Trust and stakeholder perspectives on the implementation of AI tools in clinical radiology.

OBJECTIVES: To define requirements that condition trust in artificial intelligence (AI) as clinical decision support in radiology from the perspective of various stakeholders and to explore ways to fulfil these requirements. METHODS: Semi-structured interviews were conducted with twenty-five respondents-nineteen directly involved in the development, implementation, or use of AI applications in radiology and six working with AI in other areas of healthcare. We designed the questions to explore three themes: development and use of AI, professional decision-making, and management and organizational procedures connected to AI. The transcribed interviews were analysed in an iterative coding process from open coding to theoretically informed thematic coding. RESULTS: We identified four aspects of trust that relate to reliability, transparency, quality verification, and inter-organizational compatibility. These aspects fall under the categories of substantial and procedural requirements. CONCLUSIONS: Development of appropriate levels of trust in AI in healthcare is complex and encompasses multiple dimensions of requirements. Various stakeholders will have to be involved in developing AI solutions for healthcare and radiology to fulfil these requirements. CLINICAL RELEVANCE STATEMENT: For AI to achieve advances in radiology, it must be given the opportunity to support, rather than replace, human expertise. Support requires trust. Identification of aspects and conditions for trust allows developing AI implementation strategies that facilitate advancing the field. KEY POINTS: • Dimensions of procedural and substantial demands that need to be fulfilled to foster appropriate levels of trust in AI in healthcare are conditioned on aspects related to reliability, transparency, quality verification, and inter-organizational compatibility. •Creating the conditions for trust to emerge requires the involvement of various stakeholders, who will have to compensate the problem's inherent complexity by finding and promoting well-defined solutions.

CT-based volumetric measures obtained through deep learning: Association with biomarkers of neurodegeneration.

INTRODUCTION: Cranial computed tomography (CT) is an affordable and widely available imaging modality that is used to assess structural abnormalities, but not to quantify neurodegeneration. Previously we developed a deep-learning-based model that produced accurate and robust cranial CT tissue classification. MATERIALS AND METHODS: We analyzed 917 CT and 744 magnetic resonance (MR) scans from the Gothenburg H70 Birth Cohort, and 204 CT and 241 MR scans from participants of the Memory Clinic Cohort, Singapore. We tested associations between six CT-based volumetric measures (CTVMs) and existing clinical diagnoses, fluid and imaging biomarkers, and measures of cognition. RESULTS: CTVMs differentiated cognitively healthy individuals from dementia and prodromal dementia patients with high accuracy levels comparable to MR-based measures. CTVMs were significantly associated with measures of cognition and biochemical markers of neurodegeneration. DISCUSSION: These findings suggest the potential future use of CT-based volumetric measures as an informative first-line examination tool for neurodegenerative disease diagnostics after further validation. HIGHLIGHTS: Computed tomography (CT)-based volumetric measures can distinguish between patients with neurodegenerative disease and healthy controls, as well as between patients with prodromal dementia and controls. CT-based volumetric measures associate well with relevant cognitive, biochemical, and neuroimaging markers of neurodegenerative diseases. Model performance, in terms of brain tissue classification, was consistent across two cohorts of diverse nature. Intermodality agreement between our automated CT-based and established magnetic resonance (MR)-based image segmentations was stronger than the agreement between visual CT and MR imaging assessment.

Automatic and manual segmentation of the piriform cortex: Method development and validation in patients with temporal lobe epilepsy and Alzheimer's disease.

The piriform cortex (PC) is located at the junction of the temporal and frontal lobes. It is involved physiologically in olfaction as well as memory and plays an important role in epilepsy. Its study at scale is held back by the absence of automatic segmentation methods on MRI. We devised a manual segmentation protocol for PC volumes, integrated those manually derived images into the Hammers Atlas Database (n = 30) and used an extensively validated method (multi-atlas propagation with enhanced registration, MAPER) for automatic PC segmentation. We applied automated PC volumetry to patients with unilateral temporal lobe epilepsy with hippocampal sclerosis (TLE; n = 174 including n = 58 controls) and to the Alzheimer's Disease Neuroimaging Initiative cohort (ADNI; n = 151, of whom with mild cognitive impairment (MCI), n = 71; Alzheimer's disease (AD), n = 33; controls, n = 47). In controls, mean PC volume was 485 mm3 on the right and 461 mm3 on the left. Automatic and manual segmentations overlapped with a Jaccard coefficient (intersection/union) of ~0.5 and a mean absolute volume difference of ~22 mm3 in healthy controls, ~0.40/ ~28 mm3 in patients with TLE, and ~ 0.34/~29 mm3 in patients with AD. In patients with TLE, PC atrophy lateralised to the side of hippocampal sclerosis (p < .001). In patients with MCI and AD, PC volumes were lower than those of controls bilaterally (p < .001). Overall, we have validated automatic PC volumetry in healthy controls and two types of pathology. The novel finding of early atrophy of PC at the stage of MCI possibly adds a novel biomarker. PC volumetry can now be applied at scale.

Postnatal serum IGF-1 levels associate with brain volumes at term in extremely preterm infants.

BACKGROUND: Growth factors important for normal brain development are low in preterm infants. This study investigated the link between growth factors and preterm brain volumes at term. MATERIAL/METHODS: Infants born <28 weeks gestational age (GA) were included. Endogenous levels of insulin-like growth factor (IGF)-1, brain-derived growth factor, vascular endothelial growth factor, and platelet-derived growth factor (expressed as area under the curve [AUC] for serum samples from postnatal days 1, 7, 14, and 28) were utilized in a multivariable linear regression model. Brain volumes were determined by magnetic resonance imaging (MRI) at term equivalent age. RESULTS: In total, 49 infants (median [range] GA 25.4 [22.9-27.9] weeks) were included following MRI segmentation quality assessment and AUC calculation. IGF-1 levels were independently positively associated with the total brain (p < 0.001, ß = 0.90), white matter (p = 0.007, ß = 0.33), cortical gray matter (p = 0.002, ß = 0.43), deep gray matter (p = 0.008, ß = 0.05), and cerebellar (p = 0.006, ß = 0.08) volume adjusted for GA at birth and postmenstrual age at MRI. No associations were seen for other growth factors. CONCLUSIONS: Endogenous exposure to IGF-1 during the first 4 weeks of life was associated with total and regional brain volumes at term. Optimizing levels of IGF-1 might improve brain growth in extremely preterm infants. IMPACT: High serum levels of insulin-like growth factor (IGF)-1 during the first month of life were independently associated with increased total brain volume, white matter, gray matter, and cerebellar volume at term equivalent age in extremely preterm infants. IGF-1 is a critical regulator of neurodevelopment and postnatal levels are low in preterm infants. The effects of IGF-1 levels on brain development in extremely preterm infants are not fully understood. Optimizing levels of IGF-1 may benefit early brain growth in extremely preterm infants. The effects of systemically administered IGF-1/IGFBP3 in extremely preterm infants are now being investigated in a randomized controlled trial (Clinicaltrials.gov: NCT03253263).

Deep learning from MRI-derived labels enables automatic brain tissue classification on human brain CT.

Automatic methods for feature extraction, volumetry, and morphometric analysis in clinical neuroscience typically operate on images obtained with magnetic resonance (MR) imaging equipment. Although CT scans are less expensive to acquire and more widely available than MR scans, their application is currently limited to the visual assessment of brain integrity and the exclusion of co-pathologies. CT has rarely been used for tissue classification because the contrast between grey matter and white matter was considered insufficient. In this study, we propose an automatic method for segmenting grey matter (GM), white matter (WM), cerebrospinal fluid (CSF), and intracranial volume (ICV) from head CT images. A U-Net deep learning model was trained and validated on CT images with MRI-derived segmentation labels. We used data from 744 participants of the Gothenburg H70 Birth Cohort Studies for whom CT and T1-weighted MR images had been acquired on the same day. Our proposed model predicted brain tissue classes accurately from unseen CT images (Dice coefficients of 0.79, 0.82, 0.75, 0.93 and 0.98 for GM, WM, CSF, brain volume and ICV, respectively). To contextualize these results, we generated benchmarks based on established MR-based methods and intentional image degradation. Our findings demonstrate that CT-derived segmentations can be used to delineate and quantify brain tissues, opening new possibilities for the use of CT in clinical practice and research.

Serum docosahexaenoic acid levels are associated with brain volumes in extremely preterm born infants.

BACKGROUND: Docosahexaenoic acid (DHA) and arachidonic acid (AA) are important for fetal brain growth and development. Our aim was to evaluate the association between serum DHA and AA levels and brain volumes in extremely preterm infants. METHODS: Infants born at <28 weeks gestational age in 2013-2015, a cohort derived from a randomized controlled trial comparing two types of parenteral lipid emulsions, were included (n = 90). Serum DHA and AA levels were measured at postnatal days 1, 7, 14, and 28, and the area under the curve was calculated. Magnetic resonance (MR) imaging was performed at term-equivalent age (n = 66), and volumes of six brain regions were automatically generated. RESULTS: After MR image quality assessment and area under the curve calculation, 48 infants were included (gestational age mean [SD] 25.5 [1.4] weeks). DHA levels were positively associated with total brain (B = 7.966, p = 0.012), cortical gray matter (B = 3.653, p = 0.036), deep gray matter (B = 0.439, p = 0.014), cerebellar (B = 0.932, p = 0.003), and white matter volume (B = 3.373, p = 0.022). AA levels showed no association with brain volumes. CONCLUSIONS: Serum DHA levels during the first 28 postnatal days were positively associated with volumes of several brain structures in extremely preterm infants at term-equivalent age. IMPACT: Higher serum levels of DHA in the first 28 postnatal days are positively associated with brain volumes at term-equivalent age in extremely preterm born infants. Especially the most immature infants suffer from low DHA levels in the first 28 postnatal days, with little increase over time. Future research is needed to explore whether postnatal fatty acid supplementation can improve brain development and may serve as a nutritional preventive and therapeutic treatment option in extremely preterm infants.

Inflammation in the hippocampus affects IGF1 receptor signaling and contributes to neurological sequelae in rheumatoid arthritis.

Rheumatoid arthritis (RA) is an inflammatory joint disease with a neurological component including depression, cognitive deficits, and pain, which substantially affect patients' quality of daily life. Insulin-like growth factor 1 receptor (IGF1R) signaling is one of the factors in RA pathogenesis as well as a known regulator of adult neurogenesis. The purpose of this study was to investigate the association between IGF1R signaling and the neurological symptoms in RA. In experimental RA, we demonstrated that arthritis induced enrichment of IBA1+ microglia in the hippocampus. This coincided with inhibitory phosphorylation of insulin receptor substrate 1 (IRS1) and up-regulation of IGF1R in the pyramidal cell layer of the cornus ammoni and in the dentate gyrus, reproducing the molecular features of the IGF1/insulin resistance. The aberrant IGF1R signaling was associated with reduced hippocampal neurogenesis, smaller hippocampus, and increased immobility of RA mice. Inhibition of IGF1R in experimental RA led to a reduction of IRS1 inhibition and partial improvement of neurogenesis. Evaluation of physical functioning and brain imaging in RA patients revealed that enhanced functional disability is linked with smaller hippocampus volume and aberrant IGF1R/IRS1 signaling. These results point to abnormal IGF1R signaling in the brain as a mediator of neurological sequelae in RA and provide support for the potentially reversible nature of hippocampal changes.

Early limbic microstructural alterations in apathy and depression in de novo Parkinson's disease.

BACKGROUND: Whether structural alterations underpin apathy and depression in de novo parkinsonian patients is unknown. The objectives of this study were to investigate whether apathy and depression in de novo parkinsonian patients are related to structural alterations and how structural abnormalities relate to serotonergic or dopaminergic dysfunction. METHODS: We compared the morphological and microstructural architecture in gray matter using voxel-based morphometry and diffusion tensor imaging coupled with white matter tract-based spatial statistics in a multimodal imaging case-control study enrolling 14 apathetic and 13 nonapathetic patients with de novo Parkinson's disease and 15 age-matched healthy controls, paired with PET imaging of the presynaptic dopaminergic and serotonergic systems. RESULTS: De novo parkinsonian patients with apathy had bilateral microstructural alterations in the medial corticostriatal limbic system, exhibiting decreased fractional anisotropy and increased mean diffusivity in the anterior striatum and pregenual anterior cingulate cortex in conjunction with serotonergic dysfunction. Furthermore, microstructural alterations extended to the medial frontal cortex, the subgenual anterior cingulate cortex and subcallosal gyrus, the medial thalamus, and the caudal midbrain, suggesting disruption of long-range nondopaminergic projections originating in the brainstem, in addition to microstructural alterations in callosal interhemispheric connections and frontostriatal association tracts early in the disease course. In addition, microstructural abnormalities related to depressive symptoms in apathetic and nonapathetic patients revealed a distinct, mainly right-sided limbic subnetwork involving limbic and frontal association tracts. CONCLUSIONS: Early limbic microstructural alterations specifically related to apathy and depression emphasize the role of early disruption of ascending nondopaminergic projections and related corticocortical and corticosubcortical networks which underpin the variable expression of nonmotor and neuropsychiatric symptoms in Parkinson's disease. © 2019 International Parkinson and Movement Disorder Society.

Macroanatomy and 3D probabilistic atlas of the human insula.

The human insula is implicated in numerous functions. More and more neuroimaging studies focus on this region, however no atlas offers a complete subdivision of the insula in a reference space. The aims of this study were to define a protocol to subdivide insula, to create probability maps in the MNI152 stereotaxic space, and to provide normative reference volume measurements for these subdivisions. Six regions were manually delineated bilaterally on 3D T1 MR images of 30 healthy subjects: the three short gyri, the anterior inferior cortex, and the two long gyri. The volume of the insular grey matter was 7.7 ± 0.9cm3 in native space and 9.9 ± 0.6cm3 in MNI152 space. These volumes expressed as a percentage of the ipsilateral grey matter volume were minimally larger in women (2.7±0.2%) than in men (2.6±0.2%). After spatial normalization, a stereotactic probabilistic atlas of each subregion was produced, as well as a maximum-probability atlas taking into account surrounding structures. Automatically labelling insular subregions via a multi-atlas propagation and label fusion strategy (MAPER) in a leave-one-out experiment showed high spatial overlaps of such automatically defined insular subregions with the manually derived ones (mean Jaccard index 0.65, corresponding to a mean Dice index of 0.79), with an average mean volume error of 2.6%. Probabilistic and maximum probability atlases and the original delineations are available on the web under free academic licences.

White matter development in children with benign childhood epilepsy with centro-temporal spikes.

Benign childhood epilepsy with centro-temporal spikes (BCECTS) is a unique form of non-lesional age-dependent epilepsy with rare seizures, focal electroencepalographic abnormalities affecting the same well delineated cortical region in most patients, and frequent mild to moderate cognitive dysfunctions. In this condition, it is hypothesized that interictal electroencepalographic discharges might interfere with local brain maturation, resulting in altered cognition. Diffusion tensor imaging allows testing of this hypothesis by investigating the white matter microstructure, and has previously proved sensitive to epilepsy-related alterations of fractional anisotropy and diffusivity. However, no diffusion tensor imaging study has yet been performed with a focus on BCECTS. We investigated 25 children suffering from BCECTS and 25 age-matched control subjects using diffusion tensor imaging, 3D-T1 magnetic resonance imaging, and a battery of neuropsychological tests including Conner's scale and Wechsler Intelligence Scale for Children (fourth revision). Electroencephalography was also performed in all patients within 2 months of the magnetic resonance imaging assessment. Parametric maps of fractional anisotropy, mean-, radial-, and axial diffusivity were extracted from diffusion tensor imaging data. Patients were compared with control subjects using voxel-based statistics and family-wise error correction for multiple comparisons. Each patient was also compared to control subjects. Fractional anisotropy and diffusivity images were correlated to neuropsychological and clinical variables. Group analysis showed significantly reduced fractional anisotropy and increased diffusivity in patients compared with control subjects, predominantly over the left pre- and postcentral gyri and ipsilateral to the electroencephalographic focus. At the individual level, regions of significant differences were observed in 10 patients (40%) for anisotropy (eight reduced fractional anisotropy, one increased fractional anisotropy, one both), and 17 (56%) for diffusivity (13 increased, one reduced, three both). There were significant negative correlations between fractional anisotropy maps and duration of epilepsy in the precentral gyri, bilaterally, and in the left postcentral gyrus. Accordingly, 9 of 12 patients (75%) with duration of epilepsy>12 months showed significantly reduced fractional anisotropy versus none of the 13 patients with duration of epilepsy≤12 months. Diffusivity maps positively correlated with duration of epilepsy in the cuneus. Children with BCECTS demonstrate alterations in the microstructure of the white matter, undetectable with conventional magnetic resonance imaging, predominating over the regions displaying chronic interictal epileptiform discharges. The association observed between diffusion tensor imaging changes, duration of epilepsy and cognitive performance appears compatible with the hypothesis that interictal epileptic activity alters brain maturation, which could in turn lead to cognitive dysfunction. However, such cross-sectional association does not demonstrate causality, and other hitherto unidentified factors could represent the common cause to part or all of the observed findings.

Test-retest reproducibility of cannabinoid-receptor type 1 availability quantified with the PET ligand [¹¹C]MePPEP.

BACKGROUND: Endocannabinoids are involved in normal cognition, and dysfunction in cannabinoid-receptor-mediated neurotransmission has been suggested in a variety of neurological and psychiatric pathologies. The type 1 cannabinoid receptor (CB1) is widely expressed in the human central nervous system. The objective of this study was to quantify the test-retest reproducibility of measures of the PET ligand [(11)C]MePPEP in order to assess the stability of CB1-receptor quantification in humans in vivo. METHODS: Fifteen healthy subjects (eight females; median age 32 years, range 25 to 65 years) had a 90-minute PET scan on two occasions after injection of a median dose of [(11)C]MePPEP of 364 MBq. Metabolite-corrected arterial plasma input functions were obtained for all scans. Eight ROIs, reflecting different levels of receptor densities/concentrations, were defined automatically: hippocampus, anterior cingulate gyrus, inferior frontal gyrus, caudate nucleus, globus pallidus, nucleus accumbens, thalamus, and pons. We used seven quantification methods: reversible compartmental models with one and two tissue classes, two and four rate constants, and a variable blood volume term (2kbv; 4kbv); model-free (spectral) analyses with and without regularisation, including one with voxel-wise quantification; the simplified reference tissue model (SRTM) with pons as a pseudo-reference region; and modified standard uptake values (mSUVs) calculated for the period of ~30-60 min after injection. Percentage test-retest change and between-subject variability were both assessed, and test-retest reliability was quantified by the intraclass correlation coefficient (ICC). The ratio of binding estimates pallidum:pons served as an indicator of a method's ability to reflect binding heterogeneity. RESULTS: Neither the SRTM nor the 4kbv model produced reliable measures, with ICCs around zero. Very good (>0.75) or excellent (>0.80) ICCs were obtained with the other methods. The most reliable were spectral analysis parametric maps (average across regions±standard deviation 0.83±0.03), rank shaping regularised spectral analysis (0.82±0.05), and the 2kbv model (0.82±0.09), but mSUVs were also reliable for most regions (0.79±0.13). Mean test-retest changes among the five well-performing methods ranged from 12±10% for mSUVs to 16% for 2kbv. Intersubject variability was high, with mean between-subject coefficients of variation ranging from 32±13% for mSUVs to 45% for 2kbv. The highest pallidum:pons ratios of binding estimates were achieved by mSUV (4.2), spectral analysis-derived parametric maps (3.6), and 2kbv (3.6). CONCLUSION: Quantification of CB1 receptor availability using [(11)C]MePPEP shows good to excellent reproducibility with several kinetic models and model-free analyses, whether applied on a region-of-interest or voxelwise basis. Simple mSUV measures were also reliable for most regions, but do not allow fully quantitative interpretation. [(11)C]MePPEP PET is well placed as a tool to investigate CB1-receptor mediated neurotransmission in health and disease.

Random forest-based similarity measures for multi-modal classification of Alzheimer's disease.

Neurodegenerative disorders, such as Alzheimer's disease, are associated with changes in multiple neuroimaging and biological measures. These may provide complementary information for diagnosis and prognosis. We present a multi-modality classification framework in which manifolds are constructed based on pairwise similarity measures derived from random forest classifiers. Similarities from multiple modalities are combined to generate an embedding that simultaneously encodes information about all the available features. Multi-modality classification is then performed using coordinates from this joint embedding. We evaluate the proposed framework by application to neuroimaging and biological data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Features include regional MRI volumes, voxel-based FDG-PET signal intensities, CSF biomarker measures, and categorical genetic information. Classification based on the joint embedding constructed using information from all four modalities out-performs the classification based on any individual modality for comparisons between Alzheimer's disease patients and healthy controls, as well as between mild cognitive impairment patients and healthy controls. Based on the joint embedding, we achieve classification accuracies of 89% between Alzheimer's disease patients and healthy controls, and 75% between mild cognitive impairment patients and healthy controls. These results are comparable with those reported in other recent studies using multi-kernel learning. Random forests provide consistent pairwise similarity measures for multiple modalities, thus facilitating the combination of different types of feature data. We demonstrate this by application to data in which the number of features differs by several orders of magnitude between modalities. Random forest classifiers extend naturally to multi-class problems, and the framework described here could be applied to distinguish between multiple patient groups in the future.

Quantification of opioid receptor availability following spontaneous epileptic seizures: correction of [11C]diprenorphine PET data for the partial-volume effect.

Previous positron emission tomography (PET) studies in refractory temporal lobe epilepsy (TLE) using the non-selective opioid receptor antagonist [(11)C]diprenorphine (DPN) did not detect any changes in mesial temporal structures, despite known involvement of the hippocampus in seizure generation. Normal binding in smaller hippocampi is suggestive of increased receptor concentration in the remaining grey matter. Correction for partial-volume effect (PVE) has not been used in previous DPN PET studies. Here, we present PVE-corrected DPN-PET data quantifying post-ictal and interictal opioid receptor availability in humans with mTLE. Eight paired datasets of post-ictal and interictal DPN PET scans and eleven test/retest control datasets were available from a previously published study on opioid receptor changes in TLE following seizures (Hammers et al., 2007a). Five of the eight participants with TLE had documented hippocampal sclerosis. Data were re-analyzed using regions of interest and a novel PVE correction method (structural functional synergistic-resolution recovery (SFS-RR); (Shidahara et al., 2012)). Data were denoised, followed by application of SFS-RR, with anatomical information derived via precise anatomical segmentation of the participants' MRI (MAPER; (Heckemann et al., 2010)). [(11)C]diprenorphine volume-of-distribution (VT) was quantified in six regions of interest. Post-ictal increases were observed in the ipsilateral fusiform gyri and lateral temporal pole. A novel finding was a post-ictal increase in [(11)C]DPN VT relative to the interictal state in the ipsilateral parahippocampal gyrus, not observed in uncorrected datasets. As for voxel-based (SPM) analyses, correction for global VT values was essential in order to demonstrate focal post-ictal increases in [(11)C]DPN VT. This study provides further direct human in vivo evidence for changes in opioid receptor availability in TLE following seizures, including changes that were not evident without PVE correction. Denoising, resolution recovery and precise anatomical segmentation can extract valuable information from PET studies that would be missed with conventional post-processing procedures.

Positron emission tomography with α-[11C]methyl-L-tryptophan in tuberous sclerosis complex-related epilepsy.

OBJECTIVE: Tuberous sclerosis complex (TSC) is often associated with cerebral tubers and medically intractable epilepsy. We reevaluated whether increased uptake of α-[(11) C]methyl-l-tryptophan (AMT) in cerebral tubers is associated with tuber epileptogenicity. METHODS: We included 12 patients (six male, 4-53 years old) with TSC and refractory seizures who were evaluated for epilepsy surgery in our center, including video-electroencephalographic (EEG) monitoring, fluid-attenuated inversion recovery magnetic resonance imaging (FLAIR MRI), and positron emission tomography (PET) with α-[(11) C]methyl-l-tryptophan (AMT-PET). Nine of these 12 patients also underwent intracerebral EEG recording. AMT uptake in each tuber was visually evaluated on PET coregistered with MRI. An AMT uptake index based on lesional/healthy cortex ratio was also calculated. Sensitivity and specificity values of AMT-PET in the detection of epileptogenic lesions were obtained, using the available electroclinical and neuroimaging evidence as the gold standard for epileptogenicity. RESULTS: A total of 126 tubers were identified. Two of 12 patients demonstrated a tuber with clearly increased AMT uptake, one of whom also showed a subtle increased AMT uptake in another contralateral tuber. Four other patients showed only subtle increased AMT uptake. The only two tubers with clearly increased AMT uptake proved to be epileptogenic based on intracerebral EEG data, whereas none of the tubers associated with subtle increased AMT uptake were involved at ictal onset. In a per-patient approach, this yielded a sensitivity of clearly increased AMT uptake in detecting tuber epileptogenicity of 17% (2/12 patients), whereas the per-lesion sensitivity and specificity were 12% (95% confidence interval [CI]: 3-34%) and 100% (95% CI: 97-100%), respectively. SIGNIFICANCE: AMT-PET is a specific neuroimaging technique in the identification of epileptogenic tubers in TSC. Despite its low sensitivity, the clinical usefulness of AMT-PET still deserves to be considered according to the challenging complexity of epilepsy surgery in tuberous sclerosis.

Magnetic resonance volumetry reveals focal brain atrophy in transient epileptic amnesia.

Transient epileptic amnesia (TEA) is a recently described epilepsy syndrome characterized by recurrent episodes of isolated memory loss. It is associated with two unusual forms of interictal memory impairment: accelerated long-term forgetting (ALF) and autobiographical amnesia. We investigated the neural basis of TEA using manual volumetry and automated multi-atlas-based segmentation of whole-brain magnetic resonance imaging data from 40 patients with TEA and 20 healthy controls. Both methods confirmed the presence of subtle, bilateral hippocampal atrophy. Additional atrophy was revealed in perirhinal and orbitofrontal cortices. The volumes of these regions correlated with anterograde memory performance. No structural correlates were found for ALF or autobiographical amnesia. The results support the hypothesis that TEA is a focal medial temporal lobe epilepsy syndrome but reveal additional pathology in connected brain regions. The unusual interictal memory deficits of TEA remain unexplained by structural pathology and may reflect physiological disruption of memory networks by subclinical epileptiform activity.

Neurological features of epilepsy, ataxia, sensorineural deafness, tubulopathy syndrome.

AIM: Recently, we reported a previously unrecognized symptom constellation comprising epilepsy, ataxia, sensorineural deafness, and tubulopathy (EAST syndrome) associated with recessive mutations in the KCNJ10 gene. Here, we provide a detailed characterization of the clinical features of the syndrome to aid patient management with respect to diagnosis, prognostic counselling, and identification of best treatment modalities. METHOD: We conducted a retrospective review of the detailed neurological and neuroradiological features of nine children (four females, five males; age range at last examination 6-20y) with genetically proven EAST syndrome. RESULTS: All children presented with tonic-clonic seizures in infancy. Later, non-progressive, cerebellar ataxia and hearing loss were noted. Whilst seizures mostly responded well to treatment, ataxia proved to be the most debilitating feature, with three patients non-ambulant. All available magnetic resonance imaging (MRI) revealed subtle symmetrical signal changes in the cerebellar dentate nuclei. Moreover, four patients had a small corpus callosum and brainstem hypoplasia, and three had a small spinal cord. Regional quantitative volumetric analysis of the images confirmed the corpus callosum and brainstem hypoplasia and showed further patterns of variation from the norm. INTERPRETATION: The neurological features of EAST syndrome appear to be non-progressive, which is important for prognostic counselling. The spectrum of EAST syndrome includes consistent abnormalities on brain MRI, which may aid diagnosis. Further longitudinal documentation is required to determine the true natural history of the disorder.

A robust method for investigating thalamic white matter tracts after traumatic brain injury.

Damage to the structural connections of the thalamus is a frequent feature of traumatic brain injury (TBI) and can be a key factor in determining clinical outcome. Until recently it has been difficult to quantify the extent of this damage in vivo. Diffusion tensor imaging (DTI) provides a validated method to investigate traumatic axonal injury, and can be applied to quantify damage to thalamic connections. DTI can also be used to assess white matter tract structure using tractography, and this technique has been used to study thalamo-cortical connections in the healthy brain. However, the presence of white matter injury can cause failure of tractography algorithms. Here, we report a method for investigating thalamo-cortical connectivity that bypasses the need for individual tractography. We first created a template for a number of thalamo-cortical connections using probabilistic tractography performed in ten healthy subjects. This template for investigating white matter structure was validated by comparison with individual tractography in the same group, as well as in an independent control group (N=11). We also evaluated two methods of masking tract location using the tract skeleton generated by tract based spatial statistics, and a cerebrospinal fluid mask. Voxel-wise estimates of fractional anisotropy derived from the template were more strongly correlated with individual tractography when both types of masking were used. The tract templates were then used to sample DTI measures from a group of TBI patients (N=22), with direct comparison performed against probabilistic tractography in individual patients. Probabilistic tractography often failed to produce anatomically plausible tracts in TBI patients. Importantly, we show that this problem increases as tracts become more damaged, and leads to underestimation of the amount of traumatic axonal injury. In contrast, the tract template can be used in these cases, allowing a more accurate assessment of white matter damage. In summary, we propose a method suitable for assessing specific thalamo-cortical white matter connections after TBI that is robust to the presence of varying amounts of traumatic axonal injury, as well as highlighting the potential problems of applying tractography algorithms in patient populations.

Multi-region analysis of longitudinal FDG-PET for the classification of Alzheimer's disease.

Imaging biomarkers for Alzheimer's disease are desirable for improved diagnosis and monitoring, as well as drug discovery. Automated image-based classification of individual patients could provide valuable diagnostic support for clinicians, when considered alongside cognitive assessment scores. We investigate the value of combining cross-sectional and longitudinal multi-region FDG-PET information for classification, using clinical and imaging data from the Alzheimer's Disease Neuroimaging Initiative. Whole-brain segmentations into 83 anatomically defined regions were automatically generated for baseline and 12-month FDG-PET images. Regional signal intensities were extracted at each timepoint, as well as changes in signal intensity over the follow-up period. Features were provided to a support vector machine classifier. By combining 12-month signal intensities and changes over 12 months, we achieve significantly increased classification performance compared with using any of the three feature sets independently. Based on this combined feature set, we report classification accuracies of 88% between patients with Alzheimer's disease and elderly healthy controls, and 65% between patients with stable mild cognitive impairment and those who subsequently progressed to Alzheimer's disease. We demonstrate that information extracted from serial FDG-PET through regional analysis can be used to achieve state-of-the-art classification of diagnostic groups in a realistic multi-centre setting. This finding may be usefully applied in the diagnosis of Alzheimer's disease, predicting disease course in individuals with mild cognitive impairment, and in the selection of participants for clinical trials.

Inflammation after trauma: microglial activation and traumatic brain injury.

OBJECTIVE: Patient outcome after traumatic brain injury (TBI) is highly variable. The underlying pathophysiology of this is poorly understood, but inflammation is potentially an important factor. Microglia orchestrate many aspects of this response. Their activation can be studied in vivo using the positron emission tomography (PET) ligand [11C](R)PK11195 (PK). In this study, we investigate whether an inflammatory response to TBI persists, and whether this response relates to structural brain abnormalities and cognitive function. METHODS: Ten patients, studied at least 11 months after moderate to severe TBI, underwent PK PET and structural magnetic resonance imaging (including diffusion tensor imaging). PK binding potentials were calculated in and around the site of focal brain damage, and in selected distant and subcortical brain regions. Standardized neuropsychological tests were administered. RESULTS: PK binding was significantly raised in the thalami, putamen, occipital cortices, and posterior limb of the internal capsules after TBI. There was no increase in PK binding at the original site of focal brain injury. High PK binding in the thalamus was associated with more severe cognitive impairment, although binding was not correlated with either the time since the injury or the extent of structural brain damage. INTERPRETATION: We demonstrate that increased microglial activation can be present up to 17 years after TBI. This suggests that TBI triggers a chronic inflammatory response particularly in subcortical regions. This highlights the importance of considering the response to TBI as evolving over time and suggests interventions may be beneficial for longer intervals after trauma than previously assumed.

Deep learning for automatic brain tumour segmentation on MRI: evaluation of recommended reporting criteria via a reproduction and replication study.

OBJECTIVES: To determine the reproducibility and replicability of studies that develop and validate segmentation methods for brain tumours on MRI and that follow established reproducibility criteria; and to evaluate whether the reporting guidelines are sufficient. METHODS: Two eligible validation studies of distinct deep learning (DL) methods were identified. We implemented the methods using published information and retraced the reported validation steps. We evaluated to what extent the description of the methods enabled reproduction of the results. We further attempted to replicate reported findings on a clinical set of images acquired at our institute consisting of high-grade and low-grade glioma (HGG, LGG), and meningioma (MNG) cases. RESULTS: We successfully reproduced one of the two tumour segmentation methods. Insufficient description of the preprocessing pipeline and our inability to replicate the pipeline resulted in failure to reproduce the second method. The replication of the first method showed promising results in terms of Dice similarity coefficient (DSC) and sensitivity (Sen) on HGG cases (DSC=0.77, Sen=0.88) and LGG cases (DSC=0.73, Sen=0.83), however, poorer performance was observed for MNG cases (DSC=0.61, Sen=0.71). Preprocessing errors were identified that contributed to low quantitative scores in some cases. CONCLUSIONS: Established reproducibility criteria do not sufficiently emphasise description of the preprocessing pipeline. Discrepancies in preprocessing as a result of insufficient reporting are likely to influence segmentation outcomes and hinder clinical utilisation. A detailed description of the whole processing chain, including preprocessing, is thus necessary to obtain stronger evidence of the generalisability of DL-based brain tumour segmentation methods and to facilitate translation of the methods into clinical practice.