Interpolated Compressed Sensing for 2D Multiple Slice Fast MR Imaging

Sparse MRI has been introduced to reduce the acquisition time and raw data size by undersampling the k-space data. However, the image quality, particularly the contrast to noise ratio (CNR), decreases with the undersampling rate. In this work, we proposed an interpolated Compressed Sensing (iCS) method to further enhance the imaging speed or reduce data size without significant sacrifice of image quality and CNR for multi-slice two-dimensional sparse MR imaging in humans. This method utilizes the k-space data of the neighboring slice in the multi-slice acquisition. The missing k-space data of a highly undersampled slice are estimated by using the raw data of its neighboring slice multiplied by a weighting function generated from low resolution full k-space reference images. In-vivo MR imaging in human feet has been used to investigate the feasibility and the performance of the proposed iCS method. The results show that by using the proposed iCS reconstruction method, the average image error can be reduced and the average CNR can be improved, compared with the conventional sparse MRI reconstruction at the same undersampling rate.     

Model-based simulation of dynamic magnetic resonance imaging signals

This paper presents a model-based method to efficiently simulate dynamic magnetic resonance imaging signals. Using an analytical spatiotemporal object model, the method can approximate time-varying k-space signals such as those from objects in motion and/or during dynamic contrast enhancement. Both rigid-body and non-rigid-body motions can be simulated using the proposed method. In addition, it can simulate data with arbitrary data sampling order and/or non-uniform k-space trajectory. A set of simulated images were compared with real data acquired from a rat model on a 4.7 T scanner to verify the model. The efficient simulation method is expected to be useful for rapid testing of various imaging and image analysis algorithms such as image reconstruction, image registration, motion compensation, and kinetic parameter mapping.     

Deep generative modeling for volume reconstruction in cryo-electron microscopy

Advances in cryo-electron microscopy (cryo-EM) for high-resolution imaging of biomolecules in solution have provided new challenges and opportunities for algorithm development for 3D reconstruction. Next-generation volume reconstruction algorithms that combine generative modelling with end-to-end unsupervised deep learning techniques have shown promise, but many technical and theoretical hurdles remain, especially when applied to experimental cryo-EM images. In light of the proliferation of such methods, we propose here a critical review of recent advances in the field of deep generative modelling for cryo-EM reconstruction. The present review aims to (i) provide a unified statistical framework using terminology familiar to machine learning researchers with no specific background in cryo-EM, (ii) review the current methods in this framework, and (iii) outline outstanding bottlenecks and avenues for improvements in the field.     

Time Efficient 3D Radial UTE Sampling with Fully Automatic Delay Compensation on a Clinical 3T MR Scanner

This work’s aim was to minimize the acquisition time of a radial 3D ultra-short echo-time (UTE) sequence and to provide fully automated, gradient delay compensated, and therefore artifact free, reconstruction. The radial 3D UTE sequence (echo time 60 μs) was implemented as single echo acquisition with center-out readouts and improved time efficient spoiling on a clinical 3T scanner without hardware modifications. To assess the sequence parameter dependent gradient delays each acquisition contained a quick calibration scan and utilized the phase of the readouts to detect the actual k-space center. This calibration scan does not require any user interaction. To evaluate the robustness of this automatic delay estimation phantom experiments were performed and 19 in vivo imaging data of the head, tibial cortical bone, feet and lung were acquired from 6 volunteers. As clinical application of this fast 3D UTE acquisition single breath-hold lung imaging is demonstrated. The proposed sequence allowed very short repetition times (TR~1ms), thus reducing total acquisition time. The proposed, fully automated k-phase based gradient delay calibration resulted in accurate delay estimations (difference to manually determined optimal delay −0.13 ± 0.45 μs) and allowed unsupervised reconstruction of high quality images for both phantom and in vivo data. The employed fast spoiling scheme efficiently suppressed artifacts caused by incorrectly refocused echoes. The sequence proved to be quite insensitive to motion, flow and susceptibility artifacts and provides oversampling protection against aliasing foldovers in all directions. Due to the short TR, acquisition times are attractive for a wide range of clinical applications. For short T2* mapping this sequence provides free choice of the second TE, usually within less scan time as a comparable dual echo UTE sequence.     

Hyperpolarized MRI,functional MRI,MR spectroscopy and CEST to provide metabolic information in vivo

Access to metabolic information in vivo using magnetic resonance (MR) technologies has generally been the niche of MR spectroscopy (MRS) and spectroscopic imaging (MRSI). Metabolic fluxes can be studied using the infusion of substrates labeled with magnetic isotopes, with the use of hyperpolarization especially powerful. Unfortunately, these promising methods are not yet accepted clinically, where fast, simple, and reliable measurement and diagnosis are key. Recent advances in functional MRI and chemical exchange saturation transfer (CEST) MRI allow the use of water imaging to study oxygen metabolism and tissue metabolite levels. These, together with the use of novel data analysis approaches such as machine learning for all of these metabolic MR approaches, are increasing the likelihood of their clinical translation.     

Efficient Reconstruction of Heterogeneous Networks from Time Series via Compressed Sensing

Recent years have witnessed a rapid development of network reconstruction approaches, especially for a series of methods based on compressed sensing. Although compressed-sensing based methods require much less data than conventional approaches, the compressed sensing for reconstructing heterogeneous networks has not been fully exploited because of hubs. Hub neighbors require much more data to be inferred than small-degree nodes, inducing a cask effect for the reconstruction of heterogeneous networks. Here, a conflict-based method is proposed to overcome the cast effect to considerably reduce data amounts for achieving accurate reconstruction. Moreover, an element elimination method is presented to use the partially available structural information to reduce data requirements. The integration of both methods can further improve the reconstruction performance than separately using each technique. These methods are validated by exploring two evolutionary games taking place in scale-free networks, where individual information is accessible and an attempt to decode the network structure from measurable data is made. The results demonstrate that for all of the cases, much data are saved compared to that in the absence of these two methods. Due to the prevalence of heterogeneous networks in nature and society and the high cost of data acquisition in large-scale networks, these approaches have wide applications in many fields and are valuable for understanding and controlling the collective dynamics of a variety of heterogeneous networked systems.     

Advanced diffusion MRI fiber tracking in neurosurgical and neurodegenerative disorders and neuroanatomical studies: A review

Diffusion MRI enabled in vivo microstructural imaging of the fiber tracts in the brain resulting in its application in a wide range of settings, including in neurological and neurosurgical disorders. Conventional approaches such as diffusion tensor imaging (DTI) have been shown to have limited applications due to the crossing fiber problem and the susceptibility of their quantitative indices to partial volume effects. To overcome these limitations, the recent focus has shifted to the advanced acquisition methods and their related analytical approaches. Advanced white matter imaging techniques provide superior qualitative data in terms of demonstration of multiple crossing fibers in their spatial orientation in a three dimensional manner in the brain. In this review paper, we discuss the advancements in diffusion MRI and introduce their roles. Using examples, we demonstrate the role of advanced diffusion MRI-based fiber tracking in neuroanatomical studies. Results from its preliminary application in the evaluation of intracranial space occupying lesions, including with respect to future directions for prognostication, are also presented. Building upon the previous DTI studies assessing white matter disease in Huntington's disease and Amyotrophic lateral sclerosis; we also discuss approaches which have led to encouraging preliminary results towards developing an imaging biomarker for these conditions.     

Suppressing Multi-Channel Ultra-Low-Field MRI Measurement Noise Using Data Consistency and Image Sparsity

Ultra-low-field (ULF) MRI (B ₀ = 10–100 µT) typically suffers from a low signal-to-noise ratio (SNR). While SNR can be improved by pre-polarization and signal detection using highly sensitive superconducting quantum interference device (SQUID) sensors, we propose to use the inter-dependency of the k-space data from highly parallel detection with up to tens of sensors readily available in the ULF MRI in order to suppress the noise. Furthermore, the prior information that an image can be sparsely represented can be integrated with this data consistency constraint to further improve the SNR. Simulations and experimental data using 47 SQUID sensors demonstrate the effectiveness of this data consistency constraint and sparsity prior in ULF-MRI reconstruction.     

An Augmented Lagrangian Based Compressed Sensing Reconstruction for Non-Cartesian Magnetic Resonance Imaging without Gridding and Regridding at Every Iteration

Background

Non-Cartesian trajectories are used in a variety of fast imaging applications, due to the incoherent image domain artifacts they create when undersampled. While the gridding technique is commonly utilized for reconstruction, the incoherent artifacts may be further removed using compressed sensing (CS). CS reconstruction is typically done using conjugate-gradient (CG) type algorithms, which require gridding and regridding to be performed at every iteration. This leads to a large computational overhead that hinders its applicability.

Methods

We sought to develop an alternative method for CS reconstruction that only requires two gridding and one regridding operation in total, irrespective of the number of iterations. This proposed technique is evaluated on phantom images and whole-heart coronary MRI acquired using 3D radial trajectories, and compared to conventional CS reconstruction using CG algorithms in terms of quantitative vessel sharpness, vessel length, computation time, and convergence rate.

Results

Both CS reconstructions result in similar vessel length (P = 0.30) and vessel sharpness (P = 0.62). The per-iteration complexity of the proposed technique is approximately 3-fold lower than the conventional CS reconstruction (17.55 vs. 52.48 seconds in C++). Furthermore, for in-vivo datasets, the convergence rate of the proposed technique is faster (60±13 vs. 455±320 iterations) leading to a ∼23-fold reduction in reconstruction time.

Conclusions

The proposed reconstruction provides images of similar quality to the conventional CS technique in terms of removing artifacts, but at a much lower computational complexity.     

PanClassif: Improving pan cancer classification of single cell RNA-seq gene expression data using machine learning

Cancer is one of the major causes of human death per year. In recent years, cancer identification and classification using machine learning have gained momentum due to the availability of high throughput sequencing data. Using RNA-seq, cancer research is blooming day by day and new insights of cancer and related treatments are coming into light. In this paper, we propose PanClassif, a method that requires a very few and effective genes to detect cancer from RNA-seq data and is able to provide performance gain in several wide range machine learning classifiers. We have taken 22 types of cancer samples from The Cancer Genome Atlas (TCGA) having 8287 cancer samples and 680 normal samples. Firstly, PanClassif uses k-Nearest Neighbour (k-NN) smoothing to smooth the samples to handle noise in the data. Then effective genes are selected by Anova based test. For balancing the train data, PanClassif applies an oversampling method, SMOTE. We have performed comprehensive experiments on the datasets using several classification algorithms. Experimental results shows that PanClassif outperform existing state-of-the-art methods available and shows consistent performance for two single cell RNA-seq datasets taken from Gene Expression Omnibus (GEO). PanClassif improves performances of a wide variety of classifiers for both binary cancer prediction and multi-class cancer classification. PanClassif is available as a python package (https://pypi.org/project/panclassif/). All the source code and materials of PanClassif are available at https://github.com/Zwei-inc/panclassif.     

Improving accuracy and efficiency in seagrass detection using state-of-the-art AI techniques

Seagrasses provide a wide range of ecosystem services in coastal marine environments. Despite their ecological and economic importance, these species are declining because of human impact. This decline has driven the need for monitoring and mapping to estimate the overall health and dynamics of seagrasses in coastal environments, often based on underwater images. However, seagrass detection from underwater digital images is not a trivial task; it requires taxonomic expertise and is time-consuming and expensive. Recently automatic approaches based on deep learning have revolutionised object detection performance in many computer vision applications, and there has been interest in applying this to automated seagrass detection from imagery. Deep learning–based techniques reduce the need for hardcore feature extraction by domain experts which is required in machine learning-based techniques. This study presents a YOLOv5-based one-stage detector and an EfficientDetD7–based two-stage detector for detecting seagrass, in this case, Halophila ovalis, one of the most widely distributed seagrass species. The EfficientDet-D7–based seagrass detector achieves the highest mAP of 0.484 on the ECUHO-2 dataset and mAP of 0.354 on the ECUHO-1 dataset, which are about 7% and 5% better than the state-of-the-art Halophila ovalis detection performance on those datasets, respectively. The proposed YOLOv5-based detector achieves an average inference time of 0.077 s and 0.043 s respectively which are much lower than the state-of-the-art approach on the same datasets.     

基于机器学习的医学影像分析在药物研发和精准医疗方面的应用

MRI,PET,和CT等医学影像在新药研发和精准医疗中起着越来越重要的作用。影像技术可以被用来诊断疾病,评估药效,选择适应患者,或者确定用药剂量。 随着人工智能技术的发展,特别是机器学习以及深度学习技术在医学影像中的应用,使得我们可以用更短的时间,更少的放射剂量获取更高质量的影像。这些技术还可以帮助放射科医生缩短读片时间,提高诊断准确率。除此之外,机器学习技术还可以提高量化分析的可行性和精度,帮助建立影像与基因以及疾病的临床表现之间的关系。首先根据不同形态的医学影像,简单介绍他们在药物研发和精准医疗中的应用。并对机器学习在医学影像中的功能作一概括总结。最后讨论这个领域的挑战和机遇。     

Self-Navigation with Compressed Sensing for 2D Translational Motion Correction in Free-Breathing Coronary MRI: A Feasibility Study

Purpose

Respiratory motion correction remains a challenge in coronary magnetic resonance imaging (MRI) and current techniques, such as navigator gating, suffer from sub-optimal scan efficiency and ease-of-use. To overcome these limitations, an image-based self-navigation technique is proposed that uses “sub-images” and compressed sensing (CS) to obtain translational motion correction in 2D. The method was preliminarily implemented as a 2D technique and tested for feasibility for targeted coronary imaging.

Methods

During a 2D segmented radial k-space data acquisition, heavily undersampled sub-images were reconstructed from the readouts collected during each cardiac cycle. These sub-images may then be used for respiratory self-navigation. Alternatively, a CS reconstruction may be used to create these sub-images, so as to partially compensate for the heavy undersampling. Both approaches were quantitatively assessed using simulations and in vivo studies, and the resulting self-navigation strategies were then compared to conventional navigator gating.

Results

Sub-images reconstructed using CS showed a lower artifact level than sub-images reconstructed without CS. As a result, the final image quality was significantly better when using CS-assisted self-navigation as opposed to the non-CS approach. Moreover, while both self-navigation techniques led to a 69% scan time reduction (as compared to navigator gating), there was no significant difference in image quality between the CS-assisted self-navigation technique and conventional navigator gating, despite the significant decrease in scan time.

Conclusions

CS-assisted self-navigation using 2D translational motion correction demonstrated feasibility of producing coronary MRA data with image quality comparable to that obtained with conventional navigator gating, and does so without the use of additional acquisitions or motion modeling, while still allowing for 100% scan efficiency and an improved ease-of-use. In conclusion, compressed sensing may become a critical adjunct for 2D translational motion correction in free-breathing cardiac imaging with high spatial resolution. An expansion to modern 3D approaches is now warranted.     

Robust secret image sharing scheme resistance to maliciously tampered shadows by AMBTC and quantization

For (k, n)-threshold secret image sharing (SIS) scheme, only k or more than k complete parts can recover the secret information, and the correct image cannot be obtained if the count of shadow images is not enough or the shadow images are damaged. The existing schemes are weak in resisting large-area shadow image tampering. In this paper, we propose a robust secret image sharing scheme resisting to maliciously tampered shadow images by Absolute Moment Block Truncation Coding (AMBTC) and quantization (RSIS-AQ). The secret image is successively compressed in two ways: AMBTC and quantization. The sharing shadow images contain the sharing results of both compressed image from different parts, so that even the shadow images are faced with large-scale area of malicious tampering, the secret image can be recovered with acceptable visual quality. Compared with related works, our scheme can resist larger area of tampering and yield better recovered image visual quality. The experimental results prove the effectiveness of our scheme.     

Increased Cortical-Limbic Anatomical Network Connectivity in Major Depression Revealed by Diffusion Tensor Imaging

Magnetic resonance imaging studies have reported significant functional and structural differences between depressed patients and controls. Little attention has been given, however, to the abnormalities in anatomical connectivity in depressed patients. In the present study, we aim to investigate the alterations in connectivity of whole-brain anatomical networks in those suffering from major depression by using machine learning approaches. Brain anatomical networks were extracted from diffusion magnetic resonance images obtained from both 22 first-episode, treatment-naive adults with major depressive disorder and 26 matched healthy controls. Using machine learning approaches, we differentiated depressed patients from healthy controls based on their whole-brain anatomical connectivity patterns and identified the most discriminating features that represent between-group differences. Classification results showed that 91.7% (patients = 86.4%, controls = 96.2%; permutation test, p<0.0001) of subjects were correctly classified via leave-one-out cross-validation. Moreover, the strengths of all the most discriminating connections were increased in depressed patients relative to the controls, and these connections were primarily located within the cortical-limbic network, especially the frontal-limbic network. These results not only provide initial steps toward the development of neurobiological diagnostic markers for major depressive disorder, but also suggest that abnormal cortical-limbic anatomical networks may contribute to the anatomical basis of emotional dysregulation and cognitive impairments associated with this disease.     

AI applications to medical images: From machine learning to deep learning

PurposeArtificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context.MethodsA narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections.ResultsWe first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way.ConclusionsBiomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.     

A Review of the Deep Learning Methods for Medical Images Super Resolution Problems

Super resolution problems are widely discussed in medical imaging. Spatial resolution of medical images are not sufficient due to the constraints such as image acquisition time, low irradiation dose or hardware limits. To address these problems, different super resolution methods have been proposed, such as optimization or learning-based approaches. Recently, deep learning methods become a thriving technology and are developing at an exponential speed. We think it is necessary to write a review to present the current situation of deep learning in medical imaging super resolution. In this paper, we first briefly introduce deep learning methods, then present a number of important deep learning approaches to solve super resolution problems, different architectures as well as up-sampling operations will be introduced. Afterwards, we focus on the applications of deep learning methods in medical imaging super resolution problems, the challenges to overcome will be presented as well.     

AI for COVID-19 Detection from Radiographs: Incisive Analysis of State of the Art Techniques,Key Challenges and Future Directions

Background and objectiveIn recent years, Artificial Intelligence has had an evident impact on the way research addresses challenges in different domains. It has proven to be a huge asset, especially in the medical field, allowing for time-efficient and reliable solutions. This research aims to spotlight the impact of deep learning and machine learning models in the detection of COVID-19 from medical images. This is achieved by conducting a review of the state-of-the-art approaches proposed by the recent works in this field.MethodsThe main focus of this study is the recent developments of classification and segmentation approaches to image-based COVID-19 detection. The study reviews 140 research papers published in different academic research databases. These papers have been screened and filtered based on specified criteria, to acquire insights prudent to image-based COVID-19 detection.ResultsThe methods discussed in this review include different types of imaging modality, predominantly X-rays and CT scans. These modalities are used for classification and segmentation tasks as well. This review seeks to categorize and discuss the different deep learning and machine learning architectures employed for these tasks, based on the imaging modality utilized. It also hints at other possible deep learning and machine learning architectures that can be proposed for better results towards COVID-19 detection. Along with that, a detailed overview of the emerging trends and breakthroughs in Artificial Intelligence-based COVID-19 detection has been discussed as well.ConclusionThis work concludes by stipulating the technical and non-technical challenges faced by researchers and illustrates the advantages of image-based COVID-19 detection with Artificial Intelligence techniques.     

Similarity (<Emphasis Type="Italic">range</Emphasis> and <Emphasis Type="Italic">k</Emphasis>NN) queries processing on an Intel Xeon Phi coprocessor

Nowadays, the evolution of information technologies requires fast similarity search tools for analyzing new data types as audio, video, or images. The usual search by keys or records is not possible and to search on these databases is a compute-intensive problem. Regarding this, in the latest years, compute-intensive coprocessors (mainly NVIDIA GPUs) have been studied as a tool for accelerating sequential processing algorithms. In this work, we implement kNN and range queries on the recently launched Intel Xeon Phi coprocessor. We developed exhaustive and also indexing algorithms using the LC index. This index has been widely studied in sequential computing to accelerate similarity search on multimedia databases. We implement and compare different exhaustive and indexing versions showing some key factors in Xeon Phi to deal with this type of search. For indexing algorithms, we used a strategy based on cluster distribution among cores LC MIC Dist-C obtaining up to 168\(\times \) over the sequential exhaustive algorithm. Our algorithms using exhaustive strategies in Xeon Phi for range queries achieve up to 22\(\times \) speed-up over the sequential counterpart compared to the 12\(\times \) of a 20-core machine, and a similar advantage is achieved for kNN queries. Comparing with GPUs, we obtain higher performance on our indexing algorithms on Intel Xeon Phi. However, GPU works faster with memory-aligned access exhaustive algorithms. Our exhaustive approaches on Xeon Phi can be used on a wide class of databases, for example, non-metric spaces. Finally, we extend our algorithms to be used with large databases that do not fit in the coprocessor memory, showing a good scalability with the number of elements.