arXiv subjects

Lipeng Ning

Publications and source records attributed to Lipeng Ning.

At least 19 recordsLinked to original sources

arXiv2026

HARP: HARmonizing in-vivo diffusion MRI using Phantom-only training

Purpose: Combining multi-site diffusion MRI (dMRI) data is hindered by inter-scanner variability, which confounds subsequent analysis. Previous harmonization methods require large, matched or traveling human subjects from multiple sites, which are impractical to acquire in many situations. This study aims to develop a deep learning-based dMRI harmonization framework that eliminates the reliance on multi-site in-vivo traveling human data for training. Methods: HARP employs a voxel-wise 1D neural network trained on an easily transportable diffusion phantom. The model learns relationships between spherical harmonics coefficients of different sites without memorizing spatial structures. Results: HARP reduced inter-scanner variability levels significantly in various measures. Quantitatively, it decreased inter-scanner variability as measured by standard error in FA (12%), MD (10%), and GFA (30%) with scan-rescan standard error as the baseline, while preserving fiber orientations and tractography after harmonization. Conclusion: We believe that HARP represents an important first step toward dMRI harmonization using only phantom data, thereby obviating the need for complex, matched in vivo multi-site cohorts. This phantom-only strategy substantially enhances the feasibility and scalability of quantitative dMRI for large-scale clinical studies.

cs.CV↗

arXiv2025

Is the medical image segmentation problem solved? A survey of current developments and future directions

Medical image segmentation has advanced rapidly over the past two decades, largely driven by deep learning, which has enabled accurate and efficient delineation of cells, tissues, organs, and pathologies across diverse imaging modalities. This progress raises a fundamental question: to what extent have current models overcome persistent challenges, and what gaps remain? In this work, we provide an in-depth review of medical image segmentation, tracing its progress and key developments over the past decade. We examine core principles, including multiscale analysis, attention mechanisms, and the integration of prior knowledge, across the encoder, bottleneck, skip connections, and decoder components of segmentation networks. Our discussion is organized around seven key dimensions: (1) the shift from supervised to semi-/unsupervised learning, (2) the transition from organ segmentation to lesion-focused tasks, (3) advances in multi-modality integration and domain adaptation, (4) the role of foundation models and transfer learning, (5) the move from deterministic to probabilistic segmentation, (6) the progression from 2D to 3D and 4D segmentation, and (7) the trend from model invocation to segmentation agents. Together, these perspectives provide a holistic overview of the trajectory of deep learning-based medical image segmentation and aim to inspire future innovation. To support ongoing research, we maintain a continually updated repository of relevant literature and open-source resources at https://github.com/apple1986/medicalSegReview

eess.IV↗

arXiv2025

PRIME: Phase Reversed Interleaved Multi-Echo acquisition enables highly accelerated distortion-free diffusion MRI

Purpose: To develop and evaluate a new pulse sequence for highly accelerated distortion-free diffusion MRI (dMRI) by inserting additional echoes without prolonging TR, when generalized slice dithered enhanced resolution (gSlider) radiofrequency encoding is used for volumetric acquisition. Methods: A phase-reversed interleaved multi-echo acquisition (PRIME) was developed for rapid, high-resolution, and distortion-free dMRI, which includes several echoes where the first echo is for target diffusion-weighted imaging (DWI) acquisition with high-resolution and additional echoes are acquired with either lower resolution for 1) high-fidelity field map estimation, 2) phase navigation for shot-to-shot phase correction, 3) motion navigation across diffusion directions, or with high resolution to enable 4) high fidelity diffusion relaxometry acquisitions. The sequence was evaluated on in vivo data acquired from healthy volunteers on clinical and Connectome 2.0 scanners. Results: In vivo experiments demonstrated that 1) high in-plane acceleration (Rin-plane of 5-fold with 2D partial Fourier) was achieved using the high-fidelity field maps estimated from the second echo, which was made at a lower resolution/acceleration to increase its SNR while matching the effective echo spacing of the first readout, 2) high-resolution diffusion relaxometry parameters were estimated from triple-echo PRIME data using a white matter model of multi-TE spherical mean technique (MTE-SMT), and 3) high-fidelity mesoscale DWI at 490 um isotropic resolution was obtained in vivo by capitalizing on the high-performance gradients of the Connectome 2.0 scanner. Conclusion: The proposed PRIME sequence enabled highly accelerated, high-resolution, and distortion-free dMRI using additional echoes without prolonging scan time when gSlider encoding is utilized.

physics.med-ph↗

arXiv2025

Rapid Whole Brain Motion-robust Mesoscale In-vivo MR Imaging using Multi-scale Implicit Neural Representation

High-resolution whole-brain in vivo MR imaging at mesoscale resolutions remains challenging due to long scan durations, motion artifacts, and limited signal-to-noise ratio (SNR). This study proposes Rotating-view super-resolution (ROVER)-MRI, an unsupervised framework based on multi-scale implicit neural representations (INR), enabling efficient recovery of fine anatomical details from multi-view thick-slice acquisitions. ROVER-MRI employs coordinate-based neural networks to implicitly and continuously encode image structures at multiple spatial scales, simultaneously modeling anatomical continuity and correcting inter-view motion through an integrated registration mechanism. Validation on ex-vivo monkey brain data and multiple in-vivo human datasets demonstrates substantially improved reconstruction performance compared to bicubic interpolation and state-of-the-art regularized least-squares super-resolution reconstruction (LS-SRR) with 2-fold reduction in scan time. Notably, ROVER-MRI achieves an unprecedented whole-brain in-vivo T2-weighted imaging at 180 micron isotropic resolution in only 17 minutes of scan time on a 7T scanner with 22.4% lower relative error compared to LS-SRR. We also demonstrate improved SNR using ROVER-MRI compared to a time-matched 3D GRE acquisition. Quantitative results on several datasets demonstrate better sharpness of the reconstructed images with ROVER-MRI for different super-resolution factors (5 to 11). These findings highlight ROVER-MRI's potential as a rapid, accurate, and motion-resilient mesoscale imaging solution, promising substantial advantages for neuroimaging studies.

eess.IV↗

arXiv2025

A study of why we need to reassess full reference image quality assessment with medical images

Image quality assessment (IQA) is indispensable in clinical practice to ensure high standards, as well as in the development stage of machine learning algorithms that operate on medical images. The popular full reference (FR) IQA measures PSNR and SSIM are known and tested for working successfully in many natural imaging tasks, but discrepancies in medical scenarios have been reported in the literature, highlighting the gap between development and actual clinical application. Such inconsistencies are not surprising, as medical images have very different properties than natural images, and PSNR and SSIM have neither been targeted nor properly tested for medical images. This may cause unforeseen problems in clinical applications due to wrong judgment of novel methods. This paper provides a structured and comprehensive overview of examples where PSNR and SSIM prove to be unsuitable for the assessment of novel algorithms using different kinds of medical images, including real-world MRI, CT, OCT, X-Ray, digital pathology and photoacoustic imaging data. Therefore, improvement is urgently needed in particular in this era of AI to increase reliability and explainability in machine learning for medical imaging and beyond. Lastly, we will provide ideas for future research as well as suggesting guidelines for the usage of FR-IQA measures applied to medical images.

eess.IV↗

arXiv2025

A Deep Learning Approach to Multi-Fiber Parameter Estimation and Uncertainty Quantification in Diffusion MRI

Diffusion MRI (dMRI) is the primary imaging modality used to study brain microstructure in vivo. Reliable and computationally efficient parameter inference for common dMRI biophysical models is a challenging inverse problem, due to factors such as variable dimensionalities (reflecting the unknown number of distinct white matter fiber populations in a voxel), low signal-to-noise ratios, and non-linear forward models. These challenges have led many existing methods to use biologically implausible simplified models to stabilize estimation, for instance, assuming shared microstructure across all fiber populations within a voxel. In this work, we introduce a novel sequential method for multi-fiber parameter inference that decomposes the task into a series of manageable subproblems. These subproblems are solved using deep neural networks tailored to problem-specific structure and symmetry, and trained via simulation. The resulting inference procedure is largely amortized, enabling scalable parameter estimation and uncertainty quantification across all model parameters. Simulation studies and real imaging data analysis using the Human Connectome Project (HCP) demonstrate the advantages of our method over standard alternatives. In the case of the standard model of diffusion, our results show that under HCP-like acquisition schemes, estimates for extra-cellular parallel diffusivity are highly uncertain, while those for the intra-cellular volume fraction can be estimated with relatively high precision.

eess.IV↗

arXiv2025

DDEvENet: Evidence-based Ensemble Learning for Uncertainty-aware Brain Parcellation Using Diffusion MRI

In this study, we developed an Evidence-based Ensemble Neural Network, namely EVENet, for anatomical brain parcellation using diffusion MRI. The key innovation of EVENet is the design of an evidential deep learning framework to quantify predictive uncertainty at each voxel during a single inference. To do so, we design an evidence-based ensemble learning framework for uncertainty-aware parcellation to leverage the multiple dMRI parameters derived from diffusion MRI. Using EVENet, we obtained accurate parcellation and uncertainty estimates across different datasets from healthy and clinical populations and with different imaging acquisitions. The overall network includes five parallel subnetworks, where each is dedicated to learning the FreeSurfer parcellation for a certain diffusion MRI parameter. An evidence-based ensemble methodology is then proposed to fuse the individual outputs. We perform experimental evaluations on large-scale datasets from multiple imaging sources, including high-quality diffusion MRI data from healthy adults and clinically diffusion MRI data from participants with various brain diseases (schizophrenia, bipolar disorder, attention-deficit/hyperactivity disorder, Parkinson's disease, cerebral small vessel disease, and neurosurgical patients with brain tumors). Compared to several state-of-the-art methods, our experimental results demonstrate highly improved parcellation accuracy across the multiple testing datasets despite the differences in dMRI acquisition protocols and health conditions. Furthermore, thanks to the uncertainty estimation, our EVENet approach demonstrates a good ability to detect abnormal brain regions in patients with lesions, enhancing the interpretability and reliability of the segmentation results.

eess.IV↗

arXiv2024

SlicerTMS: Real-Time Visualization of Transcranial Magnetic Stimulation for Mental Health Treatment

We present a real-time visualization system for Transcranial Magnetic Stimulation (TMS), a non-invasive neuromodulation technique for treating various brain disorders and mental health diseases. Our solution targets the current challenges of slow and labor-intensive practices in treatment planning. Integrating Deep Learning (DL), our system rapidly predicts electric field (E-field) distributions in 0.2 seconds for precise and effective brain stimulation. The core advancement lies in our tool's real-time neuronavigation visualization capabilities, which support clinicians in making more informed decisions quickly and effectively. We assess our system's performance through three studies: First, a real-world use case scenario in a clinical setting, providing concrete feedback on applicability and usability in a practical environment. Second, a comparative analysis with another TMS tool focusing on computational efficiency across various hardware platforms. Lastly, we conducted an expert user study to measure usability and influence in optimizing TMS treatment planning. The system is openly available for community use and further development on GitHub: \url{https://github.com/lorifranke/SlicerTMS}.

eess.SP↗

arXiv2024

Neural Orientation Distribution Fields for Estimation and Uncertainty Quantification in Diffusion MRI

Inferring brain connectivity and structure \textit{in-vivo} requires accurate estimation of the orientation distribution function (ODF), which encodes key local tissue properties. However, estimating the ODF from diffusion MRI (dMRI) signals is a challenging inverse problem due to obstacles such as significant noise, high-dimensional parameter spaces, and sparse angular measurements. In this paper, we address these challenges by proposing a novel deep-learning based methodology for continuous estimation and uncertainty quantification of the spatially varying ODF field. We use a neural field (NF) to parameterize a random series representation of the latent ODFs, implicitly modeling the often ignored but valuable spatial correlation structures in the data, and thereby improving efficiency in sparse and noisy regimes. An analytic approximation to the posterior predictive distribution is derived which can be used to quantify the uncertainty in the ODF estimate at any spatial location, avoiding the need for expensive resampling-based approaches that are typically employed for this purpose. We present empirical evaluations on both synthetic and real in-vivo diffusion data, demonstrating the advantages of our method over existing approaches.

eess.IV↗

arXiv2022

Minimum-entropy causal inference and its application in brain network analysis

Identification of the causal relationship between multivariate time series is a ubiquitous problem in data science. Granger causality measure (GCM) and conditional Granger causality measure (cGCM) are widely used statistical methods for causal inference and effective connectivity analysis in neuroimaging research. Both GCM and cGCM have frequency-domain formulations that are developed based on a heuristic algorithm for matrix decompositions. The goal of this work is to generalize GCM and cGCM measures and their frequency-domain formulations by using a theoretic framework for minimum entropy (ME) estimation. The proposed ME-estimation method extends the classical theory of minimum mean squared error (MMSE) estimation for stochastic processes. It provides three formulations of cGCM that include Geweke's original time-domain cGCM as a special case. But all three frequency-domain formulations of cGCM are different from previous methods. Experimental results based on simulations have shown that one of the proposed frequency-domain cGCM has enhanced sensitivity and specificity in detecting network connections compared to other methods. In an example based on in vivo functional magnetic resonance imaging, the proposed frequency-domain measure cGCM can significantly enhance the consistency between the structural and effective connectivity of human brain networks.

stat.ME↗

arXiv2020

High-fidelity, accelerated whole-brain submillimeter in-vivo diffusion MRI using gSlider-Spherical Ridgelets (gSlider-SR)

Purpose: To develop an accelerated, robust, and accurate diffusion MRI acquisition and reconstruction technique for submillimeter whole human brain in-vivo scan on a clinical scanner. Methods: We extend the ultra-high resolution diffusion MRI acquisition technique, gSlider, by allowing under-sampling in q-space and Radio-Frequency (RF)-encoded data, thereby accelerating the total acquisition time of conventional gSlider. The novel method, termed gSlider-SR, compensates for the lack of acquired information by exploiting redundancy in the dMRI data using a basis of Spherical Ridgelets (SR), while simultaneously enhancing the signal-to-noise ratio. Using Monte-Carlo simulation with realistic noise levels and several acquisitions of in-vivo human brain dMRI data (acquired on a Siemens Prisma 3T scanner), we demonstrate the efficacy of our method using several quantitative metrics. Results: For high-resolution dMRI data with realistic noise levels (synthetically added), we show that gSlider-SR can reconstruct high-quality dMRI data at different acceleration factors preserving both signal and angular information. With in-vivo data, we demonstrate that gSlider-SR can accurately reconstruct 860 $μm$ diffusion MRI data (64 diffusion directions at b = 2000 $s/ {mm}^2$), at comparable quality as that obtained with conventional gSlider with four averages, thereby providing an eight-fold reduction in scan time (from 1 h 20 min to 10 min). Conclusion: gSlider-SR enables whole-brain high angular resolution dMRI at a submillimeter spatial resolution with a dramatically reduced acquisition time, making it feasible to use the proposed scheme on existing clinical scanners.

eess.IV↗

arXiv2018

Regularization of covariance matrices on Riemannian manifolds using linear systems

We propose an approach to use the state covariance of linear systems to track time-varying covariance matrices of non-stationary time series. Following concepts from Riemmanian geometry, we investigate three types of covariance paths obtained by using different quadratic regularizations of system matrices. The first quadratic form induces the geodesics based on the Bures-Wasserstein metric from optimal mass transport theory and quantum mechanics. The second type of quadratic form leads to the geodesics based on the Fisher-Rao metric from information geometry. In the process, we introduce a fluid-mechanics interpretation of the Fisher-Rao metric for multivariate Gaussian distributions. A main contribution of this work is the introduction of the third type of covariance paths which are steered by linear system matrices with rotating eigenspace. We provide theoretical results on the existence and uniqueness of this type of covariance paths. The three types of covariance paths are compared using two examples with synthetic data and real data based on functional magnetic resonance imaging, respectively.

math.MG↗

arXiv2018

Regularization of time-varying covariance matrices using linear stochastic systems

This work focuses on modeling of time-varying covariance matrices using the state covariance of linear stochastic systems. Following concepts from optimal mass transport and the Schrödinger bridge problem (SBP), we investigate several covariance paths induced by different regularizations on the system matrices. Specifically, one of the proposed covariance path generalizes the geodesics based on the Fisher-Rao metric to the situation with stochastic input. Another type of covariance path is generated by linear system matrices with rotating eigenspace in the noiseless situation. The main contributions of this paper include the differential equations for these covariance paths and the closed-form expressions for scalar-valued covariance. We also compare these covariance paths using several examples.

math.OC↗

arXiv2017

Matricial Wasserstein-1 Distance

In this note, we propose an extension of the Wasserstein 1-metric ($W_1$) for matrix probability densities, matrix-valued density measures, and an unbalanced interpretation of mass transport. The key is using duality theory, in particular, a "dual of the dual" formulation of $W_1$. This matrix analogue of the Earth Mover's Distance has several attractive features including ease of computation.

math.FA↗

arXiv2016

Regularization and Interpolation of Positive Matrices

We consider certain matricial analogues of optimal mass transport of positive definite matrices of equal trace. The framework is motivated by the need to devise a suitable geometry for interpolating positive definite matrices in ways that allow controlling the apparent tradeoff between "aligning up their eigenstructure" and "scaling the corresponding eigenvalues". Indeed, motivation for this work is provided by power spectral analysis of multivariate time series where, linear interpolation between matrix-valued power spectra generates push-pop artifacts. Push-pop of power distribuion is objectionable as it corresponds to unrealistic response of scatterers.

math.OC↗

arXiv2014

Metrics for matrix-valued measures via test functions

It is perhaps not widely recognized that certain common notions of distance between probability measures have an alternative dual interpretation which compares corresponding functionals against suitable families of test functions. This dual viewpoint extends in a straightforward manner to suggest metrics between matrix-valued measures. Our main interest has been in developing weakly-continuous metrics that are suitable for comparing matrix-valued power spectral density functions. To this end, and following the suggested recipe of utilizing suitable families of test functions, we develop a weakly-continuous metric that is analogous to the Wasserstein metric and applies to matrix-valued densities. We use a numerical example to compare this metric to certain standard alternatives including a different version of a matricial Wasserstein metric developed earlier.

eess.SY↗

arXiv2013

Convex Clustering via Optimal Mass Transport

We consider approximating distributions within the framework of optimal mass transport and specialize to the problem of clustering data sets. Distances between distributions are measured in the Wasserstein metric. The main problem we consider is that of approximating sample distributions by ones with sparse support. This provides a new viewpoint to clustering. We propose different relaxations of a cardinality function which penalizes the size of the support set. We establish that a certain relaxation provides the tightest convex lower approximation to the cardinality penalty. We compare the performance of alternative relaxations on a numerical study on clustering.

eess.SY↗

arXiv2013

Linear models based on noisy data and the Frisch scheme

We address the problem of identifying linear relations among variables based on noisy measurements. This is, of course, a central question in problems involving "Big Data." Often a key assumption is that measurement errors in each variable are independent. This precise formulation has its roots in the work of Charles Spearman in 1904 and of Ragnar Frisch in the 1930's. Various topics such as errors-in-variables, factor analysis, and instrumental variables, all refer to alternative formulations of the problem of how to account for the anticipated way that noise enters in the data. In the present paper we begin by describing the basic theory and provide alternative modern proofs to some key results. We then go on to consider certain generalizations of the theory as well applying certain novel numerical techniques to the problem. A central role is played by the Frisch-Kalman dictum which aims at a noise contribution that allows a maximal set of simultaneous linear relations among the noise-free variables --a rank minimization problem. In the years since Frisch's original formulation, there have been several insights including trace minimization as a convenient heuristic to replace rank minimization. We discuss convex relaxations and certificates guaranteeing global optimality. A complementary point of view to the Frisch-Kalman dictum is introduced in which models lead to a min-max quadratic estimation error for the error-free variables. Points of contact between the two formalisms are discussed and various alternative regularization schemes are indicated.

eess.SY↗