Accurate segmentation of liver tumor from multi-modality non-contrast images using a dual-stream multi-level fusion framework.

The use of multi-modality non-contrast images (i.e., T1FS, T2FS and DWI) for segmenting liver tumors provides a solution by eliminating the use of contrast agents and is crucial for clinical diagnosis. However, this remains a challenging task to discover the most useful information to fuse multi-modality images for accurate segmentation due to inter-modal interference. In this paper, we propose a dual-stream multi-level fusion framework (DM-FF) to, for the first time, accurately segment liver tumors from non-contrast multi-modality images directly. Our DM-FF first designs an attention-based encoder-decoder to effectively extract multi-level feature maps corresponding to a specified representation of each modality. Then, DM-FF creates two types of fusion modules, in which a module fuses learned features to obtain a shared representation across multi-modality images to exploit commonalities and improve the performance, and a module fuses the decision evidence of segment to discover differences between modalities to prevent interference caused by modality's conflict. By integrating these three components, DM-FF enables multi-modality non-contrast images to cooperate with each other and enables an accurate segmentation. Evaluation on 250 patients including different types of tumors from two MRI scanners, DM-FF achieves a Dice of 81.20%, and improves performance (Dice by at least 11%) when comparing the eight state-of-the-art segmentation architectures. The results indicate that our DM-FF significantly promotes the development and deployment of non-contrast liver tumor technology.

Prediction of Freezing of Gait in Parkinson's disease based on multi-channel time-series neural network.

Freezing of Gait (FOG) is a noticeable symptom of Parkinson's disease, like being stuck in place and increasing the risk of falls. The wearable multi-channel sensor system is an efficient method to predict and monitor the FOG, thus warning the wearer to avoid falls and improving the quality of life. However, the existing approaches for the prediction of FOG mainly focus on a single sensor system and cannot handle the interference between multi-channel wearable sensors. Hence, we propose a novel multi-channel time-series neural network (MCT-Net) approach to merge multi-channel gait features into a comprehensive prediction framework, alerting patients to FOG symptoms in advance. Owing to the causal distributed convolution, MCT-Net is a real-time method available to give optimal prediction earlier and implemented in remote devices. Moreover, intra-channel and inter-channel transformers of MCT-Net extract and integrate different sensor position features into a unified deep learning model. Compared with four other state-of-the-art FOG prediction baselines, the proposed MCT-Net obtains 96.21% in accuracy and 80.46% in F1-score on average 2 s before FOG occurrence, demonstrating the superiority of MCT-Net.

A coronary CT angiography-derived myocardial radiomics model for predicting adverse outcomes in chronic myocardial infarction.

BACKGROUND: The prognostic efficacy of a coronary computed tomography angiography (CCTA)-derived myocardial radiomics model in patients with chronic myocardial infarction (MI) is unclear. METHODS: In this retrospective study, a cohort of 236 patients with chronic MI who underwent both CCTA and cardiac magnetic resonance (CMR) examinations within 30 days were enrolled and randomly divided into training and testing datasets at a ratio of 7:3. The clinical endpoints were major adverse cardiovascular events (MACE), defined as all-cause death, myocardial reinfarction and heart failure hospitalization. The entire three-dimensional left ventricular myocardium on CCTA images was segmented as the volume of interest for the extraction of radiomics features. Five models, namely the clinical model, CMR model, clinical+CMR model, CCTA-radiomics model, and clinical+CCTA-radiomics model, were constructed using multivariate Cox regression. The prognostic performances of these models were evaluated through receiver operating characteristic curve analysis and the index of concordance (C-index). RESULTS: Fifty-one (20.16%) patients experienced MACE during a median follow-up of 1439.5 days. The predictive performance of the CCTA-radiomics model surpassed that of the clinical model, CMR model, and clinical+CMR model in both the training (area under the curve (AUC) of 0.904 vs. 0.691, 0.764, 0.785; C-index of 0.88 vs. 0.71, 0.75, 0.76, all p values <0.001) and testing (AUC of 0.893 vs. 0.704, 0.851, 0.888; C-index of 0.86 vs. 0.73, 0.85, 0.85, all p values <0.05) datasets. CONCLUSIONS: The CCTA-based myocardial radiomics model is a valuable tool for predicting adverse outcomes in chronic MI, providing incremental value to conventional clinical and CMR parameters.

Constraint-Aware Learning for Fractional Flow Reserve Pullback Curve Estimation from Invasive Coronary Imaging.

Estimation of the fractional flow reserve (FFR) pullback curve from invasive coronary imaging is important for the intraoperative guidance of coronary intervention. Machine/deep learning has been proven effective in FFR pullback curve estimation. However, the existing methods suffer from inadequate incorporation of intrinsic geometry associations and physics knowledge. In this paper, we propose a constraint-aware learning framework to improve the estimation of the FFR pullback curve from invasive coronary imaging. It incorporates both geometrical and physical constraints to approximate the relationships between the geometric structure and FFR values along the coronary artery centerline. Our method also leverages the power of synthetic data in model training to reduce the collection costs of clinical data. Moreover, to bridge the domain gap between synthetic and real data distributions when testing on real-world imaging data, we also employ a diffusion-driven test-time data adaptation method that preserves the knowledge learned in synthetic data. Specifically, this method learns a diffusion model of the synthetic data distribution and then projects real data to the synthetic data distribution at test time. Extensive experimental studies on a synthetic dataset and a real-world dataset of 382 patients covering three imaging modalities have shown the better performance of our method for FFR estimation of stenotic coronary arteries, compared with other machine/deep learning-based FFR estimation models and computational fluid dynamics-based model. The results also provide high agreement and correlation between the FFR predictions of our method and the invasively measured FFR values. The plausibility of FFR predictions along the coronary artery centerline is also validated.

Non-invasive Assessment of Coronary Microvascular Dysfunction Using Vascular Deformation-Based Flow Estimation.

OBJECTIVE: Non-invasive computation of the index of microcirculatory resistance from coronary computed tomography angiography (CTA), referred to as IMR[Formula: see text], is a promising approach for quantitative assessment of coronary microvascular dysfunction (CMD). However, the computation of IMR[Formula: see text] remains an important unresolved problem due to its high requirement for the accuracy of coronary blood flow. Existing CTA-based methods for estimating coronary blood flow rely on physiological assumption models to indirectly identify, which leads to inadequate personalization of total and vessel-specific flow. METHODS: To overcome this challenge, we propose a vascular deformation-based flow estimation (VDFE) model to directly estimate coronary blood flow for reliable IMR[Formula: see text] computation. Specifically, we extract the vascular deformation of each vascular segment from multi-phase CTA. The concept of inverse problem solving is applied to implicitly derive coronary blood flow based on the physical constraint relationship between blood flow and vascular deformation. The vascular deformation constraints imposed on each segment within the vascular structure ensure sufficient individualization of coronary blood flow. RESULTS: Experimental studies on 106 vessels collected from 89 subjects demonstrate the validity of our VDFE, achieving an IMR[Formula: see text] accuracy of 82.08 %. The coronary blood flow estimated by VDFE has better reliability than the other four existing methods. CONCLUSION: Our proposed VDFE is an effective approach to non-invasively compute IMR[Formula: see text] with excellent diagnostic performance. SIGNIFICANCE: The VDFE has the potential to serve as a safe, effective, and cost-effective clinical tool for guiding CMD clinical treatment and assessing prognosis.

Quantification of functional hemodynamics in aortic valve disease using cardiac computed tomography angiography.

BACKGROUND AND OBJECTIVE: Cardiac computed tomography angiography (CTA) is the preferred modality for preoperative planning in aortic valve stenosis. However, it cannot provide essential functional hemodynamic data, specifically the mean transvalvular pressure gradient (MPG). This study aims to introduce a computational fluid dynamics (CFD) approach for MPG quantification using cardiac CTA, enhancing its diagnostic value. METHODS: Twenty patients underwent echocardiography, cardiac CTA, and invasive catheterization for pressure measurements. Cardiac CTA employed retrospective electrocardiographic gating to capture multi-phase data throughout the cardiac cycle. We segmented the region of interest based on mid-systolic phase cardiac CTA images. Then, we computed the average flow velocity into the aorta as the inlet boundary condition, using variations in end-diastolic and end-systolic left ventricular volume. Finally, we conducted CFD simulations using a steady-state model to obtain pressure distribution within the computational domain, allowing for the derivation of MPG. RESULTS: The mean value of MPG, measured via invasive catheterization (MPGInv), echocardiography (MPGEcho), and cardiac CTA (MPGCT), were 51.3 ± 28.4 mmHg, 44.8 ± 19.5 mmHg, and 55.8 ± 25.6 mmHg, respectively. In comparison to MPGInv, MPGCT exhibited a higher correlation of 0.91, surpassing that of MPGEcho, which was 0.82. Moreover, the limits of agreement for MPGCT ranged from -27.7 to 18.7, outperforming MPGEcho, which ranged from -40.1 to 18.0. CONCLUSIONS: The proposed method based on cardiac CTA enables the evaluation of MPG for aortic valve stenosis patients. In future clinical practice, a single cardiac CTA examination can comprehensively assess both the anatomical and functional hemodynamic aspects of aortic valve disease.

Frequency-Enhanced Geometric-Constrained Reconstruction for Localizing Myocardial Infarction in 12-Lead Electrocardiograms.

Determining the location of myocardial infarction is crucial for clinical management and therapeutic stratagem. However, existing diagnostic tools either sacrifice ease of use or are limited by their spatial resolution. Addressing this, we aim to refine myocardial infarction localization via surface potential reconstruction of the ventricles in 12-lead electrocardiograms (ECG). A notable obstacle is the ill-posed nature of such reconstructions. To overcome this, we introduce the frequency-enhanced geometric-constrained iterative network (FGIN). FGIN begins by mining the latent features from ECG data across both time and frequency domains. Subsequently, it increases the data dimensionality of ECG and captures intricate features using convolutional layers. Finally, FGIN incorporates ventricular geometry as a constraint on surface potential distribution. It allocates variable weights to distinct edges. Experimental validation of FGIN confirms its efficacy over synthetic and clinical datasets. On the synthetic dataset, FGIN outperforms seven existing reconstruction methods, attaining the highest Pearson Correlation Coefficient of 0.8624, the lowest Root Mean Square Error of 0.1548, and the highest Structural Similarity Index Measure of 0.7988. On the clinical public dataset (2007 PhysioNet/Computers in Cardiology Challenge), FGIN achieves better localization results than other approaches, according to the clinical standard 17-segment model, achieving an average Segment Overlap of 87.2%. Clinical trials on 50 patients demonstrate FGIN's effectiveness, showing an average accuracy of 91.6% and an average Segment Overlap of 88.2%.

Distraction-aware hierarchical learning for vascular structure segmentation in intravascular ultrasound images.

Vascular structure segmentation in intravascular ultrasound (IVUS) images plays an important role in pre-procedural evaluation of percutaneous coronary intervention (PCI). However, vascular structure segmentation in IVUS images has the challenge of structure-dependent distractions. Structure-dependent distractions are categorized into two cases, structural intrinsic distractions and inter-structural distractions. Traditional machine learning methods often rely solely on low-level features, overlooking high-level features. This way limits the generalization of these methods. The existing semantic segmentation methods integrate low-level and high-level features to enhance generalization performance. But these methods also introduce additional interference, which is harmful to solving structural intrinsic distractions. Distraction cue methods attempt to address structural intrinsic distractions by removing interference from the features through a unique decoder. However, they tend to overlook the problem of inter-structural distractions. In this paper, we propose distraction-aware hierarchical learning (DHL) for vascular structure segmentation in IVUS images. Inspired by distraction cue methods for removing interference in a decoder, the DHL is designed as a hierarchical decoder that gradually removes structure-dependent distractions. The DHL includes global perception process, distraction perception process and structural perception process. The global perception process and distraction perception process remove structural intrinsic distractions then the structural perception process removes inter-structural distractions. In the global perception process, the DHL searches for the coarse structural region of the vascular structures on the slice of IVUS sequence. In the distraction perception process, the DHL progressively refines the coarse structural region of the vascular structures to remove structural distractions. In the structural perception process, the DHL detects regions of inter-structural distractions in fused structure features then separates them. Extensive experiments on 361 subjects show that the DHL is effective (e.g., the average Dice is greater than 0.95), and superior to ten state-of-the-art IVUS vascular structure segmentation methods.

Embedding Tasks Into the Latent Space: Cross-Space Consistency for Multi-Dimensional Analysis in Echocardiography.

Multi-dimensional analysis in echocardiography has attracted attention due to its potential for clinical indices quantification and computer-aided diagnosis. It can utilize various information to provide the estimation of multiple cardiac indices. However, it still has the challenge of inter-task conflict. This is owing to regional confusion, global abnormalities, and time-accumulated errors. Task mapping methods have the potential to address inter-task conflict. However, they may overlook the inherent differences between tasks, especially for multi-level tasks (e.g., pixel-level, image-level, and sequence-level tasks). This may lead to inappropriate local and spurious task constraints. We propose cross-space consistency (CSC) to overcome the challenge. The CSC embeds multi-level tasks to the same-level to reduce inherent task differences. This allows multi-level task features to be consistent in a unified latent space. The latent space extracts task-common features and constrains the distance in these features. This constrains the task weight region that satisfies multiple task conditions. Extensive experiments compare the CSC with fifteen state-of-the-art echocardiographic analysis methods on five datasets (10,908 patients). The result shows that the CSC can provide left ventricular (LV) segmentation, (DSC = 0.932), keypoint detection (MAE = 3.06mm), and keyframe identification (accuracy = 0.943). These results demonstrate that our method can provide a multi-dimensional analysis of cardiac function and is robust in large-scale datasets.

Iterative Residual Optimization Network for Limited-Angle Tomographic Reconstruction.

Limited-angle tomographic reconstruction is one of the typical ill-posed inverse problems, leading to edge divergence with degraded image quality. Recently, deep learning has been introduced into image reconstruction and achieved great results. However, existing deep reconstruction methods have not fully explored data consistency, resulting in poor performance. In addition, deep reconstruction methods are still mathematically inexplicable and unstable. In this work, we propose an iterative residual optimization network (IRON) for limited-angle tomographic reconstruction. First, a new optimization objective function is established to overcome false negative and positive artifacts induced by limited-angle measurements. We integrate neural network priors as a regularizer to explore deep features within residual data. Furthermore, the block-coordinate descent is employed to achieve a novel iterative framework. Second, a convolution assisted transformer is carefully elaborated to capture both local and long-range pixel interactions simultaneously. Regarding the visual transformer, the multi-head attention is further redesigned to reduce computational costs and protect reconstructed image features. Third, based on the relative error convergence property of the convolution assisted transformer, a mathematical convergence analysis is also provided for our IRON. Both numerically simulated and clinically collected real cardiac datasets are employed to validate the effectiveness and advantages of the proposed IRON. The results show that IRON outperforms other state-of-the-art methods.

Cellular nucleus image-based smarter microscope system for single cell analysis.

Cell imaging technology is undoubtedly a powerful tool for studying single-cell heterogeneity due to its non-invasive and visual advantages. It covers microscope hardware, software, and image analysis techniques, which are hindered by low throughput owing to abundant hands-on time and expertise. Herein, a cellular nucleus image-based smarter microscope system for single-cell analysis is reported to achieve high-throughput analysis and high-content detection of cells. By combining the hardware of an automatic fluorescence microscope and multi-object recognition/acquisition software, we have achieved more advanced process automation with the assistance of Robotic Process Automation (RPA), which realizes a high-throughput collection of single-cell images. Automated acquisition of single-cell images has benefits beyond ease and throughout and can lead to uniform standard and higher quality images. We further constructed a single-cell image database-based convolutional neural network (Efficient Convolutional Neural Network, E-CNN) exceeding 20618 single-cell nucleus images. Computational analysis of large and complex data sets enhances the content and efficiency of single-cell analysis with the assistance of Artificial Intelligence (AI), which breaks through the super-resolution microscope's hardware limitation, such as specialized light sources with specific wavelengths, advanced optical components, and high-performance graphics cards. Our system can identify single-cell nucleus images that cannot be artificially distinguished with an accuracy of 95.3%. Overall, we build an ordinary microscope into a high-throughput analysis and high-content smarter microscope system, making it a candidate tool for Imaging cytology.

A Deformable Constraint Transport Network for Optimal Aortic Segmentation From CT Images.

Aortic segmentation from computed tomography (CT) is crucial for facilitating aortic intervention, as it enables clinicians to visualize aortic anatomy for diagnosis and measurement. However, aortic segmentation faces the challenge of variable geometry in space, as the geometric diversity of different diseases and the geometric transformations that occur between raw and measured images. Existing constraint-based methods can potentially solve the challenge, but they are hindered by two key issues: inaccurate definition of properties and inappropriate topology of transformation in space. In this paper, we propose a deformable constraint transport network (DCTN). The DCTN adaptively extracts aortic features to define intra-image constrained properties and guides topological implementation in space to constrain inter-image geometric transformation between raw and curved planar reformation (CPR) images. The DCTN contains a deformable attention extractor, a geometry-aware decoder and an optimal transport guider. The extractor generates variable patches that preserve semantic integrity and long-range dependency in long-sequence images. The decoder enhances the perception of geometric texture and semantic features, particularly for low-intensity aortic coarctation and false lumen, which removes background interference. The guider explores the geometric discrepancies between raw and CPR images, constructs probability distributions of discrepancies, and matches them with inter-image transformation to guide geometric topology in space. Experimental studies on 267 aortic subjects and four public datasets show the superiority of our DCTN over 23 methods. The results demonstrate DCTN's advantages in aortic segmentation for different types of aortic disease, for different aortic segments, and in the measurement of clinical indexes.

Deep Learning-based Prediction of Percutaneous Recanalization in Chronic Total Occlusion Using Coronary CT Angiography.

Background CT is helpful in guiding the revascularization of chronic total occlusion (CTO), but manual prediction scores of percutaneous coronary intervention (PCI) success have challenges. Deep learning (DL) is expected to predict success of PCI for CTO lesions more efficiently. Purpose To develop a DL model to predict guidewire crossing and PCI outcomes for CTO using coronary CT angiography (CCTA) and evaluate its performance compared with manual prediction scores. MATERIALS AND METHODS: Participants with CTO lesions were prospectively identified from one tertiary hospital between January 2018 and December 2021 as the training set to develop the DL prediction model for PCI of CTO, with fivefold cross validation. The algorithm was tested using an external test set prospectively enrolled from three tertiary hospitals between January 2021 and June 2022 with the same eligibility criteria. All participants underwent preprocedural CCTA within 1 month before PCI. The end points were guidewire crossing within 30 minutes and PCI success of CTO.Results A total of 534 participants (mean age, 57.7 years ± 10.8 [SD]; 417 [78.1%] men) with 565 CTO lesions were included. In the external test set (186 participants with 189 CTOs), the DL model saved 85.0% of the reconstruction and analysis time of manual scores (mean, 73.7 seconds vs 418.2-466.9 seconds) and had higher accuracy than manual scores in predicting guidewire crossing within 30 minutes (DL, 91.0%; CT Registry of Chronic Total Occlusion Revascularization, 61.9%; Korean Multicenter CTO CT Registry [KCCT], 68.3%; CCTA-derived Multicenter CTO Registry of Japan (J-CTO), 68.8%; P < .05) and PCI success (DL, 93.7%; KCCT, 74.6%; J-CTO, 75.1%; P < .05). For DL, the area under the receiver operating characteristic curve was 0.97 (95% CI: 0.89, 0.99) for the training test set and 0.96 (95% CI: 0.90, 0.98) for the external test set. Conclusion The DL prediction model accurately predicted the percutaneous recanalization outcomes of CTO lesions and increased the efficiency of noninvasively grading the difficulty of PCI. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Pundziute-do Prado in this issue.

Explainable Classification of Benign-Malignant Pulmonary Nodules With Neural Networks and Information Bottleneck.

Computerized tomography (CT) is a clinically primary technique to differentiate benign-malignant pulmonary nodules for lung cancer diagnosis. Early classification of pulmonary nodules is essential to slow down the degenerative process and reduce mortality. The interactive paradigm assisted by neural networks is considered to be an effective means for early lung cancer screening in large populations. However, some inherent characteristics of pulmonary nodules in high-resolution CT images, e.g., diverse shapes and sparse distribution over the lung fields, have been inducing inaccurate results. On the other hand, most existing methods with neural networks are dissatisfactory from a lack of transparency. In order to overcome these obstacles, a united framework is proposed, including the classification and feature visualization stages, to learn distinctive features and provide visual results. Specifically, a bilateral scheme is employed to synchronously extract and aggregate global-local features in the classification stage, where the global branch is constructed to perceive deep-level features and the local branch is built to focus on the refined details. Furthermore, an encoder is built to generate some features, and a decoder is constructed to simulate decision behavior, followed by the information bottleneck viewpoint to optimize the objective. Extensive experiments are performed to evaluate our framework on two publicly available datasets, namely, 1) the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) and 2) the Lung and Colon Histopathological Image Dataset (LC25000). For instance, our framework achieves 92.98% accuracy and presents additional visualizations on the LIDC. The experiment results show that our framework can obtain outstanding performance and is effective to facilitate explainability. It also demonstrates that this united framework is a serviceable tool and further has the scalability to be introduced into clinical research.

Vessel Contour Detection in Intracoronary Images via Bilateral Cross-Domain Adaptation.

Vessel contour detection (VCD) in intravascular images is important for the quantitative assessment of vessels. However, it is still a challenging task due to a high degree of morphology variability. Images from a single modality lack sufficient information on the vessel morphology due to the natural limitation of the imaging capability. Therefore, the single-modality VCD methods have difficulty extracting sufficient morphological information. Cross-modality methods have the potential to overcome morphology variability by extracting more information from different modalities. However, they still face the difficulty of the domain discrepancy, i.e., feature space discrepancy and label space inconsistency. In this paper, we aim to address the domain discrepancy for VCD. To overcome label space inconsistency, our method divides the label space into private label space and shared label space. It constructs subdomains for the private label space and the shared label space, and minimizes the task risk at the subdomain level. To overcome feature space discrepancy, it extracts domain-invariant features via domain adaptation between the subdomains. Finally, it uses the domain-invariant features as auxiliary information for each subdomain. Extensive experiments on 130 IVUS sequences (135663 images) and 124 OCT sequences (39857 images) show that our method is effective (e.g., the Dice index [Formula: see text] 0.949), and superior to the nineteen state-of-the-art VCD methods.

Survival prediction of heart failure patients using motion-based analysis method.

BACKGROUND AND OBJECTIVE: Survival prediction of heart failure patients is critical to improve the prognostic management of the cardiovascular disease. The existing survival prediction methods focus on the clinical information while lacking the cardiac motion information. we propose a motion-based analysis method to predict the survival risk of heart failure patients for aiding clinical diagnosis and treatment. METHODS: We propose a motion-based analysis method for survival prediction of heart failure patients. First, our method proposes the hierarchical spatial-temporal structure to capture the myocardial border. It promotes the model discrimination on border features. Second, our method explores the dense optical flow structure to capture motion fields. It improves the tracking capability on cardiac images. The cardiac motion information is obtained by fusing boundary information and motion fields of cardiac images. Finally, our method proposes the multi-modality deep-cox structure to predict the survival risk of heart failure patients. It improves the survival probability of heart failure patients. RESULTS: The motion-based analysis method is confirmed to be able to improve the survival prediction of heart failure patients. The precision, recall, F1-score, and C-index are 0.8519, 0.8333, 0.8425, and 0.8478, respectively, which is superior to other state-of-the-art methods. CONCLUSIONS: The experimental results show that the proposed model can effectively predict survival risk of heart failure patients. It facilitates the application of robust clinical treatment strategies.

Reliable Mutual Distillation for Medical Image Segmentation Under Imperfect Annotations.

Convolutional neural networks (CNNs) have made enormous progress in medical image segmentation. The learning of CNNs is dependent on a large amount of training data with fine annotations. The workload of data labeling can be significantly relieved via collecting imperfect annotations which only match the underlying ground truths coarsely. However, label noises which are systematically introduced by the annotation protocols, severely hinders the learning of CNN-based segmentation models. Hence, we devise a novel collaborative learning framework in which two segmentation models cooperate to combat label noises in coarse annotations. First, the complementary knowledge of two models is explored by making one model clean training data for the other model. Secondly, to further alleviate the negative impact of label noises and make sufficient usage of the training data, the specific reliable knowledge of each model is distilled into the other model with augmentation-based consistency constraints. A reliability-aware sample selection strategy is incorporated for guaranteeing the quality of the distilled knowledge. Moreover, we employ joint data and model augmentations to expand the usage of reliable knowledge. Extensive experiments on two benchmarks showcase the superiority of our proposed method against existing methods under annotations with different noise levels. For example, our approach can improve existing methods by nearly 3% DSC on the lung lesion segmentation dataset LIDC-IDRI under annotations with 80% noise ratio. Code is available at: https://github.com/Amber-Believe/ReliableMutualDistillation.

Hierarchical Perception Adversarial Learning Framework for Compressed Sensing MRI.

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.

Motion estimation based on projective information disentanglement for 3D reconstruction of rotational coronary angiography.

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.

Multiple Adversarial Learning Based Angiography Reconstruction for Ultra-Low-Dose Contrast Medium CT.

Iodinated contrast medium (ICM) dose reduction is beneficial for decreasing potential health risk to renal-insufficiency patients in CT scanning. Due to the low-intensity 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 within domain simultaneously. Finally, an adaptive fusion module by combining multi-scale 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.