arXiv subjects

Jiahao Huang

Publications and source records attributed to Jiahao Huang.

At least 73 records · Page 4Linked to original sources

arXiv2024

Diff3Dformer: Leveraging Slice Sequence Diffusion for Enhanced 3D CT Classification with Transformer Networks

The manifestation of symptoms associated with lung diseases can vary in different depths for individual patients, highlighting the significance of 3D information in CT scans for medical image classification. While Vision Transformer has shown superior performance over convolutional neural networks in image classification tasks, their effectiveness is often demonstrated on sufficiently large 2D datasets and they easily encounter overfitting issues on small medical image datasets. To address this limitation, we propose a Diffusion-based 3D Vision Transformer (Diff3Dformer), which utilizes the latent space of the Diffusion model to form the slice sequence for 3D analysis and incorporates clustering attention into ViT to aggregate repetitive information within 3D CT scans, thereby harnessing the power of the advanced transformer in 3D classification tasks on small datasets. Our method exhibits improved performance on two different scales of small datasets of 3D lung CT scans, surpassing the state of the art 3D methods and other transformer-based approaches that emerged during the COVID-19 pandemic, demonstrating its robust and superior performance across different scales of data. Experimental results underscore the superiority of our proposed method, indicating its potential for enhancing medical image classification tasks in real-world scenarios.

eess.IV↗

arXiv2024

MambaMIR: An Arbitrary-Masked Mamba for Joint Medical Image Reconstruction and Uncertainty Estimation

The recent Mamba model has shown remarkable adaptability for visual representation learning, including in medical imaging tasks. This study introduces MambaMIR, a Mamba-based model for medical image reconstruction, as well as its Generative Adversarial Network-based variant, MambaMIR-GAN. Our proposed MambaMIR inherits several advantages, such as linear complexity, global receptive fields, and dynamic weights, from the original Mamba model. The innovated arbitrary-mask mechanism effectively adapt Mamba to our image reconstruction task, providing randomness for subsequent Monte Carlo-based uncertainty estimation. Experiments conducted on various medical image reconstruction tasks, including fast MRI and SVCT, which cover anatomical regions such as the knee, chest, and abdomen, have demonstrated that MambaMIR and MambaMIR-GAN achieve comparable or superior reconstruction results relative to state-of-the-art methods. Additionally, the estimated uncertainty maps offer further insights into the reliability of the reconstruction quality. The code is publicly available at https://github.com/ayanglab/MambaMIR.

eess.IV↗

arXiv2024

Enhancing Global Sensitivity and Uncertainty Quantification in Medical Image Reconstruction with Monte Carlo Arbitrary-Masked Mamba

Deep learning has been extensively applied in medical image reconstruction, where Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) represent the predominant paradigms, each possessing distinct advantages and inherent limitations: CNNs exhibit linear complexity with local sensitivity, whereas ViTs demonstrate quadratic complexity with global sensitivity. The emerging Mamba has shown superiority in learning visual representation, which combines the advantages of linear scalability and global sensitivity. In this study, we introduce MambaMIR, an Arbitrary-Masked Mamba-based model with wavelet decomposition for joint medical image reconstruction and uncertainty estimation. A novel Arbitrary Scan Masking (ASM) mechanism "masks out" redundant information to introduce randomness for further uncertainty estimation. Compared to the commonly used Monte Carlo (MC) dropout, our proposed MC-ASM provides an uncertainty map without the need for hyperparameter tuning and mitigates the performance drop typically observed when applying dropout to low-level tasks. For further texture preservation and better perceptual quality, we employ the wavelet transformation into MambaMIR and explore its variant based on the Generative Adversarial Network, namely MambaMIR-GAN. Comprehensive experiments have been conducted for multiple representative medical image reconstruction tasks, demonstrating that the proposed MambaMIR and MambaMIR-GAN outperform other baseline and state-of-the-art methods in different reconstruction tasks, where MambaMIR achieves the best reconstruction fidelity and MambaMIR-GAN has the best perceptual quality. In addition, our MC-ASM provides uncertainty maps as an additional tool for clinicians, while mitigating the typical performance drop caused by the commonly used dropout.

eess.IV↗

arXiv2024

MoreHopQA: More Than Multi-hop Reasoning

Most existing multi-hop datasets are extractive answer datasets, where the answers to the questions can be extracted directly from the provided context. This often leads models to use heuristics or shortcuts instead of performing true multi-hop reasoning. In this paper, we propose a new multi-hop dataset, MoreHopQA, which shifts from extractive to generative answers. Our dataset is created by utilizing three existing multi-hop datasets: HotpotQA, 2WikiMultihopQA, and MuSiQue. Instead of relying solely on factual reasoning, we enhance the existing multi-hop questions by adding another layer of questioning that involves one, two, or all three of the following types of reasoning: commonsense, arithmetic, and symbolic. Our dataset is created through a semi-automated process, resulting in a dataset with 1,118 samples that have undergone human verification. We then use our dataset to evaluate five different large language models: Mistral 7B, Gemma 7B, Llama 3 (8B and 70B), and GPT-4. We also design various cases to analyze the reasoning steps in the question-answering process. Our results show that models perform well on initial multi-hop questions but struggle with our extended questions, indicating that our dataset is more challenging than previous ones. Our analysis of question decomposition reveals that although models can correctly answer questions, only a portion - 38.7% for GPT-4 and 33.4% for Llama3-70B - achieve perfect reasoning, where all corresponding sub-questions are answered correctly. Evaluation code and data are available at https://github.com/Alab-NII/morehopqa

cs.CL↗

arXiv2024

Low-rank based motion correction followed by automatic frame selection in DT-CMR

Motivation: Post-processing of in-vivo diffusion tensor CMR (DT-CMR) is challenging due to the low SNR and variation in contrast between frames which makes image registration difficult, and the need to manually reject frames corrupted by motion. Goals: To develop a semi-automatic post-processing pipeline for robust DT-CMR registration and automatic frame selection. Approach: We used low intrinsic rank averaged frames as the reference to register other low-ranked frames. A myocardium-guided frame selection rejected the frames with signal loss, through-plane motion and poor registration. Results: The proposed method outperformed our previous noise-robust rigid registration on helix angle data quality and reduced negative eigenvalues in healthy volunteers.

eess.IV↗

arXiv2024

Entanglement-enhanced quantum metrology: from standard quantum limit to Heisenberg limit

Entanglement-enhanced quantum metrology explores the utilization of quantum entanglement to enhance measurement precision. When particles in a probe are prepared into a quantum entangled state, they collectively accumulate information about the physical quantity to be measured, leading to an improvement in measurement precision beyond the standard quantum limit and approaching the Heisenberg limit. The rapid advancement of techniques for quantum manipulation and detection has enabled the generation, manipulation, and detection of multi-particle entangled states in synthetic quantum systems such as cold atoms and trapped ions. This article aims to review and illustrate the fundamental principles and experimental progresses that demonstrate multi-particle entanglement for quantum metrology, as well as discuss the potential applications of entanglement-enhanced quantum sensors.

quant-ph↗

arXiv2024

Efficient Post-processing of Diffusion Tensor Cardiac Magnetic Imaging Using Texture-conserving Deformable Registration

Diffusion tensor cardiac magnetic resonance (DT-CMR) is a method capable of providing non-invasive measurements of myocardial microstructure. Image registration is essential to correct image shifts due to intra and inter breath-hold motion and imperfect cardiac triggering. Registration is challenging in DT-CMR due to the low signal-to-noise and various contrasts induced by the diffusion encoding in the myocardium and surrounding organs. Traditional deformable registration corrects through-plane motion but at the risk of destroying the texture information while rigid registration inefficiently discards frames with local deformation. In this study, we explored the possibility of deep learning-based deformable registration on DT-CMR. Based on the noise suppression using low-rank features and diffusion encoding suppression using variational auto encoder-decoder, a B-spline based registration network extracted the displacement fields and maintained the texture features of DT-CMR. In this way, our method improved the efficiency of frame utilization, manual cropping, and computational speed.

eess.IV↗

arXiv2024

The Missing U for Efficient Diffusion Models

Diffusion Probabilistic Models stand as a critical tool in generative modelling, enabling the generation of complex data distributions. This family of generative models yields record-breaking performance in tasks such as image synthesis, video generation, and molecule design. Despite their capabilities, their efficiency, especially in the reverse process, remains a challenge due to slow convergence rates and high computational costs. In this paper, we introduce an approach that leverages continuous dynamical systems to design a novel denoising network for diffusion models that is more parameter-efficient, exhibits faster convergence, and demonstrates increased noise robustness. Experimenting with Denoising Diffusion Probabilistic Models (DDPMs), our framework operates with approximately a quarter of the parameters, and $\sim$ 30\% of the Floating Point Operations (FLOPs) compared to standard U-Nets in DDPMs. Furthermore, our model is notably faster in inference than the baseline when measured in fair and equal conditions. We also provide a mathematical intuition as to why our proposed reverse process is faster as well as a mathematical discussion of the empirical tradeoffs in the denoising downstream task. Finally, we argue that our method is compatible with existing performance enhancement techniques, enabling further improvements in efficiency, quality, and speed.

cs.LG↗

arXiv2024

Anatomy-guided fiber trajectory distribution estimation for cranial nerves tractography

Diffusion MRI tractography is an important tool for identifying and analyzing the intracranial course of cranial nerves (CNs). However, the complex environment of the skull base leads to ambiguous spatial correspondence between diffusion directions and fiber geometry, and existing diffusion tractography methods of CNs identification are prone to producing erroneous trajectories and missing true positive connections. To overcome the above challenge, we propose a novel CNs identification framework with anatomy-guided fiber trajectory distribution, which incorporates anatomical shape prior knowledge during the process of CNs tracing to build diffusion tensor vector fields. We introduce higher-order streamline differential equations for continuous flow field representations to directly characterize the fiber trajectory distribution of CNs from the tract-based level. The experimental results on the vivo HCP dataset and the clinical MDM dataset demonstrate that the proposed method reduces false-positive fiber production compared to competing methods and produces reconstructed CNs (i.e. CN II, CN III, CN V, and CN VII/VIII) that are judged to better correspond to the known anatomy.

eess.IV↗

arXiv2023

Swin Deformable Attention Hybrid U-Net for Medical Image Segmentation

Medical image segmentation is a crucial task in the field of medical image analysis. Harmonizing the convolution and multi-head self-attention mechanism is a recent research focus in this field, with various combination methods proposed. However, the lack of interpretability of these hybrid models remains a common pitfall, limiting their practical application in clinical scenarios. To address this issue, we propose to incorporate the Shifted Window (Swin) Deformable Attention into a hybrid architecture to improve segmentation performance while ensuring explainability. Our proposed Swin Deformable Attention Hybrid UNet (SDAH-UNet) demonstrates state-of-the-art performance on both anatomical and lesion segmentation tasks. Moreover, we provide a direct and visual explanation of the model focalization and how the model forms it, enabling clinicians to better understand and trust the decision of the model. Our approach could be a promising solution to the challenge of developing accurate and interpretable medical image segmentation models.

eess.IV↗

arXiv2023

Style Transfer and Self-Supervised Learning Powered Myocardium Infarction Super-Resolution Segmentation

This study proposes a pipeline that incorporates a novel style transfer model and a simultaneous super-resolution and segmentation model. The proposed pipeline aims to enhance diffusion tensor imaging (DTI) images by translating them into the late gadolinium enhancement (LGE) domain, which offers a larger amount of data with high-resolution and distinct highlighting of myocardium infarction (MI) areas. Subsequently, the segmentation task is performed on the LGE style image. An end-to-end super-resolution segmentation model is introduced to generate high-resolution mask from low-resolution LGE style DTI image. Further, to enhance the performance of the model, a multi-task self-supervised learning strategy is employed to pre-train the super-resolution segmentation model, allowing it to acquire more representative knowledge and improve its segmentation performance after fine-tuning. https: github.com/wlc2424762917/Med_Img

eess.IV↗

arXiv2023

Quantum Double Lock-in Amplifier

Quantum lock-in amplifier aims to extract an alternating signal within strong noise background by using quantum strategy. However, as the target signal usually has an unknown initial phase, we can't obtain the complete information of its amplitude, frequency and phase in a single lock-in measurement. Here, to overcome this challenge, we give a general protocol for achieving a quantum double lock-in amplifier and illustrate its realization. In analog to a classical double lock-in amplifier, our protocol is accomplished via two quantum mixers under orthogonal pulse sequences. The two orthogonal pulse sequences act the roles of two orthogonal reference signals in a classical double lock-in amplifier. Combining the output signals, the complete characteristics of the target signal can be obtained. As an example, we illustrate the realization of our quantum double lock-in amplifier via a five-level double-$Λ$ coherent population trapping system with $^{87}$Rb atoms, in which each $Λ$ structure acts as a quantum mixer and the two applied dynamical decoupling sequences take the roles of two orthogonal reference signals. Our numerical calculations show that the quantum double lock-in amplifier is robust against experimental imperfections, such as finite pulse length and stochastic noise. Our study opens an avenue for extracting complete characteristics of an alternating signal within strong noise background, which is beneficial for developing practical quantum sensing technologies.

quant-ph↗

arXiv2023

Quantum Vector DC Magnetometry via Selective Phase Accumulation

Precision measurement of magnetic fields is an important goal for fundamental science and practical sensing technology. Sensitive detection of a vector magnetic field is a crucial issue in quantum magnetometry, it remains a challenge to estimate a vector DC magnetic field with high efficiency and high precision. Here, we propose a general protocol for quantum vector DC magnetometry via selective phase accumulation of both non-entangled and entangled quantum probes. Based upon the Ramsey interferometry, our protocol may achieve selective phase accumulation of only one magnetic field component by inserting well-designed pulse sequence. In the parallel scheme, three parallel quantum interferometries are utilized to estimate three magnetic field components independently.In the sequential scheme, by applying a pulse sequence along different directions, three magnetic field components can be estimated simultaneously via only one quantum interferometry. In particular, if the input state is an entangled state such as the Greenberger-Horne-Zeilinger state, the measurement precisions of all three components may approach the Heisenberg limit. Our study not only develops a general protocol for measuring vector magnetic fields via quantum probes, but also provides a feasible way to achieve Heisenberg-limited multi-parameter estimation via many-body quantum entanglement.

quant-ph↗

arXiv2023

Is attention all you need in medical image analysis? A review

Medical imaging is a key component in clinical diagnosis, treatment planning and clinical trial design, accounting for almost 90% of all healthcare data. CNNs achieved performance gains in medical image analysis (MIA) over the last years. CNNs can efficiently model local pixel interactions and be trained on small-scale MI data. The main disadvantage of typical CNN models is that they ignore global pixel relationships within images, which limits their generalisation ability to understand out-of-distribution data with different 'global' information. The recent progress of Artificial Intelligence gave rise to Transformers, which can learn global relationships from data. However, full Transformer models need to be trained on large-scale data and involve tremendous computational complexity. Attention and Transformer compartments (Transf/Attention) which can well maintain properties for modelling global relationships, have been proposed as lighter alternatives of full Transformers. Recently, there is an increasing trend to co-pollinate complementary local-global properties from CNN and Transf/Attention architectures, which led to a new era of hybrid models. The past years have witnessed substantial growth in hybrid CNN-Transf/Attention models across diverse MIA problems. In this systematic review, we survey existing hybrid CNN-Transf/Attention models, review and unravel key architectural designs, analyse breakthroughs, and evaluate current and future opportunities as well as challenges. We also introduced a comprehensive analysis framework on generalisation opportunities of scientific and clinical impact, based on which new data-driven domain generalisation and adaptation methods can be stimulated.

cs.CV↗

arXiv2023

CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?

Deep learning has shown the capability to substantially accelerate MRI reconstruction while acquiring fewer measurements. Recently, diffusion models have gained burgeoning interests as a novel group of deep learning-based generative methods. These methods seek to sample data points that belong to a target distribution from a Gaussian distribution, which has been successfully extended to MRI reconstruction. In this work, we proposed a Cold Diffusion-based MRI reconstruction method called CDiffMR. Different from conventional diffusion models, the degradation operation of our CDiffMR is based on \textit{k}-space undersampling instead of adding Gaussian noise, and the restoration network is trained to harness a de-aliaseing function. We also design starting point and data consistency conditioning strategies to guide and accelerate the reverse process. More intriguingly, the pre-trained CDiffMR model can be reused for reconstruction tasks with different undersampling rates. We demonstrated, through extensive numerical and visual experiments, that the proposed CDiffMR can achieve comparable or even superior reconstruction results than state-of-the-art models. Compared to the diffusion model-based counterpart, CDiffMR reaches readily competing results using only $1.6 \sim 3.4\%$ for inference time. The code is publicly available at https://github.com/ayanglab/CDiffMR.

eess.IV↗

arXiv2023

Deep Learning-based Diffusion Tensor Cardiac Magnetic Resonance Reconstruction: A Comparison Study

In vivo cardiac diffusion tensor imaging (cDTI) is a promising Magnetic Resonance Imaging (MRI) technique for evaluating the micro-structure of myocardial tissue in the living heart, providing insights into cardiac function and enabling the development of innovative therapeutic strategies. However, the integration of cDTI into routine clinical practice is challenging due to the technical obstacles involved in the acquisition, such as low signal-to-noise ratio and long scanning times. In this paper, we investigate and implement three different types of deep learning-based MRI reconstruction models for cDTI reconstruction. We evaluate the performance of these models based on reconstruction quality assessment and diffusion tensor parameter assessment. Our results indicate that the models we discussed in this study can be applied for clinical use at an acceleration factor (AF) of $\times 2$ and $\times 4$, with the D5C5 model showing superior fidelity for reconstruction and the SwinMR model providing higher perceptual scores. There is no statistical difference with the reference for all diffusion tensor parameters at AF $\times 2$ or most DT parameters at AF $\times 4$, and the quality of most diffusion tensor parameter maps are visually acceptable. SwinMR is recommended as the optimal approach for reconstruction at AF $\times 2$ and AF $\times 4$. However, we believed the models discussed in this studies are not prepared for clinical use at a higher AF. At AF $\times 8$, the performance of all models discussed remains limited, with only half of the diffusion tensor parameters being recovered to a level with no statistical difference from the reference. Some diffusion tensor parameter maps even provide wrong and misleading information.

physics.med-ph↗

arXiv2023

Ramsey interferometry with arbitrary coherent-population-trapping pulse sequence

Coherent population trapping (CPT) is a multi-level quantum coherence phenomenon of promising applications in atomic clocks and magnetometers. Particularly, multi-pulse CPT-Ramsey interferometry is a powerful tool for improving the performance of CPT atomic clocks. Most studies on multi-pulse CPT-Ramsey interferometry consider periodic pulse sequence and time-independent detuning. However, to further improve the accuracy and precision, one may modify the spectrum symmetry which involves pulse sequence with time-dependent detuning or phase shift. Here, we theoretically analyze the multi-pulse CPT-Ramsey interferometry under arbitrary pulse sequences of time-dependent detuning and obtain a general analytical formula. Using our formula, we analyze the popular CPT-Ramsey interferometry schemes such as two-pulse symmetric and antisymmetric spectroscopy, and multi-pulse symmetric and antisymmetric spectroscopy. Moreover, we quantitatively obtain the influences of pulse width, pulse period, pulse number, and Rabi frequency under periodic pulses. Our theoretical results can guide the experimental design to improve the performance of atomic clocks via multi-pulse CPT-Ramsey interferometry.

physics.atom-ph↗

arXiv2023

ViGU: Vision GNN U-Net for Fast MRI

Deep learning models have been widely applied for fast MRI. The majority of existing deep learning models, e.g., convolutional neural networks, work on data with Euclidean or regular grids structures. However, high-dimensional features extracted from MR data could be encapsulated in non-Euclidean manifolds. This disparity between the go-to assumption of existing models and data requirements limits the flexibility to capture irregular anatomical features in MR data. In this work, we introduce a novel Vision GNN type network for fast MRI called Vision GNN U-Net (ViGU). More precisely, the pixel array is first embedded into patches and then converted into a graph. Secondly, a U-shape network is developed using several graph blocks in symmetrical encoder and decoder paths. Moreover, we show that the proposed ViGU can also benefit from Generative Adversarial Networks yielding to its variant ViGU-GAN. We demonstrate, through numerical and visual experiments, that the proposed ViGU and GAN variant outperform existing CNN and GAN-based methods. Moreover, we show that the proposed network readily competes with approaches based on Transformers while requiring a fraction of the computational cost. More importantly, the graph structure of the network reveals how the network extracts features from MR images, providing intuitive explainability.

eess.IV↗