Search

Abstract Prenatal tobacco smoke exposure (TSE) and prematurity are independent risk factors for abnormal neurodevelopment. The objectives were to compare differences in Bayley-III cognitive, language, and motor scores at 2 years corrected age (CA) in 395 infants born very preterm (≤ 32 weeks gestation) with and without prenatal TSE. We performed multivariable linear regression analyses to examine associations between prenatal TSE and neurodevelopmental outcomes and a mediation analysis to estimate direct effects of prenatal TSE on outcomes and indirect effects through preterm birth. In total, 50 (12.6%) infants had prenatal TSE. Infants with prenatal TSE had lower mean [95% CI] Cognitive score (82.8 [78.6, 87.1]) vs. nonexposed infants (91.7 [90.1, 93.4]). In children with and without prenatal TSE, there were significant differences in mean [95% CI] Language scores (81.7 [76.0, 87.4] vs. 92.4 [90.2, 94.6], respectively) and mean [95% CI] Motor scores (86.5 [82.2, 90.7] vs. 93.4 [91.8, 95.0], respectively); scores remained significant after controlling for confounders. Preterm birth indirectly mediated 9.0% of the total effect of prenatal TSE on Cognitive score (P = NS). However, 91% of the remaining total effect was significant and attributable to TSE’s direct harmful effects on cognitive development (β = − 5.17 [95% CI − 9.97, − 0.38]). The significant association is largely due to TSE’s direct effect on cognitive development and not primarily due to TSE’s indirect effect on preterm birth.

Very preterm (VPT) infants (born at less than 32 weeks gestational age) are at high risk for various adverse neurodevelopmental deficits. Unfortunately, most of these deficits cannot be accurately diagnosed until the age of 2-5 years old. Given the benefits of early interventions, accurate diagnosis and prediction soon after birth are urgently needed for VPT infants. Previous studies have applied deep learning models to learn the brain structural connectome (SC) to predict neurodevelopmental deficits in the preterm population. However, none of these models are specifically designed for graph-structured data, and thus may potentially miss certain topological information conveyed in the brain SC. In this study, we aim to develop deep learning models to learn the SC acquired at term-equivalent age for early prediction of neurodevelopmental deficits at 2 years corrected age in VPT infants. We directly treated the brain SC as a graph, and applied graph convolutional network (GCN) models to capture complex topological information of the SC. In addition, we applied the supervised contrastive learning (SCL) technique to mitigate the effects of the data scarcity problem, and enable robust training of GCN models. We hypothesize that SCL will enhance GCN models for early prediction of neurodevelopmental deficits in VPT infants using the SC. We used a regional prospective cohort of ∼280 VPT infants who underwent MRI examinations at term-equivalent age from the Cincinnati Infant Neurodevelopment Early Prediction Study (CINEPS). These VPT infants completed neurodevelopmental assessment at 2 years corrected age to evaluate cognition, language, and motor skills. Using the SCL technique, the GCN model achieved mean areas under the receiver operating characteristic curve (AUCs) in the range of 0.72∼0.75 for predicting three neurodevelopmental deficits, outperforming several competing models. Our results support our hypothesis that the SCL technique is able to enhance the GCN model in our prediction tasks.

Abstract Growth in preterm infants in the neonatal intensive care unit (NICU) is associated with increased global and regional brain volumes at term, and increased postnatal linear growth is associated with higher language scores at age 2. It is unknown whether these relationships persist to school age or if an association between growth and cortical metrics exists. Using regression analyses, we investigated relationships between the growth of 42 children born extremely preterm (

We studied the effect of microstructural abnormalities in the corpus callosum on language development in 348 infants born very prematurely. We discovered that the fractional anisotropy of the corpus callosum anterior midbody was a significant predictor of standardized language scores at 2 years, independent of clinical and social risk factors.

White matter tract segmentation is a pivotal research area that leverages diffusion-weighted magnetic resonance imaging (dMRI) for the identification and mapping of individual white matter tracts and their trajectories. This study aims to provide a comprehensive systematic literature review on automated methods for white matter tract segmentation in brain dMRI scans. Articles on PubMed, ScienceDirect [NeuroImage, NeuroImage (Clinical), Medical Image Analysis], Scopus and IEEEXplore databases and Conference proceedings of Medical Imaging Computing and Computer Assisted Intervention Society (MICCAI) and International Symposium on Biomedical Imaging (ISBI), were searched in the range from January 2013 until September 2023. This systematic search and review identified 619 articles. Adhering to the specified search criteria using the query, “white matter tract segmentation OR fiber tract identification OR fiber bundle segmentation OR tractography dissection OR white matter parcellation OR tract segmentation,” 59 published studies were selected. Among these, 27% employed direct voxel-based methods, 25% applied streamline-based clustering methods, 20% used streamline-based classification methods, 14% implemented atlas-based methods, and 14% utilized hybrid approaches. The paper delves into the research gaps and challenges associated with each of these categories. Additionally, this review paper illuminates the most frequently utilized public datasets for tract segmentation along with their specific characteristics. Furthermore, it presents evaluation strategies and their key attributes. The review concludes with a detailed discussion of the challenges and future directions in this field.

The computer-aided disease diagnosis from radiomic data is important in many medical applications. However, developing such a technique relies on labeling radiological images, which is a time-consuming, labor-intensive, and expensive process. In this work, we present the first novel collaborative self-supervised learning method to solve the challenge of insufficient labeled radiomic data, whose characteristics are different from text and image data. To achieve this, we present two collaborative pretext tasks that explore the latent pathological or biological relationships between regions of interest and the similarity and dissimilarity of information between subjects. Our method collaboratively learns the robust latent feature representations from radiomic data in a self-supervised manner to reduce human annotation efforts, which benefits the disease diagnosis. We compared our proposed method with other state-of-the-art self-supervised learning methods on a simulation study and two independent datasets. Extensive experimental results demonstrated that our method outperforms other self-supervised learning methods on both classification and regression tasks. With further refinement, our method will have the potential advantage in automatic disease diagnosis with large-scale unlabeled data available.

Premature children are at high risk for delays in language and reading, which can lead to poor school achievement. Neuroimaging studies have assessed structural and functional connectivity by diffusion MRI, functional MRI, and magnetoencephalography, in order to better define the “reading network” in children born preterm. Findings point to differences in structural and functional connectivity compared to children born at term. It is not entirely clear whether this discrepancy is due to delayed development or alternative mechanisms for reading, which may have developed to compensate for brain injury in the perinatal period. This narrative review critically appraises the existing literature evaluating the neural basis of reading in preterm children, summarizes the current findings, and suggests future directions in the field.

Preterm brains commonly exhibit elevated signal intensity in the white matter on T2-weighted MRI at term-equivalent age. This signal, known as diffuse excessive high signal intensity (DEHSI) or diffuse white matter abnormality (DWMA) when quantitatively assessed, is associated with abnormal microstructure on diffusion tensor imaging. However, postmortem data are largely lacking and difficult to obtain, and the pathological significance of DEHSI remains in question. In a cohort of 202 infants born preterm at ≤32 weeks gestational age, we leveraged two newer diffusion MRI models – Constrained Spherical Deconvolution (CSD) and neurite orientation dispersion and density index (NODDI) – to better characterize the macro and microstructural properties of DWMA and inform the ongoing debate around the clinical significance of DWMA. With increasing DWMA volume, fiber density broadly decreased throughout the white matter and fiber cross-section decreased in the major sensorimotor tracts. Neurite orientation dispersion decreased in the centrum semiovale, corona radiata, and temporal lobe. These findings provide insight into DWMA's biological underpinnings and demonstrate that it is a serious pathology.

Structural magnetic resonance imaging studies have shown that brain anatomical abnormalities are associated with cognitive deficits in preterm infants. Brain maturation and geometric features can be used with machine learning models for predicting later neurodevelopmental deficits. However, traditional machine learning models would suffer from a large feature-to-instance ratio (i.e., a large number of features but a small number of instances/samples). Ensemble learning is a paradigm that strategically generates and integrates a library of machine learning classifiers and has been successfully used on a wide variety of predictive modeling problems to boost model performance. Attribute (i.e., feature) bagging method is the most commonly used feature partitioning scheme, which randomly and repeatedly draws feature subsets from the entire feature set. Although attribute bagging method can effectively reduce feature dimensionality to handle the large feature-to-instance ratio, it lacks consideration of domain knowledge and latent relationship among features. In this study, we proposed a novel Ontology-guided Attribute Partitioning (OAP) method to better draw feature subsets by considering the domain-specific relationship among features. With the better-partitioned feature subsets, we developed an ensemble learning framework, which is referred to as OAP-Ensemble Learning (OAP-EL). We applied the OAP-EL to predict cognitive deficits at 2 years of age using quantitative brain maturation and geometric features obtained at term equivalent age in very preterm infants. We demonstrated that the proposed OAP-EL approach significantly outperformed the peer ensemble learning and traditional machine learning approaches.

Unaddressed maternal psychological distress within the first year postpartum is known to have numerous negative consequences on the child’s developmental outcomes, including language acquisition. This study examined the relationship between early maternal psychosocial factors and the language outcomes of children born very preterm (VPT; ≤32 weeks gestational age). It used data from the Cincinnati Infant Neurodevelopment Early Prediction Study, an ongoing National-Institutes-of-Health-funded prospective, multicenter cohort investigation of VPT infants. A total of 243 (125 boys; 118 girls) children born VPT (M = 29.03 weeks of gestation; SD = 2.47) and their corresponding 207 mothers (34 with multiple infants) were included in this study. We did not find an association between maternal depression or anxiety and Bayley-III (M = 92.3, SD = 18.9) language scores. Additionally, maternal grit and self-efficacy did not modify the relationship between depression and anxiety and language scores. A higher level of maternal education and infant female sex were significantly associated with higher language scores. While preterm birth typically results in higher rates of depression and anxiety for parents, the findings suggest that maternal depression, anxiety, and grit and the self-efficacy of the mothers in this sample did not relate to the language development of their children, independent of maternal education and infant female sex.

Approximately 32–42% of very preterm infants develop minor motor abnormalities. Earlier diagnosis soon after birth is urgently needed because the first two years of life represent a critical window of opportunity for early neuroplasticity in infants. In this study, we developed a semi-supervised graph convolutional network (GCN) model that is able to simultaneously learn the neuroimaging features of subjects and consider the pairwise similarity between them. The semi-supervised GCN model also allows us to combine labeled data with additional unlabeled data to facilitate model training. We conducted our experiments on a multisite regional cohort of 224 preterm infants (119 labeled subjects and 105 unlabeled subjects) who were born at 32 weeks or earlier from the Cincinnati Infant Neurodevelopment Early Prediction Study. A weighted loss function was applied to mitigate the impact of an imbalanced positive:negative (~1:2) subject ratio in our cohort. With only labeled data, our GCN model achieved an accuracy of 66.4% and an AUC of 0.67 in the early prediction of motor abnormalities, outperforming prior supervised learning models. By taking advantage of additional unlabeled data, the GCN model had significantly better accuracy (68.0%, p = 0.016) and a higher AUC (0.69, p = 0.029). This pilot work suggests that the semi-supervised GCN model can be utilized to aid early prediction of neurodevelopmental deficits in preterm infants.

Children born extremely preterm (

Infants born very preterm (VPT) are at risk of later visual problems. Although neonatal screening can identify ophthalmologic abnormalities, subtle perinatal brain injury and/or delayed brain maturation may be significant contributors to complex visual-behavioral problems. Our aim was to assess the micro and macrostructural antecedents of early visual-behavioral difficulties in VPT infants by using diffusion MRI (dMRI) at term-equivalent age.We prospectively recruited a cohort of 262 VPT infants (≤32 weeks gestational age [GA]) from five neonatal intensive care units. We obtained structural and diffusion MRI at term-equivalent age and administered the Preverbal Visual Assessment (PreViAs) questionnaire to parents at 3–4 months corrected age. We used constrained spherical deconvolution to reconstruct nine white matter tracts of the visual pathways with high reliability and performed fixel-based analysis to derive fiber density (FD), fiber-bundle cross-section (FC), and combined fiber density and cross-section (FDC). In multiple logistic regression analyses, we related these tract metrics to visual-behavioral function.Of 262 infants, 191 had both high-quality dMRI and completed PreViAs, constituting the final cohort: mean (SD) GA was 29.3 (2.4) weeks, 90 (47.1%) were males, and postmenstrual age (PMA) at MRI was 42.8 (1.3) weeks. FD and FC of several tracts were altered in infants with (N = 59) versus those without retinopathy of prematurity (N = 132). FDC of the left posterior thalamic radiations (PTR), left inferior longitudinal fasciculus (ILF), right superior longitudinal fasciculus (SLF), and left inferior fronto-occipital fasciculus (IFOF) were significantly associated with visual attention scores, prior to adjusting for confounders. After adjustment for PMA at MRI, GA, severe retinopathy of prematurity, and total brain volume, FDC of the left PTR, left ILF, and left IFOF remained significantly associated with visual attention.Early visual-behavioral difficulties in VPT infants are preceded by micro and macrostructural abnormalities in several major visual pathways at term-equivalent age.

Very preterm infants (born at less than 32 weeks gestational age) are at high risk for serious motor impairments, including cerebral palsy (CP). The brain network changes that antecede the early development of CP in infants are not well characterized, and a better understanding may suggest new strategies for risk-stratification at term, which could lead to earlier access to therapies. Graph theoretical methods applied to diffusion MRI-derived brain connectomes may help quantify the organization and information transfer capacity of the preterm brain with greater nuance than overt structural or regional microstructural changes. Our aim was to shed light on the pathophysiology of early CP development, before the occurrence of early intervention therapies and other environmental confounders, to help identify the best early biomarkers of CP risk in VPT infants. In a cohort of 395 very preterm infants, we extracted cortical morphometrics and brain volumes from structural MRI and also applied graph theoretical methods to diffusion MRI connectomes, both acquired at term-equivalent age. Metrics from graph network analysis, especially global efficiency, strength values of the major sensorimotor tracts, and local efficiency of the motor nodes and novel non-motor regions were strongly inversely related to early CP diagnosis. These measures remained significantly associated with CP after correction for common risk factors of motor development, suggesting that metrics of brain network efficiency at term may be sensitive biomarkers for early CP detection. We demonstrate for the first time that in VPT infants, early CP diagnosis is anteceded by decreased brain network segregation in numerous nodes, including motor regions commonly-associated with CP and also novel regions that may partially explain the high rate of cognitive impairments concomitant with CP diagnosis. These advanced MRI biomarkers may help identify the highest risk infants by term-equivalent age, facilitating earlier interventions that are informed by early pathophysiological changes.

The prevalence of disabled survivors of prematurity has increased dramatically in the past 3 decades. These survivors, especially, very preterm infants (VPIs), born ≤ 32 weeks gestational age, are at high risk for neurodevelopmental impairments. Early and clinically effective personalized prediction of outcomes, which forms the basis for early treatment decisions, is urgently needed during the peak neuroplasticity window—the first couple of years after birth—for at-risk infants, when intervention is likely to be most effective. Advances in MRI enable the noninvasive visualization of infants' brains through acquired multimodal images, which are more informative than unimodal MRI data by providing complementary/supplementary depicting of brain tissue characteristics and pathology. Thus, analyzing quantitative multimodal MRI features affords unique opportunities to study early postnatal brain development and neurodevelopmental outcome prediction in VPIs. In this study, we investigated the predictive power of multimodal MRI data, including T2-weighted anatomical MRI, diffusion tensor imaging, resting-state functional MRI, and clinical data for the prediction of neurodevelopmental deficits. We hypothesize that integrating multimodal MRI and clinical data improves the prediction over using each individual data modality. Employing the aforementioned multimodal data, we proposed novel end-to-end deep multimodal models to predict neurodevelopmental (i.e., cognitive, language, and motor) deficits independently at 2 years corrected age. We found that the proposed models can predict cognitive, language, and motor deficits at 2 years corrected age with an accuracy of 88.4, 87.2, and 86.7%, respectively, significantly better than using individual data modalities. This current study can be considered as proof-of-concept. A larger study with external validation is important to validate our approach to further assess its clinical utility and overall generalizability.

Prenatal opioid exposure has been linked to altered neurodevelopment and visual problems such as strabismus and nystagmus. The neural substrate underlying these alterations is unclear. Resting-state functional connectivity MRI (rsfMRI) is an advanced and well-established technique to evaluate brain networks. Few studies have examined the effects of prenatal opioid exposure on resting-state network connectivity in infancy. In this pilot study, we characterized network connectivity in opioid-exposed infants (n = 19) and controls (n = 20) between 4–8 weeks of age using both a whole-brain connectomic approach and a seed-based approach. Prenatal opioid exposure was associated with differences in distribution of betweenness centrality and connection length, with positive connections unique to each group significantly longer than common connections. The unique connections in the opioid-exposed group were more often inter-network connections while unique connections in controls and connections common to both groups were more often intra-network. The opioid-exposed group had smaller network volumes particularly in the primary visual network, but similar network strength as controls. Network topologies as determined by dice similarity index were different between groups, particularly in visual and executive control networks. These results may provide insight into the neural basis for the developmental and visual problems associated with prenatal opioid exposure.

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

Children born extremely preterm (EPT,

Between 50 and 80% of very preterm infants (

Up to 40% of very preterm infants (≤32 weeks’ gestational age) were identified with a cognitive deficit at 2 years of age. Yet, accurate clinical diagnosis of cognitive deficit cannot be made until early childhood around 3–5 years of age. Recently, brain structural connectome that was constructed by advanced diffusion tensor imaging (DTI) technique has been playing an important role in understanding human cognitive functions. However, available annotated neuroimaging datasets with clinical and outcome information are usually limited and expensive to enlarge in the very preterm infants’ studies. These challenges hinder the development of neonatal prognostic tools for early prediction of cognitive deficit in very preterm infants. In this study, we considered the brain structural connectome as a 2D image and applied established deep convolutional neural networks to learn the spatial and topological information of the brain connectome. Furthermore, the transfer learning technique was utilized to mitigate the issue of insufficient training data. As such, we developed a transfer learning enhanced convolutional neural network (TL-CNN) model for early prediction of cognitive assessment at 2 years of age in very preterm infants using brain structural connectome. A total of 110 very preterm infants were enrolled in this work. Brain structural connectome was constructed using DTI images scanned at term-equivalent age. Bayley III cognitive assessments were conducted at 2 years of corrected age. We applied the proposed model to both cognitive deficit classification and continuous cognitive score prediction tasks. The results demonstrated that TL-CNN achieved improved performance compared to multiple peer models. Finally, we identified the brain regions most discriminative to the cognitive deficit. The results suggest that deep learning models may facilitate early prediction of later neurodevelopmental outcomes in very preterm infants at term-equivalent age.

Very preterm infants are at high risk for motor impairments. Early interventions can improve outcomes in this cohort, but they would be most effective if clinicians could accurately identify the highest-risk infants early. A number of biomarkers for motor development exist, but currently none are sufficiently accurate for early risk-stratification. We prospectively enrolled very preterm (gestational age ≤31 weeks) infants from four level-III NICUs. Structural brain MRI was performed at term-equivalent age. We used a established pipeline to automatically derive brain volumetrics and cortical morphometrics – cortical surface area, sulcal depth, gyrification index, and inner cortical curvature – from structural MRI. We related these objective measures to Bayley-III motor scores (overall, gross, and fine) at two-years corrected age. Lasso regression identified the three best predictive biomarkers for each motor scale from our initial feature set. In multivariable regression, we assessed the independent value of these brain biomarkers, over-and-above known predictors of motor development, to predict motor scores. 75 very preterm infants had high-quality T2-weighted MRI and completed Bayley-III motor testing. All three motor scores were positively associated with regional cortical surface area and subcortical volumes and negatively associated with cortical curvature throughout the majority of brain regions. In multivariable regression modeling, thalamic volume, curvature of the temporal lobe, and curvature of the insula were significant predictors of overall motor development on the Bayley-III, independent of known predictors. Objective brain morphometric biomarkers at term show promise in predicting motor development in very preterm infants.

Multi-contrast MRI images use different echo and repetition times to highlight different tissues. However, not all desired image contrasts may be available due to scan-time limitations, suboptimal signal-to-noise ratio, and/or image artifacts. Deep learning approaches have brought revolutionary advances in medical image synthesis, enabling the generation of unacquired image contrasts (e.g., T1-weighted MRI images) from available image contrasts (e.g., T2-weighted images). Particularly, CycleGAN is an advanced technique for image synthesis using unpaired images. However, it requires two separate image generators, demanding more training resources and computations. Recently, a switchable CycleGAN has been proposed to address this limitation and successfully implemented using CT images. However, it remains unclear if switchable CycleGAN can be applied to cross-contrast MRI synthesis. In addition, whether switchable CycleGAN is able to outperform original CycleGAN on cross-contrast MRI image synthesis is still an open question. In this paper, we developed a switchable CycleGAN model for image synthesis between multi-contrast brain MRI images using a large set of publicly accessible pediatric structural brain MRI images. We conducted extensive experiments to compare switchable CycleGAN with original CycleGAN both quantitatively and qualitatively. Experimental results demonstrate that switchable CycleGAN is able to outperform CycleGAN model on pediatric MRI brain image synthesis.

Investigation of the brain's functional connectome can improve our understanding of how an individual brain's organizational changes influence cognitive function and could result in improved individual risk stratification. Brain connectome studies in adults and older children have shown that abnormal network properties may be useful as discriminative features and have exploited machine learning models for early diagnosis in a variety of neurological conditions. However, analogous studies in neonates are rare and with limited significant findings. In this paper, we propose an artificial neural network (ANN) framework for early prediction of cognitive deficits in very preterm infants based on functional connectome data from resting state fMRI. Specifically, we conducted feature selection via stacked sparse autoencoder and outcome prediction via support vector machine (SVM). The proposed ANN model was unsupervised learned using brain connectome data from 884 subjects in autism brain imaging data exchange database and SVM was cross-validated on 28 very preterm infants (born at 23–31 weeks of gestation and without brain injury; scanned at term-equivalent postmenstrual age). Using 90 regions of interests, we found that the ANN model applied to functional connectome data from very premature infants can predict cognitive outcome at 2 years of corrected age with an accuracy of 70.6% and area under receiver operating characteristic curve of 0.76. We also noted that several frontal lobe and somatosensory regions, significantly contributed to prediction of cognitive deficits 2 years later. Our work can be considered as a proof of concept for utilizing ANN models on functional connectome data to capture the individual variability inherent in the developing brains of preterm infants. The full potential of ANN will be realized and more robust conclusions drawn when applied to much larger neuroimaging datasets, as we plan to do. Keywords: Artificial neural network, Stacked sparse autoencoder, Support vector machine, Very preterm infants, Functional MRI, Cognitive deficit

Deriphyllin has been a mainstay of asthma therapy despite its narrow therapeutic index and a large pharmacokinetic variability between patients. Here, the authors decided to report a rare case of suspected deriphyllin-induced hallucinations in adults for the first time. An 83-year-old male patient who was a known case of recent onset asthma was on tablet deriphyllin 150 mg BD and salbutamol nebulization BD. He underwent emergency drainage of subdural hematoma due to a history of fall 20 days back with head injury. Within 2 days, he improved and was discharged 3 days later with the medicines. On follow-up after 7 days, he was admitted with a chief complaint of hallucinations. After stopping tablet deriphyllin, the patient's condition drastically improved in next few days and neurology was completely normal. Drug dechallenge was positive in this case since the hallucinations subsided after discontinuation of suspected drug deriphyllin. There are no such cases published previously.

Extreme prematurity (EPT,

Diffuse white matter abnormality (DWMA), or diffuse excessive high signal intensity is observed in 50–80% of very preterm infants at term-equivalent age. It is subjectively defined as higher than normal signal intensity in periventricular and subcortical white matter in comparison to normal unmyelinated white matter on T2-weighted MRI images. Despite the well-documented presence of DWMA, it remains debatable whether DWMA represents pathological tissue injury or a transient developmental phenomenon. Manual tracing of DWMA exhibits poor reliability and reproducibility and unduly increases image processing time. Thus, objective and ideally automatic assessment is critical to accurately elucidate the biologic nature of DWMA. We propose a deep learning approach to automatically identify DWMA regions on T2-weighted MRI images. Specifically, we formulated DWMA detection as an image voxel classification task; that is, the voxels on T2-weighted images are treated as samples and exclusively assigned as DWMA or normal white matter voxel classes. To utilize the spatial information of individual voxels, small image patches centered on the given voxels are retrieved. A deep convolutional neural networks (CNN) model was developed to differentiate DWMA and normal voxels. We tested our deep CNN in multiple validation experiments. First, we examined DWMA detection accuracy of our CNN model using computer simulations. This was followed by in vivo assessments in a cohort of very preterm infants (N = 95) using cross-validation and holdout validation. Finally, we tested our approach on an independent preterm cohort (N = 28) to externally validate our model. Our deep CNN model achieved Dice similarity index values ranging from 0.85 to 0.99 for DWMA detection in the aforementioned validation experiments. Our proposed deep CNN model exhibited significantly better performance than other popular machine learning models. We present an objective and automated approach for accurately identifying DWMA that may facilitate the clinical diagnosis of DWMA in very preterm infants.

Early diagnosis remains a significant challenge for many neurological disorders, especially for rare disorders where studying large cohorts is not possible. A novel solution that investigators have undertaken is combining advanced machine learning algorithms with resting-state functional Magnetic Resonance Imaging to unveil hidden pathological brain connectome patterns to uncover diagnostic and prognostic biomarkers. Recently, state-of-the-art deep learning techniques are outperforming traditional machine learning methods and are hailed as a milestone for artificial intelligence. However, whole brain classification that combines brain connectome with deep learning has been hindered by insufficient training samples. Inspired by the transfer learning strategy employed in computer vision, we exploited previously collected resting-state functional MRI data for healthy subjects from existing databases and transferred this knowledge for new disease classification tasks. We developed a deep transfer learning neural network (DTL-NN) framework for enhancing the classification of whole brain functional connectivity patterns. Briefly, we trained a stacked sparse autoencoder (SSAE) prototype to learn healthy functional connectivity patterns in an offline learning environment. Then, the SSAE prototype was transferred to a DTL-NN model for a new classification task. To test the validity of our framework, we collected resting-state functional MRI data from the Autism Brain Imaging Data Exchange (ABIDE) repository. Using autism spectrum disorder (ASD) classification as a target task, we compared the performance of our DTL-NN approach with a traditional deep neural network and support vector machine models across four ABIDE data sites that enrolled at least 60 subjects. As compared to traditional models, our DTL-NN approach achieved an improved performance in accuracy, sensitivity, specificity and area under receiver operating characteristic curve. These findings suggest that DTL-NN approaches could enhance disease classification for neurological conditions, where accumulating large neuroimaging datasets has been challenging.