Our researchers found that CHATGPT-4 can assist in liver ultrasound analysis by accurately distinguishing between fatty liver, fibrosis and healthy tissue. The large language model's speed and scalability show strong promise to assist with image analysis: https://t.co/ZZUGVQ3MGY.
🎉 Congratulations to our own Tatiana Morales for being awarded Summa Cum Laude at the 50th Annual Pendergrass Symposium! @CHOPRadiology@PennRadiology@oterocobo
Her poster, titled “Association of CEUS Perfusion Parameters with Histopathology in Pediatric Kidney Transplants,” was selected for this top honor.
📍 Join us at the poster session this afternoon to learn more about this outstanding work!
Just published: Hydralazine‐augmented contrast ultrasound imaging improves the detection of hepatocellular carcinoma https://t.co/DYwfYjjptO @VisualSonics
The use of quantitative ultrasound with #machine/deep learning methods improves the detection of early fibrosis. More complex methods like multi-layer perception yielded high performance but no significant improvement over simpler ML methods.
🔗https://t.co/QrTdX0tZDt
My #SRU22 poster presents an inexpensive upgrade for a diagnostic ultrasound machine to add THERAPUTIC, cancer-killing capabilities utilizing contrast-enhanced ultrasound
Published, Journal of Medical Devices: https://t.co/w4wQrSIHnu
@sruradiology@URLatPenn
please check our latest paper! Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics https://t.co/CvEbT9wSnq #mdpiai via @AI_MDPI@LsultanMD @Maryam34MD @MBKarmacharya#Health
To guarantee the generalizability of machine learning models, and to prevent imaging data leakage, image data acquired of the same object should be tested for independence before machine learning.
Find more details here👇
https://t.co/DVnYyf3ogw
Hot off the press! Can Sequential Images from Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics https://t.co/CvEbT9wSnq #mdpiai via @AI_MDPI@LsultanMD @Maryam34MD @MBKarmacharya@PennRadiology#Health#AI