Frontiers in radiology最新文献

Aims: To follow disease progression in a rat model of Type 2 diabetes using multimodal MRI to assess changes in brain structure and function.

Material and methods: Female rats (n = 20) were fed a high fat/high fructose diet or lab chow starting at 90 days of age. Diet fed rats were given streptozotocin to compromise pancreatic beta cells, while chow fed controls received vehicle. At intervals of 3, 6, 9, and 12 months, rats were tested for changes in behavior and sensitivity to pain. Brain structure and function were assessed using voxel based morphometry, diffusion weighted imaging and functional connectivity.

Results: Diet fed rats presented with elevated plasma glucose levels as early as 3 months and a significant gain in weight by 6 months as compared to controls. There were no significant changes in cognitive or motor behavior over the yearlong study but there was a significant increase in sensitivity to peripheral pain in diet fed rats. There were region specific decreases in brain volume e.g., basal ganglia, thalamus and brainstem in diet fed rats. These same regions showed elevated measures of water diffusivity evidence of putative vasogenic edema. By 6 months, widespread hyperconnectivity was observed across multiple brain regions. By 12 months, only the cerebellum and hippocampus showed increased connectivity, while the hypothalamus showed decreased connectivity in diet fed rats.

Conclusions: Noninvasive multimodal MRI identified site specific changes in brain structure and function in a yearlong longitudinal study of Type 2 diabetes in rats. The identified diabetic-induced neuropathological sites may serve as biomarkers for evaluating the efficacy of novel therapeutics.

Introduction: Magnetic resonance-based electrical conductivity imaging offers a promising new contrast mechanism to enhance disease diagnosis. Conductivity tensor imaging (CTI) combines data from MR diffusion microstructure imaging to reconstruct electrodeless low-frequency conductivity images. However, different microstructure imaging methods rely on varying diffusion models and parameters, leading to divergent tissue conductivity estimates. This study investigates the variability in conductivity predictions across different microstructure models and evaluates their alignment with experimental observations.

Methods: We used publicly available diffusion databases from neurotypical adults to extract microstructure parameters for three diffusion-based brain models: Neurite Orientation Dispersion and Density Imaging (NODDI), Soma and Neurite Density Imaging (SANDI), and Spherical Mean technique (SMT) conductivity predictions were calculated for gray matter (GM) and white matter (WM) tissues using each model. Comparative analyses were performed to assess the range of predicted conductivities and the consistency between bilateral tissue conductivities for each method.

Results: Significant variability in conductivity estimates was observed across the three models. Each method predicted distinct conductivity values for GM and WM tissues, with notable differences in the range of conductivities observed for specific tissue examples. Despite the variability, many WM and GM tissues exhibited symmetric bilateral conductivities within each microstructure model. SMT yielded conductivity estimates closer to values reported in experimental studies, while none of the methods aligned with spectroscopic models of tissue conductivity.

Discussion and conclusion: Our findings highlight substantial discrepancies in tissue conductivity estimates generated by different diffusion models, underscoring the challenge of selecting an appropriate model for low-frequency electrical conductivity imaging. SMT demonstrated better alignment with experimental results. However other microstructure models may produce better tissue discrimination.

Background: Dark-field chest radiography allows the assessment of the structural integrity of the alveoli by exploiting the wave properties of x-rays.

Purpose: To compare the qualitative and quantitative features of dark-field chest radiography in patients with COVID-19 pneumonia with conventional CT imaging.

Materials and methods: In this prospective study conducted from May 2020 to December 2020, patients aged at least 18 years who underwent chest CT for clinically suspected COVID-19 infection were screened for participation. Inclusion criteria were a CO-RADS score ≥4, the ability to consent to the procedure and to stand upright without help. Participants were examined with a clinical dark-field chest radiography prototype. For comparison, a healthy control cohort of 40 subjects was evaluated. Using Spearman's correlation coefficient, correlation was tested between dark-field coefficient and CT-based COVID-19 index and visual total CT score as well as between the visual total dark-field score and the visual total CT score.

Results: A total of 98 participants [mean age 58 ± 14 (standard deviation) years; 59 men] were studied. The areas of signal intensity reduction observed in dark-field images showed a strong correlation with infiltrates identified on CT scans. The dark-field coefficient had a negative correlation with both the quantitative CT-based COVID-19 index (r = -.34, p = .001) and the overall CT score used for visual grading of COVID-19 severity (r = -.44, p < .001). The total visual dark-field score for the presence of COVID-19 was positively correlated to the total CT score for visual COVID-19 severity grading (r = .85, p < .001).

Conclusion: COVID-19 pneumonia-induced signal intensity losses in dark-field chest radiographs are consistent with CT-based findings, showing the technique's potential for COVID-19 assessment.

In neuro-oncology, MR imaging is crucial for obtaining detailed brain images to identify neoplasms, plan treatment, guide surgical intervention, and monitor the tumor's response. Recent AI advances in neuroimaging have promising applications in neuro-oncology, including guiding clinical decisions and improving patient management. However, the lack of clarity on how AI arrives at predictions has hindered its clinical translation. Explainable AI (XAI) methods aim to improve trustworthiness and informativeness, but their success depends on considering end-users' (clinicians') specific context and preferences. User-Centered Design (UCD) prioritizes user needs in an iterative design process, involving users throughout, providing an opportunity to design XAI systems tailored to clinical neuro-oncology. This review focuses on the intersection of MR imaging interpretation for neuro-oncology patient management, explainable AI for clinical decision support, and user-centered design. We provide a resource that organizes the necessary concepts, including design and evaluation, clinical translation, user experience and efficiency enhancement, and AI for improved clinical outcomes in neuro-oncology patient management. We discuss the importance of multi-disciplinary skills and user-centered design in creating successful neuro-oncology AI systems. We also discuss how explainable AI tools, embedded in a human-centered decision-making process and different from fully automated solutions, can potentially enhance clinician performance. Following UCD principles to build trust, minimize errors and bias, and create adaptable software has the promise of meeting the needs and expectations of healthcare professionals.

Purpose: Successful performance of deep learning models for medical image analysis is highly dependent on the quality of the images being analysed. Factors like differences in imaging equipment and calibration, as well as patient-specific factors such as movements or biological variability (e.g., tissue density), lead to a large variability in the quality of obtained medical images. Consequently, robustness against the presence of noise is a crucial factor for the application of deep learning models in clinical contexts.

Materials and methods: We evaluate the effect of various data augmentation strategies on the robustness of a ResNet-18 trained to classify breast ultrasound images and benchmark the performance against trained human radiologists. Additionally, we introduce DreamOn, a novel, biologically inspired data augmentation strategy for medical image analysis. DreamOn is based on a conditional generative adversarial network (GAN) to generate REM-dream-inspired interpolations of training images.

Results: We find that while available data augmentation approaches substantially improve robustness compared to models trained without any data augmentation, radiologists outperform models on noisy images. Using DreamOn data augmentation, we obtain a substantial improvement in robustness in the high noise regime.

Conclusions: We show that REM-dream-inspired conditional GAN-based data augmentation is a promising approach to improving deep learning model robustness against noise perturbations in medical imaging. Additionally, we highlight a gap in robustness between deep learning models and human experts, emphasizing the imperative for ongoing developments in AI to match human diagnostic expertise.

Background: MR fingerprinting (MRF) is a novel method for quantitative assessment of in vivo MR relaxometry that has shown high precision and accuracy. However, the method requires data acquisition using customized, complex acquisition strategies and dedicated post processing methods thereby limiting its widespread application.

Objective: To develop a deep learning (DL) network for synthesizing MRF signals from conventional magnitude-only MR imaging data and to compare the results to the actual MRF signal acquired.

Methods: A U-Net DL network was developed to synthesize MRF signals from magnitude-only 3D T ₁-weighted brain MRI data acquired from 37 volunteers aged between 21 and 62 years of age. Network performance was evaluated by comparison of the relaxometry data (T ₁, T ₂) generated from dictionary matching of the deep learning synthesized and actual MRF data from 47 segmented anatomic regions. Clustered bootstrapping involving 10,000 bootstraps followed by calculation of the concordance correlation coefficient were performed for both T ₁ and T ₂ MRF data pairs. 95% confidence limits and the mean difference between true and DL relaxometry values were also calculated.

Results: The concordance correlation coefficient (and 95% confidence limits) for T ₁ and T ₂ MRF data pairs over the 47 anatomic segments were 0.8793 (0.8136-0.9383) and 0.9078 (0.8981-0.9145) respectively. The mean difference (and 95% confidence limits) were 48.23 (23.0-77.3) s and 2.02 (-1.4 to 4.8) s.

Conclusion: It is possible to synthesize MRF signals from MRI data using a DL network, thereby creating the potential for performing quantitative relaxometry assessment without the need for a dedicated MRF pulse sequence.

Pneumothorax, a life-threatening condition characterized by air accumulation in the pleural cavity, requires early and accurate detection for optimal patient outcomes. Chest X-ray radiographs are a common diagnostic tool due to their speed and affordability. However, detecting pneumothorax can be challenging for radiologists because the sole visual indicator is often a thin displaced pleural line. This research explores deep learning techniques to automate and improve the detection and segmentation of pneumothorax from chest X-ray radiographs. We propose a novel architecture that combines the advantages of fully convolutional neural networks (FCNNs) and Vision Transformers (ViTs) while using only convolutional modules to avoid the quadratic complexity of ViT's self-attention mechanism. This architecture utilizes a patch-based encoder-decoder structure with skip connections to effectively combine high-level and low-level features. Compared to prior research and baseline FCNNs, our model demonstrates significantly higher accuracy in detection and segmentation while maintaining computational efficiency. This is evident on two datasets: (1) the SIIM-ACR Pneumothorax Segmentation dataset and (2) a novel dataset we curated from The Medical City, a private hospital in the Philippines. Ablation studies further reveal that using a mixed Tversky and Focal loss function significantly improves performance compared to using solely the Tversky loss. Our findings suggest our model has the potential to improve diagnostic accuracy and efficiency in pneumothorax detection, potentially aiding radiologists in clinical settings.

Introduction: Task-based language fMRI is a non-invasive method of identifying brain regions subserving language that is used to plan neurosurgical resections which potentially encroach on eloquent regions. The use of unstructured fMRI paradigms, such as naturalistic fMRI, to map language is of increasing interest. Their analysis necessitates the use of alternative methods such as machine learning (ML) and deep learning (DL) because task regressors may be difficult to define in these paradigms.

Methods: Using task-based language fMRI as a starting point, this study investigates the use of different categories of ML and DL algorithms to identify brain regions subserving language. Data comprising of seven task-based language fMRI paradigms were collected from 26 individuals, and ML and DL models were trained to classify voxel-wise fMRI time series.

Results: The general machine learning and the interval-based methods were the most promising in identifying language areas using fMRI time series classification. The geneal machine learning method achieved a mean whole-brain Area Under the Receiver Operating Characteristic Curve (AUC) of $0.97\pm 0.03$ , mean Dice coefficient of $0.6\pm 0.34$ and mean Euclidean distance of $2.7\pm 2.4$  mm between activation peaks across the evaluated regions of interest. The interval-based method achieved a mean whole-brain AUC of $0.96\pm 0.03$ , mean Dice coefficient of $0.61\pm 0.33$ and mean Euclidean distance of $3.3\pm 2.7$  mm between activation peaks across the evaluated regions of interest.

Discussion: This study demonstrates the utility of different ML and DL methods in classifying task-based language fMRI time series. A potential application of these methods is the identification of language activation from unstructured paradigms.