Multi-source multi-modal markers for Bayesian Networks: Application to the extremely preterm born brain.

The preterm phenotype results from the interplay of multiple disorders affecting the brain and cognitive outcomes. Accurately characterising these interactions can reveal prematurity markers. Bayesian Networks (BNs) are powerful tools to disentangle these relationships, as they inherently measure associations between variables while mitigating confounding factors. We present Modified PC-HC (MPC-HC), a Bayesian Network (BN) structural learning algorithm. MPC-HC employs statistical testing and search-and-score techniques to explore equivalent classes. We employ MPC-HC to estimate BNs for extremely preterm (EP) young adults and full-term controls. Using MRI measurements and cognitive performance markers, we investigate predictive relationships and mutual influences through predictions and sensitivity analysis. We assess the confidence in the estimated BN structures using bootstrapping. Furthermore, MPC-HC's validation involves assessing its ability to recover benchmark BN structures. MPC-HC achieves an average prediction accuracy of 72.5% compared to 62.5% of PC, 64.5% of MMHC, and 71.5% of HC, while it outperforms PC, MMHC, and HC algorithms in reconstructing the true structure of benchmark BNs. The sensitivity analysis shows that MRI measurements mainly affect EP cognitive scores. Our work has two key contributions: first, the introduction and validation of a new BN structure learning method. Second, demonstrating the potential of BNs in modelling variable relationships, predicting variables of interest, modelling uncertainty, and evaluating how variables impact each other. Finally, we demonstrate this by characterising complex phenotypes, such as preterm birth, and discovering results consistent with literature findings.

Myelination of preterm brain networks at adolescence.

Prematurity and preterm stressors severely affect the development of infants born before 37 weeks of gestation, with increasing effects seen at earlier gestations. Although preterm mortality rates have declined due to the advances in neonatal care, disability rates, especially in middle-income settings, continue to grow. With the advances in MR imaging technology, there has been a focus on safely imaging the preterm brain to better understand its development and discover the brain regions and networks affected by prematurity. Such studies aim to support interventions and improve the neurodevelopment of preterm infants and deliver accurate prognoses. Few studies, however, have focused on the fully developed brain of preterm born infants, especially in extremely preterm subjects. To assess the long-term effect of prematurity on the adult brain, myelin related biomarkers such as myelin water fraction and g-ratio are measured for a cohort of 19-year-old extremely preterm born subjects. Using multi-modal imaging techniques that combine T2 relaxometry and neurite density information, the results show that specific brain regions associated with white matter injuries due to preterm birth, such as the posterior limb of the internal capsule and corpus callosum, are still less myelinated in adulthood. Furthermore, a weak positive relationship between myelin water fraction values and Full-Scale Intelligence Quotient (FSIQ) scores was found in multiple brain regions previously defined as less myelinated in the Extremely Preterm (EPT) cohort. These findings might suggest altered connectivity in the adult preterm brain and explain differences in cognitive outcomes.

Use of super resolution reconstruction MRI for surgical planning in Placenta accreta spectrum disorder: Case series.

INTRODUCTION: Comprehensive imaging using ultrasound and MRI of placenta accreta spectrum (PAS) aims to prevent catastrophic haemorrhage and maternal death. Standard MRI of the placenta is limited by between-slice motion which can be mitigated by super-resolution reconstruction (SRR) MRI. We applied SRR in suspected PAS cases to determine its ability to enhance anatomical placental assessment and predict adverse maternal outcome. METHODS: Suspected PAS patients (n = 22) underwent MRI at a gestational age (weeks + days) of (32+3±3+2, range (27+1-38+6)). SRR of the placental-myometrial-bladder interface involving rigid motion correction of acquired MRI slices combined with robust outlier detection to reconstruct an isotropic high-resolution volume, was achieved in twelve. 2D MRI or SRR images alone, and paired data were assessed by four radiologists in three review rounds. All radiologists were blinded to results of the ultrasound, original MR image reports, case outcomes, and PAS diagnosis. A Random Forest Classification model was used to highlight the most predictive pathological MRI markers for major obstetric haemorrhage (MOH), bladder adherence (BA), and placental attachment depth (PAD). RESULTS: At delivery, four patients had placenta praevia with no abnormal attachment, two were clinically diagnosed with PAS, and six had histopathological PAS confirmation. Pathological MRI markers (T2-dark intraplacental bands, and loss of retroplacental T2-hypointense line) predicting MOH were more visible using SRR imaging (accuracy 0.73), in comparison to 2D MRI or paired imaging. Bladder wall interruption, predicting BA, was only easily detected by paired imaging (accuracy 0.72). Better detection of certain pathological markers predicting PAD was found using 2D MRI (placental bulge and myometrial thinning (accuracy 0.81)), and SRR (loss of retroplacental T2-hypointense line (accuracy 0.82)). DISCUSSION: The addition of SRR to 2D MRI potentially improved anatomical assessment of certain pathological MRI markers of abnormal placentation that predict maternal morbidity which may benefit surgical planning.

Assessing informative tract segmentation and nTMS for pre-operative planning.

BACKGROUND: Deep learning-based (DL) methods are the best-performing methods for white matter tract segmentation in anatomically healthy subjects. However, tract annotations are variable or absent in clinical data and manual annotations are especially difficult in patients with tumors where normal anatomy may be distorted. Direct cortical and subcortical stimulation is the gold standard ground truth to determine the cortical and sub-cortical lo- cation of motor-eloquent areas intra-operatively. Nonetheless, this technique is invasive, prolongs the surgical procedure, and may cause patient fatigue. Navigated Transcranial Magnetic Stimulation (nTMS) has a well-established correlation to direct cortical stimulation for motor mapping and the added advantage of being able to be acquired pre-operatively. NEW METHOD: In this work, we evaluate the feasibility of using nTMS motor responses as a method to assess corticospinal tract (CST) binary masks and estimated uncertainty generated by a DL-based tract segmentation in patients with diffuse gliomas. RESULTS: Our results show CST binary masks have a high overlap coefficient (OC) with nTMS response masks. A strong negative correlation is found between estimated uncertainty and nTMS response mask distance to the CST binary mask. COMPARISON WITH EXISTING METHODS: We compare our approach (UncSeg) with the state-of-the-art TractSeg in terms of OC between the CST binary masks and nTMS response masks. CONCLUSIONS: In this study, we demonstrate that estimated uncertainty from UncSeg is a good measure of the agreement between the CST binary masks and nTMS response masks distance to the CST binary mask boundary.

Emerging Treatments for Disorders of Consciousness in Paediatric Age.

The number of paediatric patients living with a prolonged Disorder of Consciousness (DoC) is growing in high-income countries, thanks to substantial improvement in intensive care. Life expectancy is extending due to the clinical and nursing management achievements of chronic phase needs, including infections. However, long-known pharmacological therapies such as amantadine and zolpidem, as well as novel instrumental approaches using direct current stimulation and, more recently, stem cell transplantation, are applied in the absence of large paediatric clinical trials and rigorous age-balanced and dose-escalated validations. With evidence building up mainly through case reports and observational studies, there is a need for well-designed paediatric clinical trials and specific research on 0-4-year-old children. At such an early age, assessing residual and recovered abilities is most challenging due to the early developmental stage, incompletely learnt motor and cognitive skills, and unreliable communication; treatment options are also less explored in early age. In middle-income countries, the lack of rehabilitation services and professionals focusing on paediatric age hampers the overall good assistance provision. Young and fast-evolving health insurance systems prevent universal access to chronic care in some countries. In low-income countries, rescue networks are often inadequate, and there is a lack of specialised and intensive care, difficulty in providing specific pharmaceuticals, and lower compliance to intensive care hygiene standards. Despite this, paediatric cases with DoC are reported, albeit in fewer numbers than in countries with better-resourced healthcare systems. For patients with a poor prospect of recovery, withdrawal of care is inhomogeneous across countries and still heavily conditioned by treatment costs as well as ethical and cultural factors, rather than reliant on protocols for assessment and standardised treatments. In summary, there is a strong call for multicentric, international, and global health initiatives on DoC to devote resources to the paediatric age, as there is now scope for funders to invest in themes specific to DoC affecting the early years of the life course.

White matter analysis of the extremely preterm born adult brain.

The preterm brain has been analysed after birth by a large body of neuroimaging studies; however, few studies have focused on white matter alterations in preterm subjects beyond infancy, especially in individuals born at extremely low gestation age - before 28 completed weeks. Neuroimaging data of extremely preterm young adults are now available to investigate the long-term structural alterations of disrupted neurodevelopment. We examined white matter hierarchical organisation and microstructure in extremely preterm young adults. Specifically, we first identified the putative hubs and peripheral regions in 85 extremely preterm young adults and compared them with 53 socio-economically matched and full-term born peers. Moreover, we analysed Fractional Anisotropy (FA), Mean Diffusivity (MD), Neurite Density Index (NDI), and Orientation Dispersion Index (ODI) of white matter in hubs, peripheral regions, and over the whole brain. Our results suggest that the hierarchical organisation of the extremely preterm adult brain remains intact. However, there is evidence of significant alteration of white matter connectivity at both the macro- and microstructural level, with overall diminished connectivity, reduced FA and NDI, increased MD, and comparable ODI; suggesting that, although the spatial configuration of WM fibres is comparable, there are less WM fibres per voxel. These alterations are found throughout the brain and are more prevalent along the pathways between deep grey matter regions, frontal regions and cerebellum. This work provides evidence that white matter abnormalities associated with the premature exposure to the extrauterine environment not only are present at term equivalent age but persist into early adulthood.

Middle Frontal Gyrus and Area 55b: Perioperative Mapping and Language Outcomes.

Background: The simplistic approaches to language circuits are continuously challenged by new findings in brain structure and connectivity. The posterior middle frontal gyrus and area 55b (pFMG/area55b), in particular, has gained a renewed interest in the overall language network. Methods: This is a retrospective single-center cohort study of patients who have undergone awake craniotomy for tumor resection. Navigated transcranial magnetic simulation (nTMS), tractography, and intraoperative findings were correlated with language outcomes. Results: Sixty-five awake craniotomies were performed between 2012 and 2020, and 24 patients were included. nTMS elicited 42 positive responses, 76.2% in the inferior frontal gyrus (IFG), and hesitation was the most common error (71.4%). In the pMFG/area55b, there were seven positive errors (five hesitations and two phonemic errors). This area had the highest positive predictive value (43.0%), negative predictive value (98.3%), sensitivity (50.0%), and specificity (99.0%) among all the frontal gyri. Intraoperatively, there were 33 cortical positive responses-two (6.0%) in the superior frontal gyrus (SFG), 15 (45.5%) in the MFG, and 16 (48.5%) in the IFG. A total of 29 subcortical positive responses were elicited-21 in the deep IFG-MFG gyri and eight in the deep SFG-MFG gyri. The most common errors identified were speech arrest at the cortical level (20 responses-13 in the IFG and seven in the MFG) and anomia at the subcortical level (nine patients-eight in the deep IFG-MFG and one in the deep MFG-SFG). Moreover, 83.3% of patients had a transitory deterioration of language after surgery, mainly in the expressive component (p = 0.03). An increased number of gyri with intraoperative positive responses were related with better preoperative (p = 0.037) and worse postoperative (p = 0.029) outcomes. The involvement of the SFG-MFG subcortical area was related with worse language outcomes (p = 0.037). Positive nTMS mapping in the IFG was associated with a better preoperative language outcome (p = 0.017), relating to a better performance in the expressive component, while positive mapping in the MFG was related to a worse preoperative receptive component of language (p = 0.031). Conclusion: This case series suggests that the posterior middle frontal gyrus, including area 55b, is an important integration cortical hub for both dorsal and ventral streams of language.

Neuropsychiatric disease classification using functional connectomics - results of the connectomics in neuroimaging transfer learning challenge.

Large, open-source datasets, such as the Human Connectome Project and the Autism Brain Imaging Data Exchange, have spurred the development of new and increasingly powerful machine learning approaches for brain connectomics. However, one key question remains: are we capturing biologically relevant and generalizable information about the brain, or are we simply overfitting to the data? To answer this, we organized a scientific challenge, the Connectomics in NeuroImaging Transfer Learning Challenge (CNI-TLC), held in conjunction with MICCAI 2019. CNI-TLC included two classification tasks: (1) diagnosis of Attention-Deficit/Hyperactivity Disorder (ADHD) within a pre-adolescent cohort; and (2) transference of the ADHD model to a related cohort of Autism Spectrum Disorder (ASD) patients with an ADHD comorbidity. In total, 240 resting-state fMRI (rsfMRI) time series averaged according to three standard parcellation atlases, along with clinical diagnosis, were released for training and validation (120 neurotypical controls and 120 ADHD). We also provided Challenge participants with demographic information of age, sex, IQ, and handedness. The second set of 100 subjects (50 neurotypical controls, 25 ADHD, and 25 ASD with ADHD comorbidity) was used for testing. Classification methodologies were submitted in a standardized format as containerized Docker images through ChRIS, an open-source image analysis platform. Utilizing an inclusive approach, we ranked the methods based on 16 metrics: accuracy, area under the curve, F1-score, false discovery rate, false negative rate, false omission rate, false positive rate, geometric mean, informedness, markedness, Matthew's correlation coefficient, negative predictive value, optimized precision, precision, sensitivity, and specificity. The final rank was calculated using the rank product for each participant across all measures. Furthermore, we assessed the calibration curves of each methodology. Five participants submitted their method for evaluation, with one outperforming all other methods in both ADHD and ASD classification. However, further improvements are still needed to reach the clinical translation of functional connectomics. We have kept the CNI-TLC open as a publicly available resource for developing and validating new classification methodologies in the field of connectomics.

A Framework For Memory Performance Prediction From Brain Volume In Preterm-Born Adolescents.

With advances in medical care, higher numbers of extremely preterm-born babies are now surviving, however the rate of neurodevelopmental and neurological complications has not improved at the same rate and the relative rate of disabilities and health problems is increasing, with associated high costs for health care systems and education. Understanding brain development after early birth is of great importance to be able to make informed decisions. Many studies have associated different areas of the preterm brain with poor cognitive performance, however it is less clear whether these associations persist into adult life. In this study, we investigate how well cortical volumes describe memory performance in 133 19 year-old adolescents, 61% of whom were born extremely preterm. We employ LASSO to identify brain regions that better explain memory performance. The brain regions identified by LASSO explained 27% and 32% of the variance in the visual working memory scores and the visual short term memory respectively. Furthermore, the correlation between the predicted scores and validation scores is statistically significant and it is 58% for the visual working memory task and 56% for the visual short term memory task.