Our paper is out 💫
We present DISCOVER, a two-step interpretability for classification models: using fake-amplified images to interpret the semantic image properties driving the model’s decision, followed by standard instance interpretability!
https://t.co/JFwbOOn1LS
🧵
1/7
⚡️🔬📣 Excited to share our new @Nature article building and evaluating PathChat, a multimodal generative AI copilot and chatbot for human pathology. Article: https://t.co/OAIG31ofWJ Open Access Link:
https://t.co/tvw6W6qmT9
We leverage our previous success in building foundation models for computational pathology such as UNI / CONCH and combine it with the advancements of large vision language models and generative AI to enable PathChat to answer diverse pathology-related queries. We assessed PathChat using both multiple choice diagnostic questions and open-ended questions.
Congratulations to @MYLu97@chenbowen118 @DFKW_MD @richardjchen and everyone else who contributed to this work.
Also see blog post from @MYLu97 about this work: https://t.co/exjpKMnrQp , also teasing the development and preview of PathChat 2, a successor to PathChat 1 bringing new capabilities and substantially improved performance to the state-of-the-art.
Our new @biorxivpreprint in out ✨
We adopted concepts from anomaly detection to improve representations of high-content image-based phenotypic profiling while maintaining them biologically-interpretable!
https://t.co/omhEqRAnE1
🧵
1/9
Our Review on in silico labeling is out 💫
https://t.co/VgREAoHBQJ
Led by @NitsanEl with (Twitterless) Lion Ben Nedava as part of themed issue on Cell Architecture edited by @CarstenJanke and Ohad Medalia
🧵
1/7
Our new @biorxivpreprint in out 💫
We systematically analyzed the relationships between the shape and the protein expression of a single cell in the physiological context of heterogeneous human disease tissues!
https://t.co/k0MlikmKsr
🧵
1/12
Multimodal bioimaging Perspective by Maddy Parsons @KingsCollegeLon and colleagues is out🎉
@leor_rose and I contributed to the section on data analysis challenges
https://t.co/HTWMBG5hpL
New @biorxivpreprint 💫
We identified recurrent transient multicellular communication communities (“hotspots”) forming over the course of Drosophila tissue development!
Joint project with @TanentzapfLab, co-led by Saar Ben David & @KevinYLHo1
https://t.co/LLSyEnbyoe
🧵
1/n
Excited to share our new @biorxivpreprint presenting DISCOVER, a generalized method toward systematic visual interpretability of image-based classification models!
Project led by @oded_rotem in collaboration with @AiVFtech!
https://t.co/nFbxRh108P
🧵
1/n
Our paper is out! 🎉
We found that the phenotypic association between in vitro fertilization (#IVF) sibling embryos can enhance #AI models predicting an embryo’s future implantation potential!
https://t.co/JejLet1mFo
1/4
Proud of @leor_rose presenting his pipeline for quantitative nanobiopsy assessment applied to human Glioma at the annual meeting of the Israeli society of microscopy 🔥
preprint: https://t.co/5UnvXVHaUo
code: https://t.co/7wcj9Brmsw