Publications
186 results found
Papanastasiou G, Garcia Seco de Herrera A, Wang C, et al., 2023, Focus on machine learning models in medical imaging, PHYSICS IN MEDICINE AND BIOLOGY, Vol: 68, ISSN: 0031-9155
Nan Y, Ser JD, Tang Z, et al., 2023, Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation., IEEE Trans Neural Netw Learn Syst, Vol: PP
Airway segmentation is crucial for the examination, diagnosis, and prognosis of lung diseases, while its manual delineation is unduly burdensome. To alleviate this time-consuming and potentially subjective manual procedure, researchers have proposed methods to automatically segment airways from computerized tomography (CT) images. However, some small-sized airway branches (e.g., bronchus and terminal bronchioles) significantly aggravate the difficulty of automatic segmentation by machine learning models. In particular, the variance of voxel values and the severe data imbalance in airway branches make the computational module prone to discontinuous and false-negative predictions, especially for cohorts with different lung diseases. The attention mechanism has shown the capacity to segment complex structures, while fuzzy logic can reduce the uncertainty in feature representations. Therefore, the integration of deep attention networks and fuzzy theory, given by the fuzzy attention layer, should be an escalated solution for better generalization and robustness. This article presents an efficient method for airway segmentation, comprising a novel fuzzy attention neural network (FANN) and a comprehensive loss function to enhance the spatial continuity of airway segmentation. The deep fuzzy set is formulated by a set of voxels in the feature map and a learnable Gaussian membership function. Different from the existing attention mechanism, the proposed channel-specific fuzzy attention addresses the issue of heterogeneous features in different channels. Furthermore, a novel evaluation metric is proposed to assess both the continuity and completeness of airway structures. The efficiency, generalization, and robustness of the proposed method have been proved by training on normal lung disease while testing on datasets of lung cancer, COVID-19, and pulmonary fibrosis.
Liu X, Li S, Wang B, et al., 2023, Motion estimation based on projective information disentanglement for 3D reconstruction of rotational coronary angiography., Comput Biol Med, Vol: 157
The 2D projection space-based motion compensation reconstruction (2D-MCR) is a kind of representative method for 3D reconstruction of rotational coronary angiography owing to its high efficiency. However, due to the lack of accurate motion estimation of the overlapping projection pixels, existing 2D-MCR methods may still have a certain level of under-sampling artifacts or lose accuracy for cases with strong cardiac motion. To overcome this, in this study, we proposed a motion estimation approach based on projective information disentanglement (PID-ME) for 3D reconstruction of rotational coronary angiography. The reconstruction method adopts the framework of 2D-MCR, which is referred to as 2D-PID-MCR. The PID-ME consists of two parts: generation of the reference projection sequence based on the fast simplified distance driven projector (FSDDP) algorithm, motion estimation and correction based on the projective average minimal distance measure (PAMD) model. The FSDDP algorithm generates the reference projection sequence faster and accelerates the whole reconstruction greatly. The PAMD model can disentangle the projection information effectively and estimate the motion of both overlapping and non-overlapping projection pixels accurately. The main contribution of this study is the construction of 2D-PID-MCR to overcome the inherent limitations of the existing 2D-MCR method. Simulated and clinical experiments show that the PID-ME, consisting of FSDDP and PAMD, can estimate the motion of the projection sequence data accurately and efficiently. Our 2D-PID-MCR method outperforms the state-of-the-art approaches in terms of accuracy and real-time performance.
Jiang Y, Jin S, Jin X, et al., 2023, Pharmacophoric-constrained heterogeneous graph transformer model for molecular property prediction, COMMUNICATIONS CHEMISTRY, Vol: 6, ISSN: 2399-3669
Xing X, Papanastasiou G, Walsh S, et al., 2023, Less is more: unsupervised mask-guided annotated CT image synthesis with minimum manual segmentations, IEEE Transactions on Medical Imaging, Pages: 1-12, ISSN: 0278-0062
As a pragmatic data augmentation tool, data synthesis has generally returned dividends in performance for deep learning based medical image analysis. However, generating corresponding segmentation masks for synthetic medical images is laborious and subjective. To obtain paired synthetic medical images and segmentations, conditional generative models that use segmentation masks as synthesis conditions were proposed. However, these segmentation mask-conditioned generative models still relied on large, varied, and labeled training datasets, and they could only provide limited constraints on human anatomical structures, leading to unrealistic image features. Moreover, the invariant pixel-level conditions could reduce the variety of synthetic lesions and thus reduce the efficacy of data augmentation. To address these issues, in this work, we propose a novel strategy for medical image synthesis, namely Unsupervised Mask (UM)-guided synthesis, to obtain both synthetic images and segmentations using limited manual segmentation labels. We first develop a superpixel based algorithm to generate unsupervised structural guidance and then design a conditional generative model to synthesize images and annotations simultaneously from those unsupervised masks in a semi-supervised multi-task setting. In addition, we devise a multi-scale multi-task Fréchet Inception Distance (MM-FID) and multi-scale multi-task standard deviation (MM-STD) to harness both fidelity and variety evaluations of synthetic CT images. With multiple analyses on different scales, we could produce stable image quality measurements with high reproducibility. Compared with the segmentation mask guided synthesis, our UM-guided synthesis provided high-quality synthetic images with significantly higher fidelity, variety, and utility (p < 0.05 by Wilcoxon Signed Ranked test).
Zhu J, Ye J, Dong L, et al., 2023, Non-invasive prediction of overall survival time for glioblastoma multiforme patients based on multimodal MRI radiomics, INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, ISSN: 0899-9457
Zhang M, Wu Y, Zhang H, et al., 2023, Multi-site, Multi-domain Airway Tree Modeling (ATM'22): A Public Benchmark for Pulmonary Airway Segmentation
Open international challenges are becoming the de facto standard forassessing computer vision and image analysis algorithms. In recent years, newmethods have extended the reach of pulmonary airway segmentation that is closerto the limit of image resolution. Since EXACT'09 pulmonary airway segmentation,limited effort has been directed to quantitative comparison of newly emergedalgorithms driven by the maturity of deep learning based approaches andclinical drive for resolving finer details of distal airways for earlyintervention of pulmonary diseases. Thus far, public annotated datasets areextremely limited, hindering the development of data-driven methods anddetailed performance evaluation of new algorithms. To provide a benchmark forthe medical imaging community, we organized the Multi-site, Multi-domain AirwayTree Modeling (ATM'22), which was held as an official challenge event duringthe MICCAI 2022 conference. ATM'22 provides large-scale CT scans with detailedpulmonary airway annotation, including 500 CT scans (300 for training, 50 forvalidation, and 150 for testing). The dataset was collected from differentsites and it further included a portion of noisy COVID-19 CTs with ground-glassopacity and consolidation. Twenty-three teams participated in the entire phaseof the challenge and the algorithms for the top ten teams are reviewed in thispaper. Quantitative and qualitative results revealed that deep learning modelsembedded with the topological continuity enhancement achieved superiorperformance in general. ATM'22 challenge holds as an open-call design, thetraining data and the gold standard evaluation are available upon successfulregistration via its homepage.
Hasan K, Ahamad MA, Yap CH, et al., 2023, A survey, review, and future trends of skin lesion segmentation and classification, Computers in Biology and Medicine, Vol: 155, Pages: 1-36, ISSN: 0010-4825
The Computer-aided Diagnosis or Detection (CAD) approach for skin lesion analysis is an emerging field of research that has the potential to alleviate the burden and cost of skin cancer screening. Researchers have recently indicated increasing interest in developing such CAD systems, with the intention of providing a user-friendly tool to dermatologists to reduce the challenges encountered or associated with manual inspection. This article aims to provide a comprehensive literature survey and review of a total of 594 publications (356 for skin lesion segmentation and 238 for skin lesion classification) published between 2011 and 2022. These articles are analyzed and summarized in a number of different ways to contribute vital information regarding the methods for the development of CAD systems. These ways include: relevant and essential definitions and theories, input data (dataset utilization, preprocessing, augmentations, and fixing imbalance problems), method configuration (techniques, architectures, module frameworks, and losses), training tactics (hyperparameter settings), and evaluation criteria. We intend to investigate a variety of performance-enhancing approaches, including ensemble and post-processing. We also discuss these dimensions to reveal their current trends based on utilization frequencies. In addition, we highlight the primary difficulties associated with evaluating skin lesion segmentation and classification systems using minimal datasets, as well as the potential solutions to these difficulties. Findings, recommendations, and trends are disclosed to inform future research on developing an automated and robust CAD system for skin lesion analysis.
Li H, Nan Y, Del Ser J, et al., 2023, Large-kernel attention for 3D medical image segmentation, Cognitive Computation, ISSN: 1866-9956
Automated segmentation of multiple organs and tumors from 3D medical images such as magnetic resonance imaging (MRI) and computed tomography (CT) scans using deep learning methods can aid in diagnosing and treating cancer. However, organs often overlap and are complexly connected, characterized by extensive anatomical variation and low contrast. In addition, the diversity of tumor shape, location, and appearance, coupled with the dominance of background voxels, makes accurate 3D medical image segmentation difficult. In this paper, a novel 3D large-kernel (LK) attention module is proposed to address these problems to achieve accurate multi-organ segmentation and tumor segmentation. The advantages of biologically inspired self-attention and convolution are combined in the proposed LK attention module, including local contextual information, long-range dependencies, and channel adaptation. The module also decomposes the LK convolution to optimize the computational cost and can be easily incorporated into CNNs such as U-Net. Comprehensive ablation experiments demonstrated the feasibility of convolutional decomposition and explored the most efficient and effective network design. Among them, the best Mid-type 3D LK attention-based U-Net network was evaluated on CT-ORG and BraTS 2020 datasets, achieving state-of-the-art segmentation performance when compared to avant-garde CNN and Transformer-based methods for medical image segmentation. The performance improvement due to the proposed 3D LK attention module was statistically validated.
Zhu J, Yang G, Lio P, 2023, A residual dense vision transformer for medical image super-resolution with segmentation-based perceptual loss fine-tuning
Super-resolution plays an essential role in medical imaging because itprovides an alternative way to achieve high spatial resolutions and imagequality with no extra acquisition costs. In the past few decades, the rapiddevelopment of deep neural networks has promoted super-resolution performancewith novel network architectures, loss functions and evaluation metrics.Specifically, vision transformers dominate a broad range of computer visiontasks, but challenges still exist when applying them to low-level medical imageprocessing tasks. This paper proposes an efficient vision transformer withresidual dense connections and local feature fusion to achieve efficientsingle-image super-resolution (SISR) of medical modalities. Moreover, weimplement a general-purpose perceptual loss with manual control for imagequality improvements of desired aspects by incorporating prior knowledge ofmedical image segmentation. Compared with state-of-the-art methods on fourpublic medical image datasets, the proposed method achieves the best PSNRscores of 6 modalities among seven modalities. It leads to an averageimprovement of $+0.09$ dB PSNR with only 38\% parameters of SwinIR. On theother hand, the segmentation-based perceptual loss increases $+0.14$ dB PSNR onaverage for SOTA methods, including CNNs and vision transformers. Additionally,we conduct comprehensive ablation studies to discuss potential factors for thesuperior performance of vision transformers over CNNs and the impacts ofnetwork and loss function components. The code will be released on GitHub withthe paper published.
Li M, Fang Y, Tang Z, et al., 2023, Explainable COVID-19 infections identification and delineation using calibrated pseudo labels, IEEE Transactions on Emerging Topics in Computational Intelligence, Vol: 7, Pages: 26-35, ISSN: 2471-285X
The upheaval brought by the arrival of the COVID-19 pandemic has continued to bring fresh challenges over the past two years. During this COVID-19 pandemic, there has been a need for rapid identification of infected patients and specific delineation of infection areas in computed tomography (CT) images. Although deep supervised learning methods have been established quickly, the scarcity of both image-level and pixel-level labels as well as the lack of explainable transparency still hinder the applicability of AI. Can we identify infected patients and delineate the infections with extreme minimal supervision? Semi-supervised learning has demonstrated promising performance under limited labelled data and sufficient unlabelled data. Inspired by semi-supervised learning, we propose a model-agnostic calibrated pseudo-labelling strategy and apply it under a consistency regularization framework to generate explainable identification and delineation results. We demonstrate the effectiveness of our model with the combination of limited labelled data and sufficient unlabelled data or weakly-labelled data. Extensive experiments have shown that our model can efficiently utilize limited labelled data and provide explainable classification and segmentation results for decision-making in clinical routine.
Kumar S, Mallik A, Kumar A, et al., 2023, Fuzz-ClustNet: Coupled fuzzy clustering and deep neural networks for Arrhythmia detection from ECG signals, COMPUTERS IN BIOLOGY AND MEDICINE, Vol: 153, ISSN: 0010-4825
Gao Z, Guo Y, Zhang J, et al., 2023, Hierarchical Perception Adversarial Learning Framework for Compressed Sensing MRI., IEEE Trans Med Imaging, Vol: PP
The long acquisition time has limited the accessibility of magnetic resonance imaging (MRI) because it leads to patient discomfort and motion artifacts. Although several MRI techniques have been proposed to reduce the acquisition time, compressed sensing in magnetic resonance imaging (CS-MRI) enables fast acquisition without compromising SNR and resolution. However, existing CS-MRI methods suffer from the challenge of aliasing artifacts. This challenge results in the noise-like textures and missing the fine details, thus leading to unsatisfactory reconstruction performance. To tackle this challenge, we propose a hierarchical perception adversarial learning framework (HP-ALF). HP-ALF can perceive the image information in the hierarchical mechanism: image-level perception and patch-level perception. The former can reduce the visual perception difference in the entire image, and thus achieve aliasing artifact removal. The latter can reduce this difference in the regions of the image, and thus recover fine details. Specifically, HP-ALF achieves the hierarchical mechanism by utilizing multilevel perspective discrimination. This discrimination can provide the information from two perspectives (overall and regional) for adversarial learning. It also utilizes a global and local coherent discriminator to provide structure information to the generator during training. In addition, HP-ALF contains a context-aware learning block to effectively exploit the slice information between individual images for better reconstruction performance. The experiments validated on three datasets demonstrate the effectiveness of HP-ALF and its superiority to the comparative methods.
Luo W, Xing X, Yang G, 2023, Is Autoencoder Truly Applicable for 3D CT Super-Resolution?
Featured by a bottleneck structure, autoencoder (AE) and its variants havebeen largely applied in various medical image analysis tasks, such assegmentation, reconstruction and de-noising. Despite of their promisingperformances in aforementioned tasks, in this paper, we claim that AE modelsare not applicable to single image super-resolution (SISR) for 3D CT data. Ourhypothesis is that the bottleneck architecture that resizes feature maps in AEmodels degrades the details of input images, thus can sabotage the performanceof super-resolution. Although U-Net proposed skip connections that mergeinformation from different levels, we claim that the degrading impact offeature resizing operations could hardly be removed by skip connections. Byconducting large-scale ablation experiments and comparing the performancebetween models with and without the bottleneck design on a public CT lungdataset , we have discovered that AE models, including U-Net, have failed toachieve a compatible SISR result ($p<0.05$ by Student's t-test) compared to thebaseline model. Our work is the first comparative study investigating thesuitability of AE architecture for 3D CT SISR tasks and brings a rationale forresearchers to re-think the choice of model architectures especially for 3D CTSISR tasks. The full implementation and trained models can be found at:https://github.com/Roldbach/Autoencoder-3D-CT-SISR
Huang J, Aviles-Rivero A, Schonlieb C-B, et al., 2023, ViGU: Vision GNN U-Net for Fast MRI
Deep learning models have been widely applied for fast MRI. The majority ofexisting deep learning models, e.g., convolutional neural networks, work ondata with Euclidean or regular grids structures. However, high-dimensionalfeatures extracted from MR data could be encapsulated in non-Euclideanmanifolds. This disparity between the go-to assumption of existing models anddata requirements limits the flexibility to capture irregular anatomicalfeatures in MR data. In this work, we introduce a novel Vision GNN type networkfor fast MRI called Vision GNN U-Net (ViGU). More precisely, the pixel array isfirst embedded into patches and then converted into a graph. Secondly, aU-shape network is developed using several graph blocks in symmetrical encoderand decoder paths. Moreover, we show that the proposed ViGU can also benefitfrom Generative Adversarial Networks yielding to its variant ViGU-GAN. Wedemonstrate, through numerical and visual experiments, that the proposed ViGUand GAN variant outperform existing CNN and GAN-based methods. Moreover, weshow that the proposed network readily competes with approaches based onTransformers while requiring a fraction of the computational cost. Moreimportantly, the graph structure of the network reveals how the networkextracts features from MR images, providing intuitive explainability.
Zhang W, Zhou Z, Gao Z, et al., 2023, Multiple adversarial learning based angiography reconstruction for ultra-low-dose contrast medium CT., IEEE Journal of Biomedical and Health Informatics, Vol: 27, Pages: 409-420, ISSN: 2168-2194
Iodinated contrast medium (ICM) dose reduction is beneficial for decreasing potential health risk to renal-insufficiency patients in CT scanning. Due to the lowintensity vessel in ultra-low-dose-ICM CT angiography, it cannot provide clinical diagnosis of vascular diseases. Angiography reconstruction for ultra-low-dose-ICM CT can enhance vascular intensity for directly vascular diseases diagnosis. However, the angiography reconstruction is challenging since patient individual differences and vascular disease diversity. In this paper, we propose a Multiple Adversarial Learning based Angiography Reconstruction (i.e., MALAR) framework to enhance vascular intensity. Specifically, a bilateral learning mechanism is developed for mapping a relationship between source and target domains rather than the image-to-image mapping. Then, a dual correlation constraint is introduced to characterize both distribution uniformity from across-domain features and sample inconsistency with domain simultaneously. Finally, an adaptive fusion module by combining multiscale information and long-range interactive dependency is explored to alleviate the interference of high-noise metal. Experiments are performed on CT sequences with different ICM doses. Quantitative results based on multiple metrics demonstrate the effectiveness of our MALAR on angiography reconstruction. Qualitative assessments by radiographers confirm the potential of our MALAR for the clinical diagnosis of vascular diseases. The code and model are available at https://github.com/HIC-SYSU/MALAR.
Yeung M, Rundo L, Nan Y, et al., 2022, Calibrating the dice loss to handle neural network overconfidence for biomedical image segmentation, Journal of Digital Imaging, Vol: 36, Pages: 739-752, ISSN: 0897-1889
The Dice similarity coefficient (DSC) is both a widely used metric and loss function for biomedical image segmentation due to its robustness to class imbalance. However, it is well known that the DSC loss is poorly calibrated, resulting in overconfident predictions that cannot be usefully interpreted in biomedical and clinical practice. Performance is often the only metric used to evaluate segmentations produced by deep neural networks, and calibration is often neglected. However, calibration is important for translation into biomedical and clinical practice, providing crucial contextual information to model predictions for interpretation by scientists and clinicians. In this study, we provide a simple yet effective extension of the DSC loss, named the DSC++ loss, that selectively modulates the penalty associated with overconfident, incorrect predictions. As a standalone loss function, the DSC++ loss achieves significantly improved calibration over the conventional DSC loss across six well-validated open-source biomedical imaging datasets, including both 2D binary and 3D multi-class segmentation tasks. Similarly, we observe significantly improved calibration when integrating the DSC++ loss into four DSC-based loss functions. Finally, we use softmax thresholding to illustrate that well calibrated outputs enable tailoring of recall-precision bias, which is an important post-processing technique to adapt the model predictions to suit the biomedical or clinical task. The DSC++ loss overcomes the major limitation of the DSC loss, providing a suitable loss function for training deep learning segmentation models for use in biomedical and clinical practice. Source code is available at https://github.com/mlyg/DicePlusPlus.
Li H, Tang Z, Nan Y, et al., 2022, Human treelike tubular structure segmentation: A comprehensive review and future perspectives, Computers in Biology and Medicine, Vol: 151, ISSN: 0010-4825
Various structures in human physiology follow a treelike morphology, which often expresses complexity at very fine scales. Examples of such structures are intrathoracic airways, retinal blood vessels, and hepatic blood vessels. Large collections of 2D and 3D images have been made available by medical imaging modalities such as magnetic resonance imaging (MRI), computed tomography (CT), Optical coherence tomography (OCT) and ultrasound in which the spatial arrangement can be observed. Segmentation of these structures in medical imaging is of great importance since the analysis of the structure provides insights into disease diagnosis, treatment planning, and prognosis. Manually labelling extensive data by radiologists is often time-consuming and error-prone. As a result, automated or semi-automated computational models have become a popular research field of medical imaging in the past two decades, and many have been developed to date. In this survey, we aim to provide a comprehensive review of currently publicly available datasets, segmentation algorithms, and evaluation metrics. In addition, current challenges and future research directions are discussed.
Nan Y, Tang P, Zhang G, et al., 2022, Unsupervised tissue segmentation via deep constrained Gaussian network, IEEE Transactions on Medical Imaging, Vol: 41, Pages: 3799-3811, ISSN: 0278-0062
Tissue segmentation is the mainstay of pathological examination, whereas the manual delineation is unduly burdensome. To assist this time-consuming and subjective manual step, researchers have devised methods to automatically segment structures in pathological images. Recently, automated machine and deep learning based methods dominate tissue segmentation research studies. However, most machine and deep learning based approaches are supervised and developed using a large number of training samples, in which the pixel-wise annotations are expensive and sometimes can be impossible to obtain. This paper introduces a novel unsupervised learning paradigm by integrating an end-to-end deep mixture model with a constrained indicator to acquire accurate semantic tissue segmentation. This constraint aims to centralise the components of deep mixture models during the calculation of the optimisation function. In so doing, the redundant or empty class issues, which are common in current unsupervised learning methods, can be greatly reduced. By validation on both public and in-house datasets, the proposed deep constrained Gaussian network achieves significantly (Wilcoxon signed-rank test) better performance (with the average Dice scores of 0.737 and 0.735, respectively) on tissue segmentation with improved stability and robustness, compared to other existing unsupervised segmentation approaches. Furthermore, the proposed method presents a similar performance (p-value > 0.05) compared to the fully supervised U-Net.
Li H, Nan Y, Del Ser J, et al., 2022, Region-based evidential deep learning to quantify uncertainty and improve robustness of brain tumor segmentation, Neural Computing and Applications, ISSN: 0941-0643
Despite recent advances in the accuracy of brain tumor segmentation, the results still suffer from low reliability and robustness. Uncertainty estimation is an efficient solution to this problem, as it provides a measure of confidence in the segmentation results. The current uncertainty estimation methods based on quantile regression, Bayesian neural network, ensemble, and Monte Carlo dropout are limited by their high computational cost and inconsistency. In order to overcome these challenges, Evidential Deep Learning (EDL) was developed in recent work but primarily for natural image classification and showed inferior segmentation results. In this paper, we proposed a region-based EDL segmentation framework that can generate reliable uncertainty maps and accurate segmentation results, which is robust to noise and image corruption. We used the Theory of Evidence to interpret the output of a neural network as evidence values gathered from input features. Following Subjective Logic, evidence was parameterized as a Dirichlet distribution, and predicted probabilities were treated as subjective opinions. To evaluate the performance of our model on segmentation and uncertainty estimation, we conducted quantitative and qualitative experiments on the BraTS 2020 dataset. The results demonstrated the top performance of the proposed method in quantifying segmentation uncertainty and robustly segmenting tumors. Furthermore, our proposed new framework maintained the advantages of low computational cost and easy implementation and showed the potential for clinical application.
Tang Z, Yang N, Walsh S, et al., 2022, Adversarial Transformer for Repairing Human Airway Segmentation
Discontinuity in the delineation of peripheral bronchioles hinders thepotential clinical application of automated airway segmentation models.Moreover, the deployment of such models is limited by the data heterogeneityacross different centres, and pathological abnormalities also make achievingaccurate robust segmentation in distal small airways difficult. Meanwhile, thediagnosis and prognosis of lung diseases often rely on evaluating structuralchanges in those anatomical regions. To address this gap, this paper presents apatch-scale adversarial-based refinement network that takes in preliminarysegmentation along with original CT images and outputs a refined mask of theairway structure. The method is validated on three different datasetsencompassing healthy cases, cases with cystic fibrosis and cases with COVID-19.The results are quantitatively evaluated by seven metrics and achieved morethan a 15% rise in detected length ratio and detected branch ratio, showingpromising performance compared to previously proposed models. The visualillustration also proves our refinement guided by a patch-scale discriminatorand centreline objective functions is effective in detecting discontinuitiesand missing bronchioles. Furthermore, the generalizability of our refinementpipeline is tested on three previous models and improves their segmentationcompleteness significantly.
Huang J, Ding W, Lv J, et al., 2022, Edge-enhanced dual discriminator generative adversarial network for fast MRI with parallel imaging using multi-view information, Applied Intelligence, Vol: 52, Pages: 14693-1470, ISSN: 0924-669X
In clinical medicine, magnetic resonance imaging (MRI) is one of the most important tools for diagnosis, triage, prognosis, and treatment planning. However, MRI suffers from an inherent slow data acquisition process because data is collected sequentially in k-space. In recent years, most MRI reconstruction methods proposed in the literature focus on holistic image reconstruction rather than enhancing the edge information. This work steps aside this general trend by elaborating on the enhancement of edge information. Specifically, we introduce a novel parallel imaging coupled dual discriminator generative adversarial network (PIDD-GAN) for fast multi-channel MRI reconstruction by incorporating multi-view information. The dual discriminator design aims to improve the edge information in MRI reconstruction. One discriminator is used for holistic image reconstruction, whereas the other one is responsible for enhancing edge information. An improved U-Net with local and global residual learning is proposed for the generator. Frequency channel attention blocks (FCA Blocks) are embedded in the generator for incorporating attention mechanisms. Content loss is introduced to train the generator for better reconstruction quality. We performed comprehensive experiments on Calgary-Campinas public brain MR dataset and compared our method with state-of-the-art MRI reconstruction methods. Ablation studies of residual learning were conducted on the MICCAI13 dataset to validate the proposed modules. Results show that our PIDD-GAN provides high-quality reconstructed MR images, with well-preserved edge information. The time of single-image reconstruction is below 5ms, which meets the demand of faster processing.
Xing X, Wu H, Wang L, et al., 2022, Non-Imaging Medical Data Synthesis for Trustworthy AI: A Comprehensive Survey
Data quality is the key factor for the development of trustworthy AI inhealthcare. A large volume of curated datasets with controlled confoundingfactors can help improve the accuracy, robustness and privacy of downstream AIalgorithms. However, access to good quality datasets is limited by thetechnical difficulty of data acquisition and large-scale sharing of healthcaredata is hindered by strict ethical restrictions. Data synthesis algorithms,which generate data with a similar distribution as real clinical data, canserve as a potential solution to address the scarcity of good quality dataduring the development of trustworthy AI. However, state-of-the-art datasynthesis algorithms, especially deep learning algorithms, focus more onimaging data while neglecting the synthesis of non-imaging healthcare data,including clinical measurements, medical signals and waveforms, and electronichealthcare records (EHRs). Thus, in this paper, we will review the synthesisalgorithms, particularly for non-imaging medical data, with the aim ofproviding trustworthy AI in this domain. This tutorial-styled review paper willprovide comprehensive descriptions of non-imaging medical data synthesis onaspects including algorithms, evaluations, limitations and future researchdirections.
Nan Y, Ser JD, Tang Z, et al., 2022, Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation
Airway segmentation is crucial for the examination, diagnosis, and prognosisof lung diseases, while its manual delineation is unduly burdensome. Toalleviate this time-consuming and potentially subjective manual procedure,researchers have proposed methods to automatically segment airways fromcomputerized tomography (CT) images. However, some small-sized airway branches(e.g., bronchus and terminal bronchioles) significantly aggravate thedifficulty of automatic segmentation by machine learning models. In particular,the variance of voxel values and the severe data imbalance in airway branchesmake the computational module prone to discontinuous and false-negativepredictions. especially for cohorts with different lung diseases. Attentionmechanism has shown the capacity to segment complex structures, while fuzzylogic can reduce the uncertainty in feature representations. Therefore, theintegration of deep attention networks and fuzzy theory, given by the fuzzyattention layer, should be an escalated solution for better generalization androbustness. This paper presents an efficient method for airway segmentation,comprising a novel fuzzy attention neural network and a comprehensive lossfunction to enhance the spatial continuity of airway segmentation. The deepfuzzy set is formulated by a set of voxels in the feature map and a learnableGaussian membership function. Different from the existing attention mechanism,the proposed channel-specific fuzzy attention addresses the issue ofheterogeneous features in different channels. Furthermore, a novel evaluationmetric is proposed to assess both the continuity and completeness of airwaystructures. The efficiency, generalization and robustness of the proposedmethod have been proved by training on normal lung disease while testing ondatasets of lung cancer, COVID-19 and pulmonary fibrosis.
Li Y, Zhang Y, Liu J-Y, et al., 2022, Global transformer and dual local attention network via deep-shallow hierarchical feature fusion for retinal vessel segmentation, IEEE Transactions on Cybernetics, ISSN: 2168-2275
Clinically, retinal vessel segmentation is a significant step in the diagnosis of fundus diseases. However, recent methods generally neglect the difference of semantic information between deep and shallow features, which fail to capture the global and local characterizations in fundus images simultaneously, resulting in the limited segmentation performance for fine vessels. In this paper, a global transformer and dual local attention network via deep-shallow hierarchical feature fusion (GT-DLA-dsHFF) are investigated to solve the above limitations. First, the global transformer (GT) is developed to integrate the global information in the retinal image, which effectively captures the long-distance dependence between pixels, alleviating the discontinuity of blood vessels in the segmentation results. Second, the dual local attention (DLA), which is constructed using dilated convolutions with varied dilation rates, unsupervised edge detection, and squeeze-excitation block, is proposed to extract local vessel information, consolidating the edge details in the segmentation result. Finally, a novel deepshallow hierarchical feature fusion (dsHFF) algorithm is studied to fuse the features in different scales in the deep learning framework respectively, which can mitigate the attenuation of valid information in the process of feature fusion. We verified the GT-DLA-dsHFF on four typical fundus image datasets. The experimental results demonstrate our GT-DLA-dsHFF achieves superior performance against the current methods and detailed discussions verify the efficacy of the proposed three modules. Segmentation results on diseased images show the robustness of our proposed GT-DLA-dsHFF. Our codes will be available on https://github.com/YangLibuaa/GT-DLA-dsHFF.
Yan B, Li Y, Li L, et al., 2022, Quantifying the impact of Pyramid Squeeze Attention mechanism and filtering approaches on Alzheimer's disease classification, COMPUTERS IN BIOLOGY AND MEDICINE, Vol: 148, ISSN: 0010-4825
- Author Web Link
- Cite
- Citations: 1
Huang J, Fang Y, Wu Y, et al., 2022, Swin Transformer for Fast MRI, Neurocomputing, Vol: 493, Pages: 281-304, ISSN: 0925-2312
Magnetic resonance imaging (MRI) is an important non-invasive clinical tool that can produce high-resolution and reproducible images. However, a long scanning time is required for high-quality MR images, which leads to exhaustion and discomfort of patients, inducing more artefacts due to voluntary movements of the patients and involuntary physiological movements. To accelerate the scanning process, methods by k-space undersampling and deep learning based reconstruction have been popularised. This work introduced SwinMR, a novel Swin transformer based method for fast MRI reconstruction. The whole network consisted of an input module (IM), a feature extraction module (FEM) and an output module (OM). The IM and OM were 2D convolutional layers and the FEM was composed of a cascaded of residual Swin transformer blocks (RSTBs) and 2D convolutional layers. The RSTB consisted of a series of Swin transformer layers (STLs). The shifted windows multi-head self-attention (W-MSA/SW-MSA) of STL was performed in shifted windows rather than the multi-head self-attention (MSA) of the original transformer in the whole image space. A novel multi-channel loss was proposed by using the sensitivity maps, which was proved to reserve more textures and details. We performed a series of comparative studies and ablation studies in the Calgary-Campinas public brain MR dataset and conducted a downstream segmentation experiment in the Multi-modal Brain Tumour Segmentation Challenge 2017 dataset. The results demonstrate our SwinMR achieved high-quality reconstruction compared with other benchmark methods, and it shows great robustness with different undersampling masks, under noise interruption and on different datasets. The code is publicly available at https://github.com/ayanglab/SwinMR.
Zhou Z, Gao Y, Zhang W, et al., 2022, Artificial intelligence-based full aortic CT angiography imaging with ultra-low-dose contrast medium: a preliminary study, EUROPEAN RADIOLOGY, Vol: 33, Pages: 678-689, ISSN: 0938-7994
- Author Web Link
- Cite
- Citations: 1
Nan Y, Li F, Tang P, et al., 2022, Automatic fine-grained glomerular lesion recognition in kidney pathology, Pattern Recognition, Vol: 127, ISSN: 0031-3203
Recognition of glomeruli lesions is the key for diagnosis and treatment planning in kidney pathology; however, the coexisting glomerular structures such as mesangial regions exacerbate the difficulties of this task. In this paper, we introduce a scheme to recognize fine-grained glomeruli lesions from whole slide images. First, a focal instance structural similarity loss is proposed to drive the model to locate all types of glomeruli precisely. Then an Uncertainty Aided Apportionment Network is designed to carry out the fine-grained visual classification without bounding-box annotations. This double branch-shaped structure extracts common features of the child class from the parent class and produces the uncertainty factor for reconstituting the training dataset. Results of slide-wise evaluation illustrate the effectiveness of the entire scheme, with an 8–22% improvement of the mean Average Precision compared with remarkable detection methods. The comprehensive results clearly demonstrate the effectiveness of the proposed method.
Kondylakis H, Ciarrocchi E, Cerda-Alberich L, et al., 2022, Position of the AI for Health Imaging (AI4HI) network on metadata models for imaging biobanks., Eur Radiol Exp, Vol: 6
A huge amount of imaging data is becoming available worldwide and an incredible range of possible improvements can be provided by artificial intelligence algorithms in clinical care for diagnosis and decision support. In this context, it has become essential to properly manage and handle these medical images and to define which metadata have to be considered, in order for the images to provide their full potential. Metadata are additional data associated with the images, which provide a complete description of the image acquisition, curation, analysis, and of the relevant clinical variables associated with the images. Currently, several data models are available to describe one or more subcategories of metadata, but a unique, common, and standard data model capable of fully representing the heterogeneity of medical metadata has not been yet developed. This paper reports the state of the art on metadata models for medical imaging, the current limitations and further developments, and describes the strategy adopted by the Horizon 2020 "AI for Health Imaging" projects, which are all dedicated to the creation of imaging biobanks.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.