We’ve released v2 of our paper “Segment Anything Model for Medical Image Analysis: an Experimental Study"! We nearly double the no. of datasets and provide multiple novel analyses of SAM relevant to medical imaging tasks. More info and code below. arxiv.org/abs/2304.10517 (1/4)

Check out our Ph.D. student Hanxue presenting the very first oral talk at #MIDL2023 last week! Her paper is "SuperMask: Generating High-resolution object masks from multi-view, unaligned low-resolution MRIs", found here: openreview.net/pdf?id=oi5psB9…

Duke Radiology Liver Dataset contains 2146 abdominal MRI image series from 105 patients with clinical indication of liver cirrhosis buff.ly/3OutLsm Maciej A. Mazurowski Walter Wiggins, MD, PhD Duke University School of Medicine #segmentation #AI #ML

Another fun lake day with the team! I appreciate all your work.

This is a very important finding: "ConvNets Match Vision Transformers at Scale" arxiv.org/abs/2310.16764

This article from Ben Wildman-Tobriner, Maciej A. Mazurowski, et al. compared the diagnostic performance of ACR TI-RADS and a deep learning algorithm in differentiating benign and malignant thyroid nodules on ultrasound in children and young adults. ajronline.org/doi/10.2214/AJ…

Our study was selected as Best of AFR in Pediatric Radiology!

🎉 Exciting news! The paper, "Thyroid Nodules on Ultrasound in Children and Young Adults," won the Best of AJR award in Pediatric Imaging for 2023! It is co-authored by Jichen Yang, Laura C. Page, Lars Wagner, Ben Wildman-Tobriner, Logan Bisset, Donald Frush, and Maciej A. Mazurowski.