Frontiers in radiology最新文献

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.

Objective: This systematic review aims to evaluate the quality and accuracy of ML algorithms in predicting ATRX and IDH mutation status in patients with glioma through the analysis of radiomic features extracted from medical imaging. The potential clinical impacts and areas for further improvement in non-invasive glioma diagnosis, classification and prognosis are also identified and discussed.

Methods: The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic and Test Accuracy (PRISMA-DTA) statement. Databases including PubMed, Science Direct, CINAHL, Academic Search Complete, Medline, and Google Scholar were searched from inception to April 2024. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool was used to assess the risk of bias and applicability concerns. Additionally, meta-regression identified covariates contributing to heterogeneity before a subgroup meta-analysis was conducted. Pooled sensitivities, specificities and area under the curve (AUC) values were calculated for the prediction of ATRX and IDH mutations.

Results: Eleven studies involving 1,685 patients with grade I-IV glioma were included. Primary contributors to heterogeneity included the MRI modalities utilised (conventional only vs. combined) and the types of ML models employed. The meta-analysis revealed pooled sensitivities of 0.682 for prediction of ATRX loss and 0.831 for IDH mutations, specificities of 0.874 and 0.828, and AUC values of 0.842 and 0.948, respectively. Interestingly, incorporating semantics and clinical data, including patient demographics, improved the diagnostic performance of ML models.

Conclusions: The high AUC in the prediction of both mutations demonstrates an overall robust diagnostic performance of ML, indicating the potential for accurate, non-invasive diagnosis and precise prognosis. Future research should focus on integrating diverse data types, including advanced imaging, semantics and clinical data while also aiming to standardise the collection and integration of multimodal data. This approach will enhance clinical applicability and consistency.

CT perfusion (CTP) images can be easily and rapidly obtained on all modern CT scanners and have become part of the routine imaging protocol of patients with aneurysmal subarachnoid haemorrhage (aSAH). There is a growing body of evidence supporting the use of CTP imaging in these patients, however, there are significant differences in the software packages and methods of analysing CTP. In. addition, no quantitative threshold values for tissue at risk (TAR) have been validated in this patients' population. Here we discuss the contribution of the technique in the identification of patients at risk of aSAH-related delayed cerebral ischemia (DCI) and in the assessment of the response to endovascular rescue therapy (ERT). We also address the limitations and pitfalls of automated CTP postprocessing that are specific to aSAH patients as compared to acute ischemic stroke (AIS).

Introduction: Linking olfactory epithelium to the central nervous system are cranial nerve 1, the olfactory nerve, and cranial nerve "0," and the nervus terminalis (NT). Since there is minimal expression of angiotensin-converting enzyme-2 (ACE-2) in the olfactory nerve, it is unclear how SARS-CoV-2 causes anosmia (loss of smell) and hypogeusia (reduction of taste). In animal models, NT expresses ACE-2 receptors, suggesting a possible SARS-CoV-2 viral entry site in humans. The purpose of this study was to determine whether ultra-high-field 7 T magnetic resonance imaging (MRI) could visualize the NT, olfactory bulbs (OB), and olfactory tract (OT) in healthy controls and COVID-19 anosmia or hypogeusia and to qualitatively assess for volume loss and T2 alterations.

Methods: In this study, 7 T MRI was used to evaluate the brain and olfactory regions in 45 COVID-19 patients and 29 healthy controls. Neuroimaging was qualitatively assessed by four board-certified neuroradiologists who were blinded to outcome assignments: for the presence or absence of NT; for OB, OT, and brain volume loss; and altered T2 signal, white matter T2 hyperintensities, microhemorrhages, enlarged perivascular spaces, and brainstem involvement.

Results: NT was identifiable in all COVID-19 patients and controls. T2 hyperintensity in the NT, OB, and OT in COVID-19 patients with anosmia or hypogeusia was statistically significant compared to controls and COVID-19 patients without anosmia or hypogeusia.

Discussion: On 7 T MRI, NT was radiographically identifiable, adjacent to OB and OT. In COVID-19 anosmia and hypogeusia, T2 hyperintensity of NT, OB, and OT was statistically significant compared to COVID-19 patients without anosmia or hypogeusia and controls. The NT may be a potential entry site for SARs-CoV-2 and may play a role in the pathophysiology of COVID-19 anosmia.

Background: Chylous leakage (CL) is a rare but significant complication following cervical lymph node dissection, particularly in patients with papillary thyroid carcinoma (PTC). This condition is characterized by the leakage of lymphatic fluid, which can result in severe consequences such as malnutrition, immunosuppression, and prolonged hospital stays. Conventional treatments for CL include conservative measures and surgical interventions, but these approaches often face limitations and challenges. This case report discusses a successful treatment of CL using thoracic duct lymphangiography combined with local injection of sclerotherapy, demonstrating a novel and effective approach for managing this complication.

Case presentation: A 72-year-old female patient with PTC underwent total thyroidectomy and bilateral Level VI and left Levels II, III, IV, and V cervical lymph node dissection. Postoperatively, the patient developed milky drainage indicative of CL. Despite initial conservative treatments including pressure bandaging, negative pressure drainage, and nutritional adjustments, the patient's condition did not improve. The patient declined surgical options, leading to the decision to perform thoracic duct lymphangiography combined with local injection of sclerotherapy. Under real-time ultrasound guidance, the inguinal lymph nodes were accessed, and lipiodol was injected to visualize the thoracic duct. Subsequently, foam sclerosant was injected at the leakage site under fluoroscopic guidance. The procedure resulted in a significant reduction of chyle leakage, and the patient was discharged with no recurrence during a 1-year follow-up.

Conclusions: This case illustrates that thoracic duct angiography combined with local injection of sclerotherapy can be an effective treatment for high-output CL when conservative measures fail and surgical intervention is not preferred. The approach offers a minimally invasive alternative that can reduce complications and improve patient outcomes. The successful management of CL in this case underscores the potential of advanced interventional techniques in treating lymphatic system complications and highlights the need for further research to establish standardized treatment protocols.

This article explores the potential of photon-counting computed tomography (CT) in forensic medicine for a range of forensic applications. Photon-counting CT surpasses conventional CT in several key areas. It boasts superior spatial and contrast resolution, enhanced image quality at low x-ray energies, and spectral imaging capabilities that enable more precise material differentiation. These advantages translate to superior visualization of bone structures, foreign bodies, and soft tissues in postmortem examinations. The article discusses the technical principles of photon-counting CT detectors and highlights its potential applications in forensic imaging, including high-resolution virtual autopsies, pediatric forensic CT, trauma analysis, and bone density measurements. Furthermore, advancements in vascular imaging and soft tissue contrast promise to propel CT-based death investigations to an even more prominent role. The article concludes by emphasizing the immense potential of this new technology in forensic medicine and anthropology.