Sangtae Ahn
YOU?
Author Swipe
View article: Consistent performance between medical experts and non‐expert readers in forced‐choice lesion‐detection tasks with PET images
Consistent performance between medical experts and non‐expert readers in forced‐choice lesion‐detection tasks with PET images Open
Background Labeled data are used to train, validate, and test deep learning model observers (DLMOs) as well as linear model observers, such as channelized Hotelling observers (CHOs), for image quality assessment in many imaging modalities,…
View article: Artsemg: Adversarially Regularized Transformer with Channel-Wise Noise for Robust Hand Gesture Recognition Using Surface Electromyography
Artsemg: Adversarially Regularized Transformer with Channel-Wise Noise for Robust Hand Gesture Recognition Using Surface Electromyography Open
View article: A deep learning anthropomorphic model observer for a detection task in PET
A deep learning anthropomorphic model observer for a detection task in PET Open
Background Lesion detection is one of the most important clinical tasks in positron emission tomography (PET) for oncology. An anthropomorphic model observer (MO) designed to replicate human observers (HOs) in a detection task is an import…
View article: Improving the performance of object detection by preserving label distribution
Improving the performance of object detection by preserving label distribution Open
Object detection is a task that performs position identification and label classification of objects in images or videos. The information obtained through this process plays an essential role in various tasks in the field of computer visio…
View article: An Investigation of Stochastic Variance Reduction Algorithms for Relative Difference Penalized 3D PET Image Reconstruction
An Investigation of Stochastic Variance Reduction Algorithms for Relative Difference Penalized 3D PET Image Reconstruction Open
Penalised PET image reconstruction algorithms are often accelerated during early iterations with the use of subsets. However, these methods may exhibit limit cycle behaviour at later iterations due to variations between subsets. Desirable …
View article: Inflammation and tissue remodeling contribute to fibrogenesis in stricturing Crohn’s disease: image processing and analysis study
Inflammation and tissue remodeling contribute to fibrogenesis in stricturing Crohn’s disease: image processing and analysis study Open
Background: Inflammation and structural remodeling may contribute to fibrogenesis in Crohn’s disease (CD). We quantified the immunoexpression of calretinin, CD34, and calprotectin as a surrogate for mucosal innervation, telocytes (intersti…
View article: A Fast Convergent Ordered-Subsets Algorithm With Subiteration-Dependent Preconditioners for PET Image Reconstruction
A Fast Convergent Ordered-Subsets Algorithm With Subiteration-Dependent Preconditioners for PET Image Reconstruction Open
We investigated the imaging performance of a fast convergent ordered-subsets algorithm with subiteration-dependent preconditioners (SDPs) for positron emission tomography (PET) image reconstruction. In particular, we considered the use of …
View article: An Investigation of Stochastic Variance Reduction Algorithms for 3D Penalised PET Image Reconstruction
An Investigation of Stochastic Variance Reduction Algorithms for 3D Penalised PET Image Reconstruction Open
Application of stochastic variance reduction algorithms to iterative PET reconstruction. We investigated the SAGA and SVRG algorithms for non-TOF PET image reconstruction. Both similated data and a patient data sets were used in the analys…
View article: An Investigation of Stochastic Variance Reduction Algorithms for 3D Penalised PET Image Reconstruction
An Investigation of Stochastic Variance Reduction Algorithms for 3D Penalised PET Image Reconstruction Open
Application of stochastic variance reduction algorithms to iterative PET reconstruction. We investigated the SAGA and SVRG algorithms for non-TOF PET image reconstruction. Both similated data and a patient data sets were used in the analys…
View article: Deep learning-based reconstruction of highly accelerated 3D MRI
Deep learning-based reconstruction of highly accelerated 3D MRI Open
Purpose: To accelerate brain 3D MRI scans by using a deep learning method for reconstructing images from highly-undersampled multi-coil k-space data Methods: DL-Speed, an unrolled optimization architecture with dense skip-layer connections…
View article: A Fast Convergent Ordered-Subsets Algorithm with Subiteration-Dependent Preconditioners for PET Image Reconstruction
A Fast Convergent Ordered-Subsets Algorithm with Subiteration-Dependent Preconditioners for PET Image Reconstruction Open
We investigated the imaging performance of a fast convergent ordered-subsets algorithm with subiteration-dependent preconditioners (SDPs) for positron emission tomography (PET) image reconstruction. In particular, we considered the use of …
View article: A Fast Convergent Ordered-Subsets Algorithm with Subiteration-Dependent\n Preconditioners for PET Image Reconstruction
A Fast Convergent Ordered-Subsets Algorithm with Subiteration-Dependent\n Preconditioners for PET Image Reconstruction Open
We investigated the imaging performance of a fast convergent ordered-subsets\nalgorithm with subiteration-dependent preconditioners (SDPs) for positron\nemission tomography (PET) image reconstruction. In particular, we considered\nthe use …
View article: Artificial Intelligence in PET: an Industry Perspective
Artificial Intelligence in PET: an Industry Perspective Open
Artificial intelligence (AI) has significant potential to positively impact and advance medical imaging, including positron emission tomography (PET) imaging applications. AI has the ability to enhance and optimize all aspects of the PET i…
View article: Adaptive Gradient Balancing for Undersampled MRI Reconstruction and Image-to-Image Translation
Adaptive Gradient Balancing for Undersampled MRI Reconstruction and Image-to-Image Translation Open
Recent accelerated MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling much faster MRI scanning. However, these techniques sometimes …
View article: Adaptive Gradient Balancing for Undersampled MRI Reconstruction and\n Image-to-Image Translation
Adaptive Gradient Balancing for Undersampled MRI Reconstruction and\n Image-to-Image Translation Open
Recent accelerated MRI reconstruction models have used Deep Neural Networks\n(DNNs) to reconstruct relatively high-quality images from highly undersampled\nk-space data, enabling much faster MRI scanning. However, these techniques\nsometim…
View article: A Novel Approach for Correcting Multiple Discrete Rigid In-Plane Motions Artefacts in MRI Scans
A Novel Approach for Correcting Multiple Discrete Rigid In-Plane Motions Artefacts in MRI Scans Open
Motion artefacts created by patient motion during an MRI scan occur frequently in practice, often rendering the scans clinically unusable and requiring a re-scan. While many methods have been employed to ameliorate the effects of patient m…
View article: Utilization of a combined EEG/NIRS system to predict driver drowsiness
Utilization of a combined EEG/NIRS system to predict driver drowsiness Open
The large number of automobile accidents due to driver drowsiness is a critical concern of many countries. To solve this problem, numerous methods of countermeasure have been proposed. However, the results were unsatisfactory due to inadeq…
View article: Interbrain phase synchronization during turn-taking verbal interaction-a hyperscanning study using simultaneous EEG/MEG: Synchronization During Turn-Taking Verbal Interaction
Interbrain phase synchronization during turn-taking verbal interaction-a hyperscanning study using simultaneous EEG/MEG: Synchronization During Turn-Taking Verbal Interaction Open
Recently, neurophysiological findings about social interaction have been investigated widely, and hardware has been developed that can measure multiple subjects' brain activities simultaneously. These hyperscanning studies have enabled us …
View article: Multi-Modal Integration of EEG-fNIRS for Brain-Computer Interfaces – Current Limitations and Future Directions
Multi-Modal Integration of EEG-fNIRS for Brain-Computer Interfaces – Current Limitations and Future Directions Open
Multi-modal integration, which combines multiple neurophysiological signals, is gaining more attention for its potential to supplement single modality’s drawbacks and yield reliable results by extracting complementary features. In particul…
View article: Estimation of Attenuation Coefficients for Simultaneous PET/MRI Using Both MRI and PET Data Combining Bayesian Deep Learning pseudo-CT and Maximum Likelihood Estimation of Activity and Attenuation
Estimation of Attenuation Coefficients for Simultaneous PET/MRI Using Both MRI and PET Data Combining Bayesian Deep Learning pseudo-CT and Maximum Likelihood Estimation of Activity and Attenuation Open
A major remaining challenge for magnetic resonance-based attenuation correction methods (MRAC) is their susceptibility to sources of MRI artifacts (e.g. implants, motion) as well as uncertainties due to the limitations of MRI contrast (e.g…
View article: Bayesian deep learning Uncertainty estimation and pseudo-CT prior for robust Maximum Likelihood estimation of Activity and Attenuation (UpCT-MLAA) in the presence of metal implants for simultaneous PET/MRI in the pelvis
Bayesian deep learning Uncertainty estimation and pseudo-CT prior for robust Maximum Likelihood estimation of Activity and Attenuation (UpCT-MLAA) in the presence of metal implants for simultaneous PET/MRI in the pelvis Open
View article: Benefits of Using a Spatially-Variant Penalty Strength With Anatomical Priors in PET Reconstruction
Benefits of Using a Spatially-Variant Penalty Strength With Anatomical Priors in PET Reconstruction Open
In this study, we explore the use of a spatially-variant penalty strength in penalized image reconstruction using anatomical priors to reduce the dependence of lesion contrast on surrounding activity and lesion location. This work builds o…
View article: Conditional WGANs with Adaptive Gradient Balancing for Sparse MRI Reconstruction
Conditional WGANs with Adaptive Gradient Balancing for Sparse MRI Reconstruction Open
Recent sparse MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling much faster MRI scanning. However, these techniques sometimes strug…
View article: Utility of Image Processing and Analysis (IPA) for Diagnosis of Very Short Segment Hirschsprung Disease (vsHD)
Utility of Image Processing and Analysis (IPA) for Diagnosis of Very Short Segment Hirschsprung Disease (vsHD) Open
The diagnosis of vsHD, HD with distal rectal aganglionic segment of ≤2 cm, is extremely difficult as the aganglionic zone (AZ) and physiologic hypoganglionic zone may overlap. Also, proximal AZ may show calretinin-positive mucosal nerve fi…
View article: Diagnostic Utility of Calretinin-Positive Mucosal Nerve Fiber Quantification in Hirschsprung Disease (HD): An Image Processing and Analysis (IPA) Study
Diagnostic Utility of Calretinin-Positive Mucosal Nerve Fiber Quantification in Hirschsprung Disease (HD): An Image Processing and Analysis (IPA) Study Open
Transition (TZ) and normal zone (GZ) in HD pull-through specimens show variable density of calretinin-positive mucosal nerve fibers. This variability may also be present in GZ in non-HD. Despite the variability, IPA may aid in defining a c…
View article: Transition Zone in Total Colonic Aganglionosis and Colorectal Hirschsprung Disease Shows a Similar Trend of Mucosal Innervation: Image Processing and Analysis (IPA) Study
Transition Zone in Total Colonic Aganglionosis and Colorectal Hirschsprung Disease Shows a Similar Trend of Mucosal Innervation: Image Processing and Analysis (IPA) Study Open
Animal model studies suggest that total colonic aganglionosis (TCA) and aganglionosis involving the entire colorectum and up to 50 cm of the distal ileum may have a longer transition zone (TZ) than conventional colorectal Hirschsprung dise…
View article: Spatially-variant Strength for Anatomical Priors in PET Reconstruction
Spatially-variant Strength for Anatomical Priors in PET Reconstruction Open
This study explores the use of a spatially-variant penalty strength, proposed initially for quadratic penalties, in penalized image reconstruction using anatomical information. We have used the recently proposed Parallel Level Sets (PLS) a…
View article: Artillery Error Budget Method Using Optimization Algorithm
Artillery Error Budget Method Using Optimization Algorithm Open
View article: Evaluation of lesion detectability in positron emission tomography when using a convergent penalized likelihood image reconstruction method
Evaluation of lesion detectability in positron emission tomography when using a convergent penalized likelihood image reconstruction method Open
We have previously developed a convergent penalized likelihood (PL) image reconstruction algorithm using the relative difference prior (RDP) and showed that it achieves more accurate lesion quantitation compared to ordered subsets expectat…
View article: A Study on the Design of Rifling Angle by Setting up an Idealized Rifling Force Curve
A Study on the Design of Rifling Angle by Setting up an Idealized Rifling Force Curve Open
Rifling Force can be described with projectile velocity, gas pressure and rifling angle, etc. Under the same conditions, the character of the rifling angle decisively influences the rifling force. To reduce the harmful effect, locally dist…