John M. Pauly
YOU?
Author Swipe
View article: DM-Net: a physics-model-independent direct mapping approach for calibration-free multi-coil MRI
DM-Net: a physics-model-independent direct mapping approach for calibration-free multi-coil MRI Open
Deep learning-based multi-coil magnetic resonance image reconstruction has been actively investigated and increasingly applied in clinical settings. However, most models are physics-model-based approaches, which either require precalculati…
View article: LTDA-Drive: LLMs-guided Generative Models based Long-tail Data Augmentation for Autonomous Driving
LTDA-Drive: LLMs-guided Generative Models based Long-tail Data Augmentation for Autonomous Driving Open
3D perception plays an essential role for improving the safety and performance of autonomous driving. Yet, existing models trained on real-world datasets, which naturally exhibit long-tail distributions, tend to underperform on rare and sa…
View article: Using deep feature distances for evaluating the perceptual quality of MR image reconstructions
Using deep feature distances for evaluating the perceptual quality of MR image reconstructions Open
Purpose Commonly used MR image quality (IQ) metrics have poor concordance with radiologist‐perceived diagnostic IQ. Here, we develop and explore deep feature distances (DFDs)—distances computed in a lower‐dimensional feature space encoded …
View article: A NEW DLP-BASED AUTHENTICATION ALGORITHM FOR PUBLIC KEY CRYPTOSYSTEMS
A NEW DLP-BASED AUTHENTICATION ALGORITHM FOR PUBLIC KEY CRYPTOSYSTEMS Open
Authentication is essential to secure communication because it guarantees that communications come from authentic sources and are not altered while being transmitted. An efficient authentication algorithm based on the DLP (Discrete Logarit…
View article: AutoSamp: Autoencoding k-Space Sampling via Variational Information Maximization for 3D MRI
AutoSamp: Autoencoding k-Space Sampling via Variational Information Maximization for 3D MRI Open
Accelerated MRI protocols routinely involve a predefined sampling pattern that undersamples the k-space. Finding an optimal pattern can enhance the reconstruction quality, however this optimization is a challenging task. To address this ch…
View article: MRI Retrospective Respiratory Gating and Cardiac Sensing by CW Doppler Radar: A Feasibility Study
MRI Retrospective Respiratory Gating and Cardiac Sensing by CW Doppler Radar: A Feasibility Study Open
Non-contact motion correction sensing in MRI may provide better patient handling and throughput by complementing existing system sensors and motion correction algorithms.
View article: Missing Wedge Completion via Unsupervised Learning with Coordinate Networks
Missing Wedge Completion via Unsupervised Learning with Coordinate Networks Open
Cryogenic electron tomography (cryoET) is a powerful tool in structural biology, enabling detailed 3D imaging of biological specimens at a resolution of nanometers. Despite its potential, cryoET faces challenges such as the missing wedge p…
View article: Missing Wedge Completion via Unsupervised Learning with Coordinate Networks
Missing Wedge Completion via Unsupervised Learning with Coordinate Networks Open
Cryogenic electron tomography (cryoET) is a powerful tool in structural biology, enabling detailed 3D imaging of biological specimens at a resolution of nanometers. Despite its potential, cryoET faces challenges such as the missing wedge p…
View article: Adapted large language models can outperform medical experts in clinical text summarization
Adapted large language models can outperform medical experts in clinical text summarization Open
View article: Deep Learning Reconstruction for Free-breathing Radial Cine Imaging
Deep Learning Reconstruction for Free-breathing Radial Cine Imaging Open
View article: Clinical Text Summarization: Adapting Large Language Models Can Outperform Human Experts
Clinical Text Summarization: Adapting Large Language Models Can Outperform Human Experts Open
Sifting through vast textual data and summarizing key information from electronic health records (EHR) imposes a substantial burden on how clinicians allocate their time. Although large language models (LLMs) have shown immense promise in …
View article: Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization
Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization Open
Analyzing vast textual data and summarizing key information from electronic health records imposes a substantial burden on how clinicians allocate their time. Although large language models (LLMs) have shown promise in natural language pro…
View article: Erratum: “Ultra‐low‐dose PET reconstruction using generative adversarial network with feature matching and task‐specific perceptual loss”
Erratum: “Ultra‐low‐dose PET reconstruction using generative adversarial network with feature matching and task‐specific perceptual loss” Open
https://doi.org/10.1002/mp.13626 In the Conflicts of Interest section, G.Z. acknowledges funding support from GE Healthcare, consulting fees from Biogen, and equity in Subtle Medical, Inc. E.G. acknowledges equity in Subtle Medical, Inc. T…
View article: AutoSamp: Autoencoding k-space Sampling via Variational Information Maximization for 3D MRI
AutoSamp: Autoencoding k-space Sampling via Variational Information Maximization for 3D MRI Open
Accelerated MRI protocols routinely involve a predefined sampling pattern that undersamples the k-space. Finding an optimal pattern can enhance the reconstruction quality, however this optimization is a challenging task. To address this ch…
View article: RadAdapt: Radiology Report Summarization via Lightweight Domain Adaptation of Large Language Models
RadAdapt: Radiology Report Summarization via Lightweight Domain Adaptation of Large Language Models Open
We systematically investigate lightweight strategies to adapt large language models (LLMs) for the task of radiology report summarization (RRS). Specifically, we focus on domain adaptation via pretraining (on natural language, biomedical t…
View article: Optimization in the space domain for density compensation with the nonuniform FFT
Optimization in the space domain for density compensation with the nonuniform FFT Open
View article: Automated MRI Field of View Prescription from Region of Interest Prediction by Intra-Stack Attention Neural Network
Automated MRI Field of View Prescription from Region of Interest Prediction by Intra-Stack Attention Neural Network Open
Manual prescription of the field of view (FOV) by MRI technologists is variable and prolongs the scanning process. Often, the FOV is too large or crops critical anatomy. We propose a deep learning framework, trained by radiologists’ superv…
View article: RadAdapt: Radiology Report Summarization via Lightweight Domain Adaptation of Large Language Models
RadAdapt: Radiology Report Summarization via Lightweight Domain Adaptation of Large Language Models Open
Dave Van Veen, Cara Van Uden, Maayane Attias, Anuj Pareek, Christian Bluethgen, Malgorzata Polacin, Wah Chiu, Jean-Benoit Delbrouck, Juan Zambrano Chaves, Curtis Langlotz, Akshay Chaudhari, John Pauly. The 22nd Workshop on Biomedical Natur…
View article: SLfRank: Shinnar-Le-Roux Pulse Design With Reduced Energy and Accurate Phase Profiles Using Rank Factorization
SLfRank: Shinnar-Le-Roux Pulse Design With Reduced Energy and Accurate Phase Profiles Using Rank Factorization Open
The Shinnar-Le-Roux (SLR) algorithm is widely used to design frequency selective pulses with large flip angles. We improve its design process to generate pulses with lower energy (by as much as 26%) and more accurate phase profiles. Concre…
View article: Automated MRI Field of View Prescription from Region of Interest Prediction by Intra-stack Attention Neural Network
Automated MRI Field of View Prescription from Region of Interest Prediction by Intra-stack Attention Neural Network Open
Manual prescription of the field of view (FOV) by MRI technologists is variable and prolongs the scanning process. Often, the FOV is too large or crops critical anatomy. We propose a deep-learning framework, trained by radiologists' superv…
View article: Deep Learning-Based Water-Fat Separation from Dual-Echo Chemical Shift-Encoded Imaging
Deep Learning-Based Water-Fat Separation from Dual-Echo Chemical Shift-Encoded Imaging Open
Conventional water–fat separation approaches suffer long computational times and are prone to water/fat swaps. To solve these problems, we propose a deep learning-based dual-echo water–fat separation method. With IRB approval, raw data fro…
View article: Scale-Agnostic Super-Resolution in MRI using Feature-Based Coordinate Networks
Scale-Agnostic Super-Resolution in MRI using Feature-Based Coordinate Networks Open
We propose using a coordinate network decoder for the task of super-resolution in MRI. The continuous signal representation of coordinate networks enables this approach to be scale-agnostic, i.e. one can train over a continuous range of sc…
View article: A Semi-Blind Calibration and Compensation Method for Dynamic Range Recovery of Low-Power Pre-Amplifiers in MRI Receive Chains
A Semi-Blind Calibration and Compensation Method for Dynamic Range Recovery of Low-Power Pre-Amplifiers in MRI Receive Chains Open
To enable wireless MRI receive arrays, per-channel power consumption must be reduced by a significant factor. To address this, a low-power SiGe alternative to industry standard MRI pre-amplifier blocks has been proposed and its impact on i…
View article: GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction
GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction Open
Unrolled neural networks have recently achieved state-of-the-art accelerated MRI reconstruction. These networks unroll iterative optimization algorithms by alternating between physics-based consistency and neural-network based regularizati…
View article: NeRP: Implicit Neural Representation Learning With Prior Embedding for Sparsely Sampled Image Reconstruction
NeRP: Implicit Neural Representation Learning With Prior Embedding for Sparsely Sampled Image Reconstruction Open
Image reconstruction is an inverse problem that solves for a computational image based on sampled sensor measurement. Sparsely sampled image reconstruction poses additional challenges due to limited measurements. In this work, we propose a…
View article: Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers
Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers Open
Vision transformers using self-attention or its proposed alternatives have demonstrated promising results in many image related tasks. However, the underpinning inductive bias of attention is not well understood. To address this issue, thi…
View article: Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction
Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction Open
Unrolled neural networks have enabled state-of-the-art reconstruction performance and fast inference times for the accelerated magnetic resonance imaging (MRI) reconstruction task. However, these approaches depend on fully-sampled scans as…
View article: Novel-view X-ray projection synthesis through geometry-integrated deep learning
Novel-view X-ray projection synthesis through geometry-integrated deep learning Open
View article: Attention-guided deep learning for gestational age prediction using fetal brain MRI
Attention-guided deep learning for gestational age prediction using fetal brain MRI Open
View article: Artifact- and content-specific quality assessment for MRI with image rulers
Artifact- and content-specific quality assessment for MRI with image rulers Open