Jonathan Liu

@UW Professor, Director of Molecular #Biophotonics Lab. Open-top #lightsheet, #invivomicroscopy, #3Dpathology, Co-founder

[Jonathan Liu @jonliu123]

Excited to share our vision for nondestructive 3D pathology for clinical decision support! We discuss optical, computational and translational challenges. https://t.co/qVCHAXjQ39 @adam_k_glaser @hopelessk @RederredeR @UWMadisonLOCI @anantm

[Faisal Mahmood @AI4Pathology]

⚡🎉 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! 🧬 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.

🧠💡Our approach:
By pretraining on diverse 3D morphology–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 @Criis_perez99 and @GreatAndrew90, this was an exciting collaboration with @jonliu123 @SizunJ @ABashashati.

Preprint: https://t.co/yqLLQr14Bg
Demo: https://t.co/iCuN7UBahG
Read the excellent blog from our superstar grad student @Criis_perez99: https://t.co/RBHYFGUkk3

Also see our previous work on 3D Computational Pathology from @GreatAndrew90 published in Cell last year: https://t.co/DM5nwUhugD

Stay tuned for more to come.

[Adam Glaser @adam_k_glaser]

New review out on imaging 3D cell cultures. Congratulations to Huai-Ching and @jonliu123 on leading this excellent new review! https://t.co/7bZyO82f9e

[Jonathan Liu @jonliu123]

Excited to work on this with @alpenglowbio @AI4Pathology @EbenRosenthal @TopfHNS and our talented engineers and clinicians @UW !

[Mechanical Engineering at UW @ME_at_UW]

A new project led by ME Professor @jonliu123 aims to help surgeons to remove tumors more completely & rapidly during a single procedure. The multi-university and industry partnership is funded by an up to $21.1 million award from @ARPA_H. https://t.co/Zy7uxiTCqb

[Mechanical Engineering at UW @ME_at_UW]

ME Professor Jonathan Liu recently received an R01 grant from @NIDDKgov to develop computational 3D pathology methods for Barrett’s esophagus risk stratification. Learn more: https://t.co/a6M9v7C7i9 @NIH @jonliu123 @UWMedicine @BrighamWomens @fredhutch @uwengineering

[NIBIB @NIBIBgov]

3D tissues can reveal more about disease than traditional 2D slices, but they are enormously complex. Find out how a new AI tool can analyze these data-rich specimens to predict outcomes: https://t.co/02SE4akF0V @GreatAndrew90 @jonliu123 @AI4Pathology @ME_at_UW

[Jonathan Liu @jonliu123]

Proud of this latest publication from graduating PhD student, @Kevin_W_Bishop. In this 5th-generation of OTLS microscopes from our lab, we improve axial resolution to reduce out-of-focus background in densely labeled specimens (e.g. our fluorescent anolog of H&E).

[Kevin Bishop @Kevin_W_Bishop]

Happy to share our latest OTLS microscope for 3D pathology from @jonliu123's lab, out now in Optics Letters!

Full text: https://t.co/DOtIqC46K5

[Jonathan Liu @jonliu123]

In addition to fully computational analyses of our #3Dpathology datasets, we are exploring AI-triage methods to keep pathologists in the loop. This should enable improved diagnostic accuracy (due to comprehensive sampling of whole biopsies) while reducing pathologist workloads.

[GAN GAO @gaogan96]

Our paper is out @CVPR CVMI workshop!
https://t.co/FwdPAnQvPh

We report a DL approach that leverages contextual information along the depth axis to identify the highest-risk 2D sections within whole biopsies to help pathologists diagnose diseases more accurately.

[Cell Press @CellPressNews]

In this @CellCellPress article, @AI4Pathology Faisal Mahmood, @GreatAndrew90 & @jonliu123 develop TriPath, a method for analyzing 3D pathology samples using weakly supervised AI #ASCO24 https://t.co/ILvK5KznQE

[Eric Topol @EricTopol]

With #AI, it's time for pathology to go #3D
https://t.co/DxOPhiA8eJ @CellCellPress @AI4Pathology @GreatAndrew90 @jonliu123

[Jonathan Liu @jonliu123]

@GreatAndrew90 @CellCellPress @AI4Pathology Congrats and looking forward to our future collaborations to improve healthcare!

[Jonathan Liu @jonliu123]

Exciting collaboration (and more to come) with @AI4Pathology and @GreatAndrew90 , just published in Cell !

[Faisal Mahmood @AI4Pathology]

⚡️📣👇Tremendously excited to share our new @CellCellPress article, where we develop TriPath, a method for analyzing 3D pathology samples using weakly supervised AI. Article: https://t.co/7ydyLcPVww. TriPath enables 3D computational pathology via 3D multiple instance learning allowing AI models to capture intricate morphological details from pathology volumes.

Code: https://t.co/t9zeKWafsx
Blog post: https://t.co/pDzFMMG1qo

Tested on two different imaging modalities, and patient cohorts from two institutions. Our superstar @GreatAndrew90 put in a monumental effort of leading the study, in a fantastic collaboration with @jonliu123 at @UW .

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..

@harvardmed @harvard_data @MassGenBrigham @broadinstitute

[Nature Protocols @NatureProtocols]

#FeaturedProtocol: A workflow for robust #3Dpathology datasets of whole preclinical & clinical tissues from @Kevin_W_Bishop & @jonliu123 https://t.co/YXFKXquOTs

[Cole DeForest @coledeforest]

HUGE NEWS! In our new preprint, we introduce “grayscale image z-stack-guided multiphoton optical-lithography” (GIZMO) to rapidly photomodulate materials in full 3D non-binary patterns at sub-µm resolutions spanning large volumes (>mm3).

https://t.co/5QJmZDschS

Paper 🧵 (1/19)

[Kevin Bishop @Kevin_W_Bishop]

Our end-to-end workflow for 3D pathology is now published in @NatureProtocols!

This includes all the steps to go from archived pathology tissues to 3D H&E-like datasets, with an emphasis on quality control for large studies.

Full text at: https://t.co/MfPzUCe3aJ

[Jonathan Liu @jonliu123]

Entertaining article by David Sokolov at Fred Hutch Cancer Center on our AI-triaged 3D pathology work led by @LindseyBarner and Gan Gao with @DeeptiReddiMD and Bill Grady…

https://t.co/gMVQU7xe0W via @fredhutch

[Andrew H. Song @GreatAndrew90]

Super excited to see our review paper on AI for computational pathology finally out!! We provide an extensive coverage of how AI has and will shape the field of pathology.

Such a fun experience with my co-author @GuillaumeJaume, and @AI4Pathology

Link: https://t.co/yDoXl9qvZe

[Jonathan Liu @jonliu123]

Check out @LindseyBarner 's final PhD paper from my lab! "AI-triaged 3D pathology to improve detection of esophageal neoplasia while reducing pathologist workloads" With @DeeptiReddiMD and Bill Grady at @fredhutch and @AI4Pathology at @BrighamWomens. https://t.co/1fzBcOzbz6

[Jonathan Liu @jonliu123]

@Editor_GFL @Kevin_W_Bishop @pathologistmag Thanks. Will reach out if/when this manuscript is officially accepted for publication (after peer review).

[Jonathan Liu @jonliu123]

@Editor_GFL @Kevin_W_Bishop @pathologistmag Would be nice to provide an update now that it’s been quite a few years since our first publication on this technology was covered by thePathologist! - https://t.co/AMjFkV2XUp

[Jonathan Liu @jonliu123]

It’s one thing to publish images that represent our best “outliers”(which we all do initially), but a different challenge to image hundreds of clinical samples with near-100% yield. Here we release our tips and tricks from sample prep to QC, from years of iteration! #3Dpathology

[Kevin Bishop @Kevin_W_Bishop]

Excited to share our end-to-end workflow for 3D pathology - protocol preprint is out now! More👇👇

https://t.co/82ht7ihnG1