Frontiers in radiology最新文献

Activated brain regions can be visualized and localized with the use of fMRI (functional magnetic imaging). This is based on changes in the blood flow in activated regions, or more precisely on the hemodynamic response function (HRF) and the Blood-Oxygen-Level-Dependent (BOLD) effect. This study used a task-based fMRI examination with language paradigms in order to stimulate the language areas. The measured fMRI data are frequently altered by different preprocessing steps for the analysis and the display of activations. These changes can lead to discrepancies between the displayed and the truly measured location of the activations. Simple t-maps were created with unprocessed fMRI data, to provide a more realistic representation of the language areas. HRF-dependent single-voxel fMRI signal analysis was performed to improve the analyzability of these activation maps.

Introduction: Both aging and multiple sclerosis (MS) cause central nervous system (CNS) atrophy. Excess brain atrophy in MS has been interpreted as "accelerated aging." Current paper tests an alternative hypothesis: MS causes CNS atrophy by mechanism(s) different from physiological aging. Thus, subtracting effects of physiological confounders on CNS structures would isolate MS-specific effects.

Methods: Standardized brain MRI and neurological examination were acquired prospectively in 646 participants enrolled in ClinicalTrials.gov Identifier: NCT00794352 protocol. CNS volumes were measured retrospectively, by automated Lesion-TOADS algorithm and by Spinal Cord Toolbox, in a blinded fashion. Physiological confounders identified in 80 healthy volunteers were regressed out by stepwise multiple linear regression. MS specificity of confounder-adjusted MRI features was assessed in non-MS cohort (n = 158). MS patients were randomly split into training (n = 277) and validation (n = 131) cohorts. Gradient boosting machine (GBM) models were generated in MS training cohort from unadjusted and confounder-adjusted CNS volumes against four disability scales.

Results: Confounder adjustment highlighted MS-specific progressive loss of CNS white matter. GBM model performance decreased substantially from training to cross-validation, to independent validation cohorts, but all models predicted cognitive and physical disability with low p-values and effect sizes that outperform published literature based on recent meta-analysis. Models built from confounder-adjusted MRI predictors outperformed models from unadjusted predictors in the validation cohort.

Conclusion: GBM models from confounder-adjusted volumetric MRI features reflect MS-specific CNS injury, and due to stronger correlation with clinical outcomes compared to brain atrophy these models should be explored in future MS clinical trials.

With the increased reliance on medical imaging, Deep convolutional neural networks (CNNs) have become an essential tool in the medical imaging-based computer-aided diagnostic pipelines. However, training accurate and reliable classification models often require large fine-grained annotated datasets. To alleviate this, weakly-supervised methods can be used to obtain local information such as region of interest from global labels. This work proposes a weakly-supervised pipeline to extract Relevance Maps of medical images from pre-trained 3D classification models using localized perturbations. The extracted Relevance Map describes a given region's importance to the classification model and produces the segmentation for the region. Furthermore, we propose a novel optimal perturbation generation method that exploits 3D superpixels to find the most relevant area for a given classification using U-net architecture. This model is trained with perturbation loss, which maximizes the difference between unperturbed and perturbed predictions. We validated the effectiveness of our methodology by applying it to the segmentation of Glioma brain tumours in MRI scans using only classification labels for glioma type. The proposed method outperforms existing methods in both Dice Similarity Coefficient for segmentation and resolution for visualizations.

Emergency radiology has evolved into a distinct radiology subspecialty requiring a specialized skillset to make a timely and accurate diagnosis of acutely and critically ill or traumatized patients. The need for emergency and odd hour radiology coverage fuelled the growth of internal and external teleradiology and the "nighthawk" services to meet the increasing demands from all stakeholders and support the changing trends in emergency medicine and trauma surgery inclined toward increased reliance on imaging. However, the basic issues of increased imaging workload, radiologist demand-supply mismatch, complex imaging protocols are only partially addressed by teleradiology with the promise of workload balancing by operations to scale. Incorporation of artificially intelligent tools helps scale manifold by the promise of streamlining the workflow, improved detection and quantification as well as prediction. The future of emergency teleradiologists and teleradiology groups is entwined with their ability to incorporate such tools at scale and adapt to newer workflows and different roles. This agility to adopt and adapt would determine their future.

Background and purpose: To decrease the impact of radiotherapy to healthy tissues in the head and neck region, we propose to restrict the elective neck irradiation to elective lymph nodes at risk of containing micro metastases instead of the larger lymph node volumes. To assess whether this new concept is achievable in the clinic, we determined the number, volume changes and displacement of elective lymph nodes during the course of radiotherapy.

Materials and methods: MRI scans of 10 head and neck cancer (HNC) patients were acquired before radiotherapy and in week 2, 3, 4 and 5 during radiotherapy. The weekly delineations of elective lymph nodes inside the lymph node levels (Ib/II/III/IVa/V) were rigidly registered and analyzed regarding number and volume. The displacement of elective lymph nodes was determined by center of mass (COM) distances, vector-based analysis and the isotropic contour expansion of the lymph nodes of the pre-treatment scan or the scan of the previous week in order to geographically cover 95% of the lymph nodes in the scans of the other weeks.

Results: On average, 31 elective lymph nodes in levels Ib-V on each side of the neck were determined. This number remained constant throughout radiotherapy in most lymph node levels. The volume of the elective lymph nodes reduced significantly in all weeks, up to 50% in week 5, compared to the pre-treatment scan. The largest median COM displacements were seen in level V, for example 5.2 mm in week 5 compared to the pre-treatment scan. The displacement of elective lymph nodes was mainly in cranial direction. Geographical coverage was obtained when the lymph node volumes were expanded with 7 mm in case the pre-treatment scan was used and 6.5 mm in case the scan of the previous week was used.

Conclusion: Elective lymph nodes of HNC patients remained visible on MRI and decreased in size during radiotherapy. The displacement of elective lymph nodes differ per lymph node level and were mainly directed cranially. Weekly adaptation does not seem to improve coverage of elective lymph nodes. Based on our findings we expect elective lymph node irradiation is achievable in the clinic.

Hepatocellular carcinoma (HCC) is a primary liver cancer that produces a high mortality rate. It is one of the most common malignancies worldwide, especially in Asia, Africa, and southern Europe. Although surgical resection is an effective treatment, patients with HCC are at risk of recurrence after surgery. Preoperative early recurrence prediction for patients with liver cancer can help physicians develop treatment plans and will enable physicians to guide patients in postoperative follow-up. However, the conventional clinical data based methods ignore the imaging information of patients. Certain studies have used radiomic models for early recurrence prediction in HCC patients with good results, and the medical images of patients have been shown to be effective in predicting the recurrence of HCC. In recent years, deep learning models have demonstrated the potential to outperform the radiomics-based models. In this paper, we propose a prediction model based on deep learning that contains intra-phase attention and inter-phase attention. Intra-phase attention focuses on important information of different channels and space in the same phase, whereas inter-phase attention focuses on important information between different phases. We also propose a fusion model to combine the image features with clinical data. Our experiment results prove that our fusion model has superior performance over the models that use clinical data only or the CT image only. Our model achieved a prediction accuracy of 81.2%, and the area under the curve was 0.869.

Due to the limited availability of medical data, deep learning approaches for medical image analysis tend to generalise poorly to unseen data. Augmenting data during training with random transformations has been shown to help and became a ubiquitous technique for training neural networks. Here, we propose a novel adversarial counterfactual augmentation scheme that aims at finding the most effective synthesised images to improve downstream tasks, given a pre-trained generative model. Specifically, we construct an adversarial game where we update the input conditional factor of the generator and the downstream classifier with gradient backpropagation alternatively and iteratively. This can be viewed as finding the 'weakness' of the classifier and purposely forcing it to overcome its weakness via the generative model. To demonstrate the effectiveness of the proposed approach, we validate the method with the classification of Alzheimer's Disease (AD) as a downstream task. The pre-trained generative model synthesises brain images using age as conditional factor. Extensive experiments and ablation studies have been performed to show that the proposed approach improves classification performance and has potential to alleviate spurious correlations and catastrophic forgetting. Code: https://github.com/xiat0616/adversarial_counterfactual_augmentation.

Purpose: To identify common findings visualized on CT following damage control laparotomy, including post-surgical changes and additional injuries, and to determine change in frequency of post-laparotomy CT at our institution over time.

Methods: Single institution, IRB-Exempt, retrospective review of the University of Kentucky trauma registry from 1/2006 to 2/2019 for all trauma patients undergoing exploratory laparotomy initially and subsequently undergoing CT of the abdomen and pelvis within 24 hours. Operative findings from surgical operation notes and findings reported on post-laparotomy CT were recorded, including vascular and solid organ injuries, operative changes, free intraperitoneal fluid/air, and retroperitoneal findings. Next steps in management were also recorded.

Results: In total 1,047 patients underwent exploratory laparotomy initially at our institution between 1/2006-2/2019. Of those, only 96 had a diagnostic CT of the abdomen and pelvis within 24 h after initial surgery, first occurring in 2010. Among these 96, there were 71 blunt and 25 penetrating injuries. Most common injuries recognized during exploratory laparotomy were bowel/mesentery (55), spleen (34), and liver (26). Regarding CT findings, all patients (96/96, 100%) had residual pneumoperitoneum, 84/96 (87.5%) had residual hemoperitoneum, 36/96 (37.5%) noted post-surgical changes or additional injuries to the spleen, 36/96 (37.5%) to the bowel/mesentery, and 32/96 (33.3%) to the liver, and 34/96 (35.4%) were noted to have pelvic fractures. After CT, 31/96 (32.3%) went back to the OR for relook laparotomy and additional surgical intervention and 7/96 (7.3%) went to IR for embolization. Most common procedures during relaparotomy involved the bowel (8) and solid organs (6).

Conclusions: CT examination within 24 h post damage control laparotomy was exceedingly rare at our institution prior to 2012 but has steadily increased. Frequency now averages 20.5% yearly. Damage control laparotomy is an uncommon clinical scenario; however, knowledge of frequent injuries and common post-operative changes will aid in radiologist detection of additional injuries helping shape next step management and provide adequate therapy.

Diffusion kurtosis imaging (DKI) has undisputed advantages over the more classical diffusion magnetic resonance imaging (dMRI) as witnessed by the fast-increasing number of clinical applications and software packages widely adopted in brain imaging. However, in the neonatal setting, DKI is still largely underutilized, in particular in spinal cord (SC) imaging, because of its inherently demanding technological requirements. Due to its extreme sensitivity to non-Gaussian diffusion, DKI proves particularly suitable for detecting complex, subtle, fast microstructural changes occurring in this area at this early and critical stage of development, which are not identifiable with only DTI. Given the multiplicity of congenital anomalies of the spinal canal, their crucial effect on later developmental outcome, and the close interconnection between the SC region and the brain above, managing to apply such a method to the neonatal cohort becomes of utmost importance. This study will (i) mention current methodological challenges associated with the application of advanced dMRI methods, like DKI, in early infancy, (ii) illustrate the first semi-automated pipeline built on Spinal Cord Toolbox for handling the DKI data of neonatal SC, from acquisition setting to estimation of diffusion measures, through accurate adjustment of processing algorithms customized for adult SC, and (iii) present results of its application in a pilot clinical case study. With the proposed pipeline, we preliminarily show that DKI is more sensitive than DTI-related measures to alterations caused by brain white matter injuries in the underlying cervical SC.

Alzheimer's disease (AD) is the leading cause of dementia; however, men and women face differential AD prevalence, presentation, and progression risks. Characterizing metabolomic profiles during AD progression is fundamental to understand the metabolic disruptions and the biological pathways involved. However, outstanding questions remain of whether peripheral metabolic changes occur equally in men and women with AD. Here, we evaluated differential effects of metabolomic and brain volume associations between sexes. We used three cohorts from the Alzheimer's Disease Neuroimaging Initiative (ADNI), evaluated 1,368 participants, two metabolomic platforms with 380 metabolites in total, and six brain segment volumes. Using dimension reduction techniques, we took advantage of the correlation structure of the brain volume phenotypes and the metabolite concentration values to reduce the number of tests while aggregating relevant biological structures. Using WGCNA, we aggregated modules of highly co-expressed metabolites. On the other hand, we used partial least squares regression-discriminant analysis (PLS-DA) to extract components of brain volumes that maximally co-vary with AD diagnosis as phenotypes. We tested for differences in effect sizes between sexes in the association between single metabolite and metabolite modules with the brain volume components. We found five metabolite modules and 125 single metabolites with significant differences between sexes. These results highlight a differential lipid disruption in AD progression between sexes. Men showed a greater negative association of phosphatidylcholines and sphingomyelins and a positive association of VLDL and large LDL with AD progression. In contrast, women showed a positive association of triglycerides in VLDL and small and medium LDL with AD progression. Explicitly identifying sex differences in metabolomics during AD progression can highlight particular metabolic disruptions in each sex. Our research study and strategy can lead to better-tailored studies and better-suited treatments that take sex differences into account.