Nieun Seo

Attention-based Multiple Instance Learning for Classification of Inflammatory Activity in Crohn’s Disease Patients from MR Enterography

Seohyun Hwang, H.S. Lee, Nieun Seo, Joon Seok Lim et autres

This study proposes a deep learning framework that combines a foundation model, DINOv2, with an attention-based multiple instance learning (MIL) strategy to automatically assess inflammatory activity in Crohn’s disease from magnetic resonance enterography (MRE) images. The proposed method treats lesion-level MRE patches …

kr (code pays fourni par la source)

A simple MR enterography assessment of Crohn disease activity based on the most affected bowel segment: A retrospective cohort study

Nieun Seo, Joon Seok Lim, Seung‐seob Kim, H. Bae et autres

This retrospective study aimed to propose and validate a simple magnetic resonance enterography (MRE)-based assessment of Crohn disease (CD) activity based on the most inflamed bowel segment. A total of 252 adult patients who underwent MRE for suspected or known CD were …

kr (code pays fourni par la source)

Anatomy-aware diffusion-based detection of bowel inflamed lesions in MRE with foundation model-based zero-shot bowel segmentation

Chaelin Lee, Hansang Lee, Nieun Seo, Joon Seok Lim et autres

DeFloMat: Detection with Flow Matching for Stable and Efficient Generative Object Localization

H.S. Lee, Chaelin Lee, Nieun Seo, Joon Seok Lim et autres

We propose DeFloMat (Detection with Flow Matching), a novel generative object detection framework that addresses the critical latency bottleneck of diffusion-based detectors, such as DiffusionDet, by integrating Conditional Flow Matching (CFM). Diffusion models achieve high accuracy by formulating detection as a multi-step …

DeFloMat: Detection with Flow Matching for Stable and Efficient Generative Object Localization

H.S. Lee, Chaelin Lee, Nieun Seo, Joon Seok Lim et autres

We propose DeFloMat (Detection with Flow Matching), a novel generative object detection framework that addresses the critical latency bottleneck of diffusion-based detectors, such as DiffusionDet, by integrating Conditional Flow Matching (CFM). Diffusion models achieve high accuracy by formulating detection as a multi-step …

How best to combine DWI and T2WI to predict pathologic complete response: a multi-center study on interpreting MRI following chemoradiotherapy of rectal cancer

Hae Young Kim, Nieun Seo, Soon Nam Oh, Sung Kyoung Moon et autres

kr (code pays fourni par la source)

Impact of LI-RADS CT and MRI Ancillary Features on Diagnostic Performance: An Individual Participant Data Meta-Analysis

Nicole Abedrabbo, Eric Lam, Matthew D. F. McInnes, Haben Dawit et autres

In an individual participant data meta-analysis, applying individual CT and MRI ancillary features to Liver Imaging Reporting and Data System categories 1–5 observations did not improve diagnostic performance compared with major features.

us, ca, sa, cn, ch, gb, ar, pl, kr, fr, it (code pays fourni par la source)

Detection of Inflammatory Bowel Disease in MRE Images Using Contextual Information Modulation and Detection Refinement Classifier

H.S. Lee, Hansang Lee, Nieun Seo, Joon Seok Lim et autres

Crohn’s disease is a chronic inflammatory bowel disease, and accurately detecting inflammatory regions in MRE images is essential for its diagnosis and severity assessment. Detecting inflammation in MRE images is challenging due to variations in size, location, shape, and signal intensity, as …

kr (code pays fourni par la source)

Diagnostic Performance of CT/MRI LI-RADS Version 2018 Major Feature Combinations: Individual Participant Data Meta-Analysis

Robert G. Adamo, Christian B. van der Pol, Mostafa Alabousi, Eric Lam et autres

This meta-analysis showed that most major feature combinations in the same CT/MRI Liver Imaging Reporting and Data System category had similar positive predictive values for hepatocellular carcinoma in patients at high risk for cancer, with the exception of five combinations from LR-3 …

ca, us, sa, ch, gb, ar, pl, cn, kr, fr, it (code pays fourni par la source)

Detection of Inflammatory Bowel Diseases in MRE Images Using Multi-Slice Multi-Label Spatial Context Learning

H.S. Lee, Nieun Seo

Crohn’s disease is a chronic inflammatory bowel disease, and accurate detection of inflammatory regions in MRE images is essential for its diagnosis and severity assessment. Traditional single-slice-based MRE analysis fails to capture the spatial context across consecutive slices, limiting detection performance. This …

kr (code pays fourni par la source)

Context-aware focal modulation for detection of inflammatory bowel diseases from MRE images

Chaelin Lee, H.S. Lee, Nieun Seo, Joon Seok Lim et autres

Detection of inflammation in MR enterography (MRE) images is essential for the diagnosis and treatment planning of inflammatory bowel diseases. However, variability in the size, location, and shape of inflammation presents challenges for automated detection systems. This often results in false positives …

kr (code pays fourni par la source)

Artificial Intelligence Model for Detection of Colorectal Cancer on Routine Abdominopelvic CT Examinations: A Training and External-Testing Study

Seung‐seob Kim, Hyunseok Seo, Kihwan Choi, Sung‐Won Kim et autres

BACKGROUND. Radiologists are prone to missing some colorectal cancers (CRCs) on routine abdominopelvic CT examinations that are in fact detectable on the images.

kr (code pays fourni par la source)