arXiv subjects

Yingmin Liu

Publications and source records attributed to Yingmin Liu.

17 recordsLinked to original sources

arXiv2026

MOSAIC: A Self-supervised Dynamic Multi-encoding Reconstruction Framework for 3D Late Gadolinium Enhancement MRI

Purpose: To develop and evaluate a self-supervised dynamic reconstruction framework for highly undersampled dual-echo three-dimensional late gadolinium enhancement (3D LGE) MRI. Methods: MOSAIC jointly models multi-echo image content, coil sensitivity maps, and beat-specific nonrigid motion directly from acquired undersampled data, without requiring fully sampled training datasets or accurate precomputed sensitivity maps. Unlike existing methods that bin the acquired data into different motion states, with or without motion compensation, MOSAIC reconstructs a motion-resolved 3D LGE image from each heartbeat. The method was evaluated using digital phantoms with simulated myocardial scars and in vivo animal and human studies. Results: In phantom experiments, MOSAIC achieved higher peak signal-to-noise ratio and structural similarity index measure than low-rank deep image prior reconstruction and ablation variants of MOSAIC. In animal and human studies, MOSAIC achieved higher blinded expert image-quality scores than inline image-navigated compressed-sensing and low-rank deep image prior reconstructions. Conclusion: MOSAIC demonstrated the feasibility of motion-resolved free-breathing dual-echo 3D LGE MRI at acceleration factors exceeding 1,000, with improved detail preservation and artifact suppression relative to the state-of-the-art comparison methods.

eess.IV↗

arXiv2026

ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation

Retrieval-Augmented Generation (RAG) systems implicitly assume mutual consistency among retrieved documents -- an assumption that frequently fails in practice. We present ConflictRAG, a conflict-aware RAG framework that detects, classifies, and resolves knowledge conflicts prior to answer generation. The framework introduces three contributions: (1) a two-stage conflict detection module combining a lightweight embedding-based MLP classifier with selective LLM refinement, reducing API costs by 62% while maintaining 90.8% detection accuracy; (2) an Entropy-TOPSIS framework for data-driven source credibility assessment, improving selection accuracy by 7.1% over manual heuristics; and (3) a Conflict-Aware RAG Score (CARS) for diagnostic evaluation of conflict-handling capabilities. Experiments on three benchmarks against six baselines demonstrate 88.7% conflict-detection F1 and consistent 5.3--6.1% correctness gains over the strongest conflict-aware baseline, with the pipeline transferring effectively across backbone LLMs.

cs.CL↗

arXiv2026

CyberCorrect: A Cybernetic Framework for Closed-Loop Self-Correction in Large Language Models

Large language model (LLM) self-correction -- the ability to detect and fix errors in generated outputs -- remains largely ad hoc, relying on generic prompts such as "please reconsider your answer" without systematic error analysis or convergence guarantees. We propose CyberCorrect, a framework that formalizes LLM self-correction as a closed-loop control system grounded in cybernetic theory. The framework models the LLM generator as the plant and introduces a tri-modal Error Detector (combining self-consistency, verbalized confidence, and logic-chain verification) as the sensor. A type-directed Correction Controller generates targeted repair instructions based on diagnosed error categories, while a Convergence Judge determines iteration termination using stability criteria adapted from control theory. We further introduce three control-theoretic evaluation metrics -- convergence rate, overshoot rate, and oscillation rate -- that capture correction dynamics beyond final accuracy. Experiments on our constructed CyberCorrect-Bench (440 reasoning tasks with annotated error types and correction paths) show that CyberCorrect achieves 79.8% final accuracy, improving upon the best existing self-correction method by 6.2 percentage points, while reducing overshoot (erroneous over-correction) by 41% through its convergence control mechanism.

cs.AI↗

arXiv2026

Agentic Retrieval-Augmented Generation for Financial Document Question Answering

Financial document question answering (QA) demands complex multi-step numerical reasoning over heterogeneous evidence--structured tables, textual narratives, and footnotes--scattered across corporate filings. Existing retrieval-augmented generation (RAG) approaches adopt a single-pass retrieve-then-generate paradigm that struggles with the compositional reasoning chains prevalent in financial analysis. We propose FinAgent-RAG, an agentic RAG framework that orchestrates iterative retrieval-reasoning loops with self-verification, specifically engineered for the precision requirements of financial numerical reasoning. The framework integrates three domain-specific innovations: (1) a Contrastive Financial Retriever trained with hard negative mining to distinguish semantically similar but numerically distinct financial passages, (2) a Program-of-Thought reasoning module that generates executable Python code for precise arithmetic rather than relying on error-prone LLM-based mental computation, and (3) an Adaptive Strategy Router that dynamically allocates computational resources based on question complexity, reducing API costs by 41.3% on FinQA while preserving accuracy. Extensive experiments on three benchmark datasets--FinQA, ConvFinQA, and TAT-QA--demonstrate that FinAgent-RAG achieves 76.81%, 78.46%, and 74.96% execution accuracy respectively, outperforming the strongest baseline by 5.62--9.32 percentage points. Ablation studies, cross-backbone evaluation with four LLMs, and deployment cost analysis confirm the framework's robustness and practical viability for financial institutions.

cs.AI↗

arXiv2025

EMORe: Motion-Robust 5D MRI Reconstruction via Expectation-Maximization-Guided Binning Correction and Outlier Rejection

We propose EMORe, an adaptive reconstruction method designed to enhance motion robustness in free-running, free-breathing self-gated 5D cardiac magnetic resonance imaging (MRI). Traditional self-gating-based motion binning for 5D MRI often results in residual motion artifacts due to inaccuracies in cardiac and respiratory signal extraction and sporadic bulk motion, compromising clinical utility. EMORe addresses these issues by integrating adaptive inter-bin correction and explicit outlier rejection within an expectation-maximization (EM) framework, whereby the E-step and M-step are executed alternately until convergence. In the E-step, probabilistic (soft) bin assignments are refined by correcting misassignment of valid data and rejecting motion-corrupted data to a dedicated outlier bin. In the M-step, the image estimate is improved using the refined soft bin assignments. Validation in a simulated 5D MRXCAT phantom demonstrated EMORe's superior performance compared to standard compressed sensing reconstruction, showing significant improvements in peak signal-to-noise ratio, structural similarity index, edge sharpness, and bin assignment accuracy across varying levels of simulated bulk motion. In vivo validation in 13 volunteers further confirmed EMORe's robustness, significantly enhancing blood-myocardium edge sharpness and reducing motion artifacts compared to compressed sensing, particularly in scenarios with controlled coughing-induced motion. Although EMORe incurs a modest increase in computational complexity, its adaptability and robust handling of bulk motion artifacts significantly enhance the clinical applicability and diagnostic confidence of 5D cardiac MRI.

eess.IV↗

arXiv2025

A multi-dynamic low-rank deep image prior (ML-DIP) for 3D real-time cardiovascular MRI

Purpose: To develop a reconstruction framework for 3D real-time cine cardiovascular magnetic resonance (CMR) from highly undersampled data without requiring fully sampled training datasets. Methods: We developed a multi-dynamic low-rank deep image prior (ML-DIP) framework that models spatial image content and deformation fields using separate neural networks. These sub-networks are jointly trained per scan to reconstruct the dynamic image series directly from undersampled k-space data. ML-DIP was evaluated on (i) a 3D cine digital phantom with simulated premature ventricular contractions (PVCs), (ii) ten healthy subjects (including two scanned during both rest and exercise), and (iii) 12 patients with a history of PVCs. Phantom results were assessed using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). In vivo performance was evaluated by comparing left-ventricular function quantification (against 2D real-time cine) and image quality (against 2D real-time cine and binning-based 5D-Cine). Results: In the phantom study, ML-DIP achieved PSNR > 29 dB and SSIM > 0.90 for scan times as short as two minutes, while recovering cardiac motion, respiratory motion, and PVC events. In healthy subjects, ML-DIP yielded functional measurements comparable to 2D cine and higher image quality than 5D-Cine, including during exercise with high heart rates and bulk motion. In PVC patients, ML-DIP preserved beat-to-beat variability and reconstructed irregular beats, whereas 5D-Cine showed motion artifacts and information loss due to binning. Conclusion: ML-DIP enables high-quality 3D real-time CMR with acceleration factors exceeding 1,000 by learning low-rank spatial and motion representations from undersampled data, without relying on external fully sampled training datasets.

eess.IV↗

arXiv2025

An unsupervised method for MRI recovery: Deep image prior with structured sparsity

Objective: To propose and validate an unsupervised MRI reconstruction method that does not require fully sampled k-space data. Materials and Methods: The proposed method, deep image prior with structured sparsity (DISCUS), extends the deep image prior (DIP) by introducing group sparsity to frame-specific code vectors, enabling the discovery of a low-dimensional manifold for capturing temporal variations. \discus was validated using four studies: (I) simulation of a dynamic Shepp-Logan phantom to demonstrate its manifold discovery capabilities, (II) comparison with compressed sensing and DIP-based methods using simulated single-shot late gadolinium enhancement (LGE) image series from six distinct digital cardiac phantoms in terms of normalized mean square error (NMSE) and structural similarity index measure (SSIM), (III) evaluation on retrospectively undersampled single-shot LGE data from eight patients, and (IV) evaluation on prospectively undersampled single-shot LGE data from eight patients, assessed via blind scoring from two expert readers. Results: DISCUS outperformed competing methods, demonstrating superior reconstruction quality in terms of NMSE and SSIM (Studies I--III) and expert reader scoring (Study IV). Discussion: An unsupervised image reconstruction method is presented and validated on simulated and measured data. These developments can benefit applications where acquiring fully sampled data is challenging.

eess.IV↗

arXiv2024

Coil Reweighting to Suppress Motion Artifacts in Real-Time Exercise Cine Imaging

Background: Accelerated real-time cine (RT-Cine) imaging enables cardiac function assessment without the need for breath-holding. However, when performed during in-magnet exercise, RT-Cine images may exhibit significant motion artifacts. Methods: By projecting the time-averaged images to the subspace spanned by the coil sensitivity maps, we propose a coil reweighting (CR) method to automatically suppress a subset of receive coils that introduces a high level of artifacts in the reconstructed image. RT-Cine data collected at rest and during exercise from ten healthy volunteers and six patients were utilized to assess the performance of the proposed method. One short-axis and one two-chamber RT-Cine series reconstructed with and without CR from each subject were visually scored by two cardiologists in terms of the level of artifacts on a scale of 1 (worst) to 5 (best). Results: For healthy volunteers, applying CR to RT-Cine images collected at rest did not significantly change the image quality score (p=1). In contrast, for RT-Cine images collected during exercise, CR significantly improved the score from 3.9 to 4.68 (p<0.001). Similarly, in patients, CR did not significantly change the score for images collected at rest (p=0.031) but markedly improved the score from 3.15 to 4.42 (p<0.001) for images taken during exercise. Despite lower image quality scores in the patient cohort compared to healthy subjects, likely due to larger body habitus and the difficulty of limiting body motion during exercise, CR effectively suppressed motion artifacts, with all image series from the patient cohort receiving a score of four or higher. Conclusion: Using data from healthy subjects and patients, we demonstrate that the motion artifacts in the reconstructed RT-Cine images can be effectively suppressed significantly with the proposed CR method.

eess.SP↗

arXiv2024

Accelerated Real-time Cine and Flow under In-magnet Staged Exercise

Background: Cardiovascular magnetic resonance imaging (CMR) is a well established imaging tool for diagnosing and managing cardiac conditions. The integration of exercise stress with CMR (ExCMR) can enhance its diagnostic capacity. Despite recent advances in CMR technology, quantitative ExCMR during exercise remains technically challenging due to motion artifacts and limited spatial and temporal resolution. Methods: This study investigated the feasibility of biventricular functional and hemodynamic assessment using real-time (RT) ExCMR during a staged exercise protocol in 24 healthy volunteers. We employed high acceleration rates and applied a coil reweighting technique to minimize motion blurring and artifacts. We further applied a beat-selection technique that identified beats from the endexpiratory phase to minimize the impact of respiration-induced through-plane motion on cardiac function quantification. Additionally, results from six patients were presented to demonstrate clinical feasibility. Results: Our findings indicated a consistent decrease in end-systolic volume and stable end-diastolic volume across exercise intensities, leading to increased stroke volume and ejection fraction. The selection of end-expiratory beats modestly enhanced the repeatability of cardiac function parameters, as shown by scan-rescan tests in nine volunteers. High scores from a blinded image quality assessment indicated that coil reweighting effectively minimized motion artifacts. Conclusions: This study demonstrated the feasibility of RT ExCMR with inmagnet exercise in healthy subjects and patients. Our results indicate that high acceleration rates, coil reweighting, and selection of respiratory phase-specific heartbeats enhance image quality and repeatability of quantitative RT ExCMR.

eess.SP↗

arXiv2023

Deep Image prior with StruCtUred Sparsity (DISCUS) for dynamic MRI reconstruction

High-quality training data are not always available in dynamic MRI. To address this, we propose a self-supervised deep learning method called deep image prior with structured sparsity (DISCUS) for reconstructing dynamic images. DISCUS is inspired by deep image prior (DIP) and recovers a series of images through joint optimization of network parameters and input code vectors. However, DISCUS additionally encourages group sparsity on frame-specific code vectors to discover the low-dimensional manifold that describes temporal variations across frames. Compared to prior work on manifold learning, DISCUS does not require specifying the manifold dimensionality. We validate DISCUS using three numerical studies. In the first study, we simulate a dynamic Shepp-Logan phantom with frames undergoing random rotations, translations, or both, and demonstrate that DISCUS can discover the dimensionality of the underlying manifold. In the second study, we use data from a realistic late gadolinium enhancement (LGE) phantom to compare DISCUS with compressed sensing (CS) and DIP, and to demonstrate the positive impact of group sparsity. In the third study, we use retrospectively undersampled single-shot LGE data from five patients to compare DISCUS with CS reconstructions. The results from these studies demonstrate that DISCUS outperforms CS and DIP, and that enforcing group sparsity on the code vectors helps discover true manifold dimensionality and provides additional performance gain.

eess.IV↗

arXiv2023

Motion-robust free-running volumetric cardiovascular MRI

PURPOSE: To present and assess an outlier mitigation method that makes free-running volumetric cardiovascular MRI (CMR) more robust to motion. METHODS: The proposed method, called compressive recovery with outlier rejection (CORe), models outliers in the measured data as an additive auxiliary variable. We enforce MR physics-guided group sparsity on the auxiliary variable, and jointly estimate it along with the image using an iterative algorithm. For evaluation, CORe is first compared to traditional compressed sensing (CS), robust regression (RR), and an existing outlier rejection method using two simulation studies. Then, CORe is compared to CS using seven three-dimensional (3D) cine, 12 rest four-dimensional (4D) flow, and eight stress 4D flow imaging datasets. RESULTS: Our simulation studies show that CORe outperforms CS, RR, and the existing outlier rejection method in terms of normalized mean square error and structural similarity index across 55 different realizations. The expert reader evaluation of 3D cine images demonstrates that CORe is more effective in suppressing artifacts while maintaining or improving image sharpness. Finally, 4D flow images show that CORe yields more reliable and consistent flow measurements, especially in the presence of involuntary subject motion or exercise stress. CONCLUSION: An outlier rejection method is presented and tested using simulated and measured data. This method can help suppress motion artifacts in a wide range of free-running CMR applications. CODE & DATA: Implementation code and datasets are available on GitHub at http://github.com/OSU-MR/motion-robust-CMR

eess.IV↗

arXiv2023

Cardiac and respiratory motion extraction for MRI using Pilot Tone-a patient study

Background: Several studies have shown that both respiratory and cardiac motion can be extracted from the Pilot Tone (PT) signal successfully. However, most of these studies were performed in healthy volunteers. In addition, validating PT using ECG as a reference can be problematic because both PT and ECG tend to be unreliable in patients with arrhythmias. Purpose: We seek to evaluate the accuracy and reliability of the cardiac and respiratory signals extracted from PT in patients clinically referred for cardiovascular MRI with the image-derived signals as the reference. Methods: Twenty-three patients were scanned on a 1.5 T scanner using balanced steady-state free-precession real-time (RT) cine sequence. The PT signal was generated by a built-in PT transmitter integrated within the body array coil. For comparison, commercial ECG and BioMatrix (BM) respiratory sensor signals were synchronously recorded. Results: The respiratory motion extracted from PT correlated positively with the image-derived respiratory signal in all cases and showed a stronger correlation (absolute coefficient: 0.95+-0.09) than BM (0.72+-0.24). For the cardiac signal, PT trigger jitter (standard deviation of PT trigger locations relative to ECG triggers) ranged from 6.6 to 83.3 ms, with a median of 21.8 ms. The mean absolute difference between the PT and corresponding ECG cardiac cycle duration was less than 5% of the averaged ECG RR interval for 21 out of 23 patients. Overall, the performance of PT-based trigger extraction was comparable to that of ECG. We did not observe significant linear dependence (p>0.28) of PT delay and PT jitter on the patients' BMI or cardiac cycle duration. Conclusions: This study demonstrates the potential of PT to monitor both respiratory and cardiac motion in patients clinically referred for cardiovascular MRI.

eess.SP↗

arXiv2022

Technical Report (v1.0)--Pseudo-random Cartesian Sampling for Dynamic MRI

For an effective application of compressed sensing (CS), which exploits the underlying compressibility of an image, one of the requirements is that the undersampling artifact be incoherent (noise-like) in the sparsifying transform domain. For cardiovascular MRI (CMR), several pseudo-random sampling methods have been proposed that yield a high level of incoherence. In this technical report, we present a collection of five pseudo-random Cartesian sampling methods that can be applied to 2D cine and flow, 3D volumetric cine, and 4D flow imaging. Four out of the five presented methods yield fast computation for on-the-fly generation of the sampling mask, without the need to create and store pre-computed look-up tables. In addition, the sampling distribution is parameterized, providing control over the sampling density. For each sampling method in the report, (i) we briefly describe the methodology, (ii) list default values of the pertinent parameters, and (iii) provide a publicly available MATLAB implementation.

eess.SP↗

arXiv2020

Automatic image-based respiratory signal extraction in real-time CMR

Purpose: To develop a fully automatic method for extraction and directionality determination of respiratory signal in free-breathing, real-time (RT) cardiac MRI. Methods: The respiratory signal is extracted by a principal component analysis method from RT cine images. Then, a two-step procedure is used to determine the directionality (sign) of the respiratory signal. First, the signal polarity of all slices is made consistent with a reference slice. Second, a global sign correction is performed by maximizing the correlation of the respiratory signal with the zeroth-moment center curve. The proposed method is evaluated in multi-slice RT cine from eleven volunteers and two patients. The motion in a manually selected region-of-interest is used as reference. Results: The extracted respiratory signal using the proposed method exhibits high, positive correlation with the reference in all cases and is more robust compared to a recently proposed method. To demonstrate its clinical utility, the method is used to identify heartbeats from inspiratory and expiratory phases and, in turn, to account for respiration-induced changes in the cardiac output. Conclusions: The proposed method enables fully automatic extraction and directionality determinations of respiratory signal from RT cardiac cine images, allowing accurate cardiac function quantification.

eess.IV↗

arXiv2020

OCMR (v1.0)--Open-Access Multi-Coil k-Space Dataset for Cardiovascular Magnetic Resonance Imaging

Cardiovascular MRI (CMR) is a non-invasive imaging modality that provides excellent soft-tissue contrast without the use of ionizing radiation. Physiological motions and limited speed of MRI data acquisition necessitate development of accelerated methods, which typically rely on undersampling. Recovering diagnostic quality CMR images from highly undersampled data has been an active area of research. Recently, several data acquisition and processing methods have been proposed to accelerate CMR. The availability of data to objectively evaluate and compare different reconstruction methods could expedite innovation and promote clinical translation of these methods. In this work, we introduce an open-access dataset, called OCMR, that provides multi-coil k-space data from 53 fully sampled and 212 prospectively undersampled cardiac cine series.

eess.IV↗

arXiv2020

Fully Self-Gated Whole-Heart 4D Flow Imaging from a Five-Minute Scan

Purpose: To develop and validate an acquisition and processing technique that enables fully self-gated 4D flow imaging with whole-heart coverage in a fixed five-minute scan. Theory and Methods: The data are acquired continuously using Cartesian sampling and sorted into respiratory and cardiac bins using the self-gating signal. The reconstruction is performed using a recently proposed Bayesian method called ReVEAL4D. ReVEAL4D is validated using data from eight healthy volunteers and two patients and compared with a compressed sensing technique, L1-SENSE. Results: Healthy subjects -- Compared to 2D phase-contrast MRI (2D-PC), flow quantification from ReVEAL4D shows no significant bias. In contrast, the peak velocity and peak flow rate for L1-SENSE are significantly underestimated. Compared to traditional parallel MRI-based 4D flow imaging, ReVEAL4D demonstrates small but significant biases in net flow and peak flow rate, with no significant bias in peak velocity. All three indices are significantly and more markedly underestimated by L1-SENSE. Patients -- Flow quantification from ReVEAL4D agrees well with the 2D-PC reference. In contrast, L1-SENSE markedly underestimated peak velocity. Conclusions: The combination of highly accelerated five-minute Cartesian acquisition, self-gating, and ReVEAL4D enables whole-heart 4D flow imaging with accurate flow quantification.

eess.IV↗

arXiv2020

Automatic Extraction and Sign Determination of Respiratory Signal in Real-time Cardiac Magnetic Resonance imaging

In real-time (RT) cardiac cine imaging, a stack of 2D slices is collected sequentially under free-breathing conditions. A complete heartbeat from each slice is then used for cardiac function quantification. The inter-slice respiratory mismatch can compromise accurate quantification of cardiac function. Methods based on principal components analysis (PCA) have been proposed to extract the respiratory signal from RT cardiac cine, but these methods cannot resolve the inter-slice sign ambiguity of the respiratory signal. In this work, we propose a fully automatic sign correction procedure based on the similarity of neighboring slices and correlation to the center-of-mass curve. The proposed method is evaluated in eleven volunteers, with ten slices per volunteer. The motion in a manually selected region-of-interest (ROI) is used as a reference. The results show that the extracted respiratory signal has a high, positive correlation with the reference in all cases. The qualitative assessment of images also shows that the proposed approach can accurately identify heartbeats, one from each slice, belonging to the same respiratory phase. This approach can improve cardiac function quantification for RT cine without manual intervention.

eess.IV↗