Morphology of the dysplastic hip and the relationship with sex and acetabular version.

The dysplastic hip is characterized by incomplete coverage of the femoral head, resulting in increased risk of early osteoarthritis. The morphological variation of the hip joint is diverse and clear differences exist between females and males. The aim of this observational study was therefore to investigate the relationship between the morphology of the hip, sex, and hip dysplasia using a three-dimensional model. Statistical shape models of the combined femur and pelvic bones were created from bilateral hips of 75 patients. Using manual angle measurements and regression analysis, the characteristic shape differences associated with sex and hip dysplasia were determined. The model showed clear differences associated with sex and hip dysplasia. We found that the acetabular anteversion in females was significantly higher (p < 0.0001) than in males while no significant difference in acetabular anteversion was found between normal and dysplastic hips (p = 0.11). The model showed that decreased acetabular anteversion resulted in the appearance of the cross-over sign and the prominent ischial spine sign commonly associated with retroversion. Sex could be predicted with an area under the curve of 0.99 and hip dysplasia could be predicted with an area under the curve of ≥0.73. Our findings suggest that retroversion is a result of decreased anteversion of the acetabulum and is primarily associated with sex. This finding should be taken into account during the reorientation of the acetabulum in the surgical treatment of hip dysplasia.

Burden of intracranial artery calcification in white patients with ischemic stroke.

INTRODUCTION: The diagnostic workup of stroke doesn't identify an underlying cause in two-fifths of ischemic strokes. Intracranial arteriosclerosis is acknowledged as a cause of stroke in Asian and Black populations, but is underappreciated as such in whites. We explored the burden of Intracranial Artery Calcification (IAC), a marker of intracranial arteriosclerosis, as a potential cause of stroke among white patients with recent ischemic stroke or TIA. PATIENTS AND METHODS: Between December 2005 and October 2010, 943 patients (mean age 63.8 (SD ± 14.0) years, 47.9% female) were recruited, of whom 561 had ischemic stroke and 382 a TIA. CT-angiography was conducted according to stroke analysis protocols. The burden of IAC was quantified on these images, whereafter we assessed the presence of IAC per TOAST etiology underlying the stroke and assessed associations between IAC burden, symptom severity, and short-term functional outcome. RESULTS: IAC was present in 62.4% of patients. Furthermore, IAC was seen in 84.8% of atherosclerotic strokes, and also in the majority of strokes with an undetermined etiology (58.5%). Additionally, patients with larger IAC burden presented with heavier symptoms (adjusted OR 1.56 (95% CI [1.06-2.29]), but there was no difference in short-term functional outcome (1.14 [0.80-1.61]). CONCLUSION: IAC is seen in the majority of white ischemic stroke patients, aligning with findings from patient studies in other ethnicities. Furthermore, over half of patients with a stroke of undetermined etiology presented with IAC. Assessing IAC burden may help identify the cause in ischemic stroke of undetermined etiology, and could offer important prognostic information.

Where is VALDO? VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021.

Imaging markers of cerebral small vessel disease provide valuable information on brain health, but their manual assessment is time-consuming and hampered by substantial intra- and interrater variability. Automated rating may benefit biomedical research, as well as clinical assessment, but diagnostic reliability of existing algorithms is unknown. Here, we present the results of the VAscular Lesions DetectiOn and Segmentation (Where is VALDO?) challenge that was run as a satellite event at the international conference on Medical Image Computing and Computer Aided Intervention (MICCAI) 2021. This challenge aimed to promote the development of methods for automated detection and segmentation of small and sparse imaging markers of cerebral small vessel disease, namely enlarged perivascular spaces (EPVS) (Task 1), cerebral microbleeds (Task 2) and lacunes of presumed vascular origin (Task 3) while leveraging weak and noisy labels. Overall, 12 teams participated in the challenge proposing solutions for one or more tasks (4 for Task 1-EPVS, 9 for Task 2-Microbleeds and 6 for Task 3-Lacunes). Multi-cohort data was used in both training and evaluation. Results showed a large variability in performance both across teams and across tasks, with promising results notably for Task 1-EPVS and Task 2-Microbleeds and not practically useful results yet for Task 3-Lacunes. It also highlighted the performance inconsistency across cases that may deter use at an individual level, while still proving useful at a population level.

Automatic analysis of bronchus-artery dimensions to diagnose and monitor airways disease in cystic fibrosis.

BACKGROUND: Cystic fibrosis (CF) lung disease is characterised by progressive airway wall thickening and widening. We aimed to validate an artificial intelligence-based algorithm to assess dimensions of all visible bronchus-artery (BA) pairs on chest CT scans from patients with CF. METHODS: The algorithm fully automatically segments the bronchial tree; identifies bronchial generations; matches bronchi with the adjacent arteries; measures for each BA-pair bronchial outer diameter (Bout), bronchial lumen diameter (Bin), bronchial wall thickness (Bwt) and adjacent artery diameter (A); and computes Bout/A, Bin/A and Bwt/A for each BA pair from the segmental bronchi to the last visible generation. Three datasets were used to validate the automatic BA analysis. First BA analysis was executed on 23 manually annotated CT scans (11 CF, 12 control subjects) to compare automatic with manual BA-analysis outcomes. Furthermore, the BA analysis was executed on two longitudinal datasets (Copenhagen 111 CTs, ataluren 347 CTs) to assess longitudinal BA changes and compare them with manual scoring results. RESULTS: The automatic and manual BA analysis showed no significant differences in quantifying bronchi. For the longitudinal datasets the automatic BA analysis detected 247 and 347 BA pairs/CT in the Copenhagen and ataluren dataset, respectively. A significant increase of 0.02 of Bout/A and Bin/A was detected for Copenhagen dataset over an interval of 2 years, and 0.03 of Bout/A and 0.02 of Bin/A for ataluren dataset over an interval of 48 weeks (all p<0.001). The progression of 0.01 of Bwt/A was detected only in the ataluren dataset (p<0.001). BA-analysis outcomes showed weak to strong correlations (correlation coefficient from 0.29 to 0.84) with manual scoring results for airway disease. CONCLUSION: The BA analysis can fully automatically analyse a large number of BA pairs on chest CTs to detect and monitor progression of bronchial wall thickening and bronchial widening in patients with CF.

Nested star-shaped objects segmentation using diameter annotations.

Most current deep learning based approaches for image segmentation require annotations of large datasets, which limits their application in clinical practice. We observe a mismatch between the voxelwise ground-truth that is required to optimize an objective at a voxel level and the commonly used, less time-consuming clinical annotations seeking to characterize the most important information about the patient (diameters, counts, etc.). In this study, we propose to bridge this gap for the case of multiple nested star-shaped objects (e.g., a blood vessel lumen and its outer wall) by optimizing a deep learning model based on diameter annotations. This is achieved by extracting in a differentiable manner the boundary points of the objects at training time, and by using this extraction during the backpropagation. We evaluate the proposed approach on segmentation of the carotid artery lumen and wall from multisequence MR images, thus reducing the annotation burden to only four annotated landmarks required to measure the diameters in the direction of the vessel's maximum narrowing. Our experiments show that training based on diameter annotations produces state-of-the-art weakly supervised segmentations and performs reasonably compared to full supervision. We made our code publicly available at https://gitlab.com/radiology/aim/carotid-artery-image-analysis/nested-star-shaped-objects.

Reproducibility of a combined artificial intelligence and optimal-surface graph-cut method to automate bronchial parameter extraction.

OBJECTIVES: Computed tomography (CT)-based bronchial parameters correlate with disease status. Segmentation and measurement of the bronchial lumen and walls usually require significant manpower. We evaluate the reproducibility of a deep learning and optimal-surface graph-cut method to automatically segment the airway lumen and wall, and calculate bronchial parameters. METHODS: A deep-learning airway segmentation model was newly trained on 24 Imaging in Lifelines (ImaLife) low-dose chest CT scans. This model was combined with an optimal-surface graph-cut for airway wall segmentation. These tools were used to calculate bronchial parameters in CT scans of 188 ImaLife participants with two scans an average of 3 months apart. Bronchial parameters were compared for reproducibility assessment, assuming no change between scans. RESULTS: Of 376 CT scans, 374 (99%) were successfully measured. Segmented airway trees contained a mean of 10 generations and 250 branches. The coefficient of determination (R2) for the luminal area (LA) ranged from 0.93 at the trachea to 0.68 at the 6th generation, decreasing to 0.51 at the 8th generation. Corresponding values for Wall Area Percentage (WAP) were 0.86, 0.67, and 0.42, respectively. Bland-Altman analysis of LA and WAP per generation demonstrated mean differences close to 0; limits of agreement (LoA) were narrow for WAP and Pi10 (± 3.7% of mean) and wider for LA (± 16.4-22.8% for 2-6th generations). From the 7th generation onwards, there was a sharp decrease in reproducibility and a widening LoA. CONCLUSION: The outlined approach for automatic bronchial parameter measurement on low-dose chest CT scans is a reliable way to assess the airway tree down to the 6th generation. STATEMENT ON CLINICAL RELEVANCE: This reliable and fully automatic pipeline for bronchial parameter measurement on low-dose CT scans has potential applications in screening for early disease and clinical tasks such as virtual bronchoscopy or surgical planning, while also enabling the exploration of bronchial parameters in large datasets. KEY POINTS: • Deep learning combined with optimal-surface graph-cut provides accurate airway lumen and wall segmentations on low-dose CT scans. • Analysis of repeat scans showed that the automated tools had moderate-to-good reproducibility of bronchial measurements down to the 6th generation airway. • Automated measurement of bronchial parameters enables the assessment of large datasets with less man-hours.

The effect of CFTR modulators on structural lung disease in cystic fibrosis.

Background: Newly developed quantitative chest computed tomography (CT) outcomes designed specifically to assess structural abnormalities related to cystic fibrosis (CF) lung disease are now available. CFTR modulators potentially can reduce some structural lung abnormalities. We aimed to investigate the effect of CFTR modulators on structural lung disease progression using different quantitative CT analysis methods specific for people with CF (PwCF). Methods: PwCF with a gating mutation (Ivacaftor) or two Phe508del alleles (lumacaftor-ivacaftor) provided clinical data and underwent chest CT scans. Chest CTs were performed before and after initiation of CFTR modulator treatment. Structural lung abnormalities on CT were assessed using the Perth Rotterdam Annotated Grid Morphometric Analysis for CF (PRAGMA-CF), airway-artery dimensions (AA), and CF-CT methods. Lung disease progression (0-3 years) in exposed and matched unexposed subjects was compared using analysis of covariance. To investigate the effect of treatment in early lung disease, subgroup analyses were performed on data of children and adolescents aged <18 years. Results: We included 16 modulator exposed PwCF and 25 unexposed PwCF. Median (range) age at the baseline visit was 12.55 (4.25-36.49) years and 8.34 (3.47-38.29) years, respectively. The change in PRAGMA-CF %Airway disease (-2.88 (-4.46, -1.30), p = 0.001) and %Bronchiectasis extent (-2.07 (-3.13, -1.02), p < 0.001) improved in exposed PwCF compared to unexposed. Subgroup analysis of paediatric data showed that only PRAGMA-CF %Bronchiectasis (-0.88 (-1.70, -0.07), p = 0.035) improved in exposed PwCF compared to unexposed. Conclusion: In this preliminary real-life retrospective study CFTR modulators improve several quantitative CT outcomes. A follow-up study with a large cohort and standardization of CT scanning is needed to confirm our findings.

Unpaired, unsupervised domain adaptation assumes your domains are already similar.

Unsupervised domain adaptation is a popular method in medical image analysis, but it can be tricky to make it work: without labels to link the domains, domains must be matched using feature distributions. If there is no additional information, this often leaves a choice between multiple possibilities to map the data that may be equally likely but not equally correct. In this paper we explore the fundamental problems that may arise in unsupervised domain adaptation, and discuss conditions that might still make it work. Focusing on medical image analysis, we argue that images from different domains may have similar class balance, similar intensities, similar spatial structure, or similar textures. We demonstrate how these implicit conditions can affect domain adaptation performance in experiments with synthetic data, MNIST digits, and medical images. We observe that practical success of unsupervised domain adaptation relies on existing similarities in the data, and is anything but guaranteed in the general case. Understanding these implicit assumptions is a key step in identifying potential problems in domain adaptation and improving the reliability of the results.

Multivariate brain-based dimensions of child psychiatric problems: degrees of generalizability.

Multivariate machine learning techniques are a promising set of tools for identifying complex brain-behavior associations. However, failure to replicate results from these methods across samples has hampered their clinical relevance. This study aimed to delineate dimensions of brain functional connectivity that are associated with child psychiatric symptoms in two large and independent cohorts: the Adolescent Brain Cognitive Development (ABCD) Study and the Generation R Study (total n =8,605). Using sparse canonical correlations analysis, we identified three brain-behavior dimensions in ABCD: attention problems, aggression and rule-breaking behaviors, and withdrawn behaviors. Importantly, out-of-sample generalizability of these dimensions was consistently observed in ABCD, suggesting robust multivariate brain-behavior associations. Despite this, out-of-study generalizability in Generation R was limited. These results highlight that the degree of generalizability can vary depending on the external validation methods employed as well as the datasets used, emphasizing that biomarkers will remain elusive until models generalize better in true external settings.

Determinants of Perivascular Spaces in the General Population: A Pooled Cohort Analysis of Individual Participant Data.

BACKGROUND AND OBJECTIVES: Perivascular spaces (PVS) are emerging markers of cerebral small vessel disease (CSVD), but research on their determinants has been hampered by conflicting results from small single studies using heterogeneous rating methods. In this study, we therefore aimed to identify determinants of PVS burden in a pooled analysis of multiple cohort studies using 1 harmonized PVS rating method. METHODS: Individuals from 10 population-based cohort studies with adult participants from the Uniform Neuro-Imaging of Virchow-Robin Spaces Enlargement consortium and the UK Biobank were included. On MRI scans, we counted PVS in 4 brain regions (mesencephalon, hippocampus, basal ganglia, and centrum semiovale) according to a uniform and validated rating protocol, both manually and automated using a deep learning algorithm. As potential determinants, we considered demographics, cardiovascular risk factors, APOE genotypes, and other imaging markers of CSVD. Negative binomial regression models were used to examine the association between these determinants and PVS counts. RESULTS: In total, 39,976 individuals were included (age range 20-96 years). The average count of PVS in the 4 regions increased from the age 20 years (0-1 PVS) to 90 years (2-7 PVS). Men had more mesencephalic PVS (OR [95% CI] = 1.13 [1.08-1.18] compared with women), but less hippocampal PVS (0.82 [0.81-0.83]). Higher blood pressure, particularly diastolic pressure, was associated with more PVS in all regions (ORs between 1.04-1.05). Hippocampal PVS showed higher counts with higher high-density lipoprotein cholesterol levels (1.02 [1.01-1.02]), glucose levels (1.02 [1.01-1.03]), and APOE ε4-alleles (1.02 [1.01-1.04]). Furthermore, white matter hyperintensity volume and presence of lacunes were associated with PVS in multiple regions, but most strongly with the basal ganglia (1.13 [1.12-1.14] and 1.10 [1.09-1.12], respectively). DISCUSSION: Various factors are associated with the burden of PVS, in part regionally specific, which points toward a multifactorial origin beyond what can be expected from PVS-related risk factor profiles. This study highlights the power of collaborative efforts in population neuroimaging research.

DS6, Deformation-Aware Semi-Supervised Learning: Application to Small Vessel Segmentation with Noisy Training Data.

Blood vessels of the brain provide the human brain with the required nutrients and oxygen. As a vulnerable part of the cerebral blood supply, pathology of small vessels can cause serious problems such as Cerebral Small Vessel Diseases (CSVD). It has also been shown that CSVD is related to neurodegeneration, such as Alzheimer's disease. With the advancement of 7 Tesla MRI systems, higher spatial image resolution can be achieved, enabling the depiction of very small vessels in the brain. Non-Deep Learning-based approaches for vessel segmentation, e.g., Frangi's vessel enhancement with subsequent thresholding, are capable of segmenting medium to large vessels but often fail to segment small vessels. The sensitivity of these methods to small vessels can be increased by extensive parameter tuning or by manual corrections, albeit making them time-consuming, laborious, and not feasible for larger datasets. This paper proposes a deep learning architecture to automatically segment small vessels in 7 Tesla 3D Time-of-Flight (ToF) Magnetic Resonance Angiography (MRA) data. The algorithm was trained and evaluated on a small imperfect semi-automatically segmented dataset of only 11 subjects; using six for training, two for validation, and three for testing. The deep learning model based on U-Net Multi-Scale Supervision was trained using the training subset and was made equivariant to elastic deformations in a self-supervised manner using deformation-aware learning to improve the generalisation performance. The proposed technique was evaluated quantitatively and qualitatively against the test set and achieved a Dice score of 80.44 ± 0.83. Furthermore, the result of the proposed method was compared against a selected manually segmented region (62.07 resultant Dice) and has shown a considerable improvement (18.98%) with deformation-aware learning.

MRI changes in diaphragmatic motion and curvature in Pompe disease over time.

OBJECTIVES: To evaluate changes in diaphragmatic function in Pompe disease using MRI over time, both during natural disease course and during treatment with enzyme replacement therapy (ERT). METHODS: In this prospective study, 30 adult Pompe patients and 10 healthy controls underwent pulmonary function tests and spirometry-controlled MRI twice, with an interval of 1 year. In the sagittal view of 3D gradient echo breath-hold acquisitions, diaphragmatic motion (cranial-caudal ratio between end-inspiration and end-expiration) and curvature (diaphragm height and area ratio) were calculated using a machine learning algorithm based on convolutional neural networks. Changes in outcomes after 1 year were compared between Pompe patients and healthy controls using the Mann-Whitney test. RESULTS: Pulmonary function outcomes and cranial-caudal ratio in Pompe patients did not change significantly over time compared to healthy controls. Diaphragm height ratio increased by 0.04 (-0.38 to 1.79) in Pompe patients compared to -0.02 (-0.18 to 0.25) in healthy controls (p = 0.02). An increased diaphragmatic curvature over time was observed in particular in untreated Pompe patients (p = 0.03), in those receiving ERT already for over 3 years (p = 0.03), and when severe diaphragmatic weakness was found on the initial MRI (p = 0.01); no progression was observed in Pompe patients who started ERT less than 3 years ago and in Pompe patients with mild diaphragmatic weakness on their initial MRI. CONCLUSIONS: MRI enables to detect small changes in diaphragmatic curvature over 1-year time in Pompe patients. It also showed that once severe diaphragmatic weakness has occurred, improvement of diaphragmatic muscle function seems unlikely. KEY POINTS: • Changes in diaphragmatic curvature in Pompe patients over time assessed with 3D MRI may serve as an outcome measure to evaluate the effect of treatment on diaphragmatic function. • Diaphragmatic curvature showed a significant deterioration after 1 year in Pompe patients compared to healthy controls, but the curvature seems to remain stable over this period in patients who were treated with enzyme replacement therapy for less than 3 years, possibly indicating a positive effect of ERT. • Improvement of diaphragmatic curvature over time is rarely seen in Pompe patients once diaphragmatic motion shows severe impairment (cranial-caudal inspiratory/expiratory ratio < 1.4).

Deep learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge.

A key factor for assessing the state of the heart after myocardial infarction (MI) is to measure whether the myocardium segment is viable after reperfusion or revascularization therapy. Delayed enhancement-MRI or DE-MRI, which is performed 10 min after injection of the contrast agent, provides high contrast between viable and nonviable myocardium and is therefore a method of choice to evaluate the extent of MI. To automatically assess myocardial status, the results of the EMIDEC challenge that focused on this task are presented in this paper. The challenge's main objectives were twofold. First, to evaluate if deep learning methods can distinguish between non-infarct and pathological exams, i.e. exams with or without hyperenhanced area. Second, to automatically calculate the extent of myocardial infarction. The publicly available database consists of 150 exams divided into 50 cases without any hyperenhanced area after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department. Along with MRI, clinical characteristics are also provided. The obtained results issued from several works show that the automatic classification of an exam is a reachable task (the best method providing an accuracy of 0.92), and the automatic segmentation of the myocardium is possible. However, the segmentation of the diseased area needs to be improved, mainly due to the small size of these areas and the lack of contrast with the surrounding structures.

Bronchial wall parameters on CT in healthy never-smoking, smoking, COPD, and asthma populations: a systematic review and meta-analysis.

OBJECTIVE: Research on computed tomography (CT) bronchial parameter measurements shows that there are conflicting results on the values for bronchial parameters in the never-smoking, smoking, asthma, and chronic obstructive pulmonary disease (COPD) populations. This review assesses the current CT methods for obtaining bronchial wall parameters and their comparison between populations. METHODS: A systematic review of MEDLINE and Embase was conducted following PRISMA guidelines (last search date 25th October 2021). Methodology data was collected and summarised. Values of percentage wall area (WA%), wall thickness (WT), summary airway measure (Pi10), and luminal area (Ai) were pooled and compared between populations. RESULTS: A total of 169 articles were included for methodologic review; 66 of these were included for meta-analysis. Most measurements were obtained from multiplanar reconstructions of segmented airways (93 of 169 articles), using various tools and algorithms; third generation airways in the upper and lower lobes were most frequently studied. COPD (12,746) and smoking (15,092) populations were largest across studies and mostly consisted of men (median 64.4%, IQR 61.5 - 66.1%). There were significant differences between populations; the largest WA% was found in COPD (mean SD 62.93 ± 7.41%, n = 6,045), and the asthma population had the largest Pi10 (4.03 ± 0.27 mm, n = 442). Ai normalised to body surface area (Ai/BSA) (12.46 ± 4 mm2, n = 134) was largest in the never-smoking population. CONCLUSIONS: Studies on CT-derived bronchial parameter measurements are heterogenous in methodology and population, resulting in challenges to compare outcomes between studies. Significant differences between populations exist for several parameters, most notably in the wall area percentage; however, there is a large overlap in their ranges. KEY POINTS: • Diverse methodology in measuring airways contributes to overlap in ranges of bronchial parameters among the never-smoking, smoking, COPD, and asthma populations. • The combined number of never-smoking participants in studies is low, limiting insight into this population and the impact of participant characteristics on bronchial parameters. • Wall area percent of the right upper lobe apical segment is the most studied (87 articles) and differentiates all except smoking vs asthma populations.

Diaphragmatic dysfunction in neuromuscular disease, an MRI study.

The aim of this exploratory study was to evaluate diaphragmatic function across various neuromuscular diseases using spirometry-controlled MRI. We measured motion of the diaphragm relative to that of the thoracic wall (cranial-caudal ratio vs. anterior posterior ratio; CC-AP ratio), and changes in the diaphragmatic curvature (diaphragm height and area ratio) during inspiration in 12 adults with a neuromuscular disease having signs of respiratory muscle weakness, 18 healthy controls, and 35 adult Pompe patients - a group with prominent diaphragmatic weakness. CC-AP ratio was lower in patients with myopathies (n=7, 1.25±0.30) and motor neuron diseases (n=5, 1.30±0.10) than in healthy controls (1.37±0.14; p=0.001 and p=0.008), but not as abnormal as in Pompe patients (1.12±0.18; p=0.011 and p=0.024). The mean diaphragm height ratio was 1.17±0.33 in patients with myopathies, pointing at an insufficient diaphragmatic contraction. This was also seen in patients with Pompe disease (1.28±0.36), but not in healthy controls (0.82±0.33) or patients with motor neuron disease (0.82±0.24). We conclude that spirometry-controlled MRI enables us to investigate respiratory dysfunction across neuromuscular diseases, suggesting that the diaphragm is affected in a different way in myopathies and motor neuron diseases. Whether MRI can also be used to evaluate progression of diaphragmatic dysfunction requires additional studies.

Sleep and perivascular spaces in the middle-aged and elderly population.

Sleep has been hypothesised to facilitate waste clearance from the brain. We aimed to determine whether sleep is associated with perivascular spaces on brain magnetic resonance imaging (MRI), a potential marker of impaired brain waste clearance, in a population-based cohort of middle-aged and elderly people. In 559 participants (mean [SD] age 62 [6] years, 52% women) from the population-based Rotterdam Study, we measured total sleep time, sleep onset latency, wake after sleep onset and sleep efficiency with actigraphy and polysomnography. Perivascular space load was determined with brain MRI in four regions (centrum semiovale, basal ganglia, hippocampus, and midbrain) via a validated machine learning algorithm using T2-weighted MR images. Associations between sleep characteristics and perivascular space load were analysed with zero-inflated negative binomial regression models adjusted for various confounders. We found that higher actigraphy-estimated sleep efficiency was associated with a higher perivascular space load in the centrum semiovale (odds ratio 1.10, 95% confidence interval 1.04-1.16, p = 0.0008). No other actigraphic or polysomnographic sleep characteristics were associated with perivascular space load in other brain regions. We conclude that, contrary to our hypothesis, associations of sleep with perivascular space load in this middle-aged and elderly population remained limited to an association of a high actigraphy-estimated sleep efficiency with a higher perivascular space load in the centrum semiovale.

An end-to-end approach to segmentation in medical images with CNN and posterior-CRF.

Conditional Random Fields (CRFs) are often used to improve the output of an initial segmentation model, such as a convolutional neural network (CNN). Conventional CRF approaches in medical imaging use manually defined features, such as intensity to improve appearance similarity or location to improve spatial coherence. These features work well for some tasks, but can fail for others. For example, in medical image segmentation applications where different anatomical structures can have similar intensity values, an intensity-based CRF may produce incorrect results. As an alternative, we propose Posterior-CRF, an end-to-end segmentation method that uses CNN-learned features in a CRF and optimizes the CRF and CNN parameters concurrently. We validate our method on three medical image segmentation tasks: aorta and pulmonary artery segmentation in non-contrast CT, white matter hyperintensities segmentation in multi-modal MRI, and ischemic stroke lesion segmentation in multi-modal MRI. We compare this with the state-of-the-art CNN-CRF methods. In all applications, our proposed method outperforms the existing methods in terms of Dice coefficient, average volume difference, and lesion-wise F1 score.

Creating a training set for artificial intelligence from initial segmentations of airways.

Airways segmentation is important for research about pulmonary disease but require a large amount of time by trained specialists. We used an openly available software to improve airways segmentations obtained from an artificial intelligence (AI) tool and retrained the tool to get a better performance. Fifteen initial airway segmentations from low-dose chest computed tomography scans were obtained with a 3D-Unet AI tool previously trained on Danish Lung Cancer Screening Trial and Erasmus-MC Sophia datasets. Segmentations were manually corrected in 3D Slicer. The corrected airway segmentations were used to retrain the 3D-Unet. Airway measurements were automatically obtained and included count, airway length and luminal diameter per generation from the segmentations. Correcting segmentations required 2-4 h per scan. Manually corrected segmentations had more branches (p < 0.001), longer airways (p < 0.001) and smaller luminal diameters (p = 0.004) than initial segmentations. Segmentations from retrained 3D-Unets trended towards more branches and longer airways compared to the initial segmentations. The largest changes were seen in airways from 6th generation onwards. Manual correction results in significantly improved segmentations and is potentially a useful and time-efficient method to improve the AI tool performance on a specific hospital or research dataset.

Automated Segmentation and Volume Measurement of Intracranial Internal Carotid Artery Calcification at Noncontrast CT.

PURPOSE: To develop and evaluate a fully-automated deep learning-based method for assessment of intracranial internal carotid artery calcification (ICAC). MATERIALS AND METHODS: This was a secondary analysis of prospectively collected data from the Rotterdam study (2003-2006) to develop and validate a deep learning-based method for automated ICAC delineation and volume measurement. Two observers manually delineated ICAC on noncontrast CT scans of 2319 participants (mean age, 69 years ± 7 [standard deviation]; 1154 women [53.2%]), and a deep learning model was trained to segment ICAC and quantify its volume. Model performance was assessed by comparing manual and automated segmentations and volume measurements to those produced by an independent observer (available on 47 scans), comparing the segmentation accuracy in a blinded qualitative visual comparison by an expert observer, and comparing the association with first stroke incidence from the scan date until 2016. All method performance metrics were computed using 10-fold cross-validation. RESULTS: The automated delineation of ICAC reached a sensitivity of 83.8% and positive predictive value (PPV) of 88%. The intraclass correlation between automatic and manual ICAC volume measures was 0.98 (95% CI: 0.97, 0.98; computed in the entire dataset). Measured between the assessments of independent observers, sensitivity was 73.9%, PPV was 89.5%, and intraclass correlation coefficient was 0.91 (95% CI: 0.84, 0.95; computed in the 47-scan subset). In the blinded visual comparisons of 294 regions, automated delineations were judged as more accurate than manual delineations in 131 regions, less accurate in 94 regions, and equally accurate in the rest of the regions (131 of 225, 58.2%; P = .01). The association of ICAC volume with incident stroke was similarly strong for both automated (hazard ratio, 1.38 [95% CI: 1.12, 1.75]) and manually measured volumes (hazard ratio, 1.48 [95% CI: 1.20, 1.87]). CONCLUSION: The developed model was capable of automated segmentation and volume quantification of ICAC with accuracy comparable to human experts.Keywords CT, Neural Networks, Carotid Arteries, Calcifications/Calculi, Arteriosclerosis, Segmentation, Vision Application Domain, Stroke Supplemental material is available for this article. © RSNA, 2021.