Search

Abstract Background 3D reconstruction of Wilms’ tumor provides several advantages but are not systematically performed because manual segmentation is extremely time-consuming. The objective of our study was to develop an artificial intelligence tool to automate the segmentation of tumors and kidneys in children. Methods A manual segmentation was carried out by two experts on 14 CT scans. Then, the segmentation of Wilms’ tumor and neoplastic kidney was automatically performed using the CNN U-Net and the same CNN U-Net trained according to the OV2ASSION method. The time saving for the expert was estimated depending on the number of sections automatically segmented. Results When segmentations were performed manually by two experts, the inter-individual variability resulted in a Dice index of 0.95 for tumor and 0.87 for kidney. Fully automatic segmentation with the CNN U-Net yielded a poor Dice index of 0.69 for Wilms’ tumor and 0.27 for kidney. With the OV2ASSION method, the Dice index varied depending on the number of manually segmented sections. For the segmentation of the Wilms’ tumor and neoplastic kidney, it varied respectively from 0.97 to 0.94 for a gap of 1 (2 out of 3 sections performed manually) to 0.94 and 0.86 for a gap of 10 (1 section out of 6 performed manually). Conclusion Fully automated segmentation remains a challenge in the field of medical image processing. Although it is possible to use already developed neural networks, such as U-Net, we found that the results obtained were not satisfactory for segmentation of neoplastic kidneys or Wilms’ tumors in children. We developed an innovative CNN U-Net training method that makes it possible to segment the kidney and its tumor with the same precision as an expert while reducing their intervention time by 80%.

Abstract Background Cervical cancer is the fourth most frequent cancer among women, with 90% of cervical cancer-related deaths occurring in low- and middle-income countries like Cameroon. Visual inspection with acetic acid is often used in low-resource settings to screen for cervical cancer; however, its accuracy can be limited. To address this issue, the Swiss Federal Institute of Technology Lausanne and the University Hospitals of Geneva are collaborating to develop an automated smartphone-based image classifier that serves as a computer aided diagnosis tool for cancerous lesions. The primary objective of this study is to explore the acceptability and perspectives of women in Dschang regarding the usage of a screening tool for cervical cancer relying on artificial intelligence. A secondary objective is to understand the preferred form and type of information women would like to receive regarding this artificial intelligence-based screening tool. Methods A qualitative methodology was employed to gain better insight into the women’s perspectives. Participants, aged between 30 and 49 were invited from both rural and urban regions and semi-structured interviews using a pre-tested interview guide were conducted. The focus groups were divided on the basis of level of education, as well as HPV status. The interviews were audio-recorded, transcribed, and coded using the ATLAS.ti software. Results A total of 32 participants took part in the six focus groups, and 38% of participants had a primary level of education. The perspectives identified were classified using an adapted version of the Technology Acceptance Model. Key factors influencing the acceptability of artificial intelligence include privacy concerns, perceived usefulness, and trust in the competence of providers, accuracy of the tool as well as the potential negative impact of smartphones. Conclusion The results suggest that an artificial intelligence-based screening tool for cervical cancer is mostly acceptable to the women in Dschang. By ensuring patient confidentiality and by providing clear explanations, acceptance can be fostered in the community and uptake of cervical cancer screening can be improved. Trial registration Ethical Cantonal Board of Geneva, Switzerland (CCER, N°2017–0110 and CER-amendment n°4) and Cameroonian National Ethics Committee for Human Health Research (N°2022/12/1518/CE/CNERSH/SP). NCT: 03757299.

Axon radius is a potential biomarker for brain diseases and a crucial tissue microstructure parameter that determines the speed of action potentials. Diffusion MRI (dMRI) allows non-invasive estimation of axon radius, but accurately estimating the radius of axons in the human brain is challenging. Most axons in the brain have a radius below one micrometer, which falls below the sensitivity limit of dMRI signals even when using the most advanced human MRI scanners. Therefore, new MRI methods that are sensitive to small axon radii are needed. In this proof-of-concept investigation, we examine whether a surface-based axonal relaxation process could mediate a relationship between intra-axonal T2 and T1 times and inner axon radius, as measured using postmortem histology. A unique in vivo human diffusion-T1-T2 relaxation dataset was acquired on a 3T MRI scanner with ultra-strong diffusion gradients, using a strong diffusion-weighting (i.e., b = 6,000 s/mm2) and multiple inversion and echo times. A second reduced diffusion-T2 dataset was collected at various echo times to evaluate the model further. The intra-axonal relaxation times were estimated by fitting a diffusion-relaxation model to the orientation-averaged spherical mean signals. Our analysis revealed that the proposed surface-based relaxation model effectively explains the relationship between the estimated relaxation times and the histological axon radius measured in various corpus callosum regions. Using these histological values, we developed a novel calibration approach to predict axon radius in other areas of the corpus callosum. Notably, the predicted radii and those determined from histological measurements were in close agreement.

Monte-Carlo diffusion simulations are a powerful tool for validating tissue microstructure models by generating synthetic diffusion-weighted magnetic resonance images (DW-MRI) in controlled environments. This is fundamental for understanding the link between micrometre-scale tissue properties and DW-MRI signals measured at the millimetre-scale, optimizing acquisition protocols to target microstructure properties of interest, and exploring the robustness and accuracy of estimation methods. However, accurate simulations require substrates that reflect the main microstructural features of the studied tissue. To address this challenge, we introduce a novel computational workflow, CACTUS (Computational Axonal Configurator for Tailored and Ultradense Substrates), for generating synthetic white matter substrates. Our approach allows constructing substrates with higher packing density than existing methods, up to 95% intra-axonal volume fraction, and larger voxel sizes of up to 500μm3 with rich fibre complexity. CACTUS generates bundles with angular dispersion, bundle crossings, and variations along the fibres of their inner and outer radii and g-ratio. We achieve this by introducing a novel global cost function and a fibre radial growth approach that allows substrates to match predefined targeted characteristics and mirror those reported in histological studies. CACTUS improves the development of complex synthetic substrates, paving the way for future applications in microstructure imaging.

Estimating structural connectivity from diffusion-weighted magnetic resonance imaging is a challenging task, partly due to the presence of false-positive connections and the misestimation of connection weights. Building on previous efforts, the MICCAI-CDMRI Diffusion-Simulated Connectivity (DiSCo) challenge was carried out to evaluate state-of-the-art connectivity methods using novel large-scale numerical phantoms. The diffusion signal for the phantoms was obtained from Monte Carlo simulations. The results of the challenge suggest that methods selected by the 14 teams participating in the challenge can provide high correlations between estimated and ground-truth connectivity weights, in complex numerical environments. Additionally, the methods used by the participating teams were able to accurately identify the binary connectivity of the numerical dataset. However, specific false positive and false negative connections were consistently estimated across all methods. Although the challenge dataset doesn’t capture the complexity of a real brain, it provided unique data with known macrostructure and microstructure ground-truth properties to facilitate the development of connectivity estimation methods.

Ultrafast ultrasound imaging, characterized by high frame rates, generates low-quality images. Convolutional neural networks (CNNs) have demonstrated great potential to enhance image quality without compromising the frame rate. However, CNNs have been mostly trained on simulated or phantom images, leading to suboptimal performance on in vivo images. In this study, we present a method to enhance the quality of single plane wave (PW) acquisitions using a CNN trained on in vivo images. Our contribution is twofold. Firstly, we introduce a training loss function that accounts for the high dynamic range of the radio frequency data and uses the Kullback–Leibler divergence to preserve the probability distributions of the echogenicity values. Secondly, we conduct an extensive performance analysis on a large new in vivo dataset of 20,000 images, comparing the predicted images to the target images resulting from the coherent compounding of 87 PWs. Applying a volunteer-based dataset split, the peak signal-to-noise ratio and structural similarity index measure increase, respectively, from 16.466 ± 0.801 dB and 0.105 ± 0.060, calculated between the single PW and target images, to 20.292 ± 0.307 dB and 0.272 ± 0.040, between predicted and target images. Our results demonstrate significant improvements in image quality, effectively reducing artifacts.

Despite recent improvements, complete motor recovery occurs in

Tractography enables identifying and evaluating the healthy and diseased brain's white matter pathways from diffusion-weighted magnetic resonance imaging data. As previous evaluation studies have reported significant false-positive estimation biases, recent microstructure-informed tractography algorithms have been introduced to improve the trade-off between specificity and sensitivity. However, a major limitation for characterizing the performance of these techniques is the lack of ground truth brain data. In this study, we compared the performance of two relevant microstructure-informed tractography methods, SIFT2 and COMMIT, by assessing the subject specificity and reproducibility of their derived white matter pathways. Specifically, twenty healthy young subjects were scanned at eight different time points at two different sites. Subject specificity and reproducibility were evaluated using the whole-brain connectomes and a subset of 29 white matter bundles. Our results indicate that although the raw tractograms are more vulnerable to the presence of false-positive connections, they are highly reproducible, suggesting that the estimation bias is subject-specific. This high reproducibility was preserved when microstructure-informed tractography algorithms were used to filter the raw tractograms. Moreover, the resulting track-density images depicted a more uniform coverage of streamlines throughout the white matter, suggesting that these techniques could increase the biological meaning of the estimated fascicles. Notably, we observed an increased subject specificity by employing connectivity pre-processing techniques to reduce the underlaying noise and the data dimensionality (using principal component analysis), highlighting the importance of these tools for future studies. Finally, no strong bias from the scanner site or time between measurements was found. The largest intraindividual variance originated from the sole repetition of data measurements (inter-run).

Limitations in the accuracy of brain pathways reconstructed by diffusion MRI (dMRI) tractography have received considerable attention. While the technical advances spearheaded by the Human Connectome Project (HCP) led to significant improvements in dMRI data quality, it remains unclear how these data should be analyzed to maximize tractography accuracy. Over a period of two years, we have engaged the dMRI community in the IronTract Challenge, which aims to answer this question by leveraging a unique dataset. Macaque brains that have received both tracer injections and ex vivo dMRI at high spatial and angular resolution allow a comprehensive, quantitative assessment of tractography accuracy on state-of-the-art dMRI acquisition schemes. We find that, when analysis methods are carefully optimized, the HCP scheme can achieve similar accuracy as a more time-consuming, Cartesian-grid scheme. Importantly, we show that simple pre- and post-processing strategies can improve the accuracy and robustness of many tractography methods. Finally, we find that fiber configurations that go beyond crossing (e.g., fanning, branching) are the most challenging for tractography. The IronTract Challenge remains open and we hope that it can serve as a valuable validation tool for both users and developers of dMRI analysis methods.

Quantitative magnetic resonance imaging (qMRI) can increase the specificity and sensitivity of conventional weighted MRI to underlying pathology by comparing meaningful physical or chemical parameters, measured in physical units, with normative values acquired in a healthy population. This study focuses on multi-echo T2 relaxometry, a qMRI technique that probes the complex tissue microstructure by differentiating compartment-specific T2 relaxation times. However, estimation methods are still limited by their sensitivity to the underlying noise. Moreover, estimating the model's parameters is challenging because the resulting inverse problem is ill-posed, requiring advanced numerical regularization techniques. As a result, the estimates from distinct regularization strategies are different. In this work, we aimed to investigate the variability and reproducibility of different techniques for estimating the transverse relaxation time of the intra- and extra-cellular space (T2IE) in gray (GM) and white matter (WM) tissue in a clinical setting, using a multi-site, multi-session, and multi-run T2 relaxometry dataset. To this end, we evaluated three different techniques for estimating the T2 spectra (two regularized non-negative least squares methods and a machine learning approach). Two independent analyses were performed to study the effect of using raw and denoised data. For both the GM and WM regions, and the raw and denoised data, our results suggest that the principal source of variance is the inter-subject variability, showing a higher coefficient of variation (CoV) than those estimated for the inter-site, inter-session, and inter-run, respectively. For all reconstruction methods studied, the CoV ranged between 0.32 and 1.64%. Interestingly, the inter-session variability was close to the inter-scanner variability with no statistical differences, suggesting that T2IE is a robust parameter that could be employed in multi-site neuroimaging studies. Furthermore, the three tested methods showed consistent results and similar intra-class correlation (ICC), with values superior to 0.7 for most regions. Results from raw data were slightly more reproducible than those from denoised data. The regularized non-negative least squares method based on the L-curve technique produced the best results, with ICC values ranging from 0.72 to 0.92.

Abstract Pulmonary hypertension is a hemodynamic disorder defined by an abnormal elevation of pulmonary artery pressure (PAP). Current options for measuring PAP are limited in clinical practice. The aim of this study was to evaluate if electrical impedance tomography (EIT), a radiation-free and non-invasive monitoring technique, can be used for the continuous, unsupervised and safe monitoring of PAP. In 30 healthy volunteers we induced gradual increases in systolic PAP (SPAP) by exposure to normobaric hypoxemia. At various stages of the protocol, the SPAP of the subjects was estimated by transthoracic echocardiography. In parallel, in the pulmonary vasculature, pulse wave velocity was estimated by EIT and calibrated to pressure units. Within-cohort agreement between both methods on SPAP estimation was assessed through Bland–Altman analysis and at subject level, with Pearson’s correlation coefficient. There was good agreement between the two methods (inter-method difference not significant (P > 0.05), bias ± standard deviation of − 0.1 ± 4.5 mmHg) independently of the degree of PAP, from baseline oxygen saturation levels to profound hypoxemia. At subject level, the median per-subject agreement was 0.7 ± 3.8 mmHg and Pearson’s correlation coefficient 0.87 (P

Computer-aided diagnostics in histopathology are based on the digitization of glass slides. However, heterogeneity between the images generated by different slide scanners can unfavorably affect the performance of computational algorithms. Here, we evaluate the impact of scanner variability on lymph node segmentation due to its clinical importance in colorectal cancer diagnosis. 100 slides containing 276 lymph nodes were digitized using 4 different slide scanners, and 50 of the lymph nodes containing metastatic cancer cells. These 400 scans were subsequently annotated by 2 experienced pathologists to precisely label lymph node boundary. Three different segmentation methods were then applied and compared: Hematoxylin-channel-based thresholding (HCT), Hematoxylin-based active contours (HAC), and a convolution neural network (U-Net). Evaluation of U-Net trained from both a single scanner and an ensemble of all scanners was completed. Mosaic images based on representative tiles from a scanner were used as a reference image to normalize the new data from different test scanners to evaluate the performance of a pre-trained model. Fine-tuning was carried out by using weights of a model trained on one scanner to initialize model weights for other scanners. To evaluate the domain generalization, domain adversarial learning and stain mix-up augmentation were also implemented. Results show that fine-tuning and domain adversarial learning decreased the impact of scanner variability and greatly improved segmentation across scanners. Overall, U-Net with stain mix-up (Matthews correlation coefficient (MCC) = 0.87), domain adversarial learning (MCC = 0.86), and HAC (MCC = 0.87) were shown to outperform HCT (MCC = 0.81) for segmentation of lymph nodes when compared against the ground truth. The findings of this study should be considered for future algorithms applied in diagnostic routines.

The current diagnostic criteria for multiple sclerosis (MS) lack specificity, and this may lead to misdiagnosis, which remains an issue in present-day clinical practice. In addition, conventional biomarkers only moderately correlate with MS disease progression. Recently, some MS lesional imaging biomarkers such as cortical lesions (CL), the central vein sign (CVS), and paramagnetic rim lesions (PRL), visible in specialized magnetic resonance imaging (MRI) sequences, have shown higher specificity in differential diagnosis. Moreover, studies have shown that CL and PRL are potential prognostic biomarkers, the former correlating with cognitive impairments and the latter with early disability progression. As machine learning-based methods have achieved extraordinary performance in the assessment of conventional imaging biomarkers, such as white matter lesion segmentation, several automated or semi-automated methods have been proposed as well for CL, PRL, and CVS. In the present review, we first introduce these MS biomarkers and their imaging methods. Subsequently, we describe the corresponding machine learning-based methods that were proposed to tackle these clinical questions, putting them into context with respect to the challenges they are facing, including non-standardized MRI protocols, limited datasets, and moderate inter-rater variability. We conclude by presenting the current limitations that prevent their broader deployment and suggesting future research directions.

Visual inspection with acetic acid (VIA) is one of the methods recommended by the World Health Organization for cervical cancer screening. VIA is simple and low-cost; it, however, presents high subjectivity. We conducted a systematic literature search in PubMed, Google Scholar and Scopus to identify automated algorithms for classifying images taken during VIA as negative (healthy/benign) or precancerous/cancerous. Of the 2608 studies identified, 11 met the inclusion criteria. The algorithm with the highest accuracy in each study was selected, and some of its key features were analyzed. Data analysis and comparison between the algorithms were conducted, in terms of sensitivity and specificity, ranging from 0.22 to 0.93 and 0.67 to 0.95, respectively. The quality and risk of each study were assessed following the QUADAS-2 guidelines. Artificial intelligence-based cervical cancer screening algorithms have the potential to become a key tool for supporting cervical cancer screening, especially in settings where there is a lack of healthcare infrastructure and trained personnel. The presented studies, however, assess their algorithms using small datasets of highly selected images, not reflecting whole screened populations. Large-scale testing in real conditions is required to assess the feasibility of integrating those algorithms in clinical settings.

Multi-echo T2 magnetic resonance images contain information about the distribution of T2 relaxation times of compartmentalized water, from which we can estimate relevant brain tissue properties such as the myelin water fraction (MWF). Regularized non-negative least squares (NNLS) is the tool of choice for estimating non-parametric T2 spectra. However, the estimation is ill-conditioned, sensitive to noise, and highly affected by the employed regularization weight. The purpose of this study is threefold: first, we want to underline that the apparently innocuous use of two alternative parameterizations for solving the inverse problem, which we called the standard and alternative regularization forms, leads to different solutions; second, to assess the performance of both parameterizations; and third, to propose a new Bayesian regularized NNLS method (BayesReg). The performance of BayesReg was compared with that of two conventional approaches (L-curve and Chi-square (X2) fitting) using both regularization forms. We generated a large dataset of synthetic data, acquired in vivo human brain data in healthy participants for conducting a scan-rescan analysis, and correlated the myelin content derived from histology with the MWF estimated from ex vivo data. Results from synthetic data indicate that BayesReg provides accurate MWF estimates, comparable to those from L-curve and X2, and with better overall stability across a wider signal-to-noise range. Notably, we obtained superior results by using the alternative regularization form. The correlations reported in this study are higher than those reported in previous studies employing the same ex vivo and histological data. In human brain data, the estimated maps from L-curve and BayesReg were more reproducible. However, the T2 spectra produced by BayesReg were less affected by over-smoothing than those from L-curve. These findings suggest that BayesReg is a good alternative for estimating T2 distributions and MWF maps.

White matter bundle segmentation using diffusion MRI fiber tractography has become the method of choice to identify white matter fiber pathways in vivo in human brains. However, like other analyses of complex data, there is considerable variability in segmentation protocols and techniques. This can result in different reconstructions of the same intended white matter pathways, which directly affects tractography results, quantification, and interpretation. In this study, we aim to evaluate and quantify the variability that arises from different protocols for bundle segmentation. Through an open call to users of fiber tractography, including anatomists, clinicians, and algorithm developers, 42 independent teams were given processed sets of human whole-brain streamlines and asked to segment 14 white matter fascicles on six subjects. In total, we received 57 different bundle segmentation protocols, which enabled detailed volume-based and streamline-based analyses of agreement and disagreement among protocols for each fiber pathway. Results show that even when given the exact same sets of underlying streamlines, the variability across protocols for bundle segmentation is greater than all other sources of variability in the virtual dissection process, including variability within protocols and variability across subjects. In order to foster the use of tractography bundle dissection in routine clinical settings, and as a fundamental analytical tool, future endeavors must aim to resolve and reduce this heterogeneity. Although external validation is needed to verify the anatomical accuracy of bundle dissections, reducing heterogeneity is a step towards reproducible research and may be achieved through the use of standard nomenclature and definitions of white matter bundles and well-chosen constraints and decisions in the dissection process.

The methodological development in the mapping of the brain structural connectome from diffusion-weighted magnetic resonance imaging (DW-MRI) has raised many hopes in the neuroscientific community. Indeed, the knowledge of the connections between different brain regions is fundamental to study brain anatomy and function. The reliability of the structural connectome is therefore of paramount importance. In the search for accuracy, researchers have given particular attention to linking white matter tractography methods – used for estimating the connectome – with information about the microstructure of the nervous tissue. The creation and validation of methods in this context were hampered by a lack of practical numerical phantoms. To achieve this, we created a numerical phantom that mimics complex anatomical fibre pathway trajectories while also accounting for microstructural features such as axonal diameter distribution, myelin presence, and variable packing densities. The substrate has a micrometric resolution and an unprecedented size of 1 cubic millimetre to mimic an image acquisition matrix of 40×40×40 voxels. DW-MRI images were obtained from Monte Carlo simulations of spin dynamics to enable the validation of quantitative tractography. The phantom is composed of 12,196 synthetic tubular fibres with diameters ranging from 1.4 µm to 4.2 µm, interconnecting sixteen regions of interest. The simulated images capture the microscopic properties of the tissue (e.g. fibre diameter, water diffusing within and around fibres, free water compartment), while also having desirable macroscopic properties resembling the anatomy, such as the smoothness of the fibre trajectories. While previous phantoms were used to validate either tractography or microstructure, this phantom can enable a better assessment of the connectome estimation’s reliability on the one side, and its adherence to the actual microstructure of the nervous tissue on the other.

We present the comparison of two-dimensional (2D) fetal brain biometry on magnetic resonance (MR) images using orthogonal 2D T2-weighted sequences (T2WSs) vs. one 3D super-resolution (SR) reconstructed volume and evaluation of the level of confidence and concordance between an experienced pediatric radiologist (obs1) and a junior radiologist (obs2). Twenty-five normal fetal brain MRI scans (18–34 weeks of gestation) including orthogonal 3-mm-thick T2WSs were analyzed retrospectively. One 3D SR volume was reconstructed per subject based on multiple series of T2WSs. The two observers performed 11 2D biometric measurements (specifying their level of confidence) on T2WS and SR volumes. Measurements were compared using the paired Wilcoxon rank sum test between observers for each dataset (T2WS and SR) and between T2WS and SR for each observer. Bland–Altman plots were used to assess the agreement between each pair of measurements. Measurements were made with low confidence in three subjects by obs1 and in 11 subjects by obs2 (mostly concerning the length of the corpus callosum on T2WS). Inter-rater intra-dataset comparisons showed no significant difference (p > 0.05), except for brain axial biparietal diameter (BIP) on T2WS and for brain and skull coronal BIP and coronal transverse cerebellar diameter (DTC) on SR. None of them remained significant after correction for multiple comparisons. Inter-dataset intra-rater comparisons showed statistical differences in brain axial and coronal BIP for both observers, skull coronal BIP for obs1, and axial and coronal DTC for obs2. After correction for multiple comparisons, only axial brain BIP remained significantly different, but differences were small (2.95 ± 1.73 mm). SR allows similar fetal brain biometry as compared to using the conventional T2WS while improving the level of confidence in the measurements and using a single reconstructed volume.

In the central nervous system of primates, several pathways are characterized by different spectra of axon diameters. In vivo methods, based on diffusion-weighted magnetic resonance imaging, can provide axon diameter index estimates non-invasively. However, such methods report voxel-wise estimates, which vary from voxel-to-voxel for the same white matter bundle due to partial volume contributions from other pathways having different microstructure properties. Here, we propose a novel microstructure-informed tractography approach, COMMITAxSize, to resolve axon diameter index estimates at the streamline level, thus making the estimates invariant along trajectories. Compared to previously proposed voxel-wise methods, our formulation allows the estimation of a distinct axon diameter index value for each streamline, directly, furnishing a complementary measure to the existing calculation of the mean value along the bundle. We demonstrate the favourable performance of our approach comparing our estimates with existing histologically-derived measurements performed in the corpus callosum and the posterior limb of the internal capsule. Overall, our method provides a more robust estimation of the axon diameter index of pathways by jointly estimating the microstructure properties of the tissue and the macroscopic organisation of the white matter connectivity.

Abstract Recent state-of-the-art methods for skin lesion segmentation are based on convolutional neural networks (CNNs). Even though these CNN-based segmentation approaches are accurate, they are computationally expensive. In this paper, we address this problem and propose an efficient fully convolutional neural network, named DermoNet. In DermoNet, due to our densely connected convolutional blocks and skip connections, network layers can reuse information from their preceding layers and ensure high accuracy in later network layers. By doing so, we take advantage of the capability of high-level feature representations learned at intermediate layers with varying scales and resolutions for lesion segmentation. Quantitative evaluation is conducted on three well-established public benchmark datasets: the ISBI 2016, ISBI 2017, and the PH2 datasets. The experimental results show that our proposed approach outperforms the state-of-the-art algorithms on these three datasets. We also compared the runtime performance of DermoNet with two other related architectures, which are fully convolutional networks and U-Net. The proposed approach is found to be faster and suitable for practical applications.

At the typical spatial resolution of MRI in the human brain, approximately 60–90% of voxels contain multiple fiber populations. Quantifying microstructural properties of distinct fiber populations within a voxel is therefore challenging but necessary. While progress has been made for diffusion and T1-relaxation properties, how to resolve intra-voxel T2 heterogeneity remains an open question. Here a novel framework, named COMMIT-T2, is proposed that uses tractography-based spatial regularization with diffusion-relaxometry data to estimate multiple intra-axonal T2 values within a voxel. Unlike previously-proposed voxel-based T2 estimation methods, which (when applied in white matter) implicitly assume just one fiber bundle in the voxel or the same T2 for all bundles in the voxel, COMMIT-T2 can recover specific T2 values for each unique fiber population passing through the voxel. In this approach, the number of recovered unique T2 values is not determined by a number of model parameters set a priori, but rather by the number of tractography-reconstructed streamlines passing through the voxel. Proof-of-concept is provided in silico and in vivo, including a demonstration that distinct tract-specific T2 profiles can be recovered even in the three-way crossing of the corpus callosum, arcuate fasciculus, and corticospinal tract. We demonstrate the favourable performance of COMMIT-T2 compared to that of voxelwise approaches for mapping intra-axonal T2 exploiting diffusion, including a direction-averaged method and AMICO-T2, a new extension to the previously-proposed Accelerated Microstructure Imaging via Convex Optimization (AMICO) framework.

IntroductionCervical cancer remains a major public health challenge in low- and middle-income countries (LMICs) due to financial and logistical issues. WHO recommendation for cervical cancer screening in LMICs includes HPV testing as primary screening followed by visual inspection with acetic acid (VIA) and treatment. However, VIA is a subjective procedure dependent on the healthcare provider's experience. Its accuracy can be improved by computer-aided detection techniques. Our aim is to assess the performance of a smartphone-based Automated VIA Classifier (AVC) relying on Artificial Intelligence to discriminate precancerous and cancerous lesions from normal cervical tissue.MethodsThe AVC study will be nested in an ongoing cervical cancer screening program called "3T-study" (for Test, Triage and Treat), including HPV self-sampling followed by VIA triage and treatment if needed. After application of acetic acid on the cervix, precancerous and cancerous cells whiten more rapidly than non-cancerous ones and their whiteness persists stronger overtime. The AVC relies on this key feature to determine whether the cervix is suspect for precancer or cancer. In order to train and validate the AVC, 6000 women aged 30 to 49 years meeting the inclusion criteria will be recruited on a voluntary basis, with an estimated 100 CIN2+, calculated using a confidence level of 95% and an estimated sensitivity of 90% +/-7% precision on either side. Diagnostic test performance of AVC test and two current standard tests (VIA and cytology) used routinely for triage will be evaluated and compared. Histopathological examination will serve as reference standard. Participants' and providers' acceptability of the technology will also be assessed. The study protocol was registered under ClinicalTrials.gov (number NCT04859530).Expected resultsThe study will determine whether AVC test can be an effective method for cervical cancer screening in LMICs.

Diffusion-weighted magnetic resonance imaging (DW-MRI) tractography is a non-invasive tool to probe neural connections and the structure of the white matter. It has been applied successfully in studies of neurological disorders and normal connectivity. Recent work has revealed that tractography produces a high incidence of false-positive connections, often from “bottleneck” white matter configurations. The rich literature in histological connectivity analysis studies in the macaque monkey enables quantitative evaluation of the performance of tractography algorithms. In this study, we use the intricate connections of frontal, cingulate, and parietal areas, well established by the anatomical literature, to derive a symmetrical histological connectivity matrix composed of 59 cortical areas. We evaluate the performance of fifteen diffusion tractography algorithms, including global, deterministic, and probabilistic state-of-the-art methods for the connectivity predictions of 1711 distinct pairs of areas, among which 680 are reported connected by the literature. The diffusion connectivity analysis was performed on a different ex-vivo macaque brain, acquired using multi-shell DW-MRI protocol, at high spatial and angular resolutions. Across all tested algorithms, the true-positive and true-negative connections were dominant over false-positive and false-negative connections, respectively. Moreover, three-quarters of streamlines had endpoints location in agreement with histological data, on average. Furthermore, probabilistic streamline tractography algorithms show the best performances in predicting which areas are connected. Altogether, we propose a method for quantitative evaluation of tractography algorithms, which aims at improving the sensitivity and the specificity of diffusion-based connectivity analysis. Overall, those results confirm the usefulness of tractography in predicting connectivity, although errors are produced. Many of the errors result from bottleneck white matter configurations near the cortical grey matter and should be the target of future implementation of methods.

Monte-Carlo Diffusion Simulations (MCDS) have been used extensively as a ground truth tool for the validation of microstructure models for Diffusion-Weighted MRI. However, methodological pitfalls in the design of the biomimicking geometrical configurations and the simulation parameters can lead to approximation biases. Such pitfalls affect the reliability of the estimated signal, as well as its validity and reproducibility as ground truth data. In this work, we first present a set of experiments in order to study three critical pitfalls encountered in the design of MCDS in the literature, namely, the number of simulated particles and time steps, simplifications in the intra-axonal substrate representation, and the impact of the substrate's size on the signal stemming from the extra-axonal space. The results obtained show important changes in the simulated signals and the recovered microstructure features when changes in those parameters are introduced. Thereupon, driven by our findings from the first studies, we outline a general framework able to generate complex substrates. We show the framework's capability to overcome the aforementioned simplifications by generating a complex crossing substrate, which preserves the volume in the crossing area and achieves a high packing density. The results presented in this work, along with the simulator developed, pave the way toward more realistic and reproducible Monte-Carlo simulations for Diffusion-Weighted MRI.

Phase correction (PC) is a preprocessing technique that exploits the phase of images acquired in Magnetic Resonance Imaging (MRI) to obtain real-valued images containing tissue contrast with additive Gaussian noise, as opposed to magnitude images which follow a non-Gaussian distribution, e.g. Rician. PC finds its natural application to diffusion-weighted images (DWIs) due to their inherent low signal-to-noise ratio and consequent non-Gaussianity that induces a signal overestimation bias that propagates to the calculated diffusion indices. PC effectiveness depends upon the quality of the phase estimation, which is often performed via a regularization procedure. We show that a suboptimal regularization can produce alterations of the true image contrast in the real-valued phase-corrected images. We propose adaptive phase correction (APC), a method where the phase is estimated by using MRI noise information to perform a complex-valued image regularization that accounts for the local variance of the noise. We show, on synthetic and acquired data, that APC leads to phase-corrected real-valued DWIs that present a reduced number of alterations and a reduced bias. The substantial absence of parameters for which human input is required favors a straightforward integration of APC in MRI processing pipelines.

The presence of cortical lesions in multiple sclerosis patients has emerged as an important biomarker of the disease. They appear in the earliest stages of the illness and have been shown to correlate with the severity of clinical symptoms. However, cortical lesions are hardly visible in conventional magnetic resonance imaging (MRI) at 3T, and thus their automated detection has been so far little explored. In this study, we propose a fully-convolutional deep learning approach, based on the 3D U-Net, for the automated segmentation of cortical and white matter lesions at 3T. For this purpose, we consider a clinically plausible MRI setting consisting of two MRI contrasts only: one conventional T2-weighted sequence (FLAIR), and one specialized T1-weighted sequence (MP2RAGE). We include 90 patients from two different centers with a total of 728 and 3856 gray and white matter lesions, respectively. We show that two reference methods developed for white matter lesion segmentation are inadequate to detect small cortical lesions, whereas our proposed framework is able to achieve a detection rate of 76% for both cortical and white matter lesions with a false positive rate of 29% in comparison to manual segmentation. Further results suggest that our framework generalizes well for both types of lesion in subjects acquired in two hospitals with different scanners.

High spatio-angular resolution diffusion MRI (dMRI) has been shown to provide accurate identification of complex neuronal fiber configurations, albeit, at the cost of long acquisition times. We propose a method to recover intra-voxel fiber configurations at high spatio-angular resolution relying on a 3D kq-space under-sampling scheme to enable accelerated acquisitions. The inverse problem for the reconstruction of the fiber orientation distribution (FOD) is regularized by a structured sparsity prior promoting simultaneously voxel-wise sparsity and spatial smoothness of fiber orientation. Prior knowledge of the spatial distribution of white matter, gray matter, and cerebrospinal fluid is also leveraged. A minimization problem is formulated and solved via a stochastic forward–backward algorithm. Simulations and real data analysis suggest that accurate FOD mapping can be achieved from severe kq-space under-sampling regimes potentially enabling high spatio-angular resolution dMRI in the clinical setting.

Though tractography is widely used, it has not been systematically validated. Here, authors report results from 20 groups showing that many tractography algorithms produce both valid and invalid bundles.

Cervical cancer remains a major public health concern in developing countries due to financial and human resource constraints. Visual inspection with acetic acid (VIA) of the cervix was widely promoted and routinely used as a low-cost primary screening test in low- and middle-income countries. It can be performed by a variety of health workers and the result is immediate. VIA provides a transient whitening effect which appears and disappears differently in precancerous and cancerous lesions, as compared to benign conditions. Colposcopes are often used during VIA to magnify the view of the cervix and allow clinicians to visually assess it. However, this assessment is generally subjective and unreliable even for experienced clinicians. Computer-aided techniques may improve the accuracy of VIA diagnosis and be an important determinant in the promotion of cervical cancer screening. This work proposes a smartphone-based solution that automatically detects cervical precancer from the dynamic features extracted from videos taken during VIA. The proposed solution achieves a sensitivity and specificity of 0.9 and 0.87 respectively, and could be a solution for screening in countries that suffer from the lack of expensive tools such as colposcopes and well-trained clinicians.

The verification and validation of segmentation and registration methods is a necessary assessment in the development of new processing methods. However, verification and validation of diffusion MRI (dMRI) processing methods is challenging for the lack of gold-standard data. The data described here are related to the research article entitled “Surface-driven registration method for the structure-informed segmentation of diffusion MR images” [1], in which publicly available data are used to derive golden-standard reference-data to validate and evaluate segmentation and registration methods in dMRI. Keywords: Neuroimage, Image processing, MRI methods, Diffusion MRI

Higher risk for long-term cognitive and behavioral impairments is one of the hallmarks of extreme prematurity (EP) and pregnancy-associated fetal adverse conditions such as intrauterine growth restriction (IUGR). While neurodevelopmental delay and abnormal brain function occur in the absence of overt brain lesions, these conditions have been recently associated with changes in microstructural brain development. Recent imaging studies indicate changes in brain connectivity, in particular involving the white matter fibers belonging to the cortico-basal ganglia-thalamic loop. Furthermore, EP and IUGR have been related to altered brain network architecture in childhood, with reduced network global capacity, global efficiency and average nodal strength. In this study, we used a connectome analysis to characterize the structural brain networks of these children, with a special focus on their topological organization. On one hand, we confirm the reduced averaged network node degree and strength due to EP and IUGR. On the other, the decomposition of the brain networks in an optimal set of clusters remained substantially different among groups, talking in favor of a different network community structure. However, and despite the different community structure, the brain networks of these high-risk school-age children maintained the typical small-world, rich-club and modularity characteristics in all cases. Thus, our results suggest that brain reorganizes after EP and IUGR, prioritizing a tight modular structure, to maintain the small-world, rich-club and modularity characteristics. By themselves, both extreme prematurity and IUGR bear a similar risk for neurocognitive and behavioral impairment, and the here defined modular network alterations confirm similar structural changes both by IUGR and EP at school age compared to control. Interestingly, the combination of both conditions (IUGR + EP) does not result in a worse outcome. In such cases, the alteration in network topology appears mainly driven by the effect of extreme prematurity, suggesting that these brain network alterations present at school age have their origin in a common critical period, both for intrauterine and extrauterine adverse conditions.

Cardiac output (CO) and stroke volume (SV) are parameters of key clinical interest. Many techniques exist to measure CO and SV, but are either invasive or insufficiently accurate in clinical settings. Electrical impedance tomography (EIT) has been suggested as a noninvasive measure of SV, but inconsistent results have been reported. Our goal is to determine the accuracy and reliability of EIT-based SV measurements, and whether advanced image reconstruction approaches can help to improve the estimates. Data were collected on ten healthy volunteers undergoing postural changes and exercise. To overcome the sensitivity to heart displacement and thorax morphology reported in previous work, we used a 3D EIT configuration with 2 planes of 16 electrodes and subject-specific reconstruction models. Various EIT-derived SV estimates were compared to reference measurements derived from the oxygen uptake. Results revealed a dramatic impact of posture on the EIT images. Therefore, the analysis was restricted to measurements in supine position under controlled conditions (low noise and stable heart and lung regions). In these measurements, amplitudes of impedance changes in the heart and lung regions could successfully be derived from EIT using ECG gating. However, despite a subject-specific calibration the heart-related estimates showed an error of 0.0 ± 15.2 mL for absolute SV estimation. For trending of relative SV changes, a concordance rate of 80.9% and an angular error of -1.0 ± 23.0° were obtained. These performances are insufficient for most clinical uses. Similar conclusions were derived from lung-related estimates. Our findings indicate that the key difficulty in EIT-based SV monitoring is that purely amplitude-based features are strongly influenced by other factors (such as posture, electrode contact impedance and lung or heart conductivity). All the data of the present study are made publicly available for further investigations.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

ObjectiveQuantitative and semi-quantitative MRI (qMRI) metrics provide complementary specificity and differential sensitivity to pathological brain changes compatible with brain inflammation, degeneration, and repair. Moreover, advanced magnetic resonance imaging (MRI) metrics with overlapping elements amplify the true tissue-related information and limit measurement noise. In this work, we combined multiple advanced MRI parameters to assess focal and diffuse brain changes over 2 years in a group of early-stage relapsing-remitting MS patients.MethodsThirty relapsing-remitting MS patients with less than 5 years disease duration and nine healthy subjects underwent 3T MRI at baseline and after 2 years including T1, T2, T2* relaxometry, and magnetization transfer imaging. To assess longitudinal changes in normal-appearing (NA) tissue and lesions, we used analyses of variance and Bonferroni correction for multiple comparisons. Multivariate linear regression was used to assess the correlation between clinical outcome and multiparametric MRI changes in lesions and NA tissue.ResultsIn patients, we measured a significant longitudinal decrease of mean T2 relaxation times in NA white matter (p = 0.005) and a decrease of T1 relaxation times in the pallidum (p 0.4, p

Retinoblastoma and uveal melanoma are fast spreading eye tumors usually diagnosed by using 2D Fundus Image Photography (Fundus) and 2D Ultrasound (US). Diagnosis and treatment planning of such diseases often require additional complementary imaging to confirm the tumor extend via 3D Magnetic Resonance Imaging (MRI). In this context, having automatic segmentations to estimate the size and the distribution of the pathological tissue would be advantageous towards tumor characterization. Until now, the alternative has been the manual delineation of eye structures, a rather time consuming and error-prone task, to be conducted in multiple MRI sequences simultaneously. This situation, and the lack of tools for accurate eye MRI analysis, reduces the interest in MRI beyond the qualitative evaluation of the optic nerve invasion and the confirmation of recurrent malignancies below calcified tumors. In this manuscript, we propose a new framework for the automatic segmentation of eye structures and ocular tumors in multi-sequence MRI. Our key contribution is the introduction of a pathological eye model from which Eye Patient-Specific Features (EPSF) can be computed. These features combine intensity and shape information of pathological tissue while embedded in healthy structures of the eye. We assess our work on a dataset of pathological patient eyes by computing the Dice Similarity Coefficient (DSC) of the sclera, the cornea, the vitreous humor, the lens and the tumor. In addition, we quantitatively show the superior performance of our pathological eye model as compared to the segmentation obtained by using a healthy model (over 4% DSC) and demonstrate the relevance of our EPSF, which improve the final segmentation regardless of the classifier employed.

A time and covariance threshold triggered optimal maneuver planning method is proposed for orbital rendezvous using angles-only navigation (AON). In the context of Yamanaka-Ankersen orbital relative motion equations, the square root unscented Kalman filter (SRUKF) AON algorithm is developed to compute the relative state estimations from a low-volume/mass, power saving, and low-cost optical/infrared camera’s observations. Multi-impulsive Hill guidance law is employed in closed-loop linear covariance analysis model, based on which the quantitative relative position robustness and relative velocity robustness index are defined. By balancing fuel consumption, relative position robustness, and relative velocity robustness, we developed a time and covariance threshold triggered two-level optimal maneuver planning method, showing how these results correlate to past methods and missions and how they could potentially influence future ones. Numerical simulation proved that it is feasible to control the spacecraft with a two-line element- (TLE-) level uncertain, 34.6% of range, initial relative state to a 100 m v-bar relative station keeping point, at where the trajectory dispersion reduces to 3.5% of range, under a 30% data gap per revolution on account of the eclipse. Comparing with the traditional time triggered maneuver planning method, the final relative position accuracy is improved by one order and the relative trajectory robustness and collision probability are obviously improved and reduced, respectively.

Focal epilepsy is increasingly recognized as the result of an altered brain network, both on the structural and functional levels and the characterization of these widespread brain alterations is crucial for our understanding of the clinical manifestation of seizure and cognitive deficits as well as for the management of candidates to epilepsy surgery. Tractography based on Diffusion Tensor Imaging allows non-invasive mapping of white matter tracts in vivo. Recently, diffusion spectrum imaging (DSI), based on an increased number of diffusion directions and intensities, has improved the sensitivity of tractography, notably with respect to the problem of fiber crossing and recent developments allow acquisition times compatible with clinical application. We used DSI and parcellation of the gray matter in regions of interest to build whole-brain connectivity matrices describing the mutual connections between cortical and subcortical regions in patients with focal epilepsy and healthy controls. In addition, the high angular and radial resolution of DSI allowed us to evaluate also some of the biophysical compartment models, to better understand the cause of the changes in diffusion anisotropy. Global connectivity, hub architecture and regional connectivity patterns were altered in TLE patients and showed different characteristics in RTLE vs LTLE with stronger abnormalities in RTLE. The microstructural analysis suggested that disturbed axonal density contributed more than fiber orientation to the connectivity changes affecting the temporal lobes whereas fiber orientation changes were more involved in extratemporal lobe changes. Our study provides further structural evidence that RTLE and LTLE are not symmetrical entities and DSI-based imaging could help investigate the microstructural correlate of these imaging abnormalities.

Adverse conditions during fetal life have been associated to both structural and functional changes in neurodevelopment from the neonatal period to adolescence. In this study, connectomics was used to assess the evolution of brain networks from infancy to early adolescence. Brain network reorganization over time in subjects who had suffered adverse perinatal conditions is characterized and related to neurodevelopment and cognition. Three cohorts of prematurely born infants and children (between 28 and 35 weeks of gestational age), including individuals with a birth weight appropriated for gestational age and with intrauterine growth restriction (IUGR), were evaluated at one, six and ten years of age respectively. A common developmental trajectory of brain networks was identified in both control and IUGR groups: network efficiencies of the fractional anisotropy (FA)-weighted and normalized connectomes increase with age, which can be related to maturation and myelination of fiber connections while the number of connections decreases, which can be associated to an axonal pruning process and reorganization. Comparing subjects with or without IUGR, a similar pattern of network differences between groups was observed in the three developmental stages, mainly characterized by IUGR group having reduced brain network efficiencies in binary and FA-weighted connectomes and increased efficiencies in the connectome normalized by its total connection strength (FA). Associations between brain networks and neurobehavioral impairments were also evaluated showing a relationship between different network metrics and specific social cognition-related scores, as well as a higher risk of inattention/hyperactivity and/or executive functional disorders in IUGR children.

Spherical deconvolution (SD) methods are widely used to estimate the intra-voxel white-matter fiber orientations from diffusion MRI data. However, while some of these methods assume a zero-mean Gaussian distribution for the underlying noise, its real distribution is known to be non-Gaussian and to depend on many factors such as the number of coils and the methodology used to combine multichannel MRI signals. Indeed, the two prevailing methods for multichannel signal combination lead to noise patterns better described by Rician and noncentral Chi distributions. Here we develop a Robust and Unbiased Model-BAsed Spherical Deconvolution (RUMBA-SD) technique, intended to deal with realistic MRI noise, based on a Richardson-Lucy (RL) algorithm adapted to Rician and noncentral Chi likelihood models. To quantify the benefits of using proper noise models, RUMBA-SD was compared with dRL-SD, a well-established method based on the RL algorithm for Gaussian noise. Another aim of the study was to quantify the impact of including a total variation (TV) spatial regularization term in the estimation framework. To do this, we developed TV spatially-regularized versions of both RUMBA-SD and dRL-SD algorithms. The evaluation was performed by comparing various quality metrics on 132 three-dimensional synthetic phantoms involving different inter-fiber angles and volume fractions, which were contaminated with noise mimicking patterns generated by data processing in multichannel scanners. The results demonstrate that the inclusion of proper likelihood models leads to an increased ability to resolve fiber crossings with smaller inter-fiber angles and to better detect non-dominant fibers. The inclusion of TV regularization dramatically improved the resolution power of both techniques. The above findings were also verified in human brain data.

Ultrasound segmentation is a challenging problem due to the inherent speckle and some artifacts like shadows, attenuation and signal dropout. Existing methods need to include strong priors like shape priors or analytical intensity models to succeed in the segmentation. However, such priors tend to limit these methods to a specific target or imaging settings, and they are not always applicable to pathological cases. This work introduces a semi-supervised segmentation framework for ultrasound imaging that alleviates the limitation of fully automatic segmentation, that is, it is applicable to any kind of target and imaging settings. Our methodology uses a graph of image patches to represent the ultrasound image and user-assisted initialization with labels, which acts as soft priors. The segmentation problem is formulated as a continuous minimum cut problem and solved with an efficient optimization algorithm. We validate our segmentation framework on clinical ultrasound imaging (prostate, fetus, and tumors of the liver and eye). We obtain high similarity agreement with the ground truth provided by medical expert delineations in all applications (94% DICE values in average) and the proposed algorithm performs favorably with the literature.

Diffusion MRI has evolved towards an important clinical diagnostic and research tool. Though clinical routine is using mainly diffusion weighted and tensor imaging approaches, Q-ball imaging and diffusion spectrum imaging techniques have become more widely available. They are frequently used in research-oriented investigations in particular those aiming at measuring brain network connectivity. In this work, we aim at assessing the dependency of connectivity measurements on various diffusion encoding schemes in combination with appropriate data modeling. We process and compare the structural connection matrices computed from several diffusion encoding schemes, including diffusion tensor imaging, q-ball imaging and high angular resolution schemes, such as diffusion spectrum imaging with a publically available processing pipeline for data reconstruction, tracking and visualization of diffusion MR imaging. The results indicate that the high angular resolution schemes maximize the number of obtained connections when applying identical processing strategies to the different diffusion schemes. Compared to the conventional diffusion tensor imaging, the added connectivity is mainly found for pathways in the 50-100mm range, corresponding to neighboring association fibers and long-range associative, striatal and commissural fiber pathways. The analysis of the major associative fiber tracts of the brain reveals striking differences between the applied diffusion schemes. More complex data modeling techniques (beyond tensor model) are recommended 1) if the tracts of interest run through large fiber crossings such as the centrum semi-ovale, or 2) if non-dominant fiber populations, e.g. the neighboring association fibers are the subject of investigation. An important finding of the study is that since the ground truth sensitivity and specificity is not known, the comparability between results arising from different strategies in data reconstruction and/or tracking becomes implausible to understand.