Mazurowski Lab - Duke University
@MazurowskiLab
Followers
308
Following
53
Media
6
Statuses
273
An AI research lab within the Department of Radiology at Duke University.
Durham, NC
Joined December 2021
RT @nick_konz: I'm happy to share that our lab had three short papers and a long paper accepted at @midl_conference! .(1/4): Rethinking Per….
0
5
0
RT @nick_konz: Excited to share our new paper, "ContourDiff: Unpaired Image Translation with Contour-Guided Diffusion Models”, which levera….
0
3
0
🔗 Dive into our study by @Hanxue99893888, Roy Colglazier, Haoyu Dong, Jikai Zhang & more. See how we're transforming MRI analysis!:
0
0
1
🦴Introducing "SegmentAnyBone", a universal model for MRI bone segmentation. This model can segment bones in any MRI location, tackling a major challenge in medical imaging. #SegmentAnyBone #MedicalImaging #AI #DukeSpark
2
3
18
RT @nick_konz: How and why do neural nets learn differently from natural images vs. medical images? I’m happy to announce my new #ICLR2024….
0
19
0
🔍 It compared radiologists' impressions, ACR TI-RADS, & deep learning in identifying benign and malignant thyroid nodules via ultrasound. A major step in improving pediatric healthcare accuracy. Discover more: #MedicalImaging #AI.
ajronline.org
Please see the Editorial Comment by Sheng-Yang Huang discussing this article. Chinese (audio/PDF) and Spanish (audio/PDF) translations are available for this article's abstract. To listen to the...
0
0
0
🎉 Exciting news! The paper, "Thyroid Nodules on Ultrasound in Children and Young Adults," won the Best of @AJR_Radiology award in Pediatric Imaging for 2023! It is co-authored by @JichenYang10, Laura C. Page, Lars Wagner, @benWTmd, Logan Bisset, Donald Frush, and @MazurowskiPhD.
1
2
5
RT @AJR_Radiology: This article from @benWTmd, @MazurowskiPhD, et al. compared the diagnostic performance of ACR TI-RADS and a deep learnin….
0
3
0
RT @nick_konz: Which examples in a neural net’s training data were important for learning interpretable concepts? Our paper “Attributing Le….
0
2
0
RT @nick_konz: Excited to announce our new paper in IEEE Trans. in Med. Imaging, "SWSSL: Sliding window-based self-supervised learning for….
github.com
SWSSL - Sliding window-based self-supervised learning for anomaly detection in high-resolution images (IEEE Trans. on Medical Imaging 2023) - mazurowski-lab/swssl-for-anomaly-detection
0
2
0
This paper introduces a method for anomaly detection in high-resolution medical images, that outperforms state-of-the-art techniques by 8% AUC for digital breast tomosynthesis lesion detection.
0
0
1
Congratulations to our Ph.D. student Haoyu Dong for his new paper in IEEE Transactions in Medical Imaging, "SWSSL: Sliding window-based self-supervised learning for anomaly detection in high-resolution images"! .
github.com
SWSSL - Sliding window-based self-supervised learning for anomaly detection in high-resolution images (IEEE Trans. on Medical Imaging 2023) - mazurowski-lab/swssl-for-anomaly-detection
1
1
10
RT @nick_konz: Happy to announce that our paper, "Segment Anything Model for medical image analysis: An experimental study" has just been p….
0
8
0
Hanxue's co-authors include Hongyu He, Roy Colglazier, Jordan Axelrod, Robert French, and @MazurowskiPhD.
0
0
0
Check out our Ph.D. student @Hanxue99893888 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:
1
1
6
RT @nick_konz: The foreground-background imbalance problem can cause significant drops in object detection performance. Our new paper, “A s….
0
5
0
RT @nick_konz: New preprint from my lab: "Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation" by Yixin Zhang and @M….
0
5
0
Further info: Code: Authors: @MazurowskiPhD, @HaoyuDong11203, @Hanxue99893888, Jichen Yang, @nick_konz and Yixin Zhang. @duke_spark.@DukeAIHealth. Enjoy!.
github.com
Code for "Segment Anything Model for Medical Image Analysis: an Experimental Study" in Medical Image Analysis - mazurowski-lab/segment-anything-medical-evaluation
Does Segment Anything Model (SAM) really work on medical images?. We tested it on 11 datasets and wrote a paper:. In brief: Performance varies widely across different datasets from impressive (given zero-shot setup) to poor. Details follow. 🧵1/14.
0
0
0
We are already working on updating our paper, with additional datasets, other explorations of using SAM for medical image analysis, and more. Follow us to stay in the loop!.
1
0
0
Via simulated interactive segmentation, we found that SAM's performance can vary greatly over a range of medical imaging modalities and tasks, from very poor (~0.1 IoU) to high quality (>0.8 IoU). We also evaluated prompt point generation strategies, and the similar RITM model.
1
0
0