Frontiers in radiology最新文献

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.

Description: Cerebral lymphomatosis (CL) is a rare subtype of primary central nervous system lymphoma (PCNSL). In CL, atypical lymphoid cells diffusely infiltrate the cerebral parenchyma without forming a discrete mass as seen with PCNSL. We report a case of a 66-year-old woman with diffuse CL and superimposed areas of PCNSL. She presented with subacute cognitive decline and weakness. CSF studies showed lymphocytosis and IL-10 elevation. She became increasingly somnolent despite steroid and intravenous immunoglobulin trials, and she succumbed to the disease four months after symptom onset.

Radiologic findings: Her initial non-contrast head CT showed ill-defined hypodensities in the periventricular and subcortical white matter, bilateral basal ganglia, and central pons, which corresponded to diffuse T2/FLAIR hyperintensities on brain MRI. No abnormal enhancement, diffusion restriction, or discrete mass was present initially. Subsequently, MR spectroscopy demonstrated abnormally elevated choline:creatine and decreased NAA peaks, suggesting a hypercellular process. One month later, MRI revealed increasingly confluent T2/FLAIR hyperintensities with new diffusion restriction in the right caudate and left hippocampus, as well as new hyperperfusion in the right caudate. Again, no mass or enhancement was identified in these areas. On autopsy, parenchymal pathology was mostly consistent with CL. However, there were two areas of frank PCNSL in the right caudate and left hippocampus, which corresponded to the new areas of abnormality on her last MRI despite lacking the typical radiologic features of PCNSL.

Novel aspects: This is a unique case of CL with concurrent areas of PCNSL. Although CL is thought to be a distinct subtype of PCNSL, our case demonstrates that PCNSL may develop on a background of diffuse CL. In patients with subacute neurologic decline and MRI findings of diffuse leukoencephalopathy, diffuse CL should be considered.

Introduction: Clinical research on smart health has an increasing demand for intelligent and clinic-oriented medical image computing algorithms and platforms that support various applications. However, existing research platforms for medical image informatics have limited support for Artificial Intelligence (AI) algorithms and clinical applications.

Methods: To this end, we have developed SenseCare research platform, which is designed to facilitate translational research on intelligent diagnosis and treatment planning in various clinical scenarios. It has several appealing functions and features such as advanced 3D visualization, concurrent and efficient web-based access, fast data synchronization and high data security, multi-center deployment, support for collaborative research, etc.

Results and discussion: SenseCare provides a range of AI toolkits for different tasks, including image segmentation, registration, lesion and landmark detection from various image modalities ranging from radiology to pathology. It also facilitates the data annotation and model training processes, which makes it easier for clinical researchers to develop and deploy customized AI models. In addition, it is clinic-oriented and supports various clinical applications such as diagnosis and surgical planning for lung cancer, liver tumor, coronary artery disease, etc. By simplifying AI-based medical image analysis, SenseCare has a potential to promote clinical research in a wide range of disease diagnosis and treatment applications.

Aims: This study aims to assess the diagnostic accuracy of diffusion-weighted Magnetic Resonance Imaging (DW-MRI) and determine the inter-reader agreement between two expert radiologists in detecting pyelonephritic foci during the initial episode of febrile urinary tract infection (fUTI) in children aged 0-5 years. Also, we aim to establish the correlation between clinical data and DW-MRI findings.

Methods: Children aged 0-5 years presenting with their first episode of fUTI were included in the study and underwent DW-MRI and Ultrasound (US) examinations within 72 h of admission. Inter-observer agreement between the two expert radiologists in assessing DW-MRI scans was evaluated using Cohen's kappa statistic. Clinical and laboratory data were subjected to statistical analysis.

Results: 84 children (40 male, 44 female) with a mean age of 7.3 (SD 6.2) months were enrolled. DW-MRI detected pyelonephritis in 78 out of 84 cases (92.9%), with multiple foci observed in 73 out of 78 cases (93.6%). There was a "substantial" level of agreement between the two expert radiologists (κ = 0.725; observed agreement 95.2%). Renal US revealed pyelonephritis in 36 out of 78 cases (46.2%). White blood cell (WBC) count (p = 0.04) and lymphocyte count (p = 0.01) were significantly higher in patients with positive DW-MRI. Although not statistically significant, patients with positive DW-MRI had higher mean values of C-Reactive Protein, Procalcitonin, and neutrophil WBC count (7.72 mg/dl, 4.25 ng/dl, and 9,271 /μl, respectively).

Conclusions: DW-MRI exhibited excellent diagnostic performance in detecting pyelonephritic foci, with substantial inter-reader agreement among expert radiologists, indicating the reliability of the technique. However, a weak correlation was observed between laboratory parameters and DW-MRI results, potentially because of the low rate of negative DW-MRI findings.