RESUMEN
Background: Evaluation of molecular markers (IDH, pTERT, 1p/19q codeletion, and MGMT) in adult diffuse gliomas is crucial for accurate diagnosis and optimal treatment planning. Dynamic Susceptibility Contrast (DSC) and Arterial Spin Labeling (ASL) perfusion MRI techniques have both shown good performance in classifying molecular markers, however, their performance has not been compared side-by-side. Methods: Pretreatment MRI data from 90 patients diagnosed with diffuse glioma (54 men/36 female, 53.1 ± 15.5 years, grades 2-4) were retrospectively analyzed. DSC-derived normalized cerebral blood flow/volume (nCBF/nCBV) and ASL-derived nCBF in tumor and perifocal edema were analyzed in patients with available IDH-mutation (n = 67), pTERT-mutation (n = 39), 1p/19q codeletion (n = 33), and MGMT promoter methylation (n = 31) status. Cross-validated uni- and multivariate logistic regression models assessed perfusion parameters' performance in molecular marker detection. Results: ASL and DSC perfusion parameters in tumor and edema distinguished IDH-wildtype (wt) and pTERT-wt tumors from mutated ones. Univariate classification performance was comparable for ASL-nCBF and DSC-nCBV in IDH (maximum AUROCC 0.82 and 0.83, respectively) and pTERT (maximum AUROCC 0.70 and 0.81, respectively) status differentiation. The multivariate approach improved IDH (DSC-nCBV AUROCC 0.89) and pTERT (ASL-nCBF AUROCC 0.8 and DSC-nCBV AUROCC 0.86) classification. However, ASL and DSC parameters could not differentiate 1p/19q codeletion or MGMT promoter methylation status. Positive correlations were found between ASL-nCBF and DSC-nCBV/-nCBF in tumor and edema. Conclusions: ASL is a viable gadolinium-free replacement for DSC for molecular characterization of adult diffuse gliomas.
RESUMEN
Standard treatment of patients with glioblastoma includes surgical resection of the tumor. The extent of resection (EOR) achieved during surgery significantly impacts prognosis and is used to stratify patients in clinical trials. In this study, we developed a U-Net-based deep-learning model to segment contrast-enhancing tumor on post-operative MRI exams taken within 72â h of resection surgery and used these segmentations to classify the EOR as either maximal or submaximal. The model was trained on 122 multiparametric MRI scans from our institution and achieved a mean Dice score of 0.52 ± 0.03 on an external dataset (n = 248), a performance -on par with the interrater agreement between expert annotators as reported in literature. We obtained an EOR classification precision/recall of 0.72/0.78 on the internal test dataset (n = 462) and 0.90/0.87 on the external dataset. Furthermore, Kaplan-Meier curves were used to compare the overall survival between patients with maximal and submaximal resection in the internal test dataset, as determined by either clinicians or the model. There was no significant difference between the survival predictions using the model's and clinical EOR classification. We find that the proposed segmentation model is capable of reliably classifying the EOR of glioblastoma tumors on early post-operative MRI scans. Moreover, we show that stratification of patients based on the model's predictions offers at least the same prognostic value as when done by clinicians.
RESUMEN
Staging amyloid-beta (Aß) pathophysiology according to the intensity of neurodegeneration could identify individuals at risk for cognitive decline in Alzheimer's disease (AD). In blood, phosphorylated tau (p-tau) associates with Aß pathophysiology but an AD-type neurodegeneration biomarker has been lacking. In this multicenter study (n = 1076), we show that brain-derived tau (BD-tau) in blood increases according to concomitant Aß ("A") and neurodegeneration ("N") abnormalities (determined using cerebrospinal fluid biomarkers); We used blood-based A/N biomarkers to profile the participants in this study; individuals with blood-based p-tau+/BD-tau+ profiles had the fastest cognitive decline and atrophy rates, irrespective of the baseline cognitive status. Furthermore, BD-tau showed no or much weaker correlations with age, renal function, other comorbidities/risk factors and self-identified race/ethnicity, compared with other blood biomarkers. Here we show that blood-based BD-tau is a biomarker for identifying Aß-positive individuals at risk of short-term cognitive decline and atrophy, with implications for clinical trials and implementation of anti-Aß therapies.
Asunto(s)
Enfermedad de Alzheimer , Disfunción Cognitiva , Humanos , Proteínas tau/líquido cefalorraquídeo , Péptidos beta-Amiloides/metabolismo , Encéfalo/metabolismo , Biomarcadores/líquido cefalorraquídeo , AtrofiaRESUMEN
INTRODUCTION: Loss of blood-brain barrier (BBB) integrity is hypothesised to be one of the earliest microvascular signs of Alzheimer's disease (AD). Existing BBB integrity imaging methods involve contrast agents or ionising radiation, and pose limitations in terms of cost and logistics. Arterial spin labelling (ASL) perfusion MRI has been recently adapted to map the BBB permeability non-invasively. The DEveloping BBB-ASL as a non-Invasive Early biomarker (DEBBIE) consortium aims to develop this modified ASL-MRI technique for patient-specific and robust BBB permeability assessments. This article outlines the study design of the DEBBIE cohorts focused on investigating the potential of BBB-ASL as an early biomarker for AD (DEBBIE-AD). METHODS AND ANALYSIS: DEBBIE-AD consists of a multicohort study enrolling participants with subjective cognitive decline, mild cognitive impairment and AD, as well as age-matched healthy controls, from 13 cohorts. The precision and accuracy of BBB-ASL will be evaluated in healthy participants. The clinical value of BBB-ASL will be evaluated by comparing results with both established and novel AD biomarkers. The DEBBIE-AD study aims to provide evidence of the ability of BBB-ASL to measure BBB permeability and demonstrate its utility in AD and AD-related pathologies. ETHICS AND DISSEMINATION: Ethics approval was obtained for 10 cohorts, and is pending for 3 cohorts. The results of the main trial and each of the secondary endpoints will be submitted for publication in a peer-reviewed journal.
Asunto(s)
Enfermedad de Alzheimer , Disfunción Cognitiva , Humanos , Barrera Hematoencefálica/diagnóstico por imagen , Barrera Hematoencefálica/patología , Enfermedad de Alzheimer/diagnóstico por imagen , Enfermedad de Alzheimer/patología , Marcadores de Spin , Imagen por Resonancia Magnética/métodos , Disfunción Cognitiva/diagnóstico por imagen , Biomarcadores , Estudios Observacionales como AsuntoRESUMEN
Introduction: Efforts to develop cost-effective approaches for detecting amyloid pathology in Alzheimer's disease (AD) have gained significant momentum with a focus on biomarker classification. Recent research has explored non-invasive and readily accessible biomarkers, including magnetic resonance imaging (MRI) biomarkers and some AD risk factors. Methods: In this comprehensive study, we leveraged a diverse dataset, encompassing participants with varying cognitive statuses from multiple sources, including cohorts from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and our in-house Dementia Disease Initiation (DDI) cohort. As brain amyloid plaques have been proposed as sufficient for AD diagnosis, our primary aim was to assess the effectiveness of multimodal biomarkers in identifying amyloid plaques, using deep machine learning methodologies. Results: Our findings underscore the robustness of the utilized methods in detecting amyloid beta positivity across multiple cohorts. Additionally, we investigated the potential of demographic data to enhance MRI-based amyloid detection. Notably, the inclusion of demographic risk factors significantly improved our models' ability to detect amyloid-beta positivity, particularly in early-stage cases, exemplified by an average area under the ROC curve of 0.836 in the unimpaired DDI cohort. Discussion: These promising, non-invasive, and cost-effective predictors of MRI biomarkers and demographic variables hold the potential for further refinement through considerations like APOE genotype and plasma markers.
RESUMEN
OBJECTIVE: Response to antidepressant treatment in major depressive disorder varies substantially between individuals, which lengthens the process of finding effective treatment. The authors sought to determine whether a multimodal machine learning approach could predict early sertraline response in patients with major depressive disorder. They assessed the predictive contribution of MR neuroimaging and clinical assessments at baseline and after 1 week of treatment. METHODS: This was a preregistered secondary analysis of data from the Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC) study, a multisite double-blind, placebo-controlled randomized clinical trial that included 296 adult outpatients with unmedicated recurrent or chronic major depressive disorder. MR neuroimaging and clinical data were collected before and after 1 week of treatment. Performance in predicting response and remission, collected after 8 weeks, was quantified using balanced accuracy (bAcc) and area under the receiver operating characteristic curve (AUROC) scores. RESULTS: A total of 229 patients were included in the analyses (mean age, 38 years [SD=13]; 66% female). Internal cross-validation performance in predicting response to sertraline (bAcc=68% [SD=10], AUROC=0.73 [SD=0.03]) was significantly better than chance. External cross-validation on data from placebo nonresponders (bAcc=62%, AUROC=0.66) and placebo nonresponders who were switched to sertraline (bAcc=65%, AUROC=0.68) resulted in differences that suggest specificity for sertraline treatment compared with placebo treatment. Finally, multimodal models outperformed unimodal models. CONCLUSIONS: The study results confirm that early sertraline treatment response can be predicted; that the models are sertraline specific compared with placebo; that prediction benefits from integrating multimodal MRI data with clinical data; and that perfusion imaging contributes most to these predictions. Using this approach, a lean and effective protocol could individualize sertraline treatment planning to improve psychiatric care.
Asunto(s)
Trastorno Depresivo Mayor , Sertralina , Adulto , Humanos , Femenino , Masculino , Sertralina/uso terapéutico , Trastorno Depresivo Mayor/diagnóstico por imagen , Trastorno Depresivo Mayor/tratamiento farmacológico , Trastorno Depresivo Mayor/psicología , Método Doble Ciego , Antidepresivos/uso terapéutico , Imagen por Resonancia MagnéticaRESUMEN
Introduction: Radiological assessment is necessary to diagnose spontaneous intracerebral hemorrhage (ICH) and traumatic brain injury intracranial hemorrhage (TBI-bleed). Artificial intelligence (AI) deep learning tools provide a means for decision support. This study evaluates the hemorrhage segmentations produced from three-dimensional deep learning AI model that was developed using non-contrast computed tomography (CT) imaging data external to the current study. Methods: Non-contrast CT imaging data from 1263 patients were accessed across seven data sources (referred to as sites) in Norway and Sweden. Patients were included based on ICH, TBI-bleed, or mild TBI diagnosis. Initial non-contrast CT images were available for all participants. Hemorrhage location frequency maps were generated. The number of estimated haematoma clusters was correlated with the total haematoma volume. Ground truth expert annotations were available for one ICH site; hence, a comparison was made with the estimated haematoma volumes. Segmentation volume estimates were used in a receiver operator characteristics (ROC) analysis for all samples (i.e., bleed detected) and then specifically for one site with few TBI-bleed cases. Results: The hemorrhage frequency maps showed spatial patterns of estimated lesions consistent with ICH or TBI-bleed presentations. There was a positive correlation between the estimated number of clusters and total haematoma volume for each site (correlation range: 0.45-0.74; each p-value < 0.01) and evidence of ICH between-site differences. Relative to hand-drawn annotations for one ICH site, the VIOLA-AI segmentation mask achieved a median Dice Similarity Coefficient of 0.82 (interquartile range: 0.78 and 0.83), resulting in a small overestimate in the haematoma volume by a median of 0.47 mL (interquartile range: 0.04 and 1.75 mL). The bleed detection ROC analysis for the whole sample gave a high area-under-the-curve (AUC) of 0.92 (with sensitivity and specificity of 83.28% and 95.41%); however, when considering only the mild head injury site, the TBI-bleed detection gave an AUC of 0.70. Discussion: An open-source segmentation tool was used to visualize hemorrhage locations across multiple data sources and revealed quantitative hemorrhage site differences. The automated total hemorrhage volume estimate correlated with a per-participant hemorrhage cluster count. ROC results were moderate-to-high. The VIOLA-AI tool had promising results and might be useful for various types of intracranial hemorrhage.
RESUMEN
BACKGROUND: Main aim was assessment of regional blood-brain barrier (BBB) function by dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in patients with neuroborreliosis. Secondary aim was to study the correlation of BBB function with biochemical, clinical, and cognitive parameters. METHODS: Regional ethical committee approved this prospective single-center case-control study. Within 1 month after diagnosis of neuroborreliosis, 55 patients underwent DCE-MRI. The patient group consisted of 25 males and 30 females with mean age 58 years, and the controls were 8 males and 7 females with mean age 57 years. Pharmacokinetic compartment modelling with Patlak fit was applied, providing estimates for capillary leakage rate and blood volume fraction. Nine anatomical brain regions were sampled with auto-generated binary masks. Fatigue, severity of clinical symptoms and findings, and cognitive function were assessed in the acute phase and 6 months after treatment. RESULTS: Leakage rates and blood volume fractions were lower in patients compared to controls in the thalamus (p = 0.027 and p = 0.018, respectively), caudate nucleus (p = 0.009 for both), and hippocampus (p = 0.054 and p = 0.009). No correlation of leakage rates with fatigue, clinical disease severity or cognitive function was found. CONCLUSIONS: In neuroborreliosis, leakage rate and blood volume fraction in the thalamus, caudate nucleus, and hippocampus were lower in patients compared to controls. DCE-MRI provided new insight to pathophysiology of neuroborreliosis, and can serve as biomarker of BBB function and regulatory mechanisms of the neurovascular unit in infection and inflammation. RELEVANCE STATEMENT: DCE-MRI provided new insight to pathophysiology of neuroborreliosis, and can serve as biomarker of blood-brain barrier function and regulatory mechanisms of the neurovascular unit in infection and inflammation. KEY POINTS: ⢠Neuroborreliosis is an infection with disturbed BBB function. ⢠Microvessel leakage can be studied with DCE-MRI. ⢠Prospective case-control study showed altered microvessel properties in thalamus, caudate, and hippocampus.
Asunto(s)
Barrera Hematoencefálica , Sustancia Gris , Femenino , Masculino , Humanos , Persona de Mediana Edad , Barrera Hematoencefálica/diagnóstico por imagen , Estudios de Casos y Controles , Fatiga , Inflamación , Imagen por Resonancia MagnéticaRESUMEN
PURPOSE: To explore Norwegian breast radiologists' expectations of adding artificial intelligence (AI) in the interpretation procedure of screening mammograms. METHODS: All breast radiologists involved in interpretation of screening mammograms in BreastScreen Norway during 2021 and 2022 (n = 98) were invited to take part in this anonymous cross-sectional survey about use of AI in mammographic screening. The questionnaire included background information of the respondents, their expectations, considerations of biases, and ethical and social implications of implementing AI in screen reading. Data was collected digitally and analyzed using descriptive statistics. RESULTS: The response rate was 61% (60/98), and 67% (40/60) of the respondents were women. Sixty percent (36/60) reported ≥10 years' experience in screen reading, while 82% (49/60) reported no or limited experience with AI in health care. Eighty-two percent of the respondents were positive to explore AI in the interpretation procedure in mammographic screening. When used as decision support, 68% (41/60) expected AI to increase the radiologists' sensitivity for cancer detection. As potential challenges, 55% (33/60) reported lack of trust in the AI system and 45% (27/60) reported discrepancy between radiologists and AI systems as possible challenges. The risk of automation bias was considered high among 47% (28/60). Reduced time spent reading mammograms was rated as a potential benefit by 70% (42/60). CONCLUSION: The radiologists reported positive expectations of AI in the interpretation procedure of screening mammograms. Efforts to minimize the risk of automation bias and increase trust in the AI systems are important before and during future implementation of the tool.
Asunto(s)
Inteligencia Artificial , Motivación , Femenino , Humanos , Masculino , Estudios Transversales , Noruega , RadiólogosRESUMEN
An important step in the analysis of magnetic resonance imaging (MRI) data for neuroimaging is the automated segmentation of white matter hyperintensities (WMHs). Fluid Attenuated Inversion Recovery (FLAIR-weighted) is an MRI contrast that is particularly useful to visualize and quantify WMHs, a hallmark of cerebral small vessel disease and Alzheimer's disease (AD). In order to achieve high spatial resolution in each of the three voxel dimensions, clinical MRI protocols are evolving to a three-dimensional (3D) FLAIR-weighted acquisition. The current study details the deployment of deep learning tools to enable automated WMH segmentation and characterization from 3D FLAIR-weighted images acquired as part of a national AD imaging initiative. Based on data from the ongoing Norwegian Disease Dementia Initiation (DDI) multicenter study, two 3D models-one off-the-shelf from the NVIDIA nnU-Net framework and the other internally developed-were trained, validated, and tested. A third cutting-edge Deep Bayesian network model (HyperMapp3r) was implemented without any de-novo tuning to serve as a comparison architecture. The 2.5D in-house developed and 3D nnU-Net models were trained and validated in-house across five national collection sites among 441 participants from the DDI study, of whom 194 were men and whose average age was (64.91 +/- 9.32) years. Both an external dataset with 29 cases from a global collaborator and a held-out subset of the internal data from the 441 participants were used to test all three models. These test sets were evaluated independently. The ground truth human-in-the-loop segmentation was compared against five established WMH performance metrics. The 3D nnU-Net had the highest performance out of the three tested networks, outperforming both the internally developed 2.5D model and the SOTA Deep Bayesian network with an average dice similarity coefficient score of 0.76 +/- 0.16. Our findings demonstrate that WMH segmentation models can achieve high performance when trained exclusively on FLAIR input volumes that are 3D volumetric acquisitions. Single image input models are desirable for ease of deployment, as reflected in the current embedded clinical research project. The 3D nnU-Net had the highest performance, which suggests a way forward for our need to automate WMH segmentation while also evaluating performance metrics during on-going data collection and model retraining.
Asunto(s)
Enfermedad de Alzheimer , Aprendizaje Profundo , Leucoaraiosis , Sustancia Blanca , Masculino , Humanos , Persona de Mediana Edad , Anciano , Femenino , Teorema de Bayes , Sustancia Blanca/diagnóstico por imagen , Imagen por Resonancia Magnética , Neuroimagen , Enfermedad de Alzheimer/diagnóstico por imagenRESUMEN
BACKGROUND: Atrophy of the medial temporal lobe (MTL) is a biological characteristic of Alzheimer's disease (AD) and can be measured by segmentation of magnetic resonance images (MRI). OBJECTIVE: To assess the clinical utility of automated volumetry in a cognitively well-defined and biomarker-classified multi-center longitudinal predementia cohort. METHODS: We used Automatic Segmentation of Hippocampal Subfields (ASHS) to determine MTL morphometry from MRI. We harmonized scanner effects using the recently developed longitudinal ComBat. Subjects were classified according to the A/T/N system, and as normal controls (NC), subjective cognitive decline (SCD), or mild cognitive impairment (MCI). Positive or negative values of A, T, and N were determined by cerebrospinal fluid measurements of the Aß42/40 ratio, phosphorylated and total tau. From 406 included subjects, longitudinal data was available for 206 subjects by stage, and 212 subjects by A/T/N. RESULTS: Compared to A-/T-/N- at baseline, the entorhinal cortex, anterior and posterior hippocampus were smaller in A+/T+orN+. Compared to NC A- at baseline, these subregions were also smaller in MCI A+. Longitudinally, SCD A+ and MCI A+, and A+/T-/N- and A+/T+orN+, had significantly greater atrophy compared to controls in both anterior and posterior hippocampus. In the entorhinal and parahippocampal cortices, longitudinal atrophy was observed only in MCI A+ compared to NC A-, and in A+/T-/N- and A+/T+orN+ compared to A-/T-/N-. CONCLUSION: We found MTL neurodegeneration largely consistent with existing models, suggesting that harmonized MRI volumetry may be used under conditions that are common in clinical multi-center cohorts.
Asunto(s)
Enfermedad de Alzheimer , Disfunción Cognitiva , Humanos , Enfermedad de Alzheimer/patología , Lóbulo Temporal/diagnóstico por imagen , Lóbulo Temporal/patología , Corteza Entorrinal/diagnóstico por imagen , Corteza Entorrinal/patología , Disfunción Cognitiva/patología , Hipocampo/diagnóstico por imagen , Hipocampo/patología , Imagen por Resonancia Magnética/métodos , Atrofia/patologíaRESUMEN
Background and purpose: Measuring rectal tumour response to radiation is pivotal to restaging patients and for possibly stratification to a watch-and-wait strategy. Recognizing the importance of the tumour microenvironment, we investigated a less explored quantitative imaging marker assessing tumour blood flow (BF) for its potential to predict overall survival (OS). Materials and methods: 24 rectal cancer patients given curative-intent neoadjuvant radiotherapy underwent a multi-echo dynamic magnetic resonance imaging (MRI) sequence with gadolinium contrast for quantification of tumour BF before either 25x2 Gy (n = 18) with concomitant chemotherapy or 5x5 Gy (n = 6). CD34 staining of excised tumour tissue was performed and baseline blood samples were analysed for lactate dehydrogenase (LDH) and angiopoietin-2 (ANGPT-2). Tumour volumes were measured before and after treatment. After subsequent surgery, ypTN scoring assessed tumour response. Cox regression for 5-year OS analysis and t-test for group comparisons were performed. Results: The change in tumour BF (ΔBF) during neoadjuvant radiotherapy was a significant marker of OS, whereas tumour stage and volume were not related to OS. All patients with >20 % decline in BF were long-term survivors. Separating cases in two groups based on ΔBF revealed that patients with increase or a low decrease had higher baseline LDH (p = 0.032) and ANGPT-2 (p = 0.028) levels. Conclusion: MRI-assessed tumour ΔBF during neoadjuvant treatment is a significant predictor of OS in rectal cancer patients, making ΔBF a potential quantitative imaging biomarker for treatment stratification. Blood LDH and ANGPT-2 indicate that non-responding tumours may have a hypoxic microenvironment resistant to radiotherapy.
RESUMEN
OBJECTIVE: To improve accelerated MRI reconstruction through a densely connected cascading deep learning reconstruction framework. MATERIALS AND METHODS: A cascading deep learning reconstruction framework (reference model) was modified by applying three architectural modifications: input-level dense connections between cascade inputs and outputs, an improved deep learning sub-network, and long-range skip-connections between subsequent deep learning networks. An ablation study was performed, where five model configurations were trained on the NYU fastMRI neuro dataset with an end-to-end scheme conjunct on four- and eightfold acceleration. The trained models were evaluated by comparing their respective structural similarity index measure (SSIM), normalized mean square error (NMSE), and peak signal to noise ratio (PSNR). RESULTS: The proposed densely interconnected residual cascading network (DIRCN), utilizing all three suggested modifications achieved a SSIM improvement of 8% and 11%, a NMSE improvement of 14% and 23%, and a PSNR improvement of 2% and 3% for four- and eightfold acceleration, respectively. In an ablation study, the individual architectural modifications all contributed to this improvement for both acceleration factors, by improving the SSIM, NMSE, and PSNR with approximately 2-4%, 4-9%, and 0.5-1%, respectively. CONCLUSION: The proposed architectural modifications allow for simple adjustments on an already existing cascading framework to further improve the resulting reconstructions.
Asunto(s)
Aprendizaje Profundo , Imagen por Resonancia Magnética , Relación Señal-Ruido , AceleraciónRESUMEN
The compression of peritumoral healthy tissue in brain tumor patients is considered a major cause of the life-threatening neurologic symptoms. Although significant deformations caused by the tumor growth can be observed radiologically, the quantification of minor tissue deformations have not been widely investigated. In this study, we propose a method to quantify subtle peritumoral deformations. A total of 127 MRI longitudinal studies from 23 patients with high-grade glioma were included. We estimate longitudinal displacement fields based on a symmetric normalization algorithm and we propose four biomarkers. We assess the interpatient and intrapatient association between proposed biomarkers and the survival based on Cox analyses, and the potential of the biomarkers to stratify patients according to their survival based on Kaplan−Meier analysis. Biomarkers show a significant intrapatient association with survival (p < 0.05); however, only compression biomarkers show the ability to stratify patients between those with higher and lower overall survival (AUC = 0.83, HR = 6.30, p < 0.05 for CompCH). The compression biomarkers present three times higher Hazard Ratios than those representing only displacement. Our study provides a robust and automated method for quantifying and delineating compression in the peritumoral area. Based on the proposed methodology, we found an association between lower compression in the peritumoral area and good prognosis in high-grade glial tumors.
RESUMEN
Cortical microstructure is influenced by circadian rhythm and sleep deprivation, yet the precise underpinnings of these effects remain unclear. The ratio between T1-weighted and T2-weighted magnetic resonance images (T1w/T2w ratio) has been linked to myelin levels and dendrite density and may offer novel insight into the intracortical microstructure of the sleep deprived brain. Here, we examined intracortical T1w/T2w ratio in 41 healthy young adults (26 women) before and after 32 h of either sleep deprivation (n = 18) or a normal sleep-wake cycle (n = 23). Linear models revealed significant group differences in T1w/T2w ratio change after 32 h in four clusters, including bilateral effects in the insular, cingulate, and superior temporal cortices, comprising regions involved in attentional, auditory and pain processing. Across clusters, the sleep deprived group showed an increased T1w/T2w ratio, while the normal sleep-wake group exhibited a reduced ratio. These changes were not explained by in-scanner head movement, and 95% of the effects across clusters remained significant after adjusting for cortical thickness and hydration. Compared with a normal sleep-wake cycle, 32 h of sleep deprivation yields intracortical T1w/T2w ratio increases. While the intracortical changes detected by this study could reflect alterations in myelin or dendritic density, or both, histological analyses are needed to clarify the precise underlying cortical processes.
Asunto(s)
Imagen por Resonancia Magnética , Privación de Sueño , Encéfalo , Femenino , Humanos , Imagen por Resonancia Magnética/métodos , Masculino , Vaina de Mielina/patología , Privación de Sueño/diagnóstico por imagen , Adulto JovenRESUMEN
BACKGROUND: Manual assessment of bone marrow signal is time-consuming and requires meticulous standardisation to secure adequate precision of findings. OBJECTIVE: We examined the feasibility of using deep learning for automated segmentation of bone marrow signal in children and adolescents. MATERIALS AND METHODS: We selected knee images from 95 whole-body MRI examinations of healthy individuals and of children with chronic non-bacterial osteomyelitis, ages 6-18 years, in a longitudinal prospective multi-centre study cohort. Bone marrow signal on T2-weighted Dixon water-only images was divided into three color-coded intensity-levels: 1 = slightly increased; 2 = mildly increased; 3 = moderately to highly increased, up to fluid-like signal. We trained a convolutional neural network on 85 examinations to perform bone marrow segmentation. Four readers manually segmented a test set of 10 examinations and calculated ground truth using simultaneous truth and performance level estimation (STAPLE). We evaluated model and rater performance through Dice similarity coefficient and in consensus. RESULTS: Consensus score of model performance showed acceptable results for all but one examination. Model performance and reader agreement had highest scores for level-1 signal (median Dice 0.68) and lowest scores for level-3 signal (median Dice 0.40), particularly in examinations where this signal was sparse. CONCLUSION: It is feasible to develop a deep-learning-based model for automated segmentation of bone marrow signal in children and adolescents. Our model performed poorest for the highest signal intensity in examinations where this signal was sparse. Further improvement requires training on larger and more balanced datasets and validation against ground truth, which should be established by radiologists from several institutions in consensus.
Asunto(s)
Aprendizaje Profundo , Adolescente , Médula Ósea/diagnóstico por imagen , Niño , Estudios de Factibilidad , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodos , Espectroscopía de Resonancia Magnética , Estudios ProspectivosRESUMEN
Introduction: Management of patients with brain metastases is often based on manual lesion detection and segmentation by an expert reader. This is a time- and labor-intensive process, and to that end, this work proposes an end-to-end deep learning segmentation network for a varying number of available MRI available sequences. Methods: We adapt and evaluate a 2.5D and a 3D convolution neural network trained and tested on a retrospective multinational study from two independent centers, in addition, nnU-Net was adapted as a comparative benchmark. Segmentation and detection performance was evaluated by: (1) the dice similarity coefficient, (2) a per-metastases and the average detection sensitivity, and (3) the number of false positives. Results: The 2.5D and 3D models achieved similar results, albeit the 2.5D model had better detection rate, whereas the 3D model had fewer false positive predictions, and nnU-Net had fewest false positives, but with the lowest detection rate. On MRI data from center 1, the 2.5D, 3D, and nnU-Net detected 79%, 71%, and 65% of all metastases; had an average per patient sensitivity of 0.88, 0.84, and 0.76; and had on average 6.2, 3.2, and 1.7 false positive predictions per patient, respectively. For center 2, the 2.5D, 3D, and nnU-Net detected 88%, 86%, and 78% of all metastases; had an average per patient sensitivity of 0.92, 0.91, and 0.85; and had on average 1.0, 0.4, and 0.1 false positive predictions per patient, respectively. Discussion/Conclusion: Our results show that deep learning can yield highly accurate segmentations of brain metastases with few false positives in multinational data, but the accuracy degrades for metastases with an area smaller than 0.4 cm2.
RESUMEN
OBJECTIVE: To investigate the effect of inter-operator variability in arterial input function (AIF) definition on kinetic parameter estimates (KPEs) from dynamic contrast-enhanced (DCE) MRI in patients with high-grade gliomas. METHODS: The study included 118 DCE series from 23 patients. AIFs were measured by three domain experts (DEs), and a population AIF (pop-AIF) was constructed from the measured AIFs. The DE-AIFs, pop-AIF and AUC-normalized DE-AIFs were used for pharmacokinetic analysis with the extended Tofts model. AIF-dependence of KPEs was assessed by intraclass correlation coefficient (ICC) analysis, and the impact on relative longitudinal change in Ktrans was assessed by Fleiss' kappa (κ). RESULTS: There was a moderate to substantial agreement (ICC 0.51-0.76) between KPEs when using DE-AIFs, while AUC-normalized AIFs yielded ICC 0.77-0.95 for Ktrans, kep and ve and ICC 0.70 for vp. Inclusion of the pop-AIF did not reduce agreement. Agreement in relative longitudinal change in Ktrans was moderate (κ = 0.591) using DE-AIFs, while AUC-normalized AIFs gave substantial (κ = 0.809) agreement. DISCUSSION: AUC-normalized AIFs can reduce the variation in kinetic parameter results originating from operator input. The pop-AIF presented in this work may be applied in absence of a satisfactory measurement.