3D surface reconstruction of cellular cryo-soft X-ray microscopy tomograms using semisupervised deep learning.

Cryo-soft X-ray tomography (cryo-SXT) is a powerful method to investigate the ultrastructure of cells, offering resolution in the tens of nanometer range and strong contrast for membranous structures without requiring labeling or chemical fixation. The short acquisition time and the relatively large field of view leads to fast acquisition of large amounts of tomographic image data. Segmentation of these data into accessible features is a necessary step in gaining biologically relevant information from cryo-soft X-ray tomograms. However, manual image segmentation still requires several orders of magnitude more time than data acquisition. To address this challenge, we have here developed an end-to-end automated 3D segmentation pipeline based on semisupervised deep learning. Our approach is suitable for high-throughput analysis of large amounts of tomographic data, while being robust when faced with limited manual annotations and variations in the tomographic conditions. We validate our approach by extracting three-dimensional information on cellular ultrastructure and by quantifying nanoscopic morphological parameters of filopodia in mammalian cells.

Automated segmentation of epilepsy surgical resection cavities: Comparison of four methods to manual segmentation.

Accurate resection cavity segmentation on MRI is important for neuroimaging research involving epilepsy surgical outcomes. Manual segmentation, the gold standard, is highly labour intensive. Automated pipelines are an efficient potential solution; however, most have been developed for use following temporal epilepsy surgery. Our aim was to compare the accuracy of four automated segmentation pipelines following surgical resection in a mixed cohort of subjects following temporal or extra temporal epilepsy surgery. We identified 4 open-source automated segmentation pipelines. Epic-CHOP and ResectVol utilise SPM-12 within MATLAB, while Resseg and Deep Resection utilise 3D U-net convolutional neural networks. We manually segmented the resection cavity of 50 consecutive subjects who underwent epilepsy surgery (30 temporal, 20 extratemporal). We calculated Dice similarity coefficient (DSC) for each algorithm compared to the manual segmentation. No algorithm identified all resection cavities. ResectVol (n = 44, 88 %) and Epic-CHOP (n = 42, 84 %) were able to detect more resection cavities than Resseg (n = 22, 44 %, P < 0.001) and Deep Resection (n = 23, 46 %, P < 0.001). The SPM-based pipelines (Epic-CHOP and ResectVol) performed better than the deep learning-based pipelines in the overall and extratemporal surgery cohorts. In the temporal cohort, the SPM-based pipelines had higher detection rates, however there was no difference in the accuracy between methods. These pipelines could be applied to machine learning studies of outcome prediction to improve efficiency in pre-processing data, however human quality control is still required.

Automated protocols for delineating human hippocampal subfields from 3 Tesla and 7 Tesla magnetic resonance imaging data.

Researchers who study the human hippocampus are naturally interested in how its subfields function. However, many researchers are precluded from examining subfields because their manual delineation from magnetic resonance imaging (MRI) scans (still the gold standard approach) is time consuming and requires significant expertise. To help ameliorate this issue, we present here two protocols, one for 3T MRI and the other for 7T MRI, that permit automated hippocampus segmentation into six subregions, namely dentate gyrus/cornu ammonis (CA)4, CA2/3, CA1, subiculum, pre/parasubiculum, and uncus along the entire length of the hippocampus. These protocols are particularly notable relative to existing resources in that they were trained and tested using large numbers of healthy young adults (n = 140 at 3T, n = 40 at 7T) whose hippocampi were manually segmented by experts from MRI scans. Using inter-rater reliability analyses, we showed that the quality of automated segmentations produced by these protocols was high and comparable to expert manual segmenters. We provide full open access to the automated protocols, and anticipate they will save hippocampus researchers a significant amount of time. They could also help to catalyze subfield research, which is essential for gaining a full understanding of how the hippocampus functions.

Automatic deep learning segmentation of the hippocampus on high-resolution diffusion magnetic resonance imaging and its application to the healthy lifespan.

Diffusion tensor imaging (DTI) can provide unique contrast and insight into microstructural changes with age or disease of the hippocampus, although it is difficult to measure the hippocampus because of its comparatively small size, location, and shape. This has been markedly improved by the advent of a clinically feasible 1-mm isotropic resolution 6-min DTI protocol at 3 T of the hippocampus with limited brain coverage of 20 axial-oblique slices aligned along its long axis. However, manual segmentation is too laborious for large population studies, and it cannot be automatically segmented directly on the diffusion images using traditional T1 or T2 image-based methods because of the limited brain coverage and different contrast. An automatic method is proposed here that segments the hippocampus directly on high-resolution diffusion images based on an extension of well-known deep learning architectures like UNet and UNet++ by including additional dense residual connections. The method was trained on 100 healthy participants with previously performed manual segmentation on the 1-mm DTI, then evaluated on typical healthy participants (n = 53), yielding an excellent voxel overlap with a Dice score of ~ 0.90 with manual segmentation; notably, this was comparable with the inter-rater reliability of manually delineating the hippocampus on diffusion magnetic resonance imaging (MRI) (Dice score of 0.86). This method also generalized to a different DTI protocol with 36% fewer acquisitions. It was further validated by showing similar age trajectories of volumes, fractional anisotropy, and mean diffusivity from manual segmentations in one cohort (n = 153, age 5-74 years) with automatic segmentations from a second cohort without manual segmentations (n = 354, age 5-90 years). Automated high-resolution diffusion MRI segmentation of the hippocampus will facilitate large cohort analyses and, in future research, needs to be evaluated on patient groups.

The development of a deep learning model for automated segmentation of the robotic pancreaticojejunostomy.

BACKGROUND: Minimally invasive surgery provides an unprecedented opportunity to review video for assessing surgical performance. Surgical video analysis is time-consuming and expensive. Deep learning provides an alternative for analysis. Robotic pancreaticoduodenectomy (RPD) is a complex and morbid operation. Surgeon technical performance of pancreaticojejunostomy (PJ) has been associated with postoperative pancreatic fistula. In this work, we aimed to utilize deep learning to automatically segment PJ RPD videos. METHODS: This was a retrospective review of prospectively collected videos from 2011 to 2022 that were in libraries at tertiary referral centers, including 111 PJ videos. Each frame of a robotic PJ video was categorized based on 6 tasks. A 3D convolutional neural network was trained for frame-level visual feature extraction and classification. All the videos were manually annotated for the start and end of each task. RESULTS: Of the 100 videos assessed, 60 videos were used for the training the model, 10 for hyperparameter optimization, and 30 for the testing of performance. All the frames were extracted (6 frames/second) and annotated. The accuracy and mean per-class F1 scores were 88.01% and 85.34% for tasks. CONCLUSION: The deep learning model performed well for automated segmentation of PJ videos. Future work will focus on skills assessment and outcome prediction.

Automated abdominal adipose tissue segmentation and volume quantification on longitudinal MRI using 3D convolutional neural networks with multi-contrast inputs.

OBJECTIVE: Increased subcutaneous and visceral adipose tissue (SAT/VAT) volume is associated with risk for cardiometabolic diseases. This work aimed to develop and evaluate automated abdominal SAT/VAT segmentation on longitudinal MRI in adults with overweight/obesity using attention-based competitive dense (ACD) 3D U-Net and 3D nnU-Net with full field-of-view volumetric multi-contrast inputs. MATERIALS AND METHODS: 920 adults with overweight/obesity were scanned twice at multiple 3 T MRI scanners and institutions. The first scan was divided into training/validation/testing sets (n = 646/92/182). The second scan from the subjects in the testing set was used to evaluate the generalizability for longitudinal analysis. Segmentation performance was assessed by measuring Dice scores (DICE-SAT, DICE-VAT), false negatives (FN), and false positives (FP). Volume agreement was assessed using the intraclass correlation coefficient (ICC). RESULTS: ACD 3D U-Net achieved rapid (< 4.8 s/subject) segmentation with high DICE-SAT (median ≥ 0.994) and DICE-VAT (median ≥ 0.976), small FN (median ≤ 0.7%), and FP (median ≤ 1.1%). 3D nnU-Net yielded rapid (< 2.5 s/subject) segmentation with similar DICE-SAT (median ≥ 0.992), DICE-VAT (median ≥ 0.979), FN (median ≤ 1.1%) and FP (median ≤ 1.2%). Both models yielded excellent agreement in SAT/VAT volume versus reference measurements (ICC > 0.997) in longitudinal analysis. DISCUSSION: ACD 3D U-Net and 3D nnU-Net can be automated tools to quantify abdominal SAT/VAT volume rapidly, accurately, and longitudinally in adults with overweight/obesity.

Craniofacial phenotyping with fetal MRI: a feasibility study of 3D visualisation, segmentation, surface-rendered and physical models.

This study explores the potential of 3D Slice-to-Volume Registration (SVR) motion-corrected fetal MRI for craniofacial assessment, traditionally used only for fetal brain analysis. In addition, we present the first description of an automated pipeline based on 3D Attention UNet trained for 3D fetal MRI craniofacial segmentation, followed by surface refinement. Results of 3D printing of selected models are also presented.Qualitative analysis of multiplanar volumes, based on the SVR output and surface segmentations outputs, were assessed with computer and printed models, using standardised protocols that we developed for evaluating image quality and visibility of diagnostic craniofacial features. A test set of 25, postnatally confirmed, Trisomy 21 fetal cases (24-36 weeks gestational age), revealed that 3D reconstructed T2 SVR images provided 66-100% visibility of relevant craniofacial and head structures in the SVR output, and 20-100% and 60-90% anatomical visibility was seen for the baseline and refined 3D computer surface model outputs respectively. Furthermore, 12 of 25 cases, 48%, of refined surface models demonstrated good or excellent overall quality with a further 9 cases, 36%, demonstrating moderate quality to include facial, scalp and external ears. Additional 3D printing of 12 physical real-size models (20-36 weeks gestational age) revealed good/excellent overall quality in all cases and distinguishable features between healthy control cases and cases with confirmed anomalies, with only minor manual adjustments required before 3D printing.Despite varying image quality and data heterogeneity, 3D T2w SVR reconstructions and models provided sufficient resolution for the subjective characterisation of subtle craniofacial features. We also contributed a publicly accessible online 3D T2w MRI atlas of the fetal head, validated for accurate representation of normal fetal anatomy.Future research will focus on quantitative analysis, optimizing the pipeline, and exploring diagnostic, counselling, and educational applications in fetal craniofacial assessment.

Automated Deep Learning-Based Finger Joint Segmentation in 3-D Ultrasound Images With Limited Dataset.

Ultrasound imaging has shown promise in assessing synovium inflammation associated early stages of rheumatoid arthritis (RA). The precise identification of the synovium and the quantification of inflammation-specific imaging biomarkers is a crucial aspect of accurately quantifying and grading RA. In this study, a deep learning-based approach is presented that automates the segmentation of the synovium in ultrasound images of finger joints affected by RA. Two convolutional neural network architectures for image segmentation were trained and validated in a limited number of 2-D images, extracted from N = 18 3-D ultrasound volumes acquired from N = 9 RA patients, with sparse ground truth annotations of the synovium. Various augmentation strategies were employed to enhance the diversity and size of the training dataset. The utilization of geometric and noise augmentation transforms resulted in the highest dice score (0.768 ±0.031,N=6),andintersectionoverunion(0.624±0.040, N = 6), as determined via six-fold cross-validation. In addition, the segmentation model is used to generate dense 3-D segmentation maps in the ultrasound volumes, based on the available sparse annotations. The developed technique shows promise in facilitating more efficient and standardized workflow for RA screening using ultrasound imaging.

Are glenoid retroversion, humeral subluxation, and Walch classification associated with a muscle imbalance?

BACKGROUND: The etiology of humeral posterior subluxation remains unknown, and it has been hypothesized that horizontal muscle imbalance could cause this condition. The objective of this study was to compare the ratio of anterior-to-posterior rotator cuff and deltoid muscle volume as a function of humeral subluxation and glenoid morphology when analyzed as a continuous variable in arthritic shoulders. METHODS: In total, 333 computed tomography scans of shoulders (273 arthritic shoulders and 60 healthy controls) were included in this study and were segmented automatically. For each muscle, the volume of muscle fibers without intramuscular fat was measured. The ratio between the volume of the subscapularis and the volume of the infraspinatus plus teres minor (AP ratio) and the ratio between the anterior and posterior deltoids (APdeltoid) were calculated. Statistical analyses were performed to determine whether a correlation could be found between these ratios and glenoid version, humeral subluxation, and/or glenoid type per the Walch classification. RESULTS: Within the arthritic cohort, no statistically significant difference in the AP ratio was found between type A glenoids (1.09 ± 0.22) and type B glenoids (1.03 ± 0.16, P = .09), type D glenoids (1.12 ± 0.27, P = .77), or type C glenoids (1.10 ± 0.19, P > .999). No correlation was found between the AP ratio and glenoid version (ρ = -0.0360, P = .55) or humeral subluxation (ρ = 0.076, P = .21). The APdeltoid ratio of type A glenoids (0.48 ± 0.15) was significantly greater than that of type B glenoids (0.35 ± 0.16, P < .01) and type C glenoids (0.21 ± 0.10, P < .01) but was not significantly different from that of type D glenoids (0.64 ± 0.34, P > .999). When evaluating both healthy control and arthritic shoulders, moderate correlations were found between the APdeltoid ratio and both glenoid version (ρ = 0.55, P < .01) and humeral subluxation (ρ = -0.61, P < .01). CONCLUSION: This in vitro study supports the use of software for fully automated 3-dimensional reconstruction of the 4 rotator cuff muscles and the deltoid. Compared with previous 2-dimensional computed tomography scan studies, our study did not find any correlation between the anteroposterior muscle volume ratio and glenoid parameters in arthritic shoulders. However, once deformity occurred, the observed APdeltoid ratio was lower with type B and C glenoids. These findings suggest that rotator cuff muscle imbalance may not be the precipitating etiology for the posterior humeral subluxation and secondary posterior glenoid erosion characteristic of Walch type B glenoids.

High-throughput segmentation, data visualization, and analysis of sea star skeletal networks.

The remarkably complex skeletal systems of the sea stars (Echinodermata, Asteroidea), consisting of hundreds to thousands of individual elements (ossicles), have intrigued investigators for more than 150 years. While the general features and structural diversity of isolated asteroid ossicles have been well documented in the literature, the task of mapping the spatial organization of these constituent skeletal elements in a whole-animal context represents an incredibly laborious process, and as such, has remained largely unexplored. To address this unmet need, particularly in the context of understanding structure-function relationships in these complex skeletal systems, we present an integrated approach that combines micro-computed tomography, automated ossicle segmentation, data visualization tools, and the production of additively manufactured tangible models to reveal biologically relevant structural data that can be rapidly analyzed in an intuitive manner. In the present study, we demonstrate this high-throughput workflow by segmenting and analyzing entire skeletal systems of the giant knobby star, Pisaster giganteus, at four different stages of growth. The in-depth analysis, presented herein, provides a fundamental understanding of the three-dimensional skeletal architecture of the sea star body wall, the process of skeletal maturation during growth, and the relationship between skeletal organization and morphological characteristics of individual ossicles. The widespread implementation of this approach for investigating other species, subspecies, and growth series has the potential to fundamentally improve our understanding of asteroid skeletal architecture and biodiversity in relation to mobility, feeding habits, and environmental specialization in this fascinating group of echinoderms.

Deep learning-based automatic pipeline for quantitative assessment of thigh muscle morphology and fatty infiltration.

PURPOSE: Fast and accurate thigh muscle segmentation from MRI is important for quantitative assessment of thigh muscle morphology and composition. A novel deep learning (DL) based thigh muscle and surrounding tissues segmentation model was developed for fully automatic and reproducible cross-sectional area (CSA) and fat fraction (FF) quantification and tested in patients at 10 years after anterior cruciate ligament reconstructions. METHODS: A DL model combining UNet and DenseNet was trained and tested using manually segmented thighs from 16 patients (32 legs). Segmentation accuracy was evaluated using Dice similarity coefficients (DSC) and average symmetric surface distance (ASSD). A UNet model was trained for comparison. These segmentations were used to obtain CSA and FF quantification. Reproducibility of CSA and FF quantification was tested with scan and rescan of six healthy subjects. RESULTS: The proposed UNet and DenseNet had high agreement with manual segmentation (DSC >0.97, ASSD < 0.24) and improved performance compared with UNet. For hamstrings of the operated knee, the automated pipeline had largest absolute difference of 6.01% for CSA and 0.47% for FF as compared to manual segmentation. In reproducibility analysis, the average difference (absolute) in CSA quantification between scan and rescan was better for the automatic method as compared with manual segmentation (2.27% vs. 3.34%), whereas the average difference (absolute) in FF quantification were similar. CONCLUSIONS: The proposed method exhibits excellent accuracy and reproducibility in CSA and FF quantification compared with manual segmentation and can be used in large-scale patient studies.

Multivendor Evaluation of Automated MRI Postprocessing of Biventricular Size and Function for Children With and Without Congenital Heart Defects.

BACKGROUND: Manually segmenting cardiac structures is time-consuming and produces variability in MRI assessments. Automated segmentation could solve this. However, current software is developed for adults without congenital heart defects (CHD). PURPOSE: To evaluate automated segmentation of left ventricle (LV) and right ventricle (RV) for pediatric MRI studies. STUDY TYPE: Retrospective comparative study. POPULATION: Twenty children per group of: healthy children, LV-CHD, tetralogy of Fallot (ToF), and univentricular CHD, aged 11.7 [8.9-16.0], 14.2 [10.6-15.7], 14.6 [11.6-16.4], and 12.2 [10.2-14.9] years, respectively. SEQUENCE/FIELD STRENGTH: Balanced steady-state free precession at 1.5 T. ASSESSMENT: Biventricular volumes and masses were calculated from a short-axis stack of images, which were segmented manually and using two fully automated software suites (Medis Suite 3.2, Medis, Leiden, the Netherlands and SuiteHeart 5.0, Neosoft LLC, Pewaukee, USA). Fully automated segmentations were manually adjusted to provide two further sets of segmentations. Fully automated and adjusted automated segmentation were compared to manual segmentation. Segmentation times and reproducibility for each method were assessed. STATISTICAL TESTS: Bland Altman analysis and intraclass correlation coefficients (ICC) were used to compare volumes and masses between methods. Postprocessing times were compared by paired t-tests. RESULTS: Fully automated methods provided good segmentation (ICC > 0.90 compared to manual segmentation) for the LV in the healthy and left-sided CHD groups (eg LV-EDV difference for healthy children 1.4 ± 11.5 mL, ICC: 0.97, for Medis and 3.0 ± 12.2 mL, ICC: 0.96 for SuiteHeart). Both automated methods gave larger errors (ICC: 0.62-0.94) for the RV in these populations, and for all structures in the ToF and univentricular CHD groups. Adjusted automated segmentation agreed well with manual segmentation (ICC: 0.71-1.00), improved reproducibility and reduced segmentation time in all patient groups, compared to manual segmentation. DATA CONCLUSION: Fully automated segmentation eliminates observer variability but may produce large errors compared to manual segmentation. Manual adjustments reduce these errors, improve reproducibility, and reduce postprocessing times compared to manual segmentation. Adjusted automated segmentation is reasonable in children with and without CHD. EVIDENCE LEVEL: 3. TECHNICAL EFFICACY: Stage 2.

Convolutional Neural Network for Fully Automated Cerebellar Volumetry in Children in Comparison to Manual Segmentation and Developmental Trajectory of Cerebellar Volumes.

The purpose of this study was to develop a fully automated and reliable volumetry of the cerebellum of children during infancy and childhood using deep learning algorithms in comparison to manual segmentation. In addition, the clinical usefulness of measuring the cerebellar volume is shown. One hundred patients (0 to 16.3 years old) without infratentorial signal abnormalities on conventional MRI were retrospectively selected from our pool of pediatric MRI examinations. Based on a routinely acquired 3D T1-weighted magnetization prepared rapid gradient echo (MPRAGE) sequence, the cerebella were manually segmented using ITK-SNAP. The data set of all 100 cases was divided into four splits (four-fold cross-validation) to train the network (NN) to delineate the boundaries of the cerebellum. First, the accuracy of the newly created neural network was compared with the manual segmentation. Secondly, age-related volume changes were investigated. Our trained NN achieved an excellent Spearman correlation coefficient of 0.99, a Dice Coefficient of 95.0 ± 2.1%, and an intersection over union (IoU) of 90.6 ± 3.8%. Cerebellar volume increased continuously with age, showing an exponentially rapid growth within the first year of life. Using a convolutional neural network, it was possible to achieve reliable, fully automated cerebellar volume measurements in childhood and infancy, even when based on a relatively small cohort. In this preliminary study, age-dependent cerebellar volume changes could be acquired.

Automated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithm.

Quantifying the smoothness of different layers of the retina can potentially be an important and practical biomarker in various pathologic conditions like diabetic retinopathy. The purpose of this study is to develop an automated machine learning algorithm which uses support vector regression method with wavelet kernel and automatically segments two hyperreflective retinal layers (inner plexiform layer (IPL) and outer plexiform layer (OPL)) in 50 optical coherence tomography (OCT) slabs and calculates the smoothness index (SI). The Bland-Altman plots, mean absolute error, root mean square error and signed error calculations revealed a modest discrepancy between the manual approach, used as the ground truth, and the corresponding automated segmentation of IPL/ OPL, as well as SI measurements in OCT slabs. It was concluded that the constructed algorithm may be employed as a reliable, rapid and convenient approach for segmenting IPL/OPL and calculating SI in the appropriate layers.

Comparison of the morphological characteristics of the choroidal sublayer between idiopathic macular holes and epiretinal membranes with automatic analysis.

PURPOSE: To compare the choroidal sublayer morphologic features between idiopathic macular hole (IMH) and idiopathic epiretinal membrane (iERM) on spectral-domain optical coherent tomography (SD-OCT) using an automatic segmentation model. METHODS: Thirty-three patients with idiopathic IMHs and 44 with iERMs who underwent vitrectomies were involved. The enhanced depth imaging mode of SD-OCT was used to obtain the B-scan image after single line scanning of the macular fovea. The choroidal sublayer automatic analysis model divides the choroidal into the choroidal large vessel layer, the middle vessel layer and the small vessel layer (LVCL, MVCL and SVCL, respectively) and calculates the choroidal thickness (overall, LVCL, MVCL and SVCL) and vascular index (overall, LVCL, MVCL and SVCL). The morphological characteristics of the choroidal sublayer in the ERM eyes and the IMH eyes were compared. RESULTS: The mean choroidal thickness in the macular centre of the IMH eyes was significantly thinner than that of the ERM eyes (206.35 ± 81.72 vs. 273.33 ± 82.31 µm; P < 0.001). The analysis of the choroidal sublayer showed that the MVCL and SVCL macular centres and 0.5-1.5 mm of the nasal and temporal macula were significantly thinner in the IMH eyes than in the ERM eyes (P < 0.05), and there was a difference in the macular centre of the LVCL between the two groups (P < 0.05). In contrast, the choroidal vascular index of the macular centre in the IMH eyes was significantly higher than that in iERM eyes (0.2480 ± 0.0536 vs. 0.2120 ± 0.0616; P < 0.05). There was no significant difference in the CVI of other parts of the macula, the LVCL or MVCL between the two groups. CONCLUSION: The choroidal thickness of the IMH eyes was significantly thinner than that of the iERM eyes, which was mainly observed in 3 mm of the macular centre and the MVCL and SVCL layers of the choroid. The choroidal vascular index of the IMH eyes was higher than that of the iERM eyes. These findings suggest that the choroid may be involved in the pathogenesis of IMH and iERM.

Automatic Segmentation of Parkinson Disease Therapeutic Targets Using Nonlinear Registration and Clinical MR Imaging: Comparison of Methodology, Presence of Disease, and Quality Control.

INTRODUCTION: Accurate and precise delineation of the globus pallidus pars interna (GPi) and subthalamic nucleus (STN) is critical for the clinical treatment and research of Parkinson's disease (PD). Automated segmentation is a developing technology which addresses limitations of visualizing deep nuclei on MR imaging and standardizing their definition in research applications. We sought to compare manual segmentation with three workflows for template-to-patient nonlinear registration providing atlas-based automatic segmentation of deep nuclei. METHODS: Bilateral GPi, STN, and red nucleus (RN) were segmented for 20 PD and 20 healthy control (HC) subjects using 3T MRIs acquired for clinical purposes. The automated workflows used were an option available in clinical practice and two common research protocols. Quality control (QC) was performed on registered templates via visual inspection of readily discernible brain structures. Manual segmentation using T1, proton density, and T2 sequences was used as "ground truth" data for comparison. Dice similarity coefficient (DSC) was used to assess agreement between segmented nuclei. Further analysis was done to compare the influences of disease state and QC classifications on DSC. RESULTS: Automated segmentation workflows (CIT-S, CRV-AB, and DIST-S) had the highest DSC for the RN and lowest for the STN. Manual segmentations outperformed automated segmentation for all workflows and nuclei; however, for 3/9 workflows (CIT-S STN, CRV-AB STN, and CRV-AB GPi) the differences were not statically significant. HC and PD only showed significant differences in 1/9 comparisons (DIST-S GPi). QC classification only demonstrated significantly higher DSC in 2/9 comparisons (CRV-AB RN and GPi). CONCLUSION: Manual segmentations generally performed better than automated segmentations. Disease state does not appear to have a significant effect on the quality of automated segmentations via nonlinear template-to-patient registration. Notably, visual inspection of template registration is a poor indicator of the accuracy of deep nuclei segmentation. As automatic segmentation methods continue to evolve, efficient and reliable QC methods will be necessary to support safe and effective integration into clinical workflows.

Differentiation of benign and malignant vertebral fractures using a convolutional neural network to extract CT-based texture features.

PURPOSE: To assess the diagnostic performance of three-dimensional (3D) CT-based texture features (TFs) using a convolutional neural network (CNN)-based framework to differentiate benign (osteoporotic) and malignant vertebral fractures (VFs). METHODS: A total of 409 patients who underwent routine thoracolumbar spine CT at two institutions were included. VFs were categorized as benign or malignant using either biopsy or imaging follow-up of at least three months as standard of reference. Automated detection, labelling, and segmentation of the vertebrae were performed using a CNN-based framework ( https://anduin.bonescreen.de ). Eight TFs were extracted: Varianceglobal, Skewnessglobal, energy, entropy, short-run emphasis (SRE), long-run emphasis (LRE), run-length non-uniformity (RLN), and run percentage (RP). Multivariate regression models adjusted for age and sex were used to compare TFs between benign and malignant VFs. RESULTS: Skewnessglobal showed a significant difference between the two groups when analyzing fractured vertebrae from T1 to L6 (benign fracture group: 0.70 [0.64-0.76]; malignant fracture group: 0.59 [0.56-0.63]; and p = 0.017), suggesting a higher skewness in benign VFs compared to malignant VFs. CONCLUSION: Three-dimensional CT-based global TF skewness assessed using a CNN-based framework showed significant difference between benign and malignant thoracolumbar VFs and may therefore contribute to the clinical diagnostic work-up of patients with VFs.

Are glenoid retroversion, humeral subluxation and Walch classification associated with a muscle imbalance.

INTRODUCTION: The etiology of humeral posterior subluxation remains unknown, and it has been hypothesized that horizontal muscle imbalance could cause this condition. The objective of this study was to compare the ratio of anterior to posterior rotator cuff muscle and deltoid volumes as a function of humeral subluxation and glenoid morphology when analyzed as continuous variable in arthritic shoulders. METHODS: Three hundred and thirty-three (273 arthritic and 60 healthy controls) CT scans of shoulders were included in this study and were segmented automatically. For each muscle, the volume of muscle fibers without intra-muscular fat was then measured. The ratio between the volume of the subscapularis and the volume of the infraspinatus + teres minor (AP ratio) and the ratio between the anterior and posterior deltoid (APdeltoid) were calculated. Statistical analyses were performed to determine whether a correlation could be found between these ratios and glenoid version/ humeral subluxation/glenoid type in the Walch classification. RESULTS: Within the arthritic cohort, no statistically significant difference was found between the AP ratio between A and type B glenoids (1.09 ± 0.22 versus 1.03 ± 0.16 p=0.09), between A and D type glenoids (1.09 ± 0.22 versus 1.12 ± 0.27, p=0.77) nor between the A and C type glenoids (1.09 ± 0.22 versus 1.10 ± 0.19, p=1). No correlation was found between AP ratio and glenoid version/humeral subluxation (rho =-0.0360, p=0.55; rho = 0.076; p=0.21). The APdeltoid ratio of type A glenoids was significantly greater than that of type B glenoids (0.48 ± 0.15 versus 0.35 ± 0.16, p< 0.01), and type C glenoids (0.48 ± 0.15 versus 0.21±0.10, p < 0.01) but not significantly different from the APdeltoid ratio of type D glenoids (0.48 ± 0.15 versus 0.64 ± 0.34, p=1). When evaluating both healthy control and arthritic shoulders, moderate correlations were found between APdeltoid ratio and glenoid version/humeral subluxation (rho=0.55, p<0.01; rho=-0.61, p<0.01). CONCLUSION: As opposed to previous two-dimensional CT scan studies, we did not find any correlation between AP muscle volume ratio and glenoid parameters in arthritic shoulders. Therefore, rotator cuff muscle imbalance does not seem to be associated with posterior humeral subluxation leading to posterior glenoid erosion and subsequent retroversion characteristic of Walch B glenoids. However, our results could suggest that a larger posterior deltoid pulls the humerus posteriorly into posterior subluxation, but this requires further evaluation as the deltoid follows the humerus possibly leading to secondary asymmetry between the anterior and the posterior deltoid.

Performance of three freely available methods for extracting white matter hyperintensities: FreeSurfer, UBO Detector, and BIANCA.

White matter hyperintensities (WMH) of presumed vascular origin are frequently found in MRIs of healthy older adults. WMH are also associated with aging and cognitive decline. Here, we compared and validated three algorithms for WMH extraction: FreeSurfer (T1w), UBO Detector (T1w + FLAIR), and FSL's Brain Intensity AbNormality Classification Algorithm (BIANCA; T1w + FLAIR) using a longitudinal dataset comprising MRI data of cognitively healthy older adults (baseline N = 231, age range 64-87 years). As reference we manually segmented WMH in T1w, three-dimensional (3D) FLAIR, and two-dimensional (2D) FLAIR images which were used to assess the segmentation accuracy of the different automated algorithms. Further, we assessed the relationships of WMH volumes provided by the algorithms with Fazekas scores and age. FreeSurfer underestimated the WMH volumes and scored worst in Dice Similarity Coefficient (DSC = 0.434) but its WMH volumes strongly correlated with the Fazekas scores (rs  = 0.73). BIANCA accomplished the highest DSC (0.602) in 3D FLAIR images. However, the relations with the Fazekas scores were only moderate, especially in the 2D FLAIR images (rs  = 0.41), and many outlier WMH volumes were detected when exploring within-person trajectories (2D FLAIR: ~30%). UBO Detector performed similarly to BIANCA in DSC with both modalities and reached the best DSC in 2D FLAIR (0.531) without requiring a tailored training dataset. In addition, it achieved very high associations with the Fazekas scores (2D FLAIR: rs  = 0.80). In summary, our results emphasize the importance of carefully contemplating the choice of the WMH segmentation algorithm and MR-modality.

MRI lung lobe segmentation in pediatric cystic fibrosis patients using a recurrent neural network trained with publicly accessible CT datasets.

PURPOSE: To introduce a widely applicable workflow for pulmonary lobe segmentation of MR images using a recurrent neural network (RNN) trained with chest CT datasets. The feasibility is demonstrated for 2D coronal ultrafast balanced SSFP (ufSSFP) MRI. METHODS: Lung lobes of 250 publicly accessible CT datasets of adults were segmented with an open-source CT-specific algorithm. To match 2D ufSSFP MRI data of pediatric patients, both CT data and segmentations were translated into pseudo-MR images that were masked to suppress anatomy outside the lung. Network-1 was trained with pseudo-MR images and lobe segmentations and then applied to 1000 masked ufSSFP images to predict lobe segmentations. These outputs were directly used as targets to train Network-2 and Network-3 with non-masked ufSSFP data as inputs, as well as an additional whole-lung mask as input for Network-2. Network predictions were compared to reference manual lobe segmentations of ufSSFP data in 20 pediatric cystic fibrosis patients. Manual lobe segmentations were performed by splitting available whole-lung segmentations into lobes. RESULTS: Network-1 was able to segment the lobes of ufSSFP images, and Network-2 and Network-3 further increased segmentation accuracy and robustness. The average all-lobe Dice similarity coefficients were 95.0 ± 2.8 (mean ± pooled SD [%]) and 96.4 ± 2.5, 93.0 ± 2.0; and the average median Hausdorff distances were 6.1 ± 0.9 (mean ± SD [mm]), 5.3 ± 1.1, 7.1 ± 1.3 for Network-1, Network-2, and Network-3, respectively. CONCLUSION: Recurrent neural network lung lobe segmentation of 2D ufSSFP imaging is feasible, in good agreement with manual segmentations. The proposed workflow might provide access to automated lobe segmentations for various lung MRI examinations and quantitative analyses.