Sangtae Ahn

Analysis of Sensitivity Gains for BGO-Based TOF PET

Sangtae Ahn, S. Dolinsky, K.-H. Su, Kihong Kim et autres

Bismuth germanate (BGO) is a widely-used PET scintillator with many advantages over lutetium (yttrium) oxyorthosilicate (L(Y)SO), including higher stopping power, a higher photoelectric fraction, a lower cost and lower background radiation. Generally, BGO is considered to be unsuitable for time of flight …

us (code pays fourni par la source)

A Framework for BGO-Specific TOF Data Generation, Processing, and System-Level Evaluation

KyungYi Kim, Sangtae Ahn, Jiajia Qi, S R Cherry et autres

Bismuth germanate (BGO) has emerged as a promising candidate for time-of-flight (TOF) positron emission tomography (PET) imaging through detecting Cherenkov photons. However, the prompt Cherenkov emission, combined with slower scintillation photons, results in a two-component Gaussian mixture timing distribution. This study presents …

us (code pays fourni par la source)

Auto-Beta: Deep Learning-Based Automatic Beta Parameter Selection for Penalized Ml Image Reconstruction

Abolfazl Mehranian, Scott D. Wollenweber, K.-H. Su, Roger H. Johnson et autres

The automatic selection of the regularisation parameter (beta) of PET penalised reconstruction algorithms such as block-sequential regularized expectation-maximization (BSERM) has been a long-standing challenge. Here, we propose a novel framework to automatically select a patientspecific noise-aware beta value using a deep convolutional …

es, gb, us (code pays fourni par la source)

Consistent performance between medical experts and non‐expert readers in forced‐choice lesion‐detection tasks with PET images

Craig K. Abbey, Sangtae Ahn, Muhan Shao, Darrin Byrd et autres

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, including PET imaging. Ideally, these annotations would …

us (code pays fourni par la source)

Accelerating High Resolution 3D EPI with Deep Learning Reconstruction

Nastaren Abad, Sangtae Ahn, Rafi Brada, Tim Sprenger et autres

Motivation: To increase access to clinically relevant features disambiguated from partial volume based confounds by enabling ultra-high spatial resolution without clinically restrictive scan times. Goal(s): To investigate the feasibility of accelerating ultra-high resolution 3D EPI for rapid brain imaging, with DL based …

Artsemg: Adversarially Regularized Transformer with Channel-Wise Noise for Robust Hand Gesture Recognition Using Surface Electromyography

Doheun Cha, Dong-Gyu Lee, Sangtae Ahn

kr (code pays fourni par la source)

CT-free PET for Pediatric Patients with Metal Implants

Andrew T. Trout, K.-H. Su, J. MacLean, M.R. Syed et autres

Metal implants in pediatric sarcoma patients pose an inherent challenge for deep-learning (DL) based attenuation and scatter correction (ASC) in PET imaging. To address this issue, we developed a maximum a priori joint activity and attenuation (MAP-AA) PET reconstruction technique to integrate …

us (code pays fourni par la source)

Task-based evaluation of deep learning-based reconstruction for highly-accelerated 3D T1-weighted brain MRI scans

Sangtae Ahn, Chitresh Bhushan, John Huston, J. Kevin DeMarco et autres

3D MRI enables thin slices at the cost of long scan times, causing practical challenges. Recently, deep-learning (DL) techniques have successfully accelerated MR scans. However, it is challenging to characterize the image quality (IQ) performance of DL methods by conventional metrics because …

Highly accelerated FLEXA 3DTOF MR Angiography with iterative deep learning reconstruction

Naoyuki Takei, Rafi Brada, Sangtae Ahn, Graeme C. McKinnon et autres

Rapid non-contrast MRA of supra-aortic arteries is necessary to select proper patient for endovascular therapy (EVT) as EVT has become the predominant therapy of acute ischemic stroke. However, conventional 3DTOF has long scan time of 6-7 minutes to cover the entire carotid …

A deep learning anthropomorphic model observer for a detection task in PET

Muhan Shao, Darrin Byrd, Jhimli Mitra, Fatemeh Behnia et autres

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 important tool for assessing task-based image quality. …

us (code pays fourni par la source)

Improvement of Background Inpainting using Binary Masking of a Generated Image

Jihoon Lee, C S Bae, Seunghun Lee, Myung-Seok Choi et autres

최근에 딥러닝 분야에서 이미지 생성 기술은 빠르게 발전하고 있다. 이미지를 가장 잘 표현할 수 있는 방법 중 하나는 텍스트 프롬프트를 이용해 이미지를 생성하는 기술이고, 이를 이용해 이미지를 생성하는 모델의 성능은 매우 뛰어나다. 하지만 이미지에서 텍스트 프롬프트만으로 원하는 부분을 자연스럽게 바꾸는 것은 쉽지가 …

A hybrid CNN-Swin Transformer network as deep learning model observer to predict human observer performance in 2AFC trial

Muhan Shao, Jhimli Mitra, Darrin Byrd, Craig K. Abbey et autres

Model observers designed to predict human observers in detection tasks are important tools for assessing task-based image quality and optimizing imaging systems, protocol, and reconstruction algorithms. Linear model observers have been widely studied to predict human detection performance, and recently, deep learning …

us (code pays fourni par la source)