Juanma Zambrano Chaves

2️⃣ Our prior study linking muscle quality & quantity to hundreds of diseases:
doi.org/10.1016/j.eb...
3️⃣ Our prior work predicting future heart disease using body composition (and more):
doi.org/10.1038/s415...
4️⃣ Our open-source body composition segmentation library:
github.com/stanfordmimi...

💪 “𝙋𝙖𝙧𝙘𝙚, 𝗱𝗼 𝘆𝗼𝘂 𝗲𝘃𝗲𝗻 𝗹𝗶𝗳𝘁?” - 𝗪𝗵𝗮𝘁… | Juan Manuel Zambrano Chaves 💪 “𝙋𝙖𝙧𝙘𝙚, 𝗱𝗼 𝘆𝗼𝘂 𝗲𝘃𝗲𝗻 𝗹𝗶𝗳𝘁?” - 𝗪𝗵𝗮𝘁 𝘁𝗵𝗼𝘂𝘀𝗮𝗻𝗱𝘀 𝗼𝗳 𝗖𝗧 𝘀𝗰𝗮𝗻𝘀 𝘁𝗮𝘂𝗴𝗵𝘁 𝗺𝗲 After years of studying muscle and fat in medical imaging, the data was clear: strength matters. So I finally started lifting. Our...

See more details (including why I started lifting at the gym in part because of this research) here: tinyurl.com/aictsarcopenia

🔗 and some other links to dig deeper:
1️⃣ Our new study on detecting low muscle mass with AI from CT imaging:
pubs.rsna.org/doi/10.1148/...

Recently we published some new research on how AI can help bridge the documentation gap for low muscle mass (sarcopenia) in the clinic. Our research in 17,000+ patients with imaging and across >200 institutions showed that sarcopenia and sarcopenic obesity too often go undocumented, but AI can help!

aand of course I lost track of the n/n count. We really need better ways to share longer ideas.

📄 Learn more:
🔗 LLaVA-Rad MIMIC-CXR Annotations: physionet.org/content/llav...
🔗 LLaVA-Rad preprint: arxiv.org/abs/2403.08002
🔗 CheXprompt: github.com/microsoft/ch... (our validated, radiologist-aligned metric for assessing report quality)
Peer-reviewed manuscript, code/model weights: coming soon ;)

We call this resource the LLaVA-Rad MIMIC-CXR Annotations. In the spirit of reproducibility and collaboration, we are releasing the full training and evaluation dataset to support further innovation.

1️⃣ No references to prior imaging: We removed mentions of previous X-rays to reduce the risk of models generating incorrect descriptions tied to unavailable prior exams.

2️⃣ Cleaner, section-specific extractions: We refined the extraction of report sections and descriptions.

3/n

[...] describing chest X-rays in the manner of a radiologist. One major challenge we encountered was the lack of publicly available, high-quality, and standardized data.

To address this, we built on the MIMIC-CXR dataset and leveraged GPT-4 to create annotations that improve in two key ways:

2/n

The LLaVA-Rad MIMIC-CXR Annotations dataset is now public!

To advance AI in personalized medicine, we need models capable of interpreting diverse medical data, including imaging like chest X-rays. In LLaVA-Rad, we trained a model that was state of the art when released, capable of [...]

1/n

Hola BlueSky!