Automated Assessment of T2-Weighted MRI to Differentiate Malignant and Benign Primary Solid Liver Lesions in Noncirrhotic Livers Using Radiomics

RATIONALE AND OBJECTIVES

Distinguishing malignant from benign liver lesions based on magnetic resonance imaging (MRI) is an important but often challenging task, especially in noncirrhotic livers. We developed and externally validated a radiomics model to quantitatively assess T2-weighted MRI to distinguish the most common malignant and benign primary solid liver lesions in noncirrhotic livers.

MATERIALS AND METHODS

Data sets were retrospectively collected from three tertiary referral centers (A, B, and C) between 2002 and 2018. Patients with malignant (hepatocellular carcinoma and intrahepatic cholangiocarcinoma) and benign (hepatocellular adenoma and focal nodular hyperplasia) lesions were included. A radiomics model based on T2-weighted MRI was developed in data set A using a combination of machine learning approaches. The model was internally evaluated on data set A through cross-validation, externally validated on data sets B and C, and compared to visual scoring of two experienced abdominal radiologists on data set C.

RESULTS

The overall data set included 486 patients (A: 187, B: 98, and C: 201). The radiomics model had a mean area under the curve (AUC) of 0.78 upon internal validation on data set A and a similar AUC in external validation (B: 0.74 and C: 0.76). In data set C, the two radiologists showed moderate agreement (Cohen's κ: 0.61) and achieved AUCs of 0.86 and 0.82.

CONCLUSION

Our T2-weighted MRI radiomics model shows potential for distinguishing malignant from benign primary solid liver lesions. External validation indicated that the model is generalizable despite substantial MRI acquisition protocol differences. Pending further optimization and generalization, this model may aid radiologists in improving the diagnostic workup of patients with liver lesions.

Social Health Is Associated With Tract-Specific Brain White Matter Microstructure in Community-Dwelling Older Adults

Background

Poor social health has been linked to a risk of neuropsychiatric disorders. Neuroimaging studies have shown associations between social health and global white matter microstructural integrity. We aimed to identify which white matter tracts are involved in these associations.

Methods

Social health markers (loneliness, perceived social support, and partnership status) and white matter microstructural integrity of 15 white matter tracts (identified with probabilistic tractography after diffusion magnetic resonance imaging) were collected for 3352 participants (mean age 58.4 years, 54.9% female) from 2002 to 2008 in the Rotterdam Study. Cross-sectional associations were studied using multivariable linear regression.

Results

Loneliness was associated with higher mean diffusivity (MD) in the superior thalamic radiation and the parahippocampal part of the cingulum (standardized mean difference for both tracts: 0.21, 95% CI, 0.09 to 0.34). Better perceived social support was associated with lower MD in the forceps minor (standardized mean difference per point increase in social support: -0.06, 95% CI, -0.09 to -0.03), inferior fronto-occipital fasciculus, and uncinate fasciculus. In male participants, better perceived social support was associated with lower MD in the forceps minor, and not having a partner was associated with lower fractional anisotropy in the forceps minor. Loneliness was associated with higher MD in the superior thalamic radiation in female participants only.

Conclusions

Social health was associated with tract-specific white matter microstructure. Loneliness was associated with lower integrity of limbic and sensorimotor tracts, whereas better perceived social support was associated with higher integrity of association and commissural tracts, indicating that social health domains involve distinct neural pathways of the brain.

Towards quantitative digital subtraction perfusion angiography: An animal study

BACKGROUND

X-ray digital subtraction angiography (DSA) is the imaging modality for peri-procedural guidance and treatment evaluation in (neuro-) vascular interventions. Perfusion image construction from DSA, as a means of quantitatively depicting cerebral hemodynamics, has been shown feasible. However, the quantitative property of perfusion DSA has not been well studied.

PURPOSE

To comparatively study the independence of deconvolution-based perfusion DSA with respect to varying injection protocols, as well as its sensitivity to alterations in brain conditions.

METHODS

We developed a deconvolution-based algorithm to compute perfusion parametric images from DSA, including cerebral blood volume (CBV D S A $_{DSA}$ ), cerebral blood flow (CBF D S A $_{DSA}$ ), time to maximum (Tmax), and mean transit time (MTT D S A $_{DSA}$ ) and applied it to DSA sequences obtained from two swine models. We also extracted the time intensity curve (TIC)-derived parameters, that is, area under the curve (AUC), peak concentration of the curve, and the time to peak (TTP) from these sequences. Deconvolution-based parameters were quantitatively compared to TIC-derived parameters in terms of consistency upon variations in injection profile and time resolution of DSA, as well as sensitivity to alterations of cerebral condition.

RESULTS

Comparing to TIC-derived parameters, the standard deviation (SD) of deconvolution-based parameters (normalized with respect to the mean) are two to five times smaller, indicating that they are more consistent across different injection protocols and time resolutions. Upon ischemic stroke induced in a swine model, the sensitivities of deconvolution-based parameters are equal to, if not higher than, those of TIC-derived parameters.

CONCLUSIONS

In comparison to TIC-derived parameters, deconvolution-based perfusion imaging in DSA shows significantly higher quantitative reliability against variations in injection protocols across different time resolutions, and is sensitive to alterations in cerebral hemodynamics. The quantitative nature of perfusion angiography may allow for objective treatment assessment in neurovascular interventions.

NT-proBNP and changes in cognition and global brain structure: the Rotterdam Study

OBJECTIVE

To investigate the association between NT-proBNP and changes in cognition and global brain structure.

METHODS

In the Rotterdam Study, baseline NT-proBNP was assessed at baseline from 1997 to 2008. Between 1997-2016, participants without dementia or stroke at baseline (n= 9,566) had repeated cognitive tests (every 3-6 years) for global cognitive function, executive cognitive function, fine manual dexterity, and memory. Magnetic resonance imaging of the brain was performed repeatedly at re-examination visits between 2005 and 2015 for 2,607 participants to obtain brain volumes, focal brain lesions, and white matter microstructural integrity as measures of brain structure.

RESULTS

Among 9,566 participants (mean age 65.1±9.8 years), 5,444 (56.9%) were women, and repeated measures of cognition were performed during a median follow-up time of 5.5 years (range = 1.1-17.9), of whom 2,607 participants completed at least one brain imaging scans. Higher levels of NT-proBNP were associated with a faster decline of scores in the global cognitive function (P value = 0.003), and the Word-Fluency test (P value = 0.003), but were not related to a steeper deterioration in brain volumes, global fractional anisotropy and mean diffusivity, as indicators of white matter microstructural integrity, or focal brain lesions.

CONCLUSIONS

Higher baseline NT-proBNP levels were associated with a faster decline in cognition, however, no association with global brain structure was found.

Computational methods for the analysis of early-pregnancy brain ultrasonography: a systematic review

BACKGROUND

Early screening of the brain is becoming routine clinical practice. Currently, this screening is performed by manual measurements and visual analysis, which is time-consuming and prone to errors. Computational methods may support this screening. Hence, the aim of this systematic review is to gain insight into future research directions needed to bring automated early-pregnancy ultrasound analysis of the human brain to clinical practice.

METHODS

We searched PubMed (Medline ALL Ovid), EMBASE, Web of Science Core Collection, Cochrane Central Register of Controlled Trials, and Google Scholar, from inception until June 2022. This study is registered in PROSPERO at CRD42020189888. Studies about computational methods for the analysis of human brain ultrasonography acquired before the 20th week of pregnancy were included. The key reported attributes were: level of automation, learning-based or not, the usage of clinical routine data depicting normal and abnormal brain development, public sharing of program source code and data, and analysis of the confounding factors.

FINDINGS

Our search identified 2575 studies, of which 55 were included. 76% used an automatic method, 62% a learning-based method, 45% used clinical routine data and in addition, for 13% the data depicted abnormal development. None of the studies shared publicly the program source code and only two studies shared the data. Finally, 35% did not analyse the influence of confounding factors.

INTERPRETATION

Our review showed an interest in automatic, learning-based methods. To bring these methods to clinical practice we recommend that studies: use routine clinical data depicting both normal and abnormal development, make their dataset and program source code publicly available, and be attentive to the influence of confounding factors. Introduction of automated computational methods for early-pregnancy brain ultrasonography will save valuable time during screening, and ultimately lead to better detection, treatment and prevention of neuro-developmental disorders.

FUNDING

The Erasmus MC Medical Research Advisor Committee (grant number: FB 379283).

Evaluation of AR visualization approaches for catheter insertion into the ventricle cavity

Augmented reality (AR) has shown potential in computer-aided surgery. It allows for the visualization of hidden anatomical structures as well as assists in navigating and locating surgical instruments at the surgical site. Various modalities (devices and/or visualizations) have been used in the literature, but few studies investigated the adequacy/superiority of one modality over the other. For instance, the use of optical see-through (OST) HMDs has not always been scientifically justified. Our goal is to compare various visualization modalities for catheter insertion in external ventricular drain and ventricular shunt procedures. We investigate two AR approaches: (1) 2D approaches consisting of a smartphone and a 2D window visualized through an OST (Microsoft HoloLens 2), and (2) 3D approaches consisting of a fully aligned patient model and a model that is adjacent to the patient and is rotationally aligned using an OST. 32 participants joined this study. For each visualization approach, participants were asked to perform five insertions after which they filled NASA-TLX and SUS forms. Moreover, the position and orientation of the needle with respect to the planning during the insertion task were collected. The results show that participants achieved a better insertion performance significantly under 3D visualizations, and the NASA-TLX and SUS forms reflected the preference of participants for these approaches compared to 2D approaches.

Subclinical liver traits are associated with structural and hemodynamic brain imaging markers

BACKGROUND & AIMS

Impaired liver function affects brain health and therefore understanding potential mechanisms for subclinical liver disease is essential. We assessed the liver-brain associations using liver measures with brain imaging markers, and cognitive measures in the general population.

METHODS

Within the population-based Rotterdam Study, liver serum and imaging measures (ultrasound and transient elastography), metabolic dysfunction-associated fatty liver disease (MAFLD), non-alcoholic fatty liver disease (NAFLD) and fibrosis phenotypes, and brain structure were determined in 3493 non-demented and stroke-free participants in 2009-2014. This resulted in subgroups of n = 3493 for MAFLD (mean age 69 ± 9 years, 56% ♀), n = 2938 for NAFLD (mean age 70 ± 9 years, 56% ♀) and n = 2252 for fibrosis (mean age 65 ± 7 years, 54% ♀). Imaging markers of small vessel disease and neurodegeneration, cerebral blood flow (CBF) and brain perfusion (BP) were acquired from brain MRI (1.5-tesla). General cognitive function was assessed by Mini-Mental State Examination and the g-factor. Multiple linear and logistic regression models were used for liver-brain associations and adjusted for age, sex, intracranial volume, cardiovascular risk factors and alcohol use.

RESULTS

Higher gamma-glutamyltransferase (GGT) levels were significantly associated with smaller total brain volume (TBV, standardized mean difference (SMD), -0.02, 95% confidence interval (CI) (-0.03 to -0.01); p = 8.4·10^-4 ), grey matter volumes, and lower CBF and BP. Liver serum measures were not related to small vessel disease markers, nor to white matter microstructural integrity or general cognition. Participants with ultrasound-based liver steatosis had a higher fractional anisotropy (FA, SMD 0.11, 95% CI (0.04 to 0.17), p = 1.5·10^-3 ) and lower CBF and BP. MAFLD and NAFLD phenotypes were associated with alterations in white matter microstructural integrity (NAFLD ~ FA, SMD 0.14, 95% CI (0.07 to 0.22), p = 1.6·10^-4 ; NAFLD ~ mean diffusivity, SMD -0.12, 95% CI (-0.18 to -0.05), p = 4.7·10^-4 ) and also with lower CBF and BP (MAFLD ~ CBF, SMD -0.13, 95% CI (-0.20 to -0.06), p = 3.1·10^-4 ; MAFLD ~ BP, SMD -0.12, 95% CI (-0.20 to -0.05), p = 1.6·10^-3 ). Furthermore, fibrosis phenotypes were related to TBV, grey and white matter volumes.

CONCLUSIONS

Presence of liver steatosis, fibrosis and elevated serum GGT are associated with structural and hemodynamic brain markers in a population-based cross-sectional setting. Understanding the hepatic role in brain changes can target modifiable factors and prevent brain dysfunction.

Association between prenatal alcohol exposure and children's facial shape: a prospective population-based cohort study

STUDY QUESTION

Is there an association between low-to-moderate levels of prenatal alcohol exposure (PAE) and children's facial shape?

SUMMARY ANSWER

PAE before and during pregnancy, even at low level (<12 g of alcohol per week), was found associated with the facial shape of children, and these associations were found attenuated as children grow older.

WHAT IS KNOWN ALREADY

High levels of PAE during pregnancy can have significant adverse associations with a child's health development resulting in recognizably abnormal facial development.

STUDY DESIGN, SIZE, DURATION

This study was based on the Generation R Study, a prospective cohort from fetal life onwards with maternal and offspring data. We analyzed children 3-dimensional (3D) facial images taken at ages 9 (n = 3149) and 13 years (n = 2477) together with the data of maternal alcohol consumption.

PARTICIPANTS/MATERIALS, SETTING, METHODS

We defined six levels of PAE based on the frequency and dose of alcohol consumption and defined three tiers based on the timing of alcohol exposure of the unborn child. For the image analysis, we used 3D graph convolutional networks for non-linear dimensionality reduction, which compressed the high-dimensional images into 200 traits representing facial morphology. These 200 traits were used for statistical analysis to search for associations with PAE. Finally, we generated heatmaps to display the facial phenotypes associated with PAE.

MAIN RESULTS AND THE ROLE OF CHANCE

The results of the linear regression in the 9-year-old children survived correction for multiple testing with false discovery rate (FDR). In Tier 1 where we examined PAE only before pregnancy (exposed N = 278, unexposed N = 760), we found three traits survived FDR correction. The lowest FDR-P is 1.7e-05 (beta = 0.021, SE = 0.0040) in Trait #29; In Tier 2b where we examine any PAE during first trimester (exposed N = 756; unexposed N = 760), we found eight traits survived FDR correction. The lowest FDR-P is 9.0e-03 (beta = -0.013, SE = 0.0033) in Trait #139. Moreover, more statistically significant facial traits were found in higher levels of PAE. No FDR-significant results were found in the 13-year-old children. We map these significant traits back to the face, and found the most common detected facial phenotypes included turned-up nose tip, shortened nose, turned-out chin, and turned-in lower-eyelid-related regions.

LIMITATIONS, REASONS FOR CAUTION

We had no data for alcohol consumption more than three months prior to pregnancy and thus do not know if maternal drinking had chronic effects. The self-reported questionnaire might not reflect accurate alcohol measurements because mothers may have denied their alcohol consumption.

WIDER IMPLICATIONS OF THE FINDINGS

Our results imply that facial morphology, such as quantified by the approach we proposed here, can be used as a biomarker in further investigations. Furthermore, our study suggests that for women who are pregnant or want to become pregnant soon, should quit alcohol consumption several months before conception and completely during pregnancy to avoid adverse health outcomes in the offspring.

STUDY FUNDING/COMPETING INTEREST(S)

This work was supported by Erasmus Medical Centre, Rotterdam, the Erasmus University Rotterdam, and the Netherlands Organization for Health Research. V.W.V.J. reports receipt of funding from the Netherlands Organization for Health Research (ZonMw 90700303). W.J.N. is a founder, a scientific lead, and a shareholder of Quantib BV.

TRIAL REGISTRATION NUMBER

N/A.

Deep reinforcement learning for cerebral anterior vessel tree extraction from 3D CTA images

Extracting the cerebral anterior vessel tree of patients with an intracranial large vessel occlusion (LVO) is relevant to investigate potential biomarkers that can contribute to treatment decision making. The purpose of our work is to develop a method that can achieve this from routinely acquired computed tomography angiography (CTA) and computed tomography perfusion (CTP) images. To this end, we regard the anterior vessel tree as a set of bifurcations and connected centerlines. The method consists of a proximal policy optimization (PPO) based deep reinforcement learning (DRL) approach for tracking centerlines, a convolutional neural network based bifurcation detector, and a breadth-first vessel tree construction approach taking the tracking and bifurcation detection results as input. We experimentally determine the added values of various components of the tracker. Both DRL vessel tracking and CNN bifurcation detection were assessed in a cross validation experiment using 115 subjects. The anterior vessel tree formation was evaluated on an independent test set of 25 subjects, and compared to interobserver variation on a small subset of images. The DRL tracking result achieves a median overlapping rate until the first error (1.8 mm off the reference standard) of 100, [46, 100] % on 8032 vessels over 115 subjects. The bifurcation detector reaches an average recall and precision of 76% and 87% respectively during the vessel tree formation process. The final vessel tree formation achieves a median recall of 68% and precision of 70%, which is in line with the interobserver agreement.

Time dependency of automated collateral scores in computed tomography angiography and computed tomography perfusion images in patients with intracranial arterial occlusion

PURPOSE

The assessment of collateral status may depend on the timing of image acquisition. The purpose of this study is to investigate whether there are optimal time points in CT Perfusion (CTP) for collateral status assessment, and compare collaterals scores at these time points with collateral scores from multiphase CT angiography (mCTA).

METHODS

Patients with an acute intracranial occlusion who underwent baseline non-contrast CT, mCTA and CT perfusion were selected. Collateral status was assessed using an automatically computed Collateral Ratio (CR) score in mCTA, and predefined time points in CTP acquisition. CRs extracted from CTP were correlated with CRs from mCTA. In addition, all CRs were related to baseline National Institutes of Health Stroke Scale (NIHSS) and Alberta Stoke Program Early CT Score (ASPECTS) with linear regression analysis to find the optimal CR.

RESULTS

In total 58 subjects (median age 74 years; interquartile range 61-83 years; 33 male) were included. When comparing the CRs from the CTP vs. mCTA acquisition, the strongest correlations were found between CR from baseline mCTA and the CR at the maximal intensity projection of time-resolved CTP (r = 0.81) and the CR at the peak of arterial enhancement point (r = 0.78). Baseline mCTA-derived CR had the highest correlation with ASPECTS (β = 0.36 (95%CI 0.11, 0.61)) and NIHSS (β = - 0.48 (95%CI - 0.72, - 0.16)).

CONCLUSION

Collateral status assessment strongly depends on the timing of acquisition. Collateral scores obtained from mCTA imaging is close to the optimal collateral score obtained from CTP imaging.

Cardiac dysfunction in relation to vascular brain injury, cognitive impairment and depressive symptoms; The Heart-Brain Connection Study

Introduction

Cardiovascular disease is an independent contributor to cognitive impairment. With an imminent rise in chronic cardiovascular disease, a better understanding of its effects on brain health is warranted. Impaired blood flow to the brain is one of the main hypothesized mechanisms linking cardiovascular disease with abnormal brain aging.

Purpose

To investigate relations between (subclinical) cardiac dysfunction and vascular brain injury, cognitive impairment and depressive symptoms, with a side-by-side comparison of cardiac biomarkers and imaging parameters.

Methods

Multicenter, cross-sectional, observational cohort study among 559 participants: 431 with manifest cardiovascular disease (heart failure [HF], carotid occlusive disease or vascular cognitive impairment) and 128 control participants, all without dementia. Participants underwent 3T heart-brain MRI and cognitive testing. Determinants were cardiac biomarkers (NT-proBNP and high-sensitive Troponin-I) and left ventricular (LV) functional parameters by MRI (LV ejection fraction, cardiac output, LV global function index). Outcome measures were cerebral small vessel disease (CSVD) by MRI (presence of white matter hyperintensities, microbleeds, lacunar infarcts or perivascular spaces), CSVD score (0–4), cognitive impairment in ≥1 domain (memory, language, attention-psychomotor speed and executive functioning) and depressive symptoms (Geriatric Depression Scale-15 score &gt;5). Interaction analyses were used to investigate effect modification by patient group; results are reported pooled or stratified accordingly.

Results

In patients with cardiovascular disease and controls, but not in those with manifest HF, LV functional parameters were associated with CSVD and cognitive impairment, with the following associations: LVEF &lt;50% with CSVD (OR 4.67 [1.37–15.95]) and CSVD score (RR 1.38 [1.06–1.81]); LV global function index with CSVD (OR 0.71 [0.58–0.86]), CSVD score (RR 0.90 [0.84–0.96]) and cognitive impairment (OR 0.84 [0.72–0.97]). LV global function index (OR 0.82 [0.71–0.95]) and cardiac output (OR 0.81 [0.71–0.93]) were also associated with depressive symptoms in all. These relations were independent from age, sex, hypertension, diabetes, waist-hipratio, history of ischemic heart disease, transient ischemic attack or stroke. Cardiac biomarkers were univariably associated with brain outcome measures, but not in multivariable analysis.

Conclusion

This study indicates that subclinical cardiac dysfunction, as assessed by cardiovascular MRI, is independently associated with vascular brain injury, cognitive impairment and depressive symptoms. Of all parameters, LV global function index showed the most robust relations, indicating that global cardiac performance is more closely related to poorer brain outcome than merely LV systolic function. In those with clinically manifest HF, the severity of cardiac dysfunction was related to depressive symptoms but not to other brain outcome measures.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): The Netherlands CardioVascular Research Initiative; The Dutch Heart Foundation

Combined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning

BACKGROUND

Accurate characterization of glioma is crucial for clinical decision making. A delineation of the tumor is also desirable in the initial decision stages but is time-consuming. Previously, deep learning methods have been developed that can either non-invasively predict the genetic or histological features of glioma, or that can automatically delineate the tumor, but not both tasks at the same time. Here, we present our method that can predict the molecular subtype and grade, while simultaneously providing a delineation of the tumor.

METHODS

We developed a single multi-task convolutional neural network that uses the full 3D, structural, preoperative MRI scans to predict the IDH mutation status, the 1p/19q co-deletion status, and the grade of a tumor, while simultaneously segmenting the tumor. We trained our method using a patient cohort containing 1508 glioma patients from 16 institutes. We tested our method on an independent dataset of 240 patients from 13 different institutes.

RESULTS

In the independent test set, we achieved an IDH-AUC of 0.90, an 1p/19q co-deletion AUC of 0.85, and a grade AUC of 0.81 (grade II/III/IV). For the tumor delineation, we achieved a mean whole tumor Dice score of 0.84.

CONCLUSIONS

We developed a method that non-invasively predicts multiple, clinically relevant features of glioma. Evaluation in an independent dataset shows that the method achieves a high performance and that it generalizes well to the broader clinical population. This first-of-its-kind method opens the door to more generalizable, instead of hyper-specialized, AI methods.

A data-driven disease progression model of fluid biomarkers in genetic frontotemporal dementia

Several CSF and blood biomarkers for genetic frontotemporal dementia have been proposed, including those reflecting neuroaxonal loss (neurofilament light chain and phosphorylated neurofilament heavy chain), synapse dysfunction [neuronal pentraxin 2 (NPTX2)], astrogliosis (glial fibrillary acidic protein) and complement activation (C1q, C3b). Determining the sequence in which biomarkers become abnormal over the course of disease could facilitate disease staging and help identify mutation carriers with prodromal or early-stage frontotemporal dementia, which is especially important as pharmaceutical trials emerge. We aimed to model the sequence of biomarker abnormalities in presymptomatic and symptomatic genetic frontotemporal dementia using cross-sectional data from the Genetic Frontotemporal dementia Initiative (GENFI), a longitudinal cohort study. Two-hundred and seventy-five presymptomatic and 127 symptomatic carriers of mutations in GRN, C9orf72 or MAPT, as well as 247 non-carriers, were selected from the GENFI cohort based on availability of one or more of the aforementioned biomarkers. Nine presymptomatic carriers developed symptoms within 18 months of sample collection ('converters'). Sequences of biomarker abnormalities were modelled for the entire group using discriminative event-based modelling (DEBM) and for each genetic subgroup using co-initialized DEBM. These models estimate probabilistic biomarker abnormalities in a data-driven way and do not rely on previous diagnostic information or biomarker cut-off points. Using cross-validation, subjects were subsequently assigned a disease stage based on their position along the disease progression timeline. CSF NPTX2 was the first biomarker to become abnormal, followed by blood and CSF neurofilament light chain, blood phosphorylated neurofilament heavy chain, blood glial fibrillary acidic protein and finally CSF C3b and C1q. Biomarker orderings did not differ significantly between genetic subgroups, but more uncertainty was noted in the C9orf72 and MAPT groups than for GRN. Estimated disease stages could distinguish symptomatic from presymptomatic carriers and non-carriers with areas under the curve of 0.84 (95% confidence interval 0.80-0.89) and 0.90 (0.86-0.94) respectively. The areas under the curve to distinguish converters from non-converting presymptomatic carriers was 0.85 (0.75-0.95). Our data-driven model of genetic frontotemporal dementia revealed that NPTX2 and neurofilament light chain are the earliest to change among the selected biomarkers. Further research should investigate their utility as candidate selection tools for pharmaceutical trials. The model's ability to accurately estimate individual disease stages could improve patient stratification and track the efficacy of therapeutic interventions.

Augmented reality navigation for minimally invasive craniosynostosis surgery: a phantom study

Purpose

In minimally invasive spring-assisted craniectomy, surgeons plan the surgery by manually locating the cranial sutures. However, this approach is prone to error. Augmented reality (AR) could be used to visualize the cranial sutures and assist in the surgery planning. The purpose of our work is to develop an AR-based system to visualize cranial sutures, and to assess the accuracy and usability of using AR-based navigation for surgical guidance in minimally invasive spring-assisted craniectomy.

Methods

An AR system was developed that consists of an electromagnetic tracking system linked with a Microsoft HoloLens. The system was used to conduct a study with two skull phantoms. For each phantom, five sutures were annotated and visualized on the skull surface. Twelve participants assessed the system. For each participant, model alignment using six anatomical landmarks was performed, followed by the participant delineation of the visualized sutures. At the end, the participants filled a system usability scale (SUS) questionnaire. For evaluation, an independent optical tracking system was used and the delineated sutures were digitized and compared to the CT-annotated sutures.

Results

For a total of 120 delineated sutures, the distance of the annotated sutures to the planning reference was \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$2.4\pm 1.2$$\end{document}2.4±1.2 mm. The average delineation time per suture was \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$13\pm 5$$\end{document}13±5 s. For the system usability questionnaire, an average SUS score of 73 was obtained.

Conclusion

The developed AR-system has good accuracy (average 2.4 mm distance) and could be used in the OR. The system can assist in the pre-planning of minimally invasive craniosynostosis surgeries to locate cranial sutures accurately instead of the traditional approach of manual palpation. Although the conducted phantom study was designed to closely reflect the clinical setup in the OR, further clinical validation of the developed system is needed and will be addressed in a future work.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11548-022-02634-y.

Optimization of Preoperative Lymph Node Staging in Patients with Muscle-Invasive Bladder Cancer Using Radiomics on Computed Tomography

Approximately 25% of the patients with muscle-invasive bladder cancer (MIBC) who are clinically node negative have occult lymph node metastases at radical cystectomy (RC) and pelvic lymph node dissection. The aim of this study was to evaluate preoperative CT-based radiomics to differentiate between pN+ and pN0 disease in patients with clinical stage cT2-T4aN0-N1M0 MIBC. Patients with cT2-T4aN0-N1M0 MIBC, of whom preoperative CT scans and pathology reports were available, were included from the prospective, multicenter CirGuidance trial. After manual segmentation of the lymph nodes, 564 radiomics features were extracted. A combination of different machine-learning methods was used to develop various decision models to differentiate between patients with pN+ and pN0 disease. A total of 209 patients (159 pN0; 50 pN+) were included, with a total of 3153 segmented lymph nodes. None of the individual radiomics features showed significant differences between pN+ and pN0 disease, and none of the radiomics models performed substantially better than random guessing. Hence, CT-based radiomics does not contribute to differentiation between pN+ and pN0 disease in patients with cT2-T4aN0-N1M0 MIBC.

Differential Diagnosis and Molecular Stratification of Gastrointestinal Stromal Tumors on CT Images Using a Radiomics Approach

Treatment planning of gastrointestinal stromal tumors (GISTs) includes distinguishing GISTs from other intra-abdominal tumors and GISTs’ molecular analysis. The aim of this study was to evaluate radiomics for distinguishing GISTs from other intra-abdominal tumors, and in GISTs, predict the c-KIT, PDGFRA, BRAF mutational status, and mitotic index (MI). Patients diagnosed at the Erasmus MC between 2004 and 2017, with GIST or non-GIST intra-abdominal tumors and a contrast-enhanced venous-phase CT, were retrospectively included. Tumors were segmented, from which 564 image features were extracted. Prediction models were constructed using a combination of machine learning approaches. The evaluation was performed in a 100 × random-split cross-validation. Model performance was compared to that of three radiologists. One hundred twenty-five GISTs and 122 non-GISTs were included. The GIST vs. non-GIST radiomics model had a mean area under the curve (AUC) of 0.77. Three radiologists had an AUC of 0.69, 0.76, and 0.84, respectively. The radiomics model had an AUC of 0.52 for c-KIT, 0.56 for c-KIT exon 11, and 0.52 for the MI. The numbers of PDGFRA, BRAF, and other c-KIT mutations were too low for analysis. Our radiomics model was able to distinguish GISTs from non-GISTs with a performance similar to three radiologists, but less observer dependent. Therefore, it may aid in the early diagnosis of GIST, facilitating rapid referral to specialized treatment centers. As the model was not able to predict any genetic or molecular features, it cannot aid in treatment planning yet.

Classification of Clinically Significant Prostate Cancer on Multi-Parametric MRI: A Validation Study Comparing Deep Learning and Radiomics

The computer-aided analysis of prostate multiparametric MRI (mpMRI) could improve significant-prostate-cancer (PCa) detection. Various deep-learning- and radiomics-based methods for significant-PCa segmentation or classification have been reported in the literature. To be able to assess the generalizability of the performance of these methods, using various external data sets is crucial. While both deep-learning and radiomics approaches have been compared based on the same data set of one center, the comparison of the performances of both approaches on various data sets from different centers and different scanners is lacking. The goal of this study was to compare the performance of a deep-learning model with the performance of a radiomics model for the significant-PCa diagnosis of the cohorts of various patients. We included the data from two consecutive patient cohorts from our own center (n = 371 patients), and two external sets of which one was a publicly available patient cohort (n = 195 patients) and the other contained data from patients from two hospitals (n = 79 patients). Using multiparametric MRI (mpMRI), the radiologist tumor delineations and pathology reports were collected for all patients. During training, one of our patient cohorts (n = 271 patients) was used for both the deep-learning- and radiomics-model development, and the three remaining cohorts (n = 374 patients) were kept as unseen test sets. The performances of the models were assessed in terms of their area under the receiver-operating-characteristic curve (AUC). Whereas the internal cross-validation showed a higher AUC for the deep-learning approach, the radiomics model obtained AUCs of 0.88, 0.91 and 0.65 on the independent test sets compared to AUCs of 0.70, 0.73 and 0.44 for the deep-learning model. Our radiomics model that was based on delineated regions resulted in a more accurate tool for significant-PCa classification in the three unseen test sets when compared to a fully automated deep-learning model.

Associations of thrombus perviousness derived from entire thrombus segmentation with functional outcome in patients with acute ischemic stroke

Thrombus perviousness is strongly associated with functional outcome and intravenous alteplase treatment success in patients with acute ischemic stroke. Accuracy of thrombus attenuation increase (TAI) assessment may be compromised by a heterogeneous thrombus composition and interobserver variations of currently used manual measurements. We hypothesized that TAI is more strongly associated with clinical outcomes when evaluated on the entire thrombus. In 195 patients, five TAI measures were performed: one manual by placing three regions of interest (TAI_manual) and four automated ones assessing densities from the entire thrombus. The automated TAI measures were calculated by comparing quartiles; Q1, Q2, and Q3 of the non-contrast and contrast enhanced thrombus density distribution and using the lag of the maximum of the cross correlations (MCC). Associations with functional outcome (mRS at 90 days) were assessed with univariate and multivariable analyses. All entire TAI measures were significantly associated with functional outcome with odd ratios (OR) of 1.63(95 %CI:1.19-2.25, p = 0.003) for Q1, 1.56(95 %CI:1.16-2.10, p = 0.003) for Q2, 1.24(95 %CI:1.00-1.54, p = 0.045) for Q3, and 1.70(95 %CI:1.24-2.34, p = 0.001) for MCC per 10 HU increase in univariate models. TAI_manual was not significantly associated with functional outcome (p = 0.055). In the multivariable logistic regression models including age, NIHSS, and recanalization, only TAI measures derived from the entire thrombus were independently associated with favorable outcome; OR of 1.64(95 %CI:1.01-2.66, p = 0.048) for Q2 and 1.82(1.13-2.95, p = 0.014) for MCC per 10 HU increase of thrombus attenuation. The novel perviousness measures of the entire thrombus are more strongly associated with functional outcome than the traditional manual perviousness assessments.

Differences Between MR Brain Region Segmentation Methods: Impact on Single-Subject Analysis

For the segmentation of magnetic resonance brain images into anatomical regions, numerous fully automated methods have been proposed and compared to reference segmentations obtained manually. However, systematic differences might exist between the resulting segmentations, depending on the segmentation method and underlying brain atlas. This potentially results in sensitivity differences to disease and can further complicate the comparison of individual patients to normative data. In this study, we aim to answer two research questions: 1) to what extent are methods interchangeable, as long as the same method is being used for computing normative volume distributions and patient-specific volumes? and 2) can different methods be used for computing normative volume distributions and assessing patient-specific volumes? To answer these questions, we compared volumes of six brain regions calculated by five state-of-the-art segmentation methods: Erasmus MC (EMC), FreeSurfer (FS), geodesic information flows (GIF), multi-atlas label propagation with expectation–maximization (MALP-EM), and model-based brain segmentation (MBS). We applied the methods on 988 non-demented (ND) subjects and computed the correlation (PCC-v) and absolute agreement (ICC-v) on the volumes. For most regions, the PCC-v was good (>0.75), indicating that volume differences between methods in ND subjects are mainly due to systematic differences. The ICC-v was generally lower, especially for the smaller regions, indicating that it is essential that the same method is used to generate normative and patient data. To evaluate the impact on single-subject analysis, we also applied the methods to 42 patients with Alzheimer’s disease (AD). In the case where the normative distributions and the patient-specific volumes were calculated by the same method, the patient’s distance to the normative distribution was assessed with the z-score. We determined the diagnostic value of this z-score, which showed to be consistent across methods. The absolute agreement on the AD patients’ z-scores was high for regions of thalamus and putamen. This is encouraging as it indicates that the studied methods are interchangeable for these regions. For regions such as the hippocampus, amygdala, caudate nucleus and accumbens, and globus pallidus, not all method combinations showed a high ICC-z. Whether two methods are indeed interchangeable should be confirmed for the specific application and dataset of interest.

Virtual extensions improve perception-based instrument alignment using optical see-through devices

Instrument alignment is a common task in various surgical interventions using navigation. The goal of the task is to position and orient an instrument as it has been planned preoperatively. To this end, surgeons rely on patient-specific data visualized on screens alongside preplanned trajectories. The purpose of this manuscript is to investigate the effect of instrument visualization/non visualization on alignment tasks, and to compare it with virtual extensions approach which augments the realistic representation of the instrument with simple 3D objects. 18 volunteers performed six alignment tasks under each of the following conditions: no visualization on the instrument; realistic visualization of the instrument; realistic visualization extended with virtual elements (Virtual extensions). The first condition represents an egocentric-based alignment while the two other conditions additionally make use of exocentric depth estimation to perform the alignment. The device used was a see-through device (Microsoft HoloLens 2). The positions of the head and the instrument were acquired during the experiment. Additionally, the users were asked to fill NASA-TLX and SUS forms for each condition. The results show that instrument visualization is essential for a good alignment using see-through devices. Moreover, virtual extensions helped achieve the best performance compared to the other conditions with medians of 2 mm and 2° positional and angular error respectively. Furthermore, the virtual extensions decreased the average head velocity while similarly reducing the frustration levels. Therefore, making use of virtual extensions could facilitate alignment tasks in augmented and virtual reality (AR/VR) environments, specifically in AR navigated surgical procedures when using optical see-through devices.

Distinguishing pure histopathological growth patterns of colorectal liver metastases on CT using deep learning and radiomics: a pilot study

Histopathological growth patterns (HGPs) are independent prognosticators for colorectal liver metastases (CRLM). Currently, HGPs are determined postoperatively. In this study, we evaluated radiomics for preoperative prediction of HGPs on computed tomography (CT), and its robustness to segmentation and acquisition variations. Patients with pure HGPs [i.e. 100% desmoplastic (dHGP) or 100% replacement (rHGP)] and a CT-scan who were surgically treated at the Erasmus MC between 2003-2015 were included retrospectively. Each lesion was segmented by three clinicians and a convolutional neural network (CNN). A prediction model was created using 564 radiomics features and a combination of machine learning approaches by training on the clinician's and testing on the unseen CNN segmentations. The intra-class correlation coefficient (ICC) was used to select features robust to segmentation variations; ComBat was used to harmonize for acquisition variations. Evaluation was performed through a 100 × random-split cross-validation. The study included 93 CRLM in 76 patients (48% dHGP; 52% rHGP). Despite substantial differences between the segmentations of the three clinicians and the CNN, the radiomics model had a mean area under the curve of 0.69. ICC-based feature selection or ComBat yielded no improvement. Concluding, the combination of a CNN for segmentation and radiomics for classification has potential for automatically distinguishing dHGPs from rHGP, and is robust to segmentation and acquisition variations. Pending further optimization, including extension to mixed HGPs, our model may serve as a preoperative addition to postoperative HGP assessment, enabling further exploitation of HGPs as a biomarker.

Recurrent inference machines as inverse problem solvers for MR relaxometry

In this paper, we propose the use of Recurrent Inference Machines (RIMs) to perform T₁ and T₂ mapping. The RIM is a neural network framework that learns an iterative inference process based on the signal model, similar to conventional statistical methods for quantitative MRI (QMRI), such as the Maximum Likelihood Estimator (MLE). This framework combines the advantages of both data-driven and model-based methods, and, we hypothesize, is a promising tool for QMRI. Previously, RIMs were used to solve linear inverse reconstruction problems. Here, we show that they can also be used to optimize non-linear problems and estimate relaxometry maps with high precision and accuracy. The developed RIM framework is evaluated in terms of accuracy and precision and compared to an MLE method and an implementation of the Residual Neural Network (ResNet). The results show that the RIM improves the quality of estimates compared to the other techniques in Monte Carlo experiments with simulated data, test-retest analysis of a system phantom, and in-vivo scans. Additionally, inference with the RIM is 150 times faster than the MLE, and robustness to (slight) variations of scanning parameters is demonstrated. Hence, the RIM is a promising and flexible method for QMRI. Coupled with an open-source training data generation tool, it presents a compelling alternative to previous methods.

autoTICI: Automatic Brain Tissue Reperfusion Scoring on 2D DSA Images of Acute Ischemic Stroke Patients

The Thrombolysis in Cerebral Infarction (TICI) score is an important metric for reperfusion therapy assessment in acute ischemic stroke. It is commonly used as a technical outcome measure after endovascular treatment (EVT). Existing TICI scores are defined in coarse ordinal grades based on visual inspection, leading to inter- and intra-observer variation. In this work, we present autoTICI, an automatic and quantitative TICI scoring method. First, each digital subtraction angiography (DSA) acquisition is separated into four phases (non-contrast, arterial, parenchymal and venous phase) using a multi-path convolutional neural network (CNN), which exploits spatio-temporal features. The network also incorporates sequence level label dependencies in the form of a state-transition matrix. Next, a minimum intensity map (MINIP) is computed using the motion corrected arterial and parenchymal frames. On the MINIP image, vessel, perfusion and background pixels are segmented. Finally, we quantify the autoTICI score as the ratio of reperfused pixels after EVT. On a routinely acquired multi-center dataset, the proposed autoTICI shows good correlation with the extended TICI (eTICI) reference with an average area under the curve (AUC) score of 0.81. The AUC score is 0.90 with respect to the dichotomized eTICI. In terms of clinical outcome prediction, we demonstrate that autoTICI is overall comparable to eTICI.

Predicting symptomatic mesenteric mass in small intestinal neuroendocrine tumors using radiomics

Metastatic mesenteric masses of small intestinal neuroendocrine tumors (SI-NETs) are known to often cause intestinal complications. The aim of this study was to identify patients at risk to develop these complications based on routinely acquired CT scans using a standardized set of clinical criteria and radiomics. Retrospectively, CT scans of SI-NET patients with a mesenteric mass were included and systematically evaluated by five clinicians. For the radiomics approach, 1128 features were extracted from segmentations of the mesenteric mass and mesentery, after which radiomics models were created using a combination of machine learning approaches. The performances were compared to a multidisciplinary tumor board (MTB). The dataset included 68 patients (32 asymptomatic, 36 symptomatic). The clinicians had AUCs between 0.62 and 0.85 and showed poor agreement. The best radiomics model had a mean AUC of 0.77. The MTB had a sensitivity of 0.64 and specificity of 0.68. We conclude that systematic clinical evaluation of SI-NETs to predict intestinal complications had a similar performance than an expert MTB, but poor inter-observer agreement. Radiomics showed a similar performance and is objective, and thus is a promising tool to correctly identify these patients. However, further validation is needed before the transition to clinical practice.

Cross-cohort generalizability of deep and conventional machine learning for MRI-based diagnosis and prediction of Alzheimer's disease

This work validates the generalizability of MRI-based classification of Alzheimer’s disease (AD) patients and controls (CN) to an external data set and to the task of prediction of conversion to AD in individuals with mild cognitive impairment (MCI).

We used a conventional support vector machine (SVM) and a deep convolutional neural network (CNN) approach based on structural MRI scans that underwent either minimal pre-processing or more extensive pre-processing into modulated gray matter (GM) maps. Classifiers were optimized and evaluated using cross-validation in the Alzheimer’s Disease Neuroimaging Initiative (ADNI; 334 AD, 520 CN). Trained classifiers were subsequently applied to predict conversion to AD in ADNI MCI patients (231 converters, 628 non-converters) and in the independent Health-RI Parelsnoer Neurodegenerative Diseases Biobank data set. From this multi-center study representing a tertiary memory clinic population, we included 199 AD patients, 139 participants with subjective cognitive decline, 48 MCI patients converting to dementia, and 91 MCI patients who did not convert to dementia.

AD-CN classification based on modulated GM maps resulted in a similar area-under-the-curve (AUC) for SVM (0.940; 95%CI: 0.924–0.955) and CNN (0.933; 95%CI: 0.918–0.948). Application to conversion prediction in MCI yielded significantly higher performance for SVM (AUC = 0.756; 95%CI: 0.720-0.788) than for CNN (AUC = 0.742; 95%CI: 0.709-0.776) (p<0.01 for McNemar’s test). In external validation, performance was slightly decreased. For AD-CN, it again gave similar AUCs for SVM (0.896; 95%CI: 0.855–0.932) and CNN (0.876; 95%CI: 0.836–0.913). For prediction in MCI, performances decreased for both SVM (AUC = 0.665; 95%CI: 0.576-0.760) and CNN (AUC = 0.702; 95%CI: 0.624-0.786). Both with SVM and CNN, classification based on modulated GM maps significantly outperformed classification based on minimally processed images (p=0.01).

Deep and conventional classifiers performed equally well for AD classification and their performance decreased only slightly when applied to the external cohort. We expect that this work on external validation contributes towards translation of machine learning to clinical practice.

Progression along data-driven disease timelines is predictive of Alzheimer's disease in a population-based cohort

Data-driven disease progression models have provided important insight into the timeline of brain changes in AD phenotypes. However, their utility in predicting the progression of pre-symptomatic AD in a population-based setting has not yet been investigated. In this study, we investigated if the disease timelines constructed in a case-controlled setting, with subjects stratified according to APOE status, are generalizable to a population-based cohort, and if progression along these disease timelines is predictive of AD. Seven volumetric biomarkers derived from structural MRI were considered. We estimated APOE-specific disease timelines of changes in these biomarkers using a recently proposed method called co-initialized discriminative event-based modeling (co-init DEBM). This method can also estimate a disease stage for new subjects by calculating their position along the disease timelines. The model was trained and cross-validated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and tested on the population-based Rotterdam Study (RS) cohort. We compared the diagnostic and prognostic value of the disease stage in the two cohorts. Furthermore, we investigated if the rate of change of disease stage in RS participants with longitudinal MRI data was predictive of AD. In ADNI, the estimated disease timeslines for ϵ4 non-carriers and carriers were found to be significantly different from one another (p<0.001). The estimate disease stage along the respective timelines distinguished AD subjects from controls with an AUC of 0.83 in both APOEϵ4 non-carriers and carriers. In the RS cohort, we obtained an AUC of 0.83 and 0.85 in ϵ4 non-carriers and carriers, respectively. Progression along the disease timelines as estimated by the rate of change of disease stage showed a significant difference (p<0.005) for subjects with pre-symptomatic AD as compared to the general aging population in RS. It distinguished pre-symptomatic AD subjects with an AUC of 0.81 in APOEϵ4 non-carriers and 0.88 in carriers, which was better than any individual volumetric biomarker, or its rate of change, could achieve. Our results suggest that co-init DEBM trained on case-controlled data is generalizable to a population-based cohort setting and that progression along the disease timelines is predictive of the development of AD in the general population. We expect that this approach can help to identify at-risk individuals from the general population for targeted clinical trials as well as to provide biomarker based objective assessment in such trials.

The BRAF P.V600E Mutation Status of Melanoma Lung Metastases Cannot Be Discriminated on Computed Tomography by LIDC Criteria nor Radiomics Using Machine Learning

Patients with BRAF mutated (BRAF-mt) metastatic melanoma benefit significantly from treatment with BRAF inhibitors. Currently, the BRAF status is determined on archival tumor tissue or on fresh tumor tissue from an invasive biopsy. The aim of this study was to evaluate whether radiomics can predict the BRAF status in a non-invasive manner. Patients with melanoma lung metastases, known BRAF status, and a pretreatment computed tomography scan were included. After semi-automatic annotation of the lung lesions (maximum two per patient), 540 radiomics features were extracted. A chest radiologist scored all segmented lung lesions according to the Lung Image Database Consortium (LIDC) criteria. Univariate analysis was performed to assess the predictive value of each feature for BRAF mutation status. A combination of various machine learning methods was used to develop BRAF decision models based on the radiomics features and LIDC criteria. A total of 169 lung lesions from 103 patients (51 BRAF-mt; 52 BRAF wild type) were included. There were no features with a significant discriminative value in the univariate analysis. Models based on radiomics features and LIDC criteria both performed as poorly as guessing. Hence, the BRAF mutation status in melanoma lung metastases cannot be predicted using radiomics features or visually scored LIDC criteria.

Three-Dimensional Stereophotogrammetry in the Evaluation of Craniosynostosis: Current and Potential Use Cases

ABSTRACT

Three-dimensional (3D) stereophotogrammetry is a novel imaging technique that has gained popularity in the medical field as a reliable, non-invasive, and radiation-free imaging modality. It uses optical sensors to acquire multiple 2D images from different angles which are reconstructed into a 3D digital model of the subject's surface. The technique proved to be especially useful in craniofacial applications, where it serves as a tool to overcome the limitations imposed by conventional imaging modalities and subjective evaluation methods. The capability to acquire high-dimensional data in a quick and safe manner and archive them for retrospective longitudinal analyses, provides the field with a methodology to increase the understanding of the morphological development of the cranium, its growth patterns and the effect of different treatments over time.This review describes the role of 3D stereophotogrammetry in the evaluation of craniosynostosis, including reliability studies, current and potential clinical use cases, and practical challenges. Finally, developments within the research field are analyzed by means of bibliometric networks, depicting prominent research topics, authors, and institutions, to stimulate new ideas and collaborations in the field of craniofacial 3D stereophotogrammetry.We anticipate that utilization of this modality's full potential requires a global effort in terms of collaborations, data sharing, standardization, and harmonization. Such developments can facilitate larger studies and novel deep learning methods that can aid in reaching an objective consensus regarding the most effective treatments for patients with craniosynostosis and other craniofacial anomalies, and to increase our understanding of these complex dysmorphologies and associated phenotypes.

Cerebral small vessel disease genomics and its implications across the lifespan

White matter hyperintensities (WMH) are the most common brain-imaging feature of cerebral small vessel disease (SVD), hypertension being the main known risk factor. Here, we identify 27 genome-wide loci for WMH-volume in a cohort of 50,970 older individuals, accounting for modification/confounding by hypertension. Aggregated WMH risk variants were associated with altered white matter integrity (p = 2.5×10-7) in brain images from 1,738 young healthy adults, providing insight into the lifetime impact of SVD genetic risk. Mendelian randomization suggested causal association of increasing WMH-volume with stroke, Alzheimer-type dementia, and of increasing blood pressure (BP) with larger WMH-volume, notably also in persons without clinical hypertension. Transcriptome-wide colocalization analyses showed association of WMH-volume with expression of 39 genes, of which four encode known drug targets. Finally, we provide insight into BP-independent biological pathways underlying SVD and suggest potential for genetic stratification of high-risk individuals and for genetically-informed prioritization of drug targets for prevention trials.

Position paper on COVID-19 imaging and AI: From the clinical needs and technological challenges to initial AI solutions at the lab and national level towards a new era for AI in healthcare

In this position paper, we provide a collection of views on the role of AI in the COVID-19 pandemic, from clinical requirements to the design of AI-based systems, to the translation of the developed tools to the clinic. We highlight key factors in designing system solutions - per specific task; as well as design issues in managing the disease at the national level. We focus on three specific use-cases for which AI systems can be built: early disease detection, management in a hospital setting, and building patient-specific predictive models that require the combination of imaging with additional clinical data. Infrastructure considerations and population modeling in two European countries will be described. This pandemic has made the practical and scientific challenges of making AI solutions very explicit. A discussion concludes this paper, with a list of challenges facing the community in the AI road ahead.

Cerebral Blood Flow in Patients with Severe Aortic Valve Stenosis Undergoing Transcatheter Aortic Valve Implantation

BACKGROUND

Transcatheter aortic valve implantation (TAVI) is a minimally invasive, life‐saving treatment for patients with severe aortic valve stenosis that improves quality of life. We examined cardiac output and cerebral blood flow in patients undergoing TAVI to test the hypothesis that improved cardiac output after TAVI is associated with an increase in cerebral blood flow.

DESIGN

Prospective cohort study.

SETTING

European high‐volume tertiary multidisciplinary cardiac care.

PARTICIPANTS

Thirty‐one patients (78.3 ± 4.6 years; 61% female) with severe symptomatic aortic valve stenosis.

MEASUREMENTS

Noninvasive prospective assessment of cardiac output (L/min) by inert gas rebreathing and cerebral blood flow of the total gray matter (mL/100 g per min) using arterial spin labeling magnetic resonance imaging in resting state less than 24 hours before TAVI and at 3‐month follow‐up. Cerebral blood flow change was defined as the difference relative to baseline.

RESULTS

On average, cardiac output in patients with severe aortic valve stenosis increased from 4.0 ± 1.1 to 5.4 ± 2.4 L/min after TAVI (P = .003). The increase in cerebral blood flow after TAVI strongly varied between patients (7% ± 24%; P = .41) and related to the increase in cardiac output, with an 8.2% (standard error = 2.3%; P = .003) increase in cerebral blood flow per every additional liter of cardiac output following the TAVI procedure.

CONCLUSION

Following TAVI, there was an association of increase in cardiac output with increase in cerebral blood flow. These findings encourage future larger studies to determine the influence of TAVI on cerebral blood flow and cognitive function.

Hypertensive Exposure Markers by MRI in Relation to Cerebral Small Vessel Disease and Cognitive Impairment

OBJECTIVES

This study sought to investigate the extent of hypertensive exposure as assessed by cardiovascular magnetic resonance imaging (MRI) in relation to cerebral small vessel disease (CSVD) and cognitive impairment, with the aim of understanding the role of hypertension in the early stages of deteriorating brain health.

BACKGROUND

Preserving brain health into advanced age is one of the great challenges of modern medicine. Hypertension is thought to induce vascular brain injury through exposure of the cerebral microcirculation to increased pressure/pulsatility. Cardiovascular MRI provides markers of (subclinical) hypertensive exposure, such as aortic stiffness by pulse wave velocity (PWV), left ventricular (LV) mass index (LVMi), and concentricity by mass-to-volume ratio.

METHODS

A total of 559 participants from the Heart-Brain Connection Study (431 patients with manifest cardiovascular disease and 128 control participants), age 67.8 ± 8.8 years, underwent 3.0-T heart-brain MRI and extensive neuropsychological testing. Aortic PWV, LVMi, and LV mass-to-volume ratio were evaluated in relation to presence of CSVD and cognitive impairment. Effect modification by patient group was investigated by interaction terms; results are reported pooled or stratified accordingly.

RESULTS

Aortic PWV (odds ratio [OR]: 1.17; 95% confidence interval [CI]: 1.05 to 1.30 in patient groups only), LVMi (in carotid occlusive disease, OR: 5.69; 95% CI: 1.63 to 19.87; in other groups, OR: 1.30; 95% CI: 1.05 to 1.62]) and LV mass-to-volume ratio (OR: 1.81; 95% CI: 1.46 to 2.24) were associated with CSVD. Aortic PWV (OR: 1.07; 95% CI: 1.02 to 1.13) and LV mass-to-volume ratio (OR: 1.27; 95% CI: 1.07 to 1.51) were also associated with cognitive impairment. Relations were independent of sociodemographic and cardiac index and mostly persisted after correction for systolic blood pressure or medical history of hypertension. Causal mediation analysis showed significant mediation by presence of CSVD in the relation between hypertensive exposure markers and cognitive impairment.

CONCLUSIONS

The extent of hypertensive exposure is associated with CSVD and cognitive impairment beyond clinical blood pressure or medical history. The mediating role of CSVD suggests that hypertension may lead to cognitive impairment through the occurrence of CSVD.

Genetic correlations and genome-wide associations of cortical structure in general population samples of 22,824 adults

Cortical thickness, surface area and volumes vary with age and cognitive function, and in neurological and psychiatric diseases. Here we report heritability, genetic correlations and genome-wide associations of these cortical measures across the whole cortex, and in 34 anatomically predefined regions. Our discovery sample comprises 22,824 individuals from 20 cohorts within the Cohorts for Heart and Aging Research in Genomic Epidemiology (CHARGE) consortium and the UK Biobank. We identify genetic heterogeneity between cortical measures and brain regions, and 160 genome-wide significant associations pointing to wnt/β-catenin, TGF-β and sonic hedgehog pathways. There is enrichment for genes involved in anthropometric traits, hindbrain development, vascular and neurodegenerative disease and psychiatric conditions. These data are a rich resource for studies of the biological mechanisms behind cortical development and aging.

Cortex morphology varies with age, cognitive function, and in neurological and psychiatric diseases. Here the authors report 160 genome-wide significant associations with thickness, surface area and volume of the total cortex and 34 cortical regions from a GWAS meta-analysis in 22,824 adults.

Differential diagnosis and mutation stratification of desmoid-type fibromatosis on MRI using radiomics

PURPOSE

Diagnosing desmoid-type fibromatosis (DTF) requires an invasive tissue biopsy with β-catenin staining and CTNNB1 mutational analysis, and is challenging due to its rarity. The aim of this study was to evaluate radiomics for distinguishing DTF from soft tissue sarcomas (STS), and in DTF, for predicting the CTNNB1 mutation types.

METHODS

Patients with histologically confirmed extremity STS (non-DTF) or DTF and at least a pretreatment T1-weighted (T1w) MRI scan were retrospectively included. Tumors were semi-automatically annotated on the T1w scans, from which 411 features were extracted. Prediction models were created using a combination of various machine learning approaches. Evaluation was performed through a 100x random-split cross-validation. The model for DTF vs. non-DTF was compared to classification by two radiologists on a location matched subset.

RESULTS

The data included 203 patients (72 DTF, 131 STS). The T1w radiomics model showed a mean AUC of 0.79 on the full dataset. Addition of T2w or T1w post-contrast scans did not improve the performance. On the location matched cohort, the T1w model had a mean AUC of 0.88 while the radiologists had an AUC of 0.80 and 0.88, respectively. For the prediction of the CTNNB1 mutation types (S45 F, T41A and wild-type), the T1w model showed an AUC of 0.61, 0.56, and 0.74.

CONCLUSIONS

Our radiomics model was able to distinguish DTF from STS with high accuracy similar to two radiologists, but was not able to predict the CTNNB1 mutation status.

Structural disconnectivity and the risk of dementia in the general population

Objective

The disconnectivity hypothesis postulates that partial loss of connecting white matter fibers between brain regions contributes to the development of dementia. Using diffusion MRI to quantify global and tract-specific white matter microstructural integrity, we tested this hypothesis in a longitudinal population-based study.

Methods

Global and tract-specific fractional anisotropy (FA) and mean diffusivity (MD) were obtained in 4,415 people without dementia (mean age 63.9 years, 55.0% women) from the prospective population-based Rotterdam Study with brain MRI between 2005 and 2011. We modeled the association of these diffusion measures with risk of dementia (follow-up until 2016) and with changes on repeated cognitive assessment after on average 5.4 years, adjusting for age, sex, education, macrostructural MRI markers, depressive symptoms, cardiovascular risk factors, and APOE genotype.

Results

During a median follow-up of 6.8 years, 101 participants had incident dementia, of whom 83 had clinical Alzheimer disease (AD). Lower global values of FA and higher values of MD were associated with an increased risk of dementia (adjusted hazard ratio [95% confidence interval (CI)] per SD increase for MD 1.79 [1.44–2.23] and FA 0.65 [0.52–0.80]). Similarly, lower global values of FA and higher values of MD related to more cognitive decline in people without dementia (difference in global cognition per SD increase in MD [95% CI] was −0.04 [−0.07 to −0.01]). Associations were most profound in the projection, association, and limbic system tracts.

Conclusions

Structural disconnectivity is associated with an increased risk of dementia and more pronounced cognitive decline in the general population.

Automatic Collateral Scoring From 3D CTA Images

The collateral score is an important biomarker in decision making for endovascular treatment (EVT) of patients with ischemic stroke. The existing collateral grading systems are based on visual inspection and prone to subjective interpretation and interobserver variation. The purpose of our work is the development of an automatic collateral scoring method. In this work, we present a method that is inspired by human collateral scoring. Firstly, we define an anatomical region by atlas-based registration and extract vessel structures using a deep convolutional neural network. From this, high-level features based on the ratios of vessel length and volume of the occluded and the contralateral side are defined. Multi-class classification models are used to map the feature space to a four-grade collateral score and a quantitative score. The dataset used for training, validation and testing is from a registry of images acquired in clinical routine at multiple medical centers. The model performance is tested on 269 subjects, achieving an accuracy of 0.8. The dichotomized collateral score accuracy is 0.9. The error is comparable to the interobserver variation, the results are comparable to the performance of two radiologists with 10 to 30 years of experience.

Genetic variation underlying cognition and its relation with neurological outcomes and brain imaging

Cognition in adults shows variation due to developmental and degenerative components. A recent genome-wide association study identified genetic variants for general cognitive function in 148 independent loci. Here, we aimed to elucidate possible developmental and neurodegenerative pathways underlying these genetic variants by relating them to functional, clinical and neuroimaging outcomes. This study was conducted within the population-based Rotterdam Study (N=11,496, mean age 65.3±9.9 years, 58.0% female). We used lead variants for general cognitive function to construct a polygenic score (PGS), and additionally excluded developmental variants at multiple significance thresholds. A higher PGS was related to more years of education (β=0.29, p=4.3x10^-7) and a larger intracranial volume (β=0.05, p=7.5x10^-4). To a smaller extent, the PGS was associated with less cognitive decline (β_ΔG-factor=0.03, p=1.3x10^-3), which became non-significant after adjusting for education (p=1.6x10^-2). No associations were found with daily functioning, dementia, parkinsonism, stroke or microstructural white matter integrity. Excluding developmental variants attenuated nearly all associations. In conclusion, this study suggests that the genetic variants identified for general cognitive function are acting mainly through the developmental pathway of cognition. Therefore, cognition, assessed cross-sectionally, seems to have limited value as a biomarker for neurodegeneration.

Cerebral blood flow and cognitive functioning in patients with disorders along the heart-brain axis: Cerebral blood flow and the heart-brain axis

INTRODUCTION

We examined the role of hemodynamic dysfunction in cognition by relating cerebral blood flow (CBF), measured with arterial spin labeling (ASL), to cognitive functioning, in patients with heart failure (HF), carotid occlusive disease (COD), and patients with cognitive complaints and vascular brain injury on magnetic resonance imaging (MRI; ie, possible vascular cognitive impairment [VCI]).

METHODS

We included 439 participants (124 HF; 75 COD; 127 possible VCI; 113 reference participants) from the Dutch multi-center Heart-Brain Study. We used pseudo-continuous ASL to estimate whole-brain and regional partial volume-corrected CBF. Neuropsychological tests covered global cognition and four cognitive domains.

RESULTS

CBF values were lowest in COD, followed by VCI and HF, compared to reference participants. This did not explain cognitive impairment, as we did not find an association between CBF and cognitive functioning.

DISCUSSION

We found that reduced CBF is not the major explanatory factor underlying cognitive impairment in patients with hemodynamic dysfunction along the heart-brain axis.

Independent Multiple Factor Association Analysis for Multiblock Data in Imaging Genetics

Multivariate methods have the potential to better capture complex relationships that may exist between different biological levels. Multiple Factor Analysis (MFA) is one of the most popular methods to obtain factor scores and measures of discrepancy between data sets. However, singular value decomposition in MFA is based on PCA, which is adequate only if the data is normally distributed, linear or stationary. In addition, including strongly correlated variables can overemphasize the contribution of the estimated components. In this work, we introduced a novel method referred as Independent Multifactorial Analysis (ICA-MFA) to derive relevant features from multiscale data. This method is an extended implementation of MFA, where the component value decomposition is based on Independent Component Analysis. In addition, ICA-MFA incorporates a predictive step based on an Independent Component Regression. We evaluated and compared the performance of ICA-MFA with both, the MFA method and traditional univariate analyses, in a simulation study. We showed how ICA-MFA explained up to 10-fold more variance than MFA and univariate methods. We applied the proposed algorithm in a study of 4057 individuals belonging to the population-based Rotterdam Study with available genetic and neuroimaging data, as well as information about executive cognitive functioning. Specifically, we used ICA-MFA to detect relevant genetic features related to structural brain regions, which in turn were involved, in the mechanisms of executive cognitive function. The proposed strategy makes it possible to determine the degree to which the whole set of genetic and/or neuroimaging markers contribute to the variability of the symptomatology jointly, rather than individually. While univariate results and MFA combinations only explained a limited proportion of variance (less than 2%), our method increased the explained variance (10%) and allowed the identification of significant components that maximize the variance explained in the model. The potential application of the ICA-MFA algorithm constitutes an important aspect of integrating multivariate multiscale data, specifically in the field of Neurogenetics.

Changes in the intracranial volume from early adulthood to the sixth decade of life: A longitudinal study

Normal brain-aging occurs at all structural levels. Excessive pathophysiological changes in the brain, beyond the normal one, are implicated in the etiology of brain disorders such as severe forms of the schizophrenia spectrum and dementia. To account for brain-aging in health and disease, it is critical to study the age-dependent trajectories of brain biomarkers at various levels and among different age groups. The intracranial volume (ICV) is a key biological marker, and changes in the ICV during the lifespan can teach us about the biology of development, aging, and gene X environment interactions. However, whether ICV changes with age in adulthood is not resolved. Applying a semi-automatic in-house-built algorithm for ICV extraction on T1w MR brain scans in the Dutch longitudinal cohort (GROUP), we measured ICV changes. Individuals between the ages of 16 and 55 years were scanned up to three consecutive times with 3.32±0.32 years between consecutive scans (N = 482, 359, 302). Using the extracted ICVs, we calculated ICV longitudinal aging-trajectories based on three analysis methods; direct calculation of ICV differences between the first and the last scan, fitting all ICV measurements of individuals to a straight line, and applying a global linear mixed model fitting. We report statistically significant increase in the ICV in adulthood until the fourth decade of life (average change +0.03%/y, or about 0.5 ml/y, at age 20), and decrease in the ICV afterward (-0.09%/y, or about -1.2 ml/y, at age 55). To account for previous cross-sectional reports of ICV changes, we analyzed the same data using a cross-sectional approach. Our cross-sectional analysis detected ICV changes consistent with the previously reported cross-sectional effect. However, the reported amount of cross-sectional changes within this age range was significantly larger than the longitudinal changes. We attribute the cross-sectional results to a generational effect. In conclusion, the human intracranial volume does not stay constant during adulthood but instead shows a small increase during young adulthood and a decrease thereafter from the fourth decade of life. The age-related changes in the longitudinalmeasure are smaller than those reported using cross-sectional approaches and unlikely to affect structural brain imaging studies correcting for intracranial volume considerably. As to the possible mechanisms involved, this awaits further study, although thickening of the meninges and skull bones have been proposed, as well as a smaller amount of brain fluids addition above the overall loss of brain tissue.

Radiomics approach to distinguish between well differentiated liposarcomas and lipomas on MRI

Background

Well differentiated liposarcoma (WDLPS) can be difficult to distinguish from lipoma. Currently, this distinction is made by testing for MDM2 amplification, which requires a biopsy. The aim of this study was to develop a noninvasive method to predict MDM2 amplification status using radiomics features derived from MRI.

Methods

Patients with an MDM2‐negative lipoma or MDM2‐positive WDLPS and a pretreatment T1‐weighted MRI scan who were referred to Erasmus MC between 2009 and 2018 were included. When available, other MRI sequences were included in the radiomics analysis. Features describing intensity, shape and texture were extracted from the tumour region. Classification was performed using various machine learning approaches. Evaluation was performed through a 100 times random‐split cross‐validation. The performance of the models was compared with the performance of three expert radiologists.

Results

The data set included 116 tumours (58 patients with lipoma, 58 with WDLPS) and originated from 41 different MRI scanners, resulting in wide heterogeneity in imaging hardware and acquisition protocols. The radiomics model based on T1 imaging features alone resulted in a mean area under the curve (AUC) of 0·83, sensitivity of 0·68 and specificity of 0·84. Adding the T2‐weighted imaging features in an explorative analysis improved the model to a mean AUC of 0·89, sensitivity of 0·74 and specificity of 0·88. The three radiologists scored an AUC of 0·74 and 0·72 and 0·61 respectively; a sensitivity of 0·74, 0·91 and 0·64; and a specificity of 0·55, 0·36 and 0·59.

Conclusion

Radiomics is a promising, non‐invasive method for differentiating between WDLPS and lipoma, outperforming the scores of the radiologists. Further optimization and validation is needed before introduction into clinical practice.

Predicting Global Cognitive Decline in the General Population Using the Disease State Index

Background

Identifying persons at risk for cognitive decline may aid in early detection of persons at risk of dementia and to select those that would benefit most from therapeutic or preventive measures for dementia.

Objective

In this study we aimed to validate whether cognitive decline in the general population can be predicted with multivariate data using a previously proposed supervised classification method: Disease State Index (DSI).

Methods

We included 2,542 participants, non-demented and without mild cognitive impairment at baseline, from the population-based Rotterdam Study (mean age 60.9 ± 9.1 years). Participants with significant global cognitive decline were defined as the 5% of participants with the largest cognitive decline per year. We trained DSI to predict occurrence of significant global cognitive decline using a large variety of baseline features, including magnetic resonance imaging (MRI) features, cardiovascular risk factors, APOE-ε4 allele carriership, gait features, education, and baseline cognitive function as predictors. The prediction performance was assessed as area under the receiver operating characteristic curve (AUC), using 500 repetitions of 2-fold cross-validation experiments, in which (a randomly selected) half of the data was used for training and the other half for testing.

Results

A mean AUC (95% confidence interval) for DSI prediction was 0.78 (0.77–0.79) using only age as input feature. When using all available features, a mean AUC of 0.77 (0.75–0.78) was obtained. Without age, and with age-corrected features and feature selection on MRI features, a mean AUC of 0.70 (0.63–0.76) was obtained, showing the potential of other features besides age.

Conclusion

The best performance in the prediction of global cognitive decline in the general population by DSI was obtained using only age as input feature. Other features showed potential, but did not improve prediction. Future studies should evaluate whether the performance could be improved by new features, e.g., longitudinal features, and other prediction methods.

Orientation Prior and Consistent Model Selection Increase Sensitivity of Tract-Based Spatial Statistics in Crossing-Fiber Regions

The goal of this paper is to increase the statistical power of crossing-fiber statistics in voxelwise analyses of diffusion-weighted magnetic resonance imaging (DW-MRI) data. In the proposed framework, a fiber orientation atlas and a model complexity atlas were used to fit the ball-and-sticks model to diffusion-weighted images of subjects in a prospective population-based cohort study. Reproducibility and sensitivity of the partial volume fractions in the ball-and-sticks model were analyzed using TBSS (tract-based spatial statistics) and compared to a reference framework. The reproducibility was investigated on two scans of 30 subjects acquired with an interval of approximately three weeks by studying the intraclass correlation coefficient (ICC). The sensitivity to true biological effects was evaluated by studying the regression with age on 500 subjects from 65 to 90 years old. Compared to the reference framework, the ICC improved significantly when using the proposed framework. Higher t-statistics indicated that regression coefficients with age could be determined more precisely with the proposed framework and more voxels correlated significantly with age. The application of a fiber orientation atlas and a model complexity atlas can significantly improve the reproducibility and sensitivity of crossing-fiber statistics in TBSS.