Luke Sagers

44 posts

Luke Sagers

Luke Sagers

@luke_sagers

Katılım Mayıs 2020
85 Takip Edilen70 Takipçiler
Luke Sagers
Luke Sagers@luke_sagers·
Couldn’t have asked for a greater mentor these past several years, @arjunmanrai! Excited about the work we’ve done that got me to this point and looking forward to what’s next!
Arjun (Raj) Manrai@arjunmanrai

Congrats to **Dr.** @luke_sagers who brilliantly defended his PhD dissertation! Luke rigorously evaluated whether synthetic data can improve medical image classifiers across populations. It's been a privilege to work w/ Luke from when he was a summer undergrad at @HarvardDBMI

English
2
1
24
1.6K
Luke Sagers
Luke Sagers@luke_sagers·
@JamesADiao Thanks @JamesADiao, it’s been great working with and learning from you these past several years. Excited to share a graduation date in a few weeks!
English
0
0
2
31
Luke Sagers retweetledi
Arjun (Raj) Manrai
Arjun (Raj) Manrai@arjunmanrai·
It's a privilege to work alongside this creative & hard-working team. It was a great 2023 for our lab at @HarvardDBMI and we are looking forward to 2024!
Arjun (Raj) Manrai tweet media
English
0
9
58
13K
Luke Sagers
Luke Sagers@luke_sagers·
@ayushnoori Thanks for sharing, Ayush! Would love to talk more with you on this and hear some of your thoughts!
English
1
0
2
57
Ayush Noori
Ayush Noori@ayushnoori·
Appreciated the point that synthetic data can improve model fairness by increasing data representation from rare diseases and marginalized groups. ⚖️ Interested in implications for image-based AI across other medical domains: e.g., MRI and PET in neurological disease. 📷 4/4
English
1
0
1
96
Ayush Noori
Ayush Noori@ayushnoori·
I’ve been wondering about the important synthetic image data augmentation question for medical AI, and know others have been too! Funny enough, was just 🧠🌩️-ing with @lakhani_anika @JayanthPratap about this and utility of diverse dermatologic data. New work sheds light! 1/4
Arjun (Raj) Manrai@arjunmanrai

Can synthetic data produced by latent diffusion models improve medical AI? We studied this question using skin disease classifiers in our new preprint led by @luke_sagers @JamesADiao @lukemelas. Takeaways: • Synthetic images can enhance model performance in data-limited scenarios. • Gains saturate at synthetic-to-real image ratios above 10:1 and are substantially smaller than the gains obtained from adding real images. • Diverse real-world data remains the most important step to improve medical AI algorithms. Special thanks to collaborators @RoxanaDaneshjou @Dr_vron @pranavrajpurkar @AdeAdamson @mattgroh Full text: arxiv.org/abs/2308.12453

English
1
0
1
539
Luke Sagers retweetledi
Pranav Rajpurkar
Pranav Rajpurkar@pranavrajpurkar·
Does synthetic data help for medicine? Check out our work led by @luke_sagers @JamesADiao & spearheaded by @arjunmanrai.
Arjun (Raj) Manrai@arjunmanrai

Can synthetic data produced by latent diffusion models improve medical AI? We studied this question using skin disease classifiers in our new preprint led by @luke_sagers @JamesADiao @lukemelas. Takeaways: • Synthetic images can enhance model performance in data-limited scenarios. • Gains saturate at synthetic-to-real image ratios above 10:1 and are substantially smaller than the gains obtained from adding real images. • Diverse real-world data remains the most important step to improve medical AI algorithms. Special thanks to collaborators @RoxanaDaneshjou @Dr_vron @pranavrajpurkar @AdeAdamson @mattgroh Full text: arxiv.org/abs/2308.12453

English
2
7
31
6.4K
Luke Sagers
Luke Sagers@luke_sagers·
Excited to see this up on arxiv! Very grateful to work alongside a a top-tier team, including co-first authors @JamesADiao & @lukemelas, collaborators @mattgroh, @pranavrajpurkar, @Dr_vron, @AdeAdamson, and @RoxanaDaneshjou, and under the fantastic mentorship of @arjunmanrai
Arjun (Raj) Manrai@arjunmanrai

Can synthetic data produced by latent diffusion models improve medical AI? We studied this question using skin disease classifiers in our new preprint led by @luke_sagers @JamesADiao @lukemelas. Takeaways: • Synthetic images can enhance model performance in data-limited scenarios. • Gains saturate at synthetic-to-real image ratios above 10:1 and are substantially smaller than the gains obtained from adding real images. • Diverse real-world data remains the most important step to improve medical AI algorithms. Special thanks to collaborators @RoxanaDaneshjou @Dr_vron @pranavrajpurkar @AdeAdamson @mattgroh Full text: arxiv.org/abs/2308.12453

English
2
6
23
4.7K
Luke Sagers retweetledi
Arjun (Raj) Manrai
Arjun (Raj) Manrai@arjunmanrai·
Had a blast chatting about healthcare and AI (and basketball!) with @mcuban today for the @NEJM_AI Grand Rounds podcast. Episode coming soon!
Arjun (Raj) Manrai tweet media
English
2
5
34
5.6K
Luke Sagers retweetledi
Arjun (Raj) Manrai
Arjun (Raj) Manrai@arjunmanrai·
How will GPT-4 change medicine? I lost sleep after this long and fascinating conversation with @peteratmsr of Microsoft. He took us behind the scenes of the Microsoft/OpenAI partnership and predicted how GPT-4 & beyond will impact healthcare. Listen here: ai-podcast.nejm.org
English
1
20
60
8.5K
Luke Sagers retweetledi
Arjun (Raj) Manrai
Arjun (Raj) Manrai@arjunmanrai·
Thrilled to announce @NEJM_AI Grand Rounds, a new podcast I'm co-hosting with @AndrewLBeam. We'll feature informal conversations with experts exploring deep issues at the intersection of artificial intelligence, machine learning, and medicine. ai-podcast.nejm.org
NEJM AI@NEJM_AI

Launching later this month, NEJM AI Grand Rounds is a new podcast exploring how #ArtificialIntelligence will change clinical practice and healthcare. Listen to the podcast trailer and subscribe: ai-podcast.nejm.org #AIinMedicine

English
1
7
20
0
NBA.com/Stats
NBA.com/Stats@nbastats·
With Stephen Curry moving up to No. 1 all-time in made threes, check out this motion graphic representation of how the top 10 has changed over the years 🔥
English
30
624
3.3K
0