7 papers
Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs
Hoigi Seo, Byung Hyun Lee, Minjun Kim +3
Multi-modal large language models (MLLMs) achieve strong modality understanding by pairing a large language model (LLM) with an encoder for a target modality such as vision, video,…
A Target-Free Harmonization Method for MRI
Minjun Kim, Dong Ju Mun, Hwihun Jeong +4
In MRI, variations in scan parameters, sequence, or hardware can lead to discrepancies in image appearance, even for the same subject. These inconsistencies, known as domain shifts…
Predicting before Reconstruction: A generative prior framework for MRI acceleration
Juhyung Park, Rokgi Hong, Roh-Eul Yoo +4
Recent advancements in artificial intelligence have created transformative capabilities in image synthesis and generation, enabling diverse research fields to innovate at revolutio…
Efficient and robust 3D blind harmonization for large domain gaps
Hwihun Jeong, Hayeon Lee, Se Young Chun +1
Blind harmonization has emerged as a promising technique for MR image harmonization to achieve scale-invariant representations, requiring only target domain data (i.e., no source d…
Adaptive Selection of Sampling-Reconstruction in Fourier Compressed Sensing
Seongmin Hong, Jaehyeok Bae, Jongho Lee +1
Compressed sensing (CS) has emerged to overcome the inefficiency of Nyquist sampling. However, traditional optimization-based reconstruction is slow and can not yield an exact imag…
MOST: MR reconstruction Optimization for multiple downStream Tasks via continual learning
Hwihun Jeong, Se Young Chun, Jongho Lee
Deep learning-based Magnetic Resonance (MR) reconstruction methods have focused on generating high-quality images but often overlook the impact on downstream tasks (e.g., segmentat…
Self-supervised training of deep denoisers in multi-coil MRI considering noise correlations
Juhyung Park, Dongwon Park, Sooyeon Ji +3
Deep learning-based denoising methods have shown powerful results for improving the signal-to-noise ratio of magnetic resonance (MR) images, mostly by leveraging supervised learnin…