Maciej A. Mazurowski
@mazurowski.bsky.social
Associate Professor at Duke | Director of Duke Spark | AI in Medical Imaging
Thank you to the many researchers who contributed to the creation of this dataset! Duke Spark: AI in Medical Imaging
Let us know what you think!
Let us know what you think!
October 29, 2025 at 5:03 PM
Thank you to the many researchers who contributed to the creation of this dataset! Duke Spark: AI in Medical Imaging
Let us know what you think!
Let us know what you think!
Modality: Magnetic Resonance Imaging (MRI)
Location: Cervical Spine
Number of Patients: 1,232
Annotations: segmentation masks of vertebral bodies and intervertebral discs
for 481 patients
Paper: www.nature.com/articles/s4...
Download data: data.midrc.org/discovery/H... (you have to be logged in)
Location: Cervical Spine
Number of Patients: 1,232
Annotations: segmentation masks of vertebral bodies and intervertebral discs
for 481 patients
Paper: www.nature.com/articles/s4...
Download data: data.midrc.org/discovery/H... (you have to be logged in)
October 29, 2025 at 5:03 PM
Modality: Magnetic Resonance Imaging (MRI)
Location: Cervical Spine
Number of Patients: 1,232
Annotations: segmentation masks of vertebral bodies and intervertebral discs
for 481 patients
Paper: www.nature.com/articles/s4...
Download data: data.midrc.org/discovery/H... (you have to be logged in)
Location: Cervical Spine
Number of Patients: 1,232
Annotations: segmentation masks of vertebral bodies and intervertebral discs
for 481 patients
Paper: www.nature.com/articles/s4...
Download data: data.midrc.org/discovery/H... (you have to be logged in)
Here is the paper: arxiv.org/pdf/2507.11569?
October 23, 2025 at 1:45 PM
Here is the paper: arxiv.org/pdf/2507.11569?
September 16, 2025 at 5:14 PM
Congrats to Hanxue Gu, who is the first author, and the interdisciplinary team of co-authors!
September 16, 2025 at 5:14 PM
Congrats to Hanxue Gu, who is the first author, and the interdisciplinary team of co-authors!
Our method:
- automatically segments radius and ulna bones
- uses a pose estimation network to assess rotational parameters of the bones
- automatically detects fracture locations
- combines all the information to infer the 3D fracture angles
The paper has been published at MIDL.
- automatically segments radius and ulna bones
- uses a pose estimation network to assess rotational parameters of the bones
- automatically detects fracture locations
- combines all the information to infer the 3D fracture angles
The paper has been published at MIDL.
September 16, 2025 at 5:14 PM
Our method:
- automatically segments radius and ulna bones
- uses a pose estimation network to assess rotational parameters of the bones
- automatically detects fracture locations
- combines all the information to infer the 3D fracture angles
The paper has been published at MIDL.
- automatically segments radius and ulna bones
- uses a pose estimation network to assess rotational parameters of the bones
- automatically detects fracture locations
- combines all the information to infer the 3D fracture angles
The paper has been published at MIDL.
We propose a deep learning-based method that allows for measuring 3D angles from standard non-orthogonal planar X-rays, which allows for patient movement between the images are acquired.
September 16, 2025 at 5:14 PM
We propose a deep learning-based method that allows for measuring 3D angles from standard non-orthogonal planar X-rays, which allows for patient movement between the images are acquired.
Our method:
- automatically segments radius and ulna bones
- uses a pose estimation network to assess rotational parameters of the bones
- automatically detects fracture locations
- combines all the information to infer the 3D fracture angles
The paper has been published at MIDL.
- automatically segments radius and ulna bones
- uses a pose estimation network to assess rotational parameters of the bones
- automatically detects fracture locations
- combines all the information to infer the 3D fracture angles
The paper has been published at MIDL.
September 16, 2025 at 5:11 PM
Our method:
- automatically segments radius and ulna bones
- uses a pose estimation network to assess rotational parameters of the bones
- automatically detects fracture locations
- combines all the information to infer the 3D fracture angles
The paper has been published at MIDL.
- automatically segments radius and ulna bones
- uses a pose estimation network to assess rotational parameters of the bones
- automatically detects fracture locations
- combines all the information to infer the 3D fracture angles
The paper has been published at MIDL.
We propose a deep learning-based method that allows for measuring 3D angles from standard non-orthogonal planar X-rays, which allows for patient movement between the images are acquired.
September 16, 2025 at 5:11 PM
We propose a deep learning-based method that allows for measuring 3D angles from standard non-orthogonal planar X-rays, which allows for patient movement between the images are acquired.
We addressed this by using contours from the image to guide the diffusion model and showed quite a good performance of the model!
Congrats to Yuwen Chen, who is the first author, and the other team members!
Congrats to Yuwen Chen, who is the first author, and the other team members!
September 12, 2025 at 4:16 PM
We addressed this by using contours from the image to guide the diffusion model and showed quite a good performance of the model!
Congrats to Yuwen Chen, who is the first author, and the other team members!
Congrats to Yuwen Chen, who is the first author, and the other team members!
The issue for such translation is that for a given body part, the CT and MRI images often have a different field of view, resulting in different structures being portrayed in the image.
September 12, 2025 at 4:16 PM
The issue for such translation is that for a given body part, the CT and MRI images often have a different field of view, resulting in different structures being portrayed in the image.
September 1, 2025 at 3:20 PM
- we explored different ways of integrating adapted models
- we validated our method with 24 source domain-target domain splits for 3 medical imaging datasets
- our method outperforms SOTA by 2.9% on average in terms of Dice similarity coefficient
- published in a CVPR workshop
- we validated our method with 24 source domain-target domain splits for 3 medical imaging datasets
- our method outperforms SOTA by 2.9% on average in terms of Dice similarity coefficient
- published in a CVPR workshop
September 1, 2025 at 3:20 PM
- we explored different ways of integrating adapted models
- we validated our method with 24 source domain-target domain splits for 3 medical imaging datasets
- our method outperforms SOTA by 2.9% on average in terms of Dice similarity coefficient
- published in a CVPR workshop
- we validated our method with 24 source domain-target domain splits for 3 medical imaging datasets
- our method outperforms SOTA by 2.9% on average in terms of Dice similarity coefficient
- published in a CVPR workshop
Congrats to Yuwen Chen, the lead author of the paper for this terrific work!
August 25, 2025 at 2:59 PM
Congrats to Yuwen Chen, the lead author of the paper for this terrific work!
Our evaluation on multiple tasks showed strong improvements as compared to SAM 2 and a promise to significantly speed up the annotation process.
August 25, 2025 at 2:59 PM
Our evaluation on multiple tasks showed strong improvements as compared to SAM 2 and a promise to significantly speed up the annotation process.
Introducing Short-Long Memory SAM 2 (SLM-SAM 2) with a novel architecture combining short and long memory banks. The motivation was to reduce the propagation of error to slices far from the annotated ones.
August 25, 2025 at 2:59 PM
Introducing Short-Long Memory SAM 2 (SLM-SAM 2) with a novel architecture combining short and long memory banks. The motivation was to reduce the propagation of error to slices far from the annotated ones.
The recently released Segment Anything Model 2 (SAM 2) allows for extending annotations from one frame of a video to other frames. We leveraged this ability but discovered that it doesn't translate well to medical imaging and had to make a few changes.
August 25, 2025 at 2:59 PM
The recently released Segment Anything Model 2 (SAM 2) allows for extending annotations from one frame of a video to other frames. We leveraged this ability but discovered that it doesn't translate well to medical imaging and had to make a few changes.