lee entitled “Integrating Bone and Joint Geometry into Musculoskeletal Models”
Research presentation: youtu.be/QtqDx3_uK9I
Tutorial: youtu.be/wqxQl3Dm9lc
Research presentation: youtu.be/QtqDx3_uK9I
Tutorial: youtu.be/wqxQl3Dm9lc
Reposted by Anthony A. Gatti
This ☝🏽 💯
If 🇨🇦 created a thriving research environment by investing in tri-council & ditching the PJT focused approach that kills investment in long term programs - we would ATTRACT international talent vs bribing them to move here; to only leave later when they see there’s no sustainable funding!
If 🇨🇦 created a thriving research environment by investing in tri-council & ditching the PJT focused approach that kills investment in long term programs - we would ATTRACT international talent vs bribing them to move here; to only leave later when they see there’s no sustainable funding!
September 19, 2025 at 3:43 PM
This ☝🏽 💯
If 🇨🇦 created a thriving research environment by investing in tri-council & ditching the PJT focused approach that kills investment in long term programs - we would ATTRACT international talent vs bribing them to move here; to only leave later when they see there’s no sustainable funding!
If 🇨🇦 created a thriving research environment by investing in tri-council & ditching the PJT focused approach that kills investment in long term programs - we would ATTRACT international talent vs bribing them to move here; to only leave later when they see there’s no sustainable funding!
Reposted by Anthony A. Gatti
I can't* fathom why the top picture, and not the bottom picture, is the standard diagram for an autoencoder.
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
August 29, 2025 at 10:46 PM
I can't* fathom why the top picture, and not the bottom picture, is the standard diagram for an autoencoder.
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
Reposted by Anthony A. Gatti
“Everyone knows” what an autoencoder is… but there's an important complementary picture missing from most introductory material.
In short: we emphasize how autoencoders are implemented—but not always what they represent (and some of the implications of that representation).🧵
In short: we emphasize how autoencoders are implemented—but not always what they represent (and some of the implications of that representation).🧵
September 6, 2025 at 9:20 PM
“Everyone knows” what an autoencoder is… but there's an important complementary picture missing from most introductory material.
In short: we emphasize how autoencoders are implemented—but not always what they represent (and some of the implications of that representation).🧵
In short: we emphasize how autoencoders are implemented—but not always what they represent (and some of the implications of that representation).🧵
Reposted by Anthony A. Gatti
We are starting to see some nuanced discussions of what it means to work with advanced AI in its current state
In this case, GPT-5 Pro was able to do novel math, but only when guided by a math professor (though the paper also noted the speed of advance since GPT-4)
The reflection is worth reading.
In this case, GPT-5 Pro was able to do novel math, but only when guided by a math professor (though the paper also noted the speed of advance since GPT-4)
The reflection is worth reading.
September 6, 2025 at 9:55 PM
We are starting to see some nuanced discussions of what it means to work with advanced AI in its current state
In this case, GPT-5 Pro was able to do novel math, but only when guided by a math professor (though the paper also noted the speed of advance since GPT-4)
The reflection is worth reading.
In this case, GPT-5 Pro was able to do novel math, but only when guided by a math professor (though the paper also noted the speed of advance since GPT-4)
The reflection is worth reading.
Reposted by Anthony A. Gatti
We're thrilled to introduce ATHENA: Automatically Tracking Hands Expertly with No Annotations – our open-source, Python-based toolbox for 3D markerless hand tracking!
Paper: www.biorxiv.org/content/10....
Paper: www.biorxiv.org/content/10....
August 16, 2025 at 12:49 AM
We're thrilled to introduce ATHENA: Automatically Tracking Hands Expertly with No Annotations – our open-source, Python-based toolbox for 3D markerless hand tracking!
Paper: www.biorxiv.org/content/10....
Paper: www.biorxiv.org/content/10....
Reposted by Anthony A. Gatti
Reposted by Anthony A. Gatti
Oh so it does have phd level intelligence
Google Gemini doesn’t appear to be doing too well:
‘"I am a disgrace to this planet. I am a disgrace to this universe. I am a disgrace to all universes . . . I am a disgrace to all possible and impossible universes and all that is not a universe," the bot continued.’
‘"I am a disgrace to this planet. I am a disgrace to this universe. I am a disgrace to all universes . . . I am a disgrace to all possible and impossible universes and all that is not a universe," the bot continued.’
Google says it's working on a fix for Gemini's self-loathing 'I am a failure' comments
Google Gemini users said the bot is sharing self-loathing messages while attempting to solve tasks, including "I am a disgrace to this universe."
www.businessinsider.com
August 8, 2025 at 8:42 AM
Oh so it does have phd level intelligence
Reposted by Anthony A. Gatti
Methods like NeRF and Gaussian Splats model the world as radioactive fog, rendered using alpha blending. This produces great results.. but are volumes the only way to get there?🤔 Our new SIGGRAPH'25 paper directly reconstructs surfaces without heuristics or regularizers.
August 7, 2025 at 12:21 PM
Methods like NeRF and Gaussian Splats model the world as radioactive fog, rendered using alpha blending. This produces great results.. but are volumes the only way to get there?🤔 Our new SIGGRAPH'25 paper directly reconstructs surfaces without heuristics or regularizers.
Reposted by Anthony A. Gatti
Rest in peace, boss. @beierlab.bsky.social -- your stoic and positive support helped me in too many ways to count over the years.
Cancer update. A bit darker than usual. Cancer has advanced and it looks like I only have a few months left. Took me a few days to get used to this new timeline. Time to start wrapping things up at home and at the lab. Thankfully there is little pain and I am relatively functional.
July 20, 2025 at 4:26 PM
Rest in peace, boss. @beierlab.bsky.social -- your stoic and positive support helped me in too many ways to count over the years.
Reposted by Anthony A. Gatti
What an absolutely extraordinary milestone. Congrats @fmrib-steve.bsky.social @fmrib-karla.bsky.social and everyone else involved.
www.bbc.co.uk/news/article...
www.bbc.co.uk/news/article...
Biggest human imaging study scans 100,000th UK volunteer
UK Biobank scientists say the human body can be studied in greater detail than ever thanks to people like Steve.
www.bbc.co.uk
July 15, 2025 at 9:19 AM
What an absolutely extraordinary milestone. Congrats @fmrib-steve.bsky.social @fmrib-karla.bsky.social and everyone else involved.
www.bbc.co.uk/news/article...
www.bbc.co.uk/news/article...
I love this type of approach - for imaging, biomechanics, or other domains…
Take high quality dense data, use physics simulators to generate synthetic sparse data, then train a model to recon dense data from sparse measurements.
Lots of potential pitfalls, but the concept is immensely powerful.
Take high quality dense data, use physics simulators to generate synthetic sparse data, then train a model to recon dense data from sparse measurements.
Lots of potential pitfalls, but the concept is immensely powerful.
Pixel-level lung thickness maps for real and synthetic radiographs generated with a U-Net trained on synthetic data https://doi.org/10.1148/ryai.240484 #ChestRad #LungVolume #ChestXray
July 6, 2025 at 11:24 PM
I love this type of approach - for imaging, biomechanics, or other domains…
Take high quality dense data, use physics simulators to generate synthetic sparse data, then train a model to recon dense data from sparse measurements.
Lots of potential pitfalls, but the concept is immensely powerful.
Take high quality dense data, use physics simulators to generate synthetic sparse data, then train a model to recon dense data from sparse measurements.
Lots of potential pitfalls, but the concept is immensely powerful.
Reposted by Anthony A. Gatti
White text on white background instructing LLMs to give positive reviews is apparently now common enough to show up in searches for boilerplate text.
July 5, 2025 at 7:51 PM
White text on white background instructing LLMs to give positive reviews is apparently now common enough to show up in searches for boilerplate text.
Reposted by Anthony A. Gatti
We write papers, but we build people.
You (yes, you, my fellow academic) too; please don’t forget that.
You (yes, you, my fellow academic) too; please don’t forget that.
July 4, 2025 at 11:56 PM
We write papers, but we build people.
You (yes, you, my fellow academic) too; please don’t forget that.
You (yes, you, my fellow academic) too; please don’t forget that.
Reposted by Anthony A. Gatti
✨Some news✨: after finishing my postdoc, I’ll be starting my lab as an Assistant Professor at Georgia Tech. Join us in Atlanta to study how joints work and where they come from!
July 2, 2025 at 12:53 PM
✨Some news✨: after finishing my postdoc, I’ll be starting my lab as an Assistant Professor at Georgia Tech. Join us in Atlanta to study how joints work and where they come from!
Reposted by Anthony A. Gatti
Something big is coming up tomorrow. Watch this space…
💪🏻 ⚡️ ⚽️ 💪🏻🦵🏃🏻♂️➡️👟🥋🏋🏻🚴♂️📈📊📚
💪🏻 ⚡️ ⚽️ 💪🏻🦵🏃🏻♂️➡️👟🥋🏋🏻🚴♂️📈📊📚
June 25, 2025 at 6:28 PM
Something big is coming up tomorrow. Watch this space…
💪🏻 ⚡️ ⚽️ 💪🏻🦵🏃🏻♂️➡️👟🥋🏋🏻🚴♂️📈📊📚
💪🏻 ⚡️ ⚽️ 💪🏻🦵🏃🏻♂️➡️👟🥋🏋🏻🚴♂️📈📊📚
Reposted by Anthony A. Gatti
Are there useful or interesting ways to use LLMs other than prompting them? I feel like compressing all the text in the world via a hierarchically structured statistical model is probably useful, but that we're using it in a way that is unlikely to do what we'd hope.
June 15, 2025 at 7:06 PM
Are there useful or interesting ways to use LLMs other than prompting them? I feel like compressing all the text in the world via a hierarchically structured statistical model is probably useful, but that we're using it in a way that is unlikely to do what we'd hope.
Since LLMs came out I’ve thought they are the perfect tool for systematic reviews. This is an excellent use case.
👀This is impressive: Using an autonomous agent based on o3-mini and GPT-4.1, a team from Harvard, MIT & other institutions reproduced and updated an entire issue of Cochrane Reviews in two days… saving 12 person-years of work.
The AI reviews captured more papers & were more accurate than humans.
The AI reviews captured more papers & were more accurate than humans.
June 14, 2025 at 2:28 AM
Since LLMs came out I’ve thought they are the perfect tool for systematic reviews. This is an excellent use case.
Reposted by Anthony A. Gatti
Are you interested in muscle #biomechanics and looking for #postdoc opportunities?
If you have skills in (statistical) shape modelling, advanced data analyses or 3D imaging/model reconstructions, get in touch with me!
I will be at #SEB2025 (Antwerp), #CNB2025 (Helsinki), and #ISB2025 (Stockholm).
If you have skills in (statistical) shape modelling, advanced data analyses or 3D imaging/model reconstructions, get in touch with me!
I will be at #SEB2025 (Antwerp), #CNB2025 (Helsinki), and #ISB2025 (Stockholm).
June 12, 2025 at 2:56 PM
Are you interested in muscle #biomechanics and looking for #postdoc opportunities?
If you have skills in (statistical) shape modelling, advanced data analyses or 3D imaging/model reconstructions, get in touch with me!
I will be at #SEB2025 (Antwerp), #CNB2025 (Helsinki), and #ISB2025 (Stockholm).
If you have skills in (statistical) shape modelling, advanced data analyses or 3D imaging/model reconstructions, get in touch with me!
I will be at #SEB2025 (Antwerp), #CNB2025 (Helsinki), and #ISB2025 (Stockholm).
Reposted by Anthony A. Gatti
Our Siemens 7T Collaboration Scientist is moving to support the Siemens 7T Terra.X Impulse at Stanford. Siemens is rehiring for our position, located in Canada's National Ultra-High Field MRI platform cfmm.uwo.ca in London, Ontario 🇨🇦. onehealthineers.wd3.myworkdayjobs.com/SHSJB/job/OA...
Centre of Functional and Metabolic Mapping - Western University
Western University, in vibrant London, Ontario, delivers an academic and student experience second to none.
cfmm.uwo.ca
June 10, 2025 at 2:41 PM
Our Siemens 7T Collaboration Scientist is moving to support the Siemens 7T Terra.X Impulse at Stanford. Siemens is rehiring for our position, located in Canada's National Ultra-High Field MRI platform cfmm.uwo.ca in London, Ontario 🇨🇦. onehealthineers.wd3.myworkdayjobs.com/SHSJB/job/OA...
Reposted by Anthony A. Gatti
MIT News today features a paper with fun examples coming out this summer by our brilliant PhD student Leticia Mattos Da Silva, postdoc—and Columbia professor in a matter of days!— @silviasellan.bsky.social, and PhD student collaborator Natalia Pacheco-Tallaj. news.mit.edu/2025/animati... Flubber!
Animation technique simulates the motion of squishy objects
MIT researchers developed a computationally efficient method that could enable artists to design realistic simulations of elastic objects, like bouncy or squishy characters, for animated movies or vid...
news.mit.edu
June 6, 2025 at 1:15 PM
MIT News today features a paper with fun examples coming out this summer by our brilliant PhD student Leticia Mattos Da Silva, postdoc—and Columbia professor in a matter of days!— @silviasellan.bsky.social, and PhD student collaborator Natalia Pacheco-Tallaj. news.mit.edu/2025/animati... Flubber!
Reposted by Anthony A. Gatti
Radiology: Artificial Intelligence has joined the rapidly growing #Bluesky social media network https://pubs.rsna.org/page/ai/blog/our_presence_on_bluesky @radiology-ai.bsky.social @cekahn.bsky.social #ESPR2025 #PedsRad #radiology
June 5, 2025 at 7:15 AM
Radiology: Artificial Intelligence has joined the rapidly growing #Bluesky social media network https://pubs.rsna.org/page/ai/blog/our_presence_on_bluesky @radiology-ai.bsky.social @cekahn.bsky.social #ESPR2025 #PedsRad #radiology
Reposted by Anthony A. Gatti
90% of doing science is being open to new ideas.
May 31, 2025 at 6:14 PM
90% of doing science is being open to new ideas.
Reposted by Anthony A. Gatti
Reposted by Anthony A. Gatti
Over the last few years we have been developing methods for markerless motion capture of biomechanics and getting them into the clinics, such as at @abilitylab.bsky.social.
We are now developing foundation models from these large datasets and testing what this enables. Two recent preprints:
We are now developing foundation models from these large datasets and testing what this enables. Two recent preprints:
May 27, 2025 at 9:36 PM
Over the last few years we have been developing methods for markerless motion capture of biomechanics and getting them into the clinics, such as at @abilitylab.bsky.social.
We are now developing foundation models from these large datasets and testing what this enables. Two recent preprints:
We are now developing foundation models from these large datasets and testing what this enables. Two recent preprints: