Loading video...

Video Failed to Load

Go Home

๐Ÿš€ Weโ€™re hiring! Staff Scientist / Postdoc โ€“ Tissue Clearing & 3D Image Analysis (m/f/d) (LMU Munich) Are you a great fit, or do you know someone outstanding, please reach out ๐Ÿ” If you want to at the frontier of whole-organ / whole-body 3D imaging, and help generate truly...

erturklab's profile picture

Ali Max Erturk

90,722 subscribers

14,717 views โ€ข 6 months ago โ€ขvia X (Twitter)

LIVE

Anya Rossiโ€ข Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Another beautiful 3D analysis of mouse eye vasculature using tissue clearing and light-sheet microscopy. Unlike many others (but like EyeDISCO) it can be applied to pigmented eyes Luc Krimpenfort et al., Lars Jakobsson lab
0:25

Another beautiful 3D analysis of mouse eye vasculature using tissue clearing and light-sheet microscopy. Unlike many others (but like EyeDISCO) it can be applied to pigmented eyes Luc Krimpenfort et al., Lars Jakobsson lab

Alain Chรฉdotal

97,020 views โ€ข 3 years ago

Tissue clearing of bones + 3D light-sheet imaging combined with high-dimensional spatial profiling reveals how CML rewires the bone marrow microenvironment in region-specific ways, far beyond simple changes in cell counts. Bettina Weigelin and Christian M. Schรผrch teams. #DISCO #clearing #3Dimaging #lightsheet #bone
0:25

Tissue clearing of bones + 3D light-sheet imaging combined with high-dimensional spatial profiling reveals how CML rewires the bone marrow microenvironment in region-specific ways, far beyond simple changes in cell counts. Bettina Weigelin and Christian M. Schรผrch teams. #DISCO #clearing #3Dimaging #lightsheet #bone

Ali Max Erturk

22,759 views โ€ข 4 months ago

We are hiring a Lab Technician/Scientist at Deep Piction At Deep Piction, we work on medically unmet challenges using high-resolution whole-body imaging with AI. To make this possible, we need strong wet-lab execution. ๐Ÿ”— APPLY HERE: This role will support the team across diverse experimental workflows and help ensure that our work is reliable, reproducible, and scalable. If you enjoy hands-on lab work, structure, and making things run properly, this could be a great fit. ๐Ÿ“ Munich, on-site At Deep Piction, we work on medically unmet challenges, including infectious diseases and cancer. We combine high-resolution whole-body imaging with AI to develop the most targeted and precise therapies. To make this possible, we need strong wet-lab execution. This role will support the team across diverse experimental workflows and help ensure that our work is reliable, reproducible, and scalable. If you enjoy hands-on lab work, structure, and making things run properly, this could be a great fit. ๐Ÿ“ Munich, on-site If someone comes to mind who would be a great fit, Iโ€™m sure they would be excited to see this opportunity, please feel free to share. If someone comes to mind who would be a great fit, Iโ€™m sure they would be excited to see this opportunity, please feel free to share.
0:36

We are hiring a Lab Technician/Scientist at Deep Piction At Deep Piction, we work on medically unmet challenges using high-resolution whole-body imaging with AI. To make this possible, we need strong wet-lab execution. ๐Ÿ”— APPLY HERE: This role will support the team across diverse experimental workflows and help ensure that our work is reliable, reproducible, and scalable. If you enjoy hands-on lab work, structure, and making things run properly, this could be a great fit. ๐Ÿ“ Munich, on-site At Deep Piction, we work on medically unmet challenges, including infectious diseases and cancer. We combine high-resolution whole-body imaging with AI to develop the most targeted and precise therapies. To make this possible, we need strong wet-lab execution. This role will support the team across diverse experimental workflows and help ensure that our work is reliable, reproducible, and scalable. If you enjoy hands-on lab work, structure, and making things run properly, this could be a great fit. ๐Ÿ“ Munich, on-site If someone comes to mind who would be a great fit, Iโ€™m sure they would be excited to see this opportunity, please feel free to share. If someone comes to mind who would be a great fit, Iโ€™m sure they would be excited to see this opportunity, please feel free to share.

Ali Max Erturk

13,615 views โ€ข 2 months ago

Weโ€™re open-sourcing HY-World 2.0, a multimodal world model that generates, reconstructs, and simulates interactive *3D worlds* from text, images, and videos. Outputs can be integrated into game engines and embodied simulation pipelines. Key highlights: ๐Ÿ”น One-click world generation Turn text or image into interactive 3D worlds automatically. ๐Ÿ”น Pipeline-ready 3D outputs Editable 3D worlds for Unity and Unreal Engine, with standard 3D exports including mesh, 3DGS, and point clouds. ๐Ÿ”น Unified world model system One model family for world generation and reconstruction across synthetic and real-world scenes. ๐Ÿ”น Interactive character mode Explore generated 3D worlds in real time with physics-aware movement and collision support. โœจ Apply for access: ๐Ÿ”— GitHub: ๐Ÿค— Hugging Face: ๐Ÿ“„ Technical Report:
1:04

Weโ€™re open-sourcing HY-World 2.0, a multimodal world model that generates, reconstructs, and simulates interactive *3D worlds* from text, images, and videos. Outputs can be integrated into game engines and embodied simulation pipelines. Key highlights: ๐Ÿ”น One-click world generation Turn text or image into interactive 3D worlds automatically. ๐Ÿ”น Pipeline-ready 3D outputs Editable 3D worlds for Unity and Unreal Engine, with standard 3D exports including mesh, 3DGS, and point clouds. ๐Ÿ”น Unified world model system One model family for world generation and reconstruction across synthetic and real-world scenes. ๐Ÿ”น Interactive character mode Explore generated 3D worlds in real time with physics-aware movement and collision support. โœจ Apply for access: ๐Ÿ”— GitHub: ๐Ÿค— Hugging Face: ๐Ÿ“„ Technical Report:

Tencent Hy

368,961 views โ€ข 2 months ago

โšก๐ŸŽ‰ We are thrilled to introduce VORTEX, an AI-powered computational framework for predicting 3D Spatial Transcriptomics (ST) using 3D tissue images and minimal 2D ST! ๐Ÿงฌ By combining cutting-edge 3D non-destructive tissue imaging with AI, VORTEX imputes the 3D molecular landscape of large tissue samples in a cost-effective and scalable manner. ๐Ÿง ๐Ÿ’กOur approach: By pretraining on diverse 3D morphologyโ€“2D transcriptomic pairs from heterogeneous tissue samples, and then fine-tuning on minimal 2D ST data from a volume of interest, VORTEX leverages both generic tissue-specific and sample-specific morphomolecular correlates to predict 3D ST. Congratulations to our superstar co-leads Cristina Almagro Pรฉrez and Andrew H. Song, this was an exciting collaboration with Jonathan Liu Sizun Jiang Ali Bashashati. Preprint: Demo: Read the excellent blog from our superstar grad student Cristina Almagro Pรฉrez: Also see our previous work on 3D Computational Pathology from Andrew H. Song published in Cell last year: Stay tuned for more to come.
0:51

โšก๐ŸŽ‰ We are thrilled to introduce VORTEX, an AI-powered computational framework for predicting 3D Spatial Transcriptomics (ST) using 3D tissue images and minimal 2D ST! ๐Ÿงฌ By combining cutting-edge 3D non-destructive tissue imaging with AI, VORTEX imputes the 3D molecular landscape of large tissue samples in a cost-effective and scalable manner. ๐Ÿง ๐Ÿ’กOur approach: By pretraining on diverse 3D morphologyโ€“2D transcriptomic pairs from heterogeneous tissue samples, and then fine-tuning on minimal 2D ST data from a volume of interest, VORTEX leverages both generic tissue-specific and sample-specific morphomolecular correlates to predict 3D ST. Congratulations to our superstar co-leads Cristina Almagro Pรฉrez and Andrew H. Song, this was an exciting collaboration with Jonathan Liu Sizun Jiang Ali Bashashati. Preprint: Demo: Read the excellent blog from our superstar grad student Cristina Almagro Pรฉrez: Also see our previous work on 3D Computational Pathology from Andrew H. Song published in Cell last year: Stay tuned for more to come.

Faisal Mahmood

17,969 views โ€ข 1 year ago

My studio is hiring a remote 3D Houdini Motion Designer! ๐Ÿ™Œ If you have experience with Houdini & Redshift and a passion for design, apply now to work on exciting projects for top brands. Also, if you know someone interested, please share this post! Link to application in bio.
0:23

My studio is hiring a remote 3D Houdini Motion Designer! ๐Ÿ™Œ If you have experience with Houdini & Redshift and a passion for design, apply now to work on exciting projects for top brands. Also, if you know someone interested, please share this post! Link to application in bio.

Romain Guillon

21,956 views โ€ข 2 years ago

#MicroscopyMonday ๐Ÿ”ฌ โ€” A 3D reconstruction of a cleared mouse embryo labeled for neurons (magenta) and muscles (cyan). This type of imaging lets researchers can image deep into biological tissue to study neuronal morphology in an intact animal or embryo. Credit: G Carrillo
0:33

#MicroscopyMonday ๐Ÿ”ฌ โ€” A 3D reconstruction of a cleared mouse embryo labeled for neurons (magenta) and muscles (cyan). This type of imaging lets researchers can image deep into biological tissue to study neuronal morphology in an intact animal or embryo. Credit: G Carrillo

Marine Biological Laboratory (MBL)

21,065 views โ€ข 1 year ago

Prince of Persia โ€“ Community Project The Prince of Persia community has come together to create its own project following the cancellation of the Sands of Time remake! This is not a traditional remake, but a large-scale mod aiming to replace most 3D models with high-quality assets and introduce global illumination through path tracing technology. Weโ€™re working on an official website โ€” stay tuned! Current Status: Early developmentโณ About the Project: ๐Ÿ”น Public and community-driven ๐Ÿ”น Fully playable ๐Ÿ”น Focused on next-gen visuals while preserving the original experience We are looking for contributors! ๐Ÿ”น 3D Modelers / Artists ๐Ÿ”น Texture Artists ๐Ÿ”น Programmers ๐Ÿ”น RTX Remix experts This is a hobby project with no payment, focused on long-term development without strict deadlines. Weโ€™re looking for passionate people who enjoy creating and want to be part of something specialโœจ Join us on Discord and become part of the team: ๐Ÿ‘‰๐Ÿป Follow our progress, share feedback, or get involved in development!๐Ÿ˜‰ #PrinceofPersia #ThePoPProject
0:20

Prince of Persia โ€“ Community Project The Prince of Persia community has come together to create its own project following the cancellation of the Sands of Time remake! This is not a traditional remake, but a large-scale mod aiming to replace most 3D models with high-quality assets and introduce global illumination through path tracing technology. Weโ€™re working on an official website โ€” stay tuned! Current Status: Early developmentโณ About the Project: ๐Ÿ”น Public and community-driven ๐Ÿ”น Fully playable ๐Ÿ”น Focused on next-gen visuals while preserving the original experience We are looking for contributors! ๐Ÿ”น 3D Modelers / Artists ๐Ÿ”น Texture Artists ๐Ÿ”น Programmers ๐Ÿ”น RTX Remix experts This is a hobby project with no payment, focused on long-term development without strict deadlines. Weโ€™re looking for passionate people who enjoy creating and want to be part of something specialโœจ Join us on Discord and become part of the team: ๐Ÿ‘‰๐Ÿป Follow our progress, share feedback, or get involved in development!๐Ÿ˜‰ #PrinceofPersia #ThePoPProject

PoP Universe

67,158 views โ€ข 2 months ago

DISCO-MS allows molecular analysis via proteomics and AI after tissue clearing. Now we are in the game to discover the molecular underpinnings of diseases. To this end, we are expanding our proteomics team. Please apply at (distribute๐Ÿ˜Š):
0:58

DISCO-MS allows molecular analysis via proteomics and AI after tissue clearing. Now we are in the game to discover the molecular underpinnings of diseases. To this end, we are expanding our proteomics team. Please apply at (distribute๐Ÿ˜Š):

Ali Max Erturk

31,956 views โ€ข 2 years ago

Introducing ComfyUI in Unity demo - Supercharges your game development with open-source gen AI. Run any creative workflow in the cloud, and integrative nicely to your Unity scene view port. Imaging what you can already do with ComfyUI - texture, sprite generation - 3d generation - llm, story generation You can now scale, and build tools around these creative workflows. And integrate it into any domain-specific pipeline. Inspired by Magnific.ai ! Running serverless with Modal p.s. I'm still in GDC, if anyone is interested please reach out. Will be testing with more workflows this week.
0:52

Introducing ComfyUI in Unity demo - Supercharges your game development with open-source gen AI. Run any creative workflow in the cloud, and integrative nicely to your Unity scene view port. Imaging what you can already do with ComfyUI - texture, sprite generation - 3d generation - llm, story generation You can now scale, and build tools around these creative workflows. And integrate it into any domain-specific pipeline. Inspired by Magnific.ai ! Running serverless with Modal p.s. I'm still in GDC, if anyone is interested please reach out. Will be testing with more workflows this week.

BennyKok

57,899 views โ€ข 2 years ago

From 3D imaging to therapy Using our DISCO tissue clearing and whole organ 3D imaging platform, we revealed skull to meninges microchannels connecting calvarial bone marrow with the brain borders in mice (Cai...Ertรผrk, Nature Neuroscience,2018, We then extended this biology to humans, discovering distinct skull bone marrow programs and structural skull meninges connections in health and neurological disease (Kolabas...Ertรผrk, Cell, 2023). Now, a new study reports a first therapeutic application of this route: intracalvariosseous (calvarial) injection of drug loaded albumin nanoparticles to โ€œhijackโ€ calvarial immune cells, which then migrate via skull meninges microchannels to CNS lesions, bypassing the blood brain barrier and improving outcomes in stroke models, with encouraging clinical feasibility data (Gao et al., Cell, 2026) We are proud that DISCO enabled biology that is now turning into concrete therapeutic strategies for devastating neurological diseases. More to come. #DISCO #TissueClearing #Neuroimmunology #Stroke #Nanomedicine #DrugDelivery #BBB #CNS Refs (for linking in comments): Cai et al. Nat Neuroscience, Kolabas et al. Cell 2023, the video from Gao et al. Cell 2026 (online Jan 16, 2026).
0:29

From 3D imaging to therapy Using our DISCO tissue clearing and whole organ 3D imaging platform, we revealed skull to meninges microchannels connecting calvarial bone marrow with the brain borders in mice (Cai...Ertรผrk, Nature Neuroscience,2018, We then extended this biology to humans, discovering distinct skull bone marrow programs and structural skull meninges connections in health and neurological disease (Kolabas...Ertรผrk, Cell, 2023). Now, a new study reports a first therapeutic application of this route: intracalvariosseous (calvarial) injection of drug loaded albumin nanoparticles to โ€œhijackโ€ calvarial immune cells, which then migrate via skull meninges microchannels to CNS lesions, bypassing the blood brain barrier and improving outcomes in stroke models, with encouraging clinical feasibility data (Gao et al., Cell, 2026) We are proud that DISCO enabled biology that is now turning into concrete therapeutic strategies for devastating neurological diseases. More to come. #DISCO #TissueClearing #Neuroimmunology #Stroke #Nanomedicine #DrugDelivery #BBB #CNS Refs (for linking in comments): Cai et al. Nat Neuroscience, Kolabas et al. Cell 2023, the video from Gao et al. Cell 2026 (online Jan 16, 2026).

Ali Max Erturk

15,808 views โ€ข 5 months ago

๐Ÿš€ Introducing Meshy-4 โ€” The next-gen 3D model generator is now available to everyone at โœจ Experience dramatically improved mesh geometry in both Image to 3D and Text to 3D workflows. โค๏ธ Watch the video and discover Meshyโ€™s full potential with us!
0:54

๐Ÿš€ Introducing Meshy-4 โ€” The next-gen 3D model generator is now available to everyone at โœจ Experience dramatically improved mesh geometry in both Image to 3D and Text to 3D workflows. โค๏ธ Watch the video and discover Meshyโ€™s full potential with us!

MeshyAI

52,437 views โ€ข 1 year ago

Generate image, 3D, and video from a single sketch in one click in ComfyUI with AI! Iโ€™m excited to share a cutting-edge workflow Iโ€™ve developed that combines inside ComfyUI: Runway with fal. ai api (yes there is a node for it :) ), Stable AIโ€™s stable fast 3D , powerful Flux, ControlNet, IPAdapter, Gemini LLm in ComfyUI. This innovation allows you to generate high-quality visuals and 3D models, reposition objects, and create videosโ€”completely automated from a simple sketch input. Would you link a tutorial for it ? #AI #ComfyUI #3DModeling #Automation #CreativeTech
0:20

Generate image, 3D, and video from a single sketch in one click in ComfyUI with AI! Iโ€™m excited to share a cutting-edge workflow Iโ€™ve developed that combines inside ComfyUI: Runway with fal. ai api (yes there is a node for it :) ), Stable AIโ€™s stable fast 3D , powerful Flux, ControlNet, IPAdapter, Gemini LLm in ComfyUI. This innovation allows you to generate high-quality visuals and 3D models, reposition objects, and create videosโ€”completely automated from a simple sketch input. Would you link a tutorial for it ? #AI #ComfyUI #3DModeling #Automation #CreativeTech

Lovis Odin

36,789 views โ€ข 1 year ago

The time has finally come! After months of hard work, the Three.js Roadmap beta is now LIVE! ๐Ÿ™Œ๐Ÿป ๐Ÿ‘‰๐Ÿป If you're interested in learning 3D web development but are on a tight budget๐Ÿ’ฐ, my courses are perfect for you! I've launched the site with four short courses: โœ… Introduction to Three.js (FREE) โœ… 3D Math Fundamentals โœ… Creating a Debug UI โœ… Lighting and Shadows Purchasing a paid course will also gain you access to the Three.js Roadmap Discord server where you can ask questions and chat with other developers. For the next few weeks I'll be focusing on polish and stability for the site, and then I will go into full content-creation mode and start pumping out new courses! Looking forward to seeing what we build together! ๐Ÿ”จ #threejs #webgl #gamedev
0:47

The time has finally come! After months of hard work, the Three.js Roadmap beta is now LIVE! ๐Ÿ™Œ๐Ÿป ๐Ÿ‘‰๐Ÿป If you're interested in learning 3D web development but are on a tight budget๐Ÿ’ฐ, my courses are perfect for you! I've launched the site with four short courses: โœ… Introduction to Three.js (FREE) โœ… 3D Math Fundamentals โœ… Creating a Debug UI โœ… Lighting and Shadows Purchasing a paid course will also gain you access to the Three.js Roadmap Discord server where you can ask questions and chat with other developers. For the next few weeks I'll be focusing on polish and stability for the site, and then I will go into full content-creation mode and start pumping out new courses! Looking forward to seeing what we build together! ๐Ÿ”จ #threejs #webgl #gamedev

Dan Greenheck

21,272 views โ€ข 1 year ago

STEAL THE BRAINROT is expanding. Weโ€™re hiring a high-level UEFN Level Designer to lead our in-game events. Weโ€™re looking for someone very experienced and creative, who knows how to bring their talent and ideas into high-quality in-game events. There is an existing structure and visual style, and the role requires the ability to adapt and build new events based on what has already been done. Requirements: - Several years of experience in level / environment design - Strong portfolio - All assets must be custom made - Strong experience with Blender - Deep understanding of materials - Advanced UEFN experience (materials, VFX, optimization) - Full-time availability - Available to start immediately Weโ€™re looking for talented people with real experience, not beginners. Compensation is high and based on experience. A signing bonus is available for the right candidate. Below are examples of past events, this is the quality bar: 100% custom assets, modeled in Blender, with custom materials & VFX in UEFN, fully optimized. DM me with your portfolio.
0:41

STEAL THE BRAINROT is expanding. Weโ€™re hiring a high-level UEFN Level Designer to lead our in-game events. Weโ€™re looking for someone very experienced and creative, who knows how to bring their talent and ideas into high-quality in-game events. There is an existing structure and visual style, and the role requires the ability to adapt and build new events based on what has already been done. Requirements: - Several years of experience in level / environment design - Strong portfolio - All assets must be custom made - Strong experience with Blender - Deep understanding of materials - Advanced UEFN experience (materials, VFX, optimization) - Full-time availability - Available to start immediately Weโ€™re looking for talented people with real experience, not beginners. Compensation is high and based on experience. A signing bonus is available for the right candidate. Below are examples of past events, this is the quality bar: 100% custom assets, modeled in Blender, with custom materials & VFX in UEFN, fully optimized. DM me with your portfolio.

FeRinS

128,870 views โ€ข 6 months ago

๐Ÿšจ Hunyuan 3D 3.1 Pro and Rapid is here on fal! ๐ŸŽฏ Pro: High-fidelity Image-to-3D and Text-to-3D generation โšก Rapid: Speed-optimized 3D generation โœจ Smart Topology and Part generation for advanced 3D workflows
0:21

๐Ÿšจ Hunyuan 3D 3.1 Pro and Rapid is here on fal! ๐ŸŽฏ Pro: High-fidelity Image-to-3D and Text-to-3D generation โšก Rapid: Speed-optimized 3D generation โœจ Smart Topology and Part generation for advanced 3D workflows

fal

26,048 views โ€ข 4 months ago

๐Ÿš€Exciting News! Tencent Hunyuan 3D AI Creation Engine v2.5 is here, revolutionizing 3D generation with ultra-high-definition modeling! 1โƒฃMassive Leap in Precision: Upgraded geometric model with 10B parameters (up from 1B) and 10x more mesh faces, delivering 1024-resolution geometric detailsโ€”smoother surfaces, sharper edges, and richer visuals! 2โƒฃHigh-quality Textures & PBR: Supports high-quality textures and fine-grained bump mapping for lifelike surfaces. Industry-first multi-view PBR generation for realistic lighting and reflections. 3โƒฃAnimation Boost: Optimized skeletal rigging with automatic bone binding and skin weight assignment, streamlining 3D animation workflows. 4โƒฃFlexible Workflows: New pipeline templates for text-to-3D and image-to-3D mesh reduction, plus multi-view 3D generation, empowering game development, animation, and more with customizable 3D assets. 5โƒฃAccessible Creation: Generate high-quality 3D models from text or images, slashing complexity. Free daily quota doubled to 20 for the AI Engine, with the API now live on Tencent Cloud! โ˜€๏ธFrom games to AR/VR, Hunyuan 3D is redefining 3D AIGC, making creation faster, smarter, and more inclusive. Try it now! Tencent Hunyuan 3D AI Creation Engine: Tencent Hunyuan 3D Open Source:
1:30

๐Ÿš€Exciting News! Tencent Hunyuan 3D AI Creation Engine v2.5 is here, revolutionizing 3D generation with ultra-high-definition modeling! 1โƒฃMassive Leap in Precision: Upgraded geometric model with 10B parameters (up from 1B) and 10x more mesh faces, delivering 1024-resolution geometric detailsโ€”smoother surfaces, sharper edges, and richer visuals! 2โƒฃHigh-quality Textures & PBR: Supports high-quality textures and fine-grained bump mapping for lifelike surfaces. Industry-first multi-view PBR generation for realistic lighting and reflections. 3โƒฃAnimation Boost: Optimized skeletal rigging with automatic bone binding and skin weight assignment, streamlining 3D animation workflows. 4โƒฃFlexible Workflows: New pipeline templates for text-to-3D and image-to-3D mesh reduction, plus multi-view 3D generation, empowering game development, animation, and more with customizable 3D assets. 5โƒฃAccessible Creation: Generate high-quality 3D models from text or images, slashing complexity. Free daily quota doubled to 20 for the AI Engine, with the API now live on Tencent Cloud! โ˜€๏ธFrom games to AR/VR, Hunyuan 3D is redefining 3D AIGC, making creation faster, smarter, and more inclusive. Try it now! Tencent Hunyuan 3D AI Creation Engine: Tencent Hunyuan 3D Open Source:

Tencent Hy

58,152 views โ€ข 1 year ago

๐ŸŽ FELIX Grand Presence of K-POP Our LED truck is in front of the JYPE building until 4 PM KST! Weโ€™re sharing our love and support for Felix and hope heโ€™ll see it, or that a staff member will show him. ๐Ÿฅฐ ๐Ÿ”น If you see the truck, please feel free to share photos and videos with us! #WELOVEYOUFELIX
0:30

๐ŸŽ FELIX Grand Presence of K-POP Our LED truck is in front of the JYPE building until 4 PM KST! Weโ€™re sharing our love and support for Felix and hope heโ€™ll see it, or that a staff member will show him. ๐Ÿฅฐ ๐Ÿ”น If you see the truck, please feel free to share photos and videos with us! #WELOVEYOUFELIX

Felix ํ•„๋ฆญ์Šค Central

96,443 views โ€ข 5 months ago

Today weโ€™re excited to unveil a new generation of Segment Anything Models: 1๏ธโƒฃ SAM 3 enables detecting, segmenting and tracking of objects across images and videos, now with short text phrases and exemplar prompts. ๐Ÿ”— Learn more about SAM 3: 2๏ธโƒฃ SAM 3D brings the model collection into the 3rd dimension to enable precise reconstruction of 3D objects and people from a single 2D image. ๐Ÿ”— Learn more about SAM 3D: These models offer innovative capabilities and unique tools for developers and researchers to create, experiment and uplevel media workflows.
0:34

Today weโ€™re excited to unveil a new generation of Segment Anything Models: 1๏ธโƒฃ SAM 3 enables detecting, segmenting and tracking of objects across images and videos, now with short text phrases and exemplar prompts. ๐Ÿ”— Learn more about SAM 3: 2๏ธโƒฃ SAM 3D brings the model collection into the 3rd dimension to enable precise reconstruction of 3D objects and people from a single 2D image. ๐Ÿ”— Learn more about SAM 3D: These models offer innovative capabilities and unique tools for developers and researchers to create, experiment and uplevel media workflows.

AI at Meta

1,087,119 views โ€ข 7 months ago

โšก๏ธ๐Ÿ“ฃ๐Ÿ‘‡Tremendously excited to share our new Cell article, where we develop TriPath, a method for analyzing 3D pathology samples using weakly supervised AI. Article: TriPath enables 3D computational pathology via 3D multiple instance learning allowing AI models to capture intricate morphological details from pathology volumes. Code: Blog post: Tested on two different imaging modalities, and patient cohorts from two institutions. Our superstar Andrew H. Song put in a monumental effort of leading the study, in a fantastic collaboration with Jonathan Liu at University of Washington . Interesting aspects: - Utilizing the whole tissue volume and leveraging 3D deep learning enable superior risk prediction performance compared to 2D deep learning baselines based on a few sampled tissue sections that emulate standard clinical practice. This indicates TriPath can harness additional information provided by 3D tissue morphology. - The performance is also superior to clinical baselines from a reader study that involved six expert pathologists. - The morphologically heterogeneous tissue volume could lead to opposing patient-level outcome predictions, dependent on which portion of the tissue volume is used. This concurs with current clinical literature warning that tissue sampling bias can lead to misdiagnosis. Some limitations: - While the 3D pathology cohort size is unprecedented, it is smaller than typical 2D pathology cohorts. Further large-scale studies will be required for validation. Nevertheless, we believe that this study will initiate a positive cycle, encouraging academic institutions and pharmaceutical companies to contribute large banks of human tissue blocks with paired clinical outcomes, thus speeding up advancements in 3D computational pathology. Concluding insights: We believe that 3D pathology is just around the corner - It has the huge potential to not only augment/improve the current clinical practice centered around 2D examination of human tissue, but also help reveal novel biomarkers for prognosis and therapeutic response.. Harvard Medical School Harvard Data Science Initiative Mass General Brigham Broad Institute
4:23

โšก๏ธ๐Ÿ“ฃ๐Ÿ‘‡Tremendously excited to share our new Cell article, where we develop TriPath, a method for analyzing 3D pathology samples using weakly supervised AI. Article: TriPath enables 3D computational pathology via 3D multiple instance learning allowing AI models to capture intricate morphological details from pathology volumes. Code: Blog post: Tested on two different imaging modalities, and patient cohorts from two institutions. Our superstar Andrew H. Song put in a monumental effort of leading the study, in a fantastic collaboration with Jonathan Liu at University of Washington . Interesting aspects: - Utilizing the whole tissue volume and leveraging 3D deep learning enable superior risk prediction performance compared to 2D deep learning baselines based on a few sampled tissue sections that emulate standard clinical practice. This indicates TriPath can harness additional information provided by 3D tissue morphology. - The performance is also superior to clinical baselines from a reader study that involved six expert pathologists. - The morphologically heterogeneous tissue volume could lead to opposing patient-level outcome predictions, dependent on which portion of the tissue volume is used. This concurs with current clinical literature warning that tissue sampling bias can lead to misdiagnosis. Some limitations: - While the 3D pathology cohort size is unprecedented, it is smaller than typical 2D pathology cohorts. Further large-scale studies will be required for validation. Nevertheless, we believe that this study will initiate a positive cycle, encouraging academic institutions and pharmaceutical companies to contribute large banks of human tissue blocks with paired clinical outcomes, thus speeding up advancements in 3D computational pathology. Concluding insights: We believe that 3D pathology is just around the corner - It has the huge potential to not only augment/improve the current clinical practice centered around 2D examination of human tissue, but also help reveal novel biomarkers for prognosis and therapeutic response.. Harvard Medical School Harvard Data Science Initiative Mass General Brigham Broad Institute

Faisal Mahmood

65,520 views โ€ข 2 years ago