Our research is now published in #Nature ๐๐ถ๐ผ๐บ๐ฒ๐ฑ๐ถ๐ฐ๐ฎ๐น ๐๐ป๐ด๐ถ๐ป๐ฒ๐ฒ๐ฟ๐ถ๐ป๐ด! ๐คฉ๐คฏ๐คฉ And it's like the stars have aligned perfectly: this publication is coming out on... my birthday! ๐ Best gift I could ask for! ๐๐
@halperineran@UCLA@CompMedUCLA@UCLAHealth@natBME
Introducing TriFetch: your clinic's first AI employee.
Only do the work you want to do; give AI everything else.
We will change the US healthcare system, forever.
@Trifetchai@rosemary0680
๐ข Just published!
M1CR0B1AL1Z3R๐ฆ v2.0 is now live and published in Nucleic Acids Research ๐งฌ
A powerful, user-friendly web server for large-scale #microbial#genome#analysis. Proud to be co-senior author on this follow-up to my PhD work ๐
@NAR_Open
๐ฃ๐ฃ๐ฃ
Thrilled to speak at @CUAnschutz about potential avenues to tackle pressing challenges in research and care using #AI. Iโll be for a few days so if youโre in the area, hit me up!
This Week! Bytes to Bedside: Oren Avram, PhD
๐๏ธ Thursday, Feb. 27
โฐ 12 (noon)โ1 p.m.
๐ AHSB 7042
โก๏ธ DBMI is excited to welcome Oren Avram, PhD to campus for a special Bytes to Bedside seminar, Practical Pathways to Better Health.
UCLA just unveiled SLIViT, an AI model that analyzes 3D medical images faster and cheaper than human experts.
Key points:
1๏ธโฃ Analyzes MRIs, CTs, and more in a fraction of the time.
2๏ธโฃ Detects disease markers across multiple scan types
3๏ธโฃ Outperforms other models, making imaging more accessible
4๏ธโฃ Can handle large data and adapt to new imaging techniques
5๏ธโฃ Useful in areas lacking medical imaging experts.
6๏ธโฃ Trained on 2D data, fine-tuned for accurate 3D analysis
7๏ธโฃ Applies knowledge from one scan type to another.
SLIViT could revolutionize fast, affordable medical diagnoses
Researchers @halperineran and @orenavram at #UCLA have developed a new, #AI-powered foundation model that can accurately analyze #3D medical imagery, like MRIs and CT scans, in a fraction of the time it would otherwise take a human expert.
โก๏ธ https://t.co/MQCxgxHRh7
The model was pre-trained on publicly available, relatively inexpensive 2D imagery, and fine-tuned on a relatively small amounts of #3D medical imagery, meaning it can potentially be an affordable and scalable model with widespread impact for different communities around the world.
The researchers found the model can do transfer learning across different types of organs and image modalities. A retinal scanโor OCTโ of an eye can improve the modelโs ability to identify disease biomarkers in MRIs of livers, or other types of organs.
This #AI-powered model can potentially democratize expert level analysis of 3D medical images.
@CompMedUCLA@UCLAengineering
@EricTopol@natBME@EricTopol thanks for highlighting our research. This is the (second-)best birthday gift I could've asked for! ;-) https://t.co/URMq5Q9PVe
Our research is now published in #Nature ๐๐ถ๐ผ๐บ๐ฒ๐ฑ๐ถ๐ฐ๐ฎ๐น ๐๐ป๐ด๐ถ๐ป๐ฒ๐ฒ๐ฟ๐ถ๐ป๐ด! ๐คฉ๐คฏ๐คฉ And it's like the stars have aligned perfectly: this publication is coming out on... my birthday! ๐ Best gift I could ask for! ๐๐
@halperineran@UCLA@CompMedUCLA@UCLAHealth@natBME