Magnetic Resonance Data Sets Research Articles

Deep learning super-resolution reconstruction for fast and high-quality cine cardiovascular magnetic resonance.

To compare standard-resolution balanced steady-state free precession (bSSFP) cine images with cine images acquired at low resolution but reconstructed with a deep learning (DL) super-resolution algorithm. Cine cardiovascular magnetic resonance (CMR) datasets (short-axis and 4-chamber views) were prospectively acquired in healthy volunteers and patients at normal (cineNR: 1.89 × 1.96 mm2, reconstructed at 1.04 × 1.04 mm2) and at a low-resolution (2.98 × 3.00 mm2, reconstructed at 1.04 × 1.04 mm2). Low-resolution images were reconstructed using compressed sensing DL denoising and resolution upscaling (cineDL). Left ventricular ejection fraction (LVEF), end-diastolic volume index (LVEDVi), and strain were assessed. Apparent signal-to-noise (aSNR) and contrast-to-noise ratios (aCNR) were calculated. Subjective image quality was assessed on a 5-point Likert scale. Student's paired t-test, Wilcoxon matched-pairs signed-rank-test, and intraclass correlation coefficient (ICC) were used for statistical analysis. Thirty participants were analyzed (37 ± 16 years; 20 healthy volunteers and 10 patients). Short-axis views whole-stack acquisition duration of cineDL was shorter than cineNR (57.5 ± 8.7 vs 98.7 ± 12.4 s; p < 0.0001). No differences were noted for: LVEF (59 ± 7 vs 59 ± 7%; ICC: 0.95 [95% confidence interval: 0.94, 0.99]; p = 0.17), LVEDVi (85.0 ± 13.5 vs 84.4 ± 13.7 mL/m2; ICC: 0.99 [0.98, 0.99]; p = 0.12), longitudinal strain (-19.5 ± 4.3 vs -19.8 ± 3.9%; ICC: 0.94 [0.88, 0.97]; p = 0.52), short-axis aSNR (81 ± 49 vs 69 ± 38; p = 0.32), aCNR (53 ± 31 vs 45 ± 27; p = 0.33), or subjective image quality (5.0 [IQR 4.9, 5.0] vs 5.0 [IQR 4.7, 5.0]; p = 0.99). Deep-learning reconstruction of cine images acquired at a lower spatial resolution led to a decrease in acquisition times of 42% with shorter breath-holds without affecting volumetric results or image quality. Question Cine CMR acquisitions are time-intensive and vulnerable to artifacts. Findings Low-resolution upscaled reconstructions using DL super-resolution decreased acquisition times by 35-42% without a significant difference in volumetric results or subjective image quality. Clinical relevance DL super-resolution reconstructions of bSSFP cine images acquired at a lower spatial resolution reduce acquisition times while preserving diagnostic accuracy, improving the clinical feasibility of cine imaging by decreasing breath hold duration.

DAW-FA: Domain-aware adaptive weighting with fine-grain attention for unsupervised MRI harmonization

Magnetic resonance (MR) imaging often lacks standardized acquisition protocols across various sites, leading to contrast variations that reduce image quality and hinder automated analysis. MR harmonization improves consistency by integrating data from multiple sources, ensuring reproducible analysis. Recent advances leverage image-to-image translation and disentangled representation learning to decompose anatomical and contrast representations, achieving consistent cross-site harmonization. However, these methods face two significant drawbacks: imbalanced contrast availability during training affects adaptation performance, and insufficient utilization of spatial variability in local anatomical structures limits model adaptability to different sites. To address these challenges, we propose Domain-aware Adaptive Weighting with Fine-Grain Attention (DAW-FA) for Unsupervised MRI Harmonization. DAW-FA incorporates an adaptive weighting mechanism and enhanced self-attention to mitigate MR contrast imbalance during training and account for spatial variability in local anatomical structures. This facilitates robust cross-site harmonization without requiring paired inter-site images. We evaluated DAW-FA on MR datasets with varying scanners and acquisition protocols. Experimental results show DAW-FA outperforms existing methods, with an average increase of 1.92 ± 0.56 in Peak Signal-to-Noise Ratio (PSNR) and 0.023 ± 0.011 in Structural Similarity Index Measure (SSIM). Additionally, we demonstrate DAW-FA’s impact on downstream tasks: Alzheimer’s disease classification and whole-brain segmentation, highlighting its potential clinical relevance.

Explainable Reverse Verification of Goodness of Classification of MRI Images by Clinical Experts.

Radiology offers a presumptive diagnosis. The etiology of radiological errors are prevalent, recurrent, and multi-factorial. The pseudo-diagnostic conclusions can arise from varying factors such as, poor technique, failures of visual perception, lack of knowledge, and misjudgments. This retrospective and interpretive errors can influence and alter the Ground Truth (GT) of Magnetic Resonance (MR) imaging which in turn result in faulty class labeling. Wrong class labels can lead to erroneous training and illogical classification outcomes for Computer Aided Diagnosis (CAD) systems. This work aims at verifying and authenticating the accuracy and exactness of the GT of biomedical datasets which are extensively used in binary classification frameworks. Generally such datasets are labeled by only one radiologist. Our article adheres a hypothetical approach to generate few faulty iterations. An iteration here considers simulation of faulty radiologist's perspective in MR image labeling. To achieve this, we try to simulate radiologists who are subjected to human error while taking decision regarding the class labels. In this context, we swap the class labels randomly and force them to be faulty. The experiments are carried out on some iterations (with varying number of brain images) randomly created from the brain MR datasets. The experiments are carried out on two benchmark datasets DS-75 and DS-160 collected from Harvard Medical School website and one larger input pool of self-collected dataset NITR-DHH. To validate our work, average classification parameter values of faulty iterations are compared with that of original dataset. It is presumed that, the presented approach provides a potential solution to verify the genuineness and reliability of the GT of the MR datasets. This approach can be utilized as a standard technique to validate the correctness of any biomedical dataset.

Rapid simulation of two-dimensional spectra with correlated anisotropic dimensions.

A new algorithm has been developed to simulate two-dimensional (2D) spectra with correlated anisotropic frequencies faster and more accurately than previous methods. The technique uses finite-element numerical integration on the sphere and an interpolation scheme based on the Alderman-Solum-Grant algorithm. This method is particularly useful for numerical calculations of joint probability distribution functions involving quantities with a parametric orientation dependence. The technique's efficiency also allows for practical least-squares fitting of experimental 2D solid-state nuclear magnetic resonance (NMR) datasets. The simulation method is illustrated for select 2D NMR methods, and a least-squares analysis is demonstrated in the extraction of paramagnetic shift and quadrupolar coupling tensors and their relative orientation from the experimental shifting-d echo 2H NMR spectrum of a NiCl2 · 2D2O salt.

Spatial attention-based implicit neural representation for arbitrary reduction of MRI slice spacing

Magnetic resonance (MR) images collected in 2D clinical protocols typically have large inter-slice spacing, resulting in high in-plane resolution and reduced through-plane resolution. Super-resolution technique can enhance the through-plane resolution of MR images to facilitate downstream visualization and computer-aided diagnosis. However, most existing works train the super-resolution network at a fixed scaling factor, which is not friendly to clinical scenes of varying inter-slice spacing in MR scanning. Inspired by the recent progress in implicit neural representation, we propose a Spatial Attention-based Implicit Neural Representation (SA-INR) network for arbitrary reduction of MR inter-slice spacing. The SA-INR aims to represent an MR image as a continuous implicit function of 3D coordinates. In this way, the SA-INR can reconstruct the MR image with arbitrary inter-slice spacing by continuously sampling the coordinates in 3D space. In particular, a local-aware spatial attention operation is introduced to model nearby voxels and their affinity more accurately in a larger receptive field. Meanwhile, to improve the computational efficiency, a gradient-guided gating mask is proposed for applying the local-aware spatial attention to selected areas only. We evaluate our method on the public HCP-1200 dataset and the clinical knee MR dataset to demonstrate its superiority over other existing methods.

An effective and robust lattice Boltzmann model guided by atlas for hippocampal subregions segmentation.

Given the varying vulnerability of the rostral and caudal regions of the hippocampus to neuropathology in the Alzheimer's disease (AD) continuum, accurately assessing structural changes in these subregions is crucial for early AD detection. The development of reliable and robust automatic segmentation methods for hippocampal subregions (HS) is of utmostimportance. Our aim is to propose and validate a HS segmentation model that is both training-free and highly generalizable. This method should exhibit comparable accuracy and efficiency to state-of-the-art techniques. The segmented HS can serve as a biomarker for studying the progression ofAD. We utilized the functional magnetic resonance imaging of the Brain's Integrated Registration and Segmentation Tool (FIRST) to segment the entire hippocampus. By intersecting the segmentation results with the Brainnetome (BN) atlas, we obtained coarse segmentation of the four HS regions. This coarse segmentation was then employed as a shape prior term in the lattice Boltzmann (LB) model, as well as for initializing contours. Additionally, image gradients and local gray levels were integrated into the external force terms of the LB model to refine the coarse segmentation results. We assessed the segmentation accuracy of the model using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and evaluated the potential of the segmentation results as AD biomarkers on both the ADNI and Xuanwudatasets. The median Dice similarity coefficients (DSC) for the left caudal, right caudal, left rostral, and right rostral hippocampus were 0.87, 0.88, 0.88, and 0.89, respectively. The proportion of segmentation results with a DSC exceeding 0.8 was 77%, 78%, 77%, and 94% for the respective regions. In terms of volume, the correlation coefficients between the segmentation results of the four HS regions and the gold standard were 0.95, 0.93, 0.96, and 0.96, respectively. Regarding asymmetry, the correlation coefficient between the segmentation result's right caudal minus left caudal and the corresponding gold standard was 0.91, while for right rostral minus left rostral, it was 0.93. Over time, we observed a decline in the volumes of the four HS regions and the total hippocampal volume of mild cognitive impairment (MCI) converters. Analysis of inter-group differences revealed that, except for the right rostral region in the ADNI dataset, the p-values for the four HS regions in the normal controls (NC), MCI, and AD groups from both datasets were all below 0.05. The right caudal hippocampal volume demonstrated correlation coefficients of 0.47 and 0.43 with the mini-mental state examination (MMSE) and Montreal cognitive assessment (MoCA), respectively. Similarly, the left rostral hippocampal volume showed correlation coefficients of 0.50 and 0.58 with MMSE and MoCA,respectively. Our framework allows for direct application to different brain magnetic resonance (MR) datasets without the need for training. It eliminates the requirement for complex image preprocessing steps while achieving segmentation accuracy comparable to deep learning (DL) methods even with small sample sizes. Compared to traditional active contour models (ACM) and atlas-based methods, our approach exhibits significant speed advantages. The segmented HS regions hold promise as potential biomarkers for studying the progression ofAD.

Unified Multi-Modal Image Synthesis for Missing Modality Imputation.

Multi-modal medical images provide complementary soft-tissue characteristics that aid in the screening and diagnosis of diseases. However, limited scanning time, image corruption and various imaging protocols often result in incomplete multi-modal images, thus limiting the usage of multi-modal data for clinical purposes. To address this issue, in this paper, we propose a novel unified multi-modal image synthesis method for missing modality imputation. Our method overall takes a generative adversarial architecture, which aims to synthesize missing modalities from any combination of available ones with a single model. To this end, we specifically design a Commonality- and Discrepancy-Sensitive Encoder for the generator to exploit both modality-invariant and specific information contained in input modalities. The incorporation of both types of information facilitates the generation of images with consistent anatomy and realistic details of the desired distribution. Besides, we propose a Dynamic Feature Unification Module to integrate information from a varying number of available modalities, which enables the network to be robust to random missing modalities. The module performs both hard integration and soft integration, ensuring the effectiveness of feature combination while avoiding information loss. Verified on two public multi-modal magnetic resonance datasets, the proposed method is effective in handling various synthesis tasks and shows superior performance compared to previous methods.

Application of singular value decomposition analysis: Insights into the complex mechanisms of amyloidogenesis

Amyloidogenesis, with its multifaceted nature spanning from peptide self-assembly to membrane-mediated structural transitions, presents a significant challenge for the interdisciplinary scientific community. Here, we emphasize on how Singular Value Decomposition (SVD) can be employed to reveal hidden patterns and dominant modes of interaction that govern the complex process of amyloidogenesis. We first utilize SVD analysis on Circular Dichroism (CD) spectral datasets to identify the intermediate structural species emerging during peptide-membrane interactions and to determine binding constants more precisely than conventional methods. We investigate the monomer loss kinetics associated with peptide self-assembly using Nuclear Magnetic Resonance (NMR) dataset and determine the global kinetic parameters through SVD. Furthermore, we explore the seeded growth of amyloid fibrils by analyzing a time-dependent NMR dataset, shedding light on the kinetic intricacies of this process. Our analysis uncovers two distinct states in the aggregation of Aβ40 and pinpoints key residues responsible for this seeded growth. To strengthen our findings and enhance their robustness, we validate those using simulated data, thereby highlighting the physical interpretations derived from SVD. Overall, SVD analysis offers a model-free, global kinetic perspective, enabling the selection of optimal kinetic models. This study not only contributes valuable insights into the dynamics but also highlights the versatility of SVD in unravelling complex processes of amyloidogenesis.

The PREMISE database of 20 Macaca fascicularis PET/MRI brain images available for research

Non-human primate studies are unique in translational research, especially in neurosciences where neuroimaging approaches are the preferred methods used for cross-species comparative neurosciences. In this regard, neuroimaging database development and sharing are encouraged to increase the number of subjects available to the community, while limiting the number of animals used in research. Here we present a simultaneous positron emission tomography (PET)/magnetic resonance (MR) dataset of 20 Macaca fascicularis images structured according to the Brain Imaging Data Structure standards. This database contains multiple MR imaging sequences (anatomical, diffusion and perfusion imaging notably), as well as PET perfusion and inflammation imaging using respectively [15O]H2O and [11C]PK11195 radiotracers. We describe the pipeline method to assemble baseline data from various cohorts and qualitatively assess all the data using signal-to-noise and contrast-to-noise ratios as well as the median of intensity and the pseudo-noise-equivalent-count rate (dynamic and at maximum) for PET data. Our study provides a detailed example for quality control integration in preclinical and translational PET/MR studies with the aim of increasing reproducibility. The PREMISE database is stored and available through the PRIME-DE consortium repository.

HACA3: A unified approach for multi-site MR image harmonization.

The lack of standardization and consistency of acquisition is a prominent issue in magnetic resonance (MR) imaging. This often causes undesired contrast variations in the acquired images due to differences in hardware and acquisition parameters. In recent years, image synthesis-based MR harmonization with disentanglement has been proposed to compensate for the undesired contrast variations. The general idea is to disentangle anatomy and contrast information from MR images to achieve cross-site harmonization. Despite the success of existing methods, we argue that major improvements can be made from three aspects. First, most existing methods are built upon the assumption that multi-contrast MR images of the same subject share the same anatomy. This assumption is questionable, since different MR contrasts are specialized to highlight different anatomical features. Second, these methods often require a fixed set of MR contrasts for training (e.g., both T1-weighted and T2-weighted images), limiting their applicability. Lastly, existing methods are generally sensitive to imaging artifacts. In this paper, we present Harmonization with Attention-based Contrast, Anatomy, and Artifact Awareness (HACA3), a novel approach to address these three issues. HACA3 incorporates an anatomy fusion module that accounts for the inherent anatomical differences between MR contrasts. Furthermore, HACA3 can be trained and applied to any combination of MR contrasts and is robust to imaging artifacts. HACA3 is developed and evaluated on diverse MR datasets acquired from 21 sites with varying field strengths, scanner platforms, and acquisition protocols. Experiments show that HACA3 achieves state-of-the-art harmonization performance under multiple image quality metrics. We also demonstrate the versatility and potential clinical impact of HACA3 on downstream tasks including white matter lesion segmentation for people with multiple sclerosis and longitudinal volumetric analyses for normal aging subjects. Code is available at https://github.com/lianruizuo/haca3.

Improvement in male pelvis magnetic resonance image contouring following radiologist-delivered training.

The magnetic resonance linear accelerator (MRL) combines both magnetic resonance imaging and a linear accelerator, allowing for daily treatment adaptation. This study aimed to assess the impact of radiologist-delivered training in magnetic resonance (MR) contouring of relevant structures within the male pelvis. Two radiation oncologists, two radiation oncology registrars and seven radiation therapists completed contouring on 10 male pelvis MR datasets both pre- and post-training. A 2-hour MR anatomy training session was delivered by a radiologist, who also provided the 'gold standard' contours. The pre- and post-training contours were compared against the gold standard with Dice similarity coefficient (DSC) and Hausdorff distances calculated; and the pre- and post-confidence scores and timing were compared. The improvement in DSC were significant in prostate, rectum and seminal vesicles, with a post-training median DSC of 0.87 ± 0.06, 0.92 ± 0.04 and 0.80 ± 0.14, respectively. The median Hausdorff improved with a median of 1.46 ± 0.78 mm, 0.52 ± 0.32 mm and 1.11 ± 0.86 mm for prostate, rectum and seminal vesicles, respectively. Bladder concordance was high both pre- and post-training. Urethra contours improved post-training, however, remained difficult to contour with a median post-DSC of 0.51 ± 0.24. Overall, confidence scoring improved (P < 0.001) and timing decreased by an average of 4.4 ± 16.4 min post-training. Radiologist-delivered training improved concordance of male pelvis contouring on MR datasets. Further work is required in the identification of urethra on MRs. These findings are of importance in the MRL adaptive workflow.

Evaluating semi-supervision methods for medical image segmentation: applications in cardiac magnetic resonance imaging.

Neural networks have potential to automate medical image segmentation but require expensive labeling efforts. While methods have been proposed to reduce the labeling burden, most have not been thoroughly evaluated on large, clinical datasets or clinical tasks. We propose a method to train segmentation networks with limited labeled data and focus on thorough network evaluation. We propose a semi-supervised method that leverages data augmentation, consistency regularization, and pseudolabeling and train four cardiac magnetic resonance (MR) segmentation networks. We evaluate the models on multiinstitutional, multiscanner, multidisease cardiac MR datasets using five cardiac functional biomarkers, which are compared to an expert's measurements using Lin's concordance correlation coefficient (CCC), the within-subject coefficient of variation (CV), and the Dice coefficient. The semi-supervised networks achieve strong agreement using Lin's CCC ( ), CV similar to an expert, and strong generalization performance. We compare the error modes of the semi-supervised networks against fully supervised networks. We evaluate semi-supervised model performance as a function of labeled training data and with different types of model supervision, showing that a model trained with 100 labeled image slices can achieve a Dice coefficient within 1.10% of a network trained with 16,000+ labeled image slices. We evaluate semi-supervision for medical image segmentation using heterogeneous datasets and clinical metrics. As methods for training models with little labeled data become more common, knowledge about how they perform on clinical tasks, how they fail, and how they perform with different amounts of labeled data is useful to model developers and users.

BMAnet: Boundary Mining With Adversarial Learning for Semi-Supervised 2D Myocardial Infarction Segmentation.

Automatic segmentation of myocardial infarction (MI) regions in late gadolinium-enhanced cardiac magnetic resonance images is an essential step in the computed diagnosis of myocardial infarction. Most of the current myocardial infarction region segmentation methods are based on fully supervised deep learning. However, cardiologists' annotation of myocardial infarction regions in cardiac magnetic resonance images during the diagnosis process is time-consuming and expensive. This paper proposes a semi-supervised myocardial infarction segmentation. It consists of two models: 1) a boundary mining model and 2) an adversarial learning model. The boundary mining model can solve the boundary ambiguity problem by enlarging the gap between the foreground and background features, thus segmenting the myocardial infarction region accurately. The adversarial learning model can make the boundary mining model learn from additional unlabeled data by evaluating the segmentation performance and providing pseudo supervision, which significantly increases the robustness of the boundary mining model. We conduct extensive experiments on an in-house myocardial magnetic resonance dataset. The experimental results on six evaluation metrics demonstrate that our method achieves excellent results in myocardial infarction segmentation and outperforms the state-of-the-art semi-supervised methods.

Transformer-based multilevel region and edge aggregation network for magnetic resonance image segmentation

To improve the quality of magnetic resonance (MR) image edge segmentation, some researchers applied additional edge labels to train the network to extract edge information and aggregate it with region information. They have made significant progress. However, due to the intrinsic locality of convolution operations, the convolution neural network-based region and edge aggregation has limitations in modeling long-range information. To solve this problem, we proposed a novel transformer-based multilevel region and edge aggregation network for MR image segmentation. To the best of our knowledge, this is the first literature on transformer-based region and edge aggregation. We first extract multilevel region and edge features using a dual-branch module. Then, the region and edge features at different levels are inferred and aggregated through multiple transformer-based inference modules to form multilevel complementary features. Finally, the attention feature selection module aggregates these complementary features with the corresponding level region and edge features to decode the region and edge features. We evaluated our method on a public MR dataset: Medical image computation and computer-assisted intervention atrial segmentation challenge (ASC). Meanwhile, the private MR dataset considered infrapatellar fat pad (IPFP). Our method achieved a dice score of 93.2% for ASC and 91.9% for IPFP. Compared with other 2D segmentation methods, our method improved a dice score by 0.6% for ASC and 3.0% for IPFP.

Learning Deep Representations of Cardiac Structures for 4D Cine MRI Image Segmentation through Semi-Supervised Learning.

Learning good data representations for medical imaging tasks ensures the preservation of relevant information and the removal of irrelevant information from the data to improve the interpretability of the learned features. In this paper, we propose a semi-supervised model-namely, combine-all in semi-supervised learning (CqSL)-to demonstrate the power of a simple combination of a disentanglement block, variational autoencoder (VAE), generative adversarial network (GAN), and a conditioning layer-based reconstructor for performing two important tasks in medical imaging: segmentation and reconstruction. Our work is motivated by the recent progress in image segmentation using semi-supervised learning (SSL), which has shown good results with limited labeled data and large amounts of unlabeled data. A disentanglement block decomposes an input image into a domain-invariant spatial factor and a domain-specific non-spatial factor. We assume that medical images acquired using multiple scanners (different domain information) share a common spatial space but differ in non-spatial space (intensities, contrast, etc.). Hence, we utilize our spatial information to generate segmentation masks from unlabeled datasets using a generative adversarial network (GAN). Finally, to reconstruct the original image, our conditioning layer-based reconstruction block recombines spatial information with random non-spatial information sampled from the generative models. Our ablation study demonstrates the benefits of disentanglement in holding domain-invariant (spatial) as well as domain-specific (non-spatial) information with high accuracy. We further apply a structured similarity loss along with a mutual information minimizer (MIM) to improve the adversarially trained generative models for better reconstruction. Experimental results achieved on the STACOM 2017 ACDC cine cardiac magnetic resonance (MR) dataset suggest that our proposed (CqSL) model outperforms fully supervised and semi-supervised models, achieving an 83.2% performance accuracy even when using only 1% labeled data. We hypothesize that our proposed model has the potential to become an efficient semantic segmentation tool that may be used for domain adaptation in data-limited medical imaging scenarios, where annotations are expensive. Code, and experimental configurations will be made available publicly.

CAN3D: Fast 3D medical image segmentation via compact context aggregation.

Direct automatic segmentation of objects in 3D medical imaging, such as magnetic resonance (MR) imaging, is challenging as it often involves accurately identifying multiple individual structures with complex geometries within a large volume under investigation. Most deep learning approaches address these challenges by enhancing their learning capability through a substantial increase in trainable parameters within their models. An increased model complexity will incur high computational costs and large memory requirements unsuitable for real-time implementation on standard clinical workstations, as clinical imaging systems typically have low-end computer hardware with limited memory and CPU resources only. This paper presents a compact convolutional neural network (CAN3D) designed specifically for clinical workstations and allows the segmentation of large 3D Magnetic Resonance (MR) images in real-time. The proposed CAN3D has a shallow memory footprint to reduce the number of model parameters and computer memory required for state-of-the-art performance and maintain data integrity by directly processing large full-size 3D image input volumes with no patches required. The proposed architecture significantly reduces computational costs, especially for inference using the CPU. We also develop a novel loss function with extra shape constraints to improve segmentation accuracy for imbalanced classes in 3D MR images. Compared to state-of-the-art approaches (U-Net3D, improved U-Net3D and V-Net), CAN3D reduced the number of parameters up to two orders of magnitude and achieved much faster inference, up to 5 times when predicting with a standard commercial CPU (instead of GPU). For the open-access OAI-ZIB knee MR dataset, in comparison with manual segmentation, CAN3D achieved Dice coefficient values of (mean = 0.87±0.02 and 0.85±0.04) with mean surface distance errors (mean = 0.36±0.32mm and 0.29±0.10mm) for imbalanced classes such as (femoral and tibial) cartilage volumes respectively when training volume-wise under only 12G video memory. Similarly, CAN3D demonstrated high accuracy and efficiency on a pelvis 3D MR imaging dataset for prostate cancer consisting of 211 examinations with expert manual semantic labels (bladder, body, bone, rectum, prostate) now released publicly for scientific use as part of this work.

Improving Transcranial Acoustic Targeting: The Limits of CT-Based Velocity Estimates and the Role of MR.

Transcranial magnetic resonance-guided focused ultrasound (tcMRgFUS) enables the noninvasive treatment of the deep brain. This capacity relies on the ability to focus acoustic energy through the in-tact skull, a feat that requires accurate estimates of the acoustic velocity in individual patient skulls. In current practice, these estimates are generated using a pretreatment computed tomography (CT) scan and then registered to a magnetic resonance (MR) dataset on the day of the treatment. Treatment safety and efficacy can be improved by eliminating the need to register the CT data to the MR images and by improving the accuracy of acoustic velocity measurements. In this study, we examine the capacity of MR to supplement or replace CT as a means of estimating velocity in the skull. We find that MR can predict velocity with less but comparable accuracy to CT. We then use micro-CT imaging to better understand the limitations of Hounsfield unit (HU)-based estimates of velocity, demonstrating that the macrostructure of pores in the skull contributes to the acoustic velocity of the bone. We find evidence that detailed T2 measurements provide information about pore macrostructure similar to the information obtained with micro-CT, offering a potential clinical mechanism for improving patient-specific estimates of acoustic velocity in the human skull.

Minimising multi-centre radiomics variability through image normalisation: a pilot study

Radiomics is an emerging technique for the quantification of imaging data that has recently shown great promise for deeper phenotyping of cardiovascular disease. Thus far, the technique has been mostly applied in single-centre studies. However, one of the main difficulties in multi-centre imaging studies is the inherent variability of image characteristics due to centre differences. In this paper, a comprehensive analysis of radiomics variability under several image- and feature-based normalisation techniques was conducted using a multi-centre cardiovascular magnetic resonance dataset. 218 subjects divided into healthy (n = 112) and hypertrophic cardiomyopathy (n = 106, HCM) groups from five different centres were considered. First and second order texture radiomic features were extracted from three regions of interest, namely the left and right ventricular cavities and the left ventricular myocardium. Two methods were used to assess features’ variability. First, feature distributions were compared across centres to obtain a distribution similarity index. Second, two classification tasks were proposed to assess: (1) the amount of centre-related information encoded in normalised features (centre identification) and (2) the generalisation ability for a classification model when trained on these features (healthy versus HCM classification). The results showed that the feature-based harmonisation technique ComBat is able to remove the variability introduced by centre information from radiomic features, at the expense of slightly degrading classification performance. Piecewise linear histogram matching normalisation gave features with greater generalisation ability for classification ( balanced accuracy in between 0.78 ± 0.08 and 0.79 ± 0.09). Models trained with features from images without normalisation showed the worst performance overall ( balanced accuracy in between 0.45 ± 0.28 and 0.60 ± 0.22). In conclusion, centre-related information removal did not imply good generalisation ability for classification.

Towards fully automated segmentation of rat cardiac MRI by leveraging deep learning frameworks

Automated segmentation of human cardiac magnetic resonance datasets has been steadily improving during recent years. Similar applications would be highly useful to improve and speed up the studies of cardiac function in rodents in the preclinical context. However, the transfer of such segmentation methods to the preclinical research is compounded by the limited number of datasets and lower image resolution. In this paper we present a successful application of deep architectures 3D cardiac segmentation for rats in preclinical contexts which to our knowledge has not yet been reported. We developed segmentation models that expand on the standard U-Net architecture and evaluated models separately trained for systole and diastole phases (2MSA) and a single model trained for all phases (1MSA). Furthermore, we calibrated model outputs using a Gaussian process (GP)-based prior to improve phase selection. The resulting models approach human performance in terms of left ventricular segmentation quality and ejection fraction (EF) estimation in both 1MSA and 2MSA settings (Sørensen-Dice score 0.91 ± 0.072 and 0.93 ± 0.032, respectively). 2MSA achieved a mean absolute difference between estimated and reference EF of 3.5 ± 2.5%, while 1MSA resulted in 4.1 ± 3.0%. Applying GPs to 1MSA enabled automating systole and diastole phase selection. Both segmentation approaches (1MSA and 2MSA) were statistically equivalent. Combined with a proposed cardiac phase selection strategy, our work presents an important first step towards a fully automated segmentation pipeline in the context of rat cardiac analysis.

Brain MR images segmentation using 3D CNN with features recalibration mechanism for segmented CT generation

The segmentation of MR (magnetic resonance) images is a simple approach to create Pseudo CT images which are useful for many medical imaging analysis applications. One of the main challenges of this process is the bone segmentation of brain MR images. Deep convolutional neural networks (CNNs) have been widely and efficiently applied to perform MR images segmentation. The aim of this work is to propose a novel excitation-based CNN by recalibrating the network features adaptively to enhance the bone segmentation by segmenting the brain MR images into three tissue classes: bone, soft tissue, and air. The proposed method combines two types of features excitation mechanisms namely: (1) spatial squeeze and channel excitation block (cSE) and (2) channel squeeze and spatial excitation block (sSE). The two blocks are combined sequentially and integrated seamlessly into a 3D convolutional encoder decoder network. The novelty of this work emerges in the combination of the two excitation blocks sequentially to improve the segmentation performance and reduce the model complexity. The proposed approach is evaluated through a comparison with computed tomography (CT) images as ground truth and validated with other methods in the literature that applied deep CNN approaches to perform MR image segmentation for PET attenuation correction. Brain MR and CT datasets which consist of 50 patients are used to evaluate the proposed method. The segmentation performance of the three brain classes is evaluated using precision, recall, dice similarity coefficient (DSC), and Jaccard index. The presented method improves the bone tissue segmentation compared to the baseline model and other methods in the literature where the DSC is improved from 0.6278 ± 0.0006 to 0.6437 ± 0.0006 with an improvement percentage of 2.53% for bone class. The proposed excitation-based segmentation network architecture demonstrates promising and competitive results compared with other methods in the literature and reduces the model complexity thanks to the sequential combination of the two excitation blocks.