Medical Image Reconstruction Research Articles

Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration.

The deep unfolding approach has attracted significant attention in computer vision tasks, which well connects conventional image processing modeling manners with more recent deep learning techniques. Specifically, by establishing a direct correspondence between algorithm operators at each implementation step and network modules within each layer, one can rationally construct an almost "white box" network architecture with high interpretability. In this architecture, only the predefined component of the proximal operator, known as a proximal network, needs manual configuration, enabling the network to automatically extract intrinsic image priors in a data-driven manner. In current deep unfolding methods, such a proximal network is generally designed as a CNN architecture, whose necessity has been proven by a recent theory. That is, CNN structure substantially delivers the translational symmetry image prior, which is the most universally possessed structural prior across various types of images. However, standard CNN-based proximal networks have essential limitations in capturing the rotation symmetry prior, another universal structural prior underlying general images. This leaves a large room for further performance improvement in deep unfolding approaches. To address this issue, this study makes efforts to suggest a high-accuracy rotation equivariant proximal network that effectively embeds rotation symmetry priors into the deep unfolding framework. Especially, we deduce, for the first time, the theoretical equivariant error for such a designed proximal network with arbitrary layers under arbitrary rotation degrees. This analysis should be the most refined theoretical conclusion for such error evaluation to date and is also indispensable for supporting the rationale behind such networks with intrinsic interpretability requirements. Through experimental validation on different vision tasks, including blind image super-resolution, medical image reconstruction, and image de-raining, the proposed method is validated to be capable of directly replacing the proximal network in current deep unfolding architecture and readily enhancing their state-of-the-art performance. This indicates its potential usability in general vision tasks.

Data encryption/decryption and medical image reconstruction based on a sustainable biomemristor designed logic gate circuit

Memristors are considered one of the most promising new-generation memory technologies due to their high integration density, fast read/write speeds, and ultra-low power consumption. Natural biomaterials have attracted interest in integrated circuits and electronics because of their environmental friendliness, sustainability, low cost, and excellent biocompatibility. In this study, a sustainable biomemristor with Ag/mugwort:PVDF/ITO structure was prepared using spin-coating and magnetron sputtering methods, which exhibited excellent durability, significant resistance switching (RS) behavior and unidirectional conduction properties when three metals were used as top electrode. By studying the conductivity mechanism of the device, a charge conduction model was established by the combination of F-N tunneling, redox, and complexation reaction. Finally, the novel logic gate circuits were constructed using the as-prepared memristor, and further memristor based encryption circuit using 3-8 decoder was innovatively designed, which can realize uniform rule encryption and decryption of medical information for data and medical images. Therefore, this work realizes the integration of memristor with traditional electronic technology and expands the applications of sustainable biomemristors in digital circuits, data encryption, and medical image security.

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.

Recent advances and applications of artificial intelligence in 3D bioprinting.

3D bioprinting techniques enable the precise deposition of living cells, biomaterials, and biomolecules, emerging as a promising approach for engineering functional tissues and organs. Meanwhile, recent advances in 3D bioprinting enable researchers to build in vitro models with finely controlled and complex micro-architecture for drug screening and disease modeling. Recently, artificial intelligence (AI) has been applied to different stages of 3D bioprinting, including medical image reconstruction, bioink selection, and printing process, with both classical AI and machine learning approaches. The ability of AI to handle complex datasets, make complex computations, learn from past experiences, and optimize processes dynamically makes it an invaluable tool in advancing 3D bioprinting. The review highlights the current integration of AI in 3D bioprinting and discusses future approaches to harness the synergistic capabilities of 3D bioprinting and AI for developing personalized tissues and organs.

Applications of Artificial Intelligence for Pediatric Cancer Imaging.

Artificial intelligence (AI) is transforming the medical imaging of adult patients. However, its utilization in pediatric oncology imaging remains constrained, in part due to the inherent scarcity of data associated with childhood cancers. Pediatric cancers are rare, and imaging technologies are evolving rapidly, leading to insufficient data of a particular type to effectively train these algorithms. The small market size of pediatric patients compared with adult patients could also contribute to this challenge, as market size is a driver of commercialization. This review provides an overview of the current state of AI applications for pediatric cancer imaging, including applications for medical image acquisition, processing, reconstruction, segmentation, diagnosis, staging, and treatment response monitoring. Although current developments are promising, impediments due to the diverse anatomies of growing children and nonstandardized imaging protocols have led to limited clinical translation thus far. Opportunities include leveraging reconstruction algorithms to achieve accelerated low-dose imaging and automating the generation of metric-based staging and treatment monitoring scores. Transfer learning of adult-based AI models to pediatric cancers, multiinstitutional data sharing, and ethical data privacy practices for pediatric patients with rare cancers will be keys to unlocking the full potential of AI for clinical translation and improving outcomes for these young patients.

Reconstruction of Knowledge and Medical Images in the Convergence of Chinese and Western Medicine ——Taking “Sweet Meat” as an Example

Abstract: The pancreas is neither part of the five Zang organs (五脏) nor the six Fu organs (六腑). Thus, it has received little attention in Chinese medical literature. In the late 19th century, medical missionaries in China started translating and introducing anatomical and physiological knowledge about the pancreas. As for the word pancreas, an early and influential translation was “sweet meat” (甜肉), proposed by Benjamin Hobson (合信). The translation “sweet meat” is not faithful to the original meaning of “pancreas”, but is a term coined by Hobson based on his personal habits, and the word “sweet” appeared by chance. However, in the decades since the term “sweet meat” became popular, Chinese medicine practitioners, such as Tang Zonghai (唐宗海), reinterpreted it by drawing new medical illustrations for “sweet meat” and giving new connotations to the word “sweet”. This discussion and interpretation of “sweet meat” in modern China, particularly among Chinese medicine professionals, is not only a dissemination and interpretation of the knowledge of “pancreas”, but also a construction of knowledge around the term “sweet meat”.

Integrating PointNet-Based Model and Machine Learning Algorithms for Classification of Rupture Status of IAs.

The rupture of intracranial aneurysms (IAs) would result in subarachnoid hemorrhage with high mortality and disability. Predicting the risk of IAs rupture remains a challenge. This paper proposed an effective method for classifying IAs rupture status by integrating a PointNet-based model and machine learning algorithms. First, medical image segmentation and reconstruction algorithms were applied to 3D Digital Subtraction Angiography (DSA) imaging data to construct three-dimensional IAs geometric models. Geometrical parameters of IAs were then acquired using Geomagic, followed by the computation of hemodynamic clouds and hemodynamic parameters using Computational Fluid Dynamics (CFD). A PointNet-based model was developed to extract different dimensional hemodynamic cloud features. Finally, five types of machine learning algorithms were applied on geometrical parameters, hemodynamic parameters, and hemodynamic cloud features to classify and recognize IAs rupture status. The classification performance of different dimensional hemodynamic cloud features was also compared. The 16-, 32-, 64-, and 1024-dimensional hemodynamic cloud features were extracted with the PointNet-based model, respectively, and the four types of cloud features in combination with the geometrical parameters and hemodynamic parameters were respectively applied to classify the rupture status of IAs. The best classification outcomes were achieved in the case of 16-dimensional hemodynamic cloud features, the accuracy of XGBoost, CatBoost, SVM, LightGBM, and LR algorithms was 0.887, 0.857, 0.854, 0.857, and 0.908, respectively, and the AUCs were 0.917, 0.934, 0.946, 0.920, and 0.944. In contrast, when only utilizing geometrical parameters and hemodynamic parameters, the accuracies were 0.836, 0.816, 0.826, 0.832, and 0.885, respectively, with AUC values of 0.908, 0.922, 0.930, 0.884, and 0.921. In this paper, classification models for IAs rupture status were constructed by integrating a PointNet-based model and machine learning algorithms. Experiments demonstrated that hemodynamic cloud features had a certain contribution weight to the classification of IAs rupture status. When 16-dimensional hemodynamic cloud features were added to the morphological and hemodynamic features, the models achieved the highest classification accuracies and AUCs. Our models and algorithms would provide valuable insights for the clinical diagnosis and treatment of IAs.

Plane-wave medical image reconstruction based on dynamic Criss-Cross attention and multi-scale convolution.

Plane-wave imaging is widely employed in medical imaging due to its ultra-fast imaging speed. However, the image quality is compromised. Existing techniques to enhance image quality tend to sacrifice the imaging frame rate. The study aims to reconstruct high-quality plane-wave images while maintaining the imaging frame rate. The proposed method utilizes a U-Net-based generator incorporating a multi-scale convolution module in the encoder to extract information at different levels. Additionally, a Dynamic Criss-Cross Attention (DCCA) mechanism is proposed in the decoder of the U-Net-based generator to extract both local and global features of plane-wave images while avoiding interference caused by irrelevant regions. In the reconstruction of point targets, the experimental images achieved a reduction in Full Width at Half Maximum (FWHM) of 0.0499 mm, compared to the Coherent Plane-Wave Compounding (CPWC) method using 75-beam plane waves. For the reconstruction of cyst targets, the simulated image achieved a 3.78% improvement in Contrast Ratio (CR) compared to CPWC. The proposed model effectively addresses the issue of unclear lesion sites in plane-wave images.

A review of deep learning and Generative Adversarial Networks applications in medical image analysis

Nowadays, computer-aided decision support systems (CADs) for the analysis of images have been a perennial technique in the medical imaging field. In CADs, deep learning algorithms are widely used to perform tasks like classification, identification of patterns, detection, etc. Deep learning models learn feature representations from images rather than handcrafted features. Hence, deep learning models are quickly becoming the state-of-the-art method to achieve good performances in different computer-aided decision-support systems in medical applications. Similarly, deep learning-based generative models called Generative Adversarial Networks (GANs) have recently been developed as a novel method to produce realistic-looking synthetic data. GANs are used in different domains, including medical imaging generation. The common problems, like class imbalance and a small dataset, in healthcare are well addressed by GANs, and it is a leading area of research. Segmentation, reconstruction, detection, denoising, registration, etc. are the important applications of GANs. So in this work, the successes of deep learning methods in segmentation, classification, cell structure and fracture detection, computer-aided identification, and GANs in synthetic medical image generation, segmentation, reconstruction, detection, denoising, and registration in recent times are reviewed. Lately, the review article concludes by raising research directions for DL models and GANs in medical applications.

Modified tuna swarm optimization algorithm for brain stroke imaging with electrical impedance tomography

Stroke is a common disease characterized by high disability rate and high mortality rate. Accurate detection and continuous monitoring are vital for the treatment of stroke. As a promising medical imaging technique, electrical impedance tomography (EIT) is able to provide an alternative for brain imaging. With this technique, conductivity distribution variation caused by pathological change can be visualized. However, image reconstruction is a severely ill-posed inverse problem. Particularly in brain imaging, irregular and multi-layered head structure along with low-conductivity skull further aggravate the challenge for accurate reconstruction. To solve this problem, a novel image-reconstruction method based on modified tuna swarm optimization is proposed for visualizing the conductivity distribution in brain EIT. To evaluate the performance of the proposed method, extensive simulations are carried out on a three-layer head model. The anti-noise performance of the proposed method is estimated by considering noise with different signal-to-noise ratios. In addition to simulation, phantom experiments are conducted to further verify the effectiveness of the proposed method. Both reconstructed images and quantitative evaluations demonstrate that the proposed approach performs well in the reconstruction of simulated intracerebral hemorrhage and secondary ischemia. This work would offer an alternative for accurate reconstruction in medical imaging based on EIT.

Embedding-Alignment Fusion-Based Graph Convolution Network With Mixed Learning Strategy for 4D Medical Image Reconstruction.

In recent years, 4D medical image involving structural and motion information of tissue has attracted increasing attention. The key to the 4D image reconstruction is to stack the 2D slices based on matching the aligned motion states. In this study, the distribution of the 2D slices with the different motion states is modeled as a manifold graph, and the reconstruction is turned to be the graph alignment. An embedding-alignment fusion-based graph convolution network (GCN) with a mixed-learning strategy is proposed to align the graphs. Herein, the embedding and alignment processes of graphs interact with each other to realize a precise alignment with retaining the manifold distribution. The mixed strategy of self- and semi-supervised learning makes the alignment sparse to avoid the mismatching caused by outliers in the graph. In the experiment, the proposed 4D reconstruction approach is validated on the different modalities including Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Ultrasound (US). We evaluate the reconstruction accuracy and compare it with those of state-of-the-art methods. The experiment results demonstrate that our approach can reconstruct a more accurate 4D image.

Deep Learning-Based Medical Image Reconstruction: Overview, Analysis, and Challenges

Deep Learning-Based Medical Image Reconstruction: Overview, Analysis, and Challenges

Research and Application of Deep Learning in Medical Image Reconstruction and Enhancement

In recent years, deep learning technology has made remarkable progress in medical image reconstruction and enhancement, and has become one of the research hotspots in the field of medical image processing. This paper discusses the latest research progress and application of deep learning in medical image reconstruction and enhancement. Firstly, the importance of medical image reconstruction and enhancement and the limitations of traditional methods are introduced. Then, a detailed discussion was conducted on the application of deep learning models, including Convolutional Neural Networks (CNN), Generative Adversarial Networks (GAN), and Autoencoders, in medical image processing. Specifically, an analysis and comparison were conducted on the image reconstruction ability of CNN models, the image enhancement effect of GAN models, and the image denoising and reconstruction of Autoencoder models. Then, the advantages and challenges of deep learning model in medical image processing are discussed, and the future development direction is discussed. Finally, the research results of this paper are summarized and the prospect of future research is put forward. The research in this paper provides some enlightenment and reference for researchers and practitioners in the field of medical image processing, which is helpful to promote the continuous innovation and progress of medical image processing technology.

Sparse Bayesian Deep Learning for Cross Domain Medical Image Reconstruction

Cross domain medical image reconstruction aims to address the issue that deep learning models trained solely on one source dataset might not generalize effectively to unseen target datasets from different hospitals. Some recent methods achieve satisfactory reconstruction performance, but often at the expense of extensive parameters and time consumption. To strike a balance between cross domain image reconstruction quality and model computational efficiency, we propose a lightweight sparse Bayesian deep learning method. Notably, we apply a fixed-form variational Bayes (FFVB) approach to quantify pixel-wise uncertainty priors derived from degradation distribution of the source domain. Furthermore, by integrating the uncertainty prior into the posterior sampled through stochastic gradient Langevin dynamics (SGLD), we develop a training strategy that dynamically generates and optimizes the prior distribution on the network weights for each unseen domain. This strategy enhances generalizability and ensures robust reconstruction performance. When evaluated on medical image reconstruction tasks, our proposed approach demonstrates impressive performance across various previously unseen domains.

Numerical Simulations of the Epley Maneuver With Clinical Implications.

Canalith repositioning procedures to treat benign paroxysmal positional vertigo are often applied following standardized criteria, without considering the possible anatomical singularities of the membranous labyrinth for each individual. As a result, certain patients may become refractory to the treatment due to significant deviations from the ideal membranous labyrinth, that was considered when the maneuvers were designed. This study aims to understand the dynamics of the endolymphatic fluid and otoconia, within the membranous labyrinth geometry, which may contribute to the ineffectiveness of the Epley maneuver. Simultaneously, the study seeks to explore methods to avoid or reduce treatment failure. We conducted a study on the Epley maneuver using numerical simulations based on a three-dimensional medical image reconstruction of the human left membranous labyrinth. A high-quality micro-computed tomography of a human temporal bone specimen was utilized for the image reconstruction, and a mathematical model for the endolymphatic fluid was developed and coupled with a spherical particle model representing otoconia inside the fluid. This allowed us to measure the position and time of each particle throughout all the steps of the maneuver, using equations that describe the physics behind benign paroxysmal positional vertigo. Numerical simulations of the standard Epley maneuver applied to this membranous labyrinth model yielded unsatisfactory results, as otoconia do not reach the frontside of the utricle, which in this study is used as the measure of success. The resting times between subsequent steps indicated that longer intervals are required for smaller otoconia. Using different angles of rotation can prevent otoconia from entering the superior semicircular canal or the posterior ampulla. Steps 3, 4, and 5 exhibited a heightened susceptibility to failure, as otoconia could be accidentally displaced into these regions. We demonstrate that modifying the Epley maneuver based on the numerical results obtained in the membranous labyrinth of the human specimen under study can have a significant effect on the success or failure of the treatment. The use of numerical simulations appears to be a useful tool for future canalith repositioning procedures that aim to personalize the treatment by modifying the rotation planes currently defined as the standard criteria.

Diffusion models for medical image reconstruction

Abstract Better algorithms for medical image reconstruction can improve image quality and enable reductions in acquisition time and radiation dose. A prior understanding of the distribution of plausible images is key to realising these benefits. Recently, research into deep-learning image reconstruction has started to look into using unsupervised diffusion models, trained only on high-quality medical images (ie, without needing paired scanner measurement data), for modelling this prior understanding. Image reconstruction algorithms incorporating unsupervised diffusion models have already attained state-of-the-art accuracy for reconstruction tasks ranging from highly accelerated MRI to ultra-sparse-view CT and low-dose PET. Key advantages of diffusion model approach over previous deep learning approaches for reconstruction include state-of-the-art image distribution modelling, improved robustness to domain shift, and principled quantification of reconstruction uncertainty. If hallucination concerns can be alleviated, their key advantages and impressive performance could mean these algorithms are better suited to clinical use than previous deep-learning approaches. In this review, we provide an accessible introduction to image reconstruction and diffusion models, outline guidance for using diffusion-model-based reconstruction methodology, summarise modality-specific challenges, and identify key research themes. We conclude with a discussion of the opportunities and challenges of using diffusion models for medical image reconstruction.

Development of a Low-Cost and Compact Medical Image Reconstruction Platform Based on EIT Technique

Electrical impedance tomography (EIT) is an important imaging modality in non-invasive and radiation-free image reconstruction techniques. With the advantages of real-time imaging capabilities, portability, and safety features, EIT has acquired substantial significance as a valuable technique for lung patients during the COVID-19 pandemic. Nevertheless, a significant challenge arises when many COVID-19 patients need to utilize EIT devices for monitoring and treatment. To address this problem, a low-cost and compact wireless communication EIT platform was developed for impedance image reconstruction and real-time monitoring of human lung operations. Since the system was structured as a platform, it can be readily replicated and scaled up in emergencies. The proposed system consisted of 16 electrodes placed on the chest of the lung patients. A stable current was injected into the object through a pair of adjacent electrodes, while the voltage was measured on the remaining electrode pairs using a lock-in amplifier. The electrical impedance between each electrode pair was determined based on Ohm’s law. Experimental results showed that the system could reconstruct the shape and the position of objects inside the medium with high accuracy. The average blur radius and percentage of the location error of the reconstructed image were 1.01 ± 0.28 and 5.18 ± 1.35%, respectively. Furthermore, images showing the operation of the human lung were also observed by the proposed system, confirming the possibility of using the system in clinical applications. The proposed EIT system with wireless communication is a potential study for large-scale implementation, particularly in response to the COVID-19 pandemic.

Score-Based Generative Models for PET Image Reconstruction

Score-based generative models have demonstrated highly promising results for medical image reconstruction tasks in magnetic resonance imaging or computed tomography. However, their application to Positron Emission Tomography (PET) is still largely unexplored. PET image reconstruction involves a variety of challenges, including Poisson noise with high variance and a wide dynamic range. To address these challenges, we propose several PET-specific adaptations of score-based generative models. The proposed framework is developed for both 2D and 3D PET. In addition, we provide an extension to guided reconstruction using magnetic resonance images. We validate the approach through extensive 2D and 3D <emph>in-silico</emph> experiments with a model trained on patient-realistic data without lesions, and evaluate on data without lesions as well as out-of-distribution data with lesions. This demonstrates the proposed method’s robustness and significant potential for improved PET reconstruction.

Reconstruction of a 3D medical image from pre-processed 2D DICOM slices: clinical application

Reconstruction of a 3D medical image from pre-processed 2D DICOM slices: clinical application

Transfer Deep Learning for Dielectric Profile Reconstruction in Microwave Medical Imaging

Transfer Deep Learning for Dielectric Profile Reconstruction in Microwave Medical Imaging