Diagnostic and interventional radiology最新文献

The rapid evolution of artificial intelligence (AI), particularly in deep learning, has significantly impacted radiology, introducing an array of AI solutions for interpretative tasks. This paper provides radiology departments with a practical guide for selecting and integrating AI solutions, focusing on interpretative tasks that require the active involvement of radiologists. Our approach is not to list available applications or review scientific evidence, as this information is readily available in previous studies; instead, we concentrate on the essential factors radiology departments must consider when choosing AI solutions. These factors include clinical relevance, performance and validation, implementation and integration, clinical usability, costs and return on investment, and regulations, security, and privacy. We illustrate each factor with hypothetical scenarios to provide a clearer understanding and practical relevance. Through our experience and literature review, we provide insights and a practical roadmap for radiologists to navigate the complex landscape of AI in radiology. We aim to assist in making informed decisions that enhance diagnostic precision, improve patient outcomes, and streamline workflows, thus contributing to the advancement of radiological practices and patient care.

Purpose: Pediatric lung tumors are primarily discussed in the surgical literature. However, limited research has been reported on their imaging findings, and only a few tumor types have been documented. Therefore, the aim of this article is to describe the imaging features of primary lung tumors in children.

Methods: The archives of the pediatric radiology unit were reviewed for primary lung tumors documented between 2007 and 2023. In total, 24 patients (9 girls and 15 boys; aged 5 months to 16 years) were included in the study. Their demographic characteristics, clinical presentation, and histopathologic results were obtained. All imaging studies were reviewed by two radiologists for various findings (e.g., lymphadenopathy, atelectasis, pleural effusion, calcification, multiplicity, pneumothorax, axial and lobar location, laterality, tumor margin, mediastinal shift, contrast enhancement pattern, signal intensity on T1- and T2-weighted images, and diffusion pattern), and a final decision was made by consensus. The mean tumor size was compared between the benign and malignant groups using a t-test.

Results: There were 15 (62.5%) benign tumors, as follows: inflammatory myofibroblastic tumor (IMT; n = 10, 41%), hemangioma (n = 2, 8%), pneumocytoma (n = 2, 8%), and mature cystic teratoma (n = 1, 4%). Moreover, there were 9 (37.5%) malignant tumors, as follows: pleuropulmonary blastoma (PPB; n = 6, 25%), adenocarcinoma (n = 2, 8%), and lymphoepithelioma-like carcinoma (LELC) (n = 1, 4%). The most frequently reported symptoms were cough, fever, dyspnea, chest pain, and recurrent infection; six patients reported no clinical symptoms. Fifteen tumors (62%) were located in the right lung. The mean tumor diameter at the time of diagnosis was 6.4 ± 3 cm (benign group: 6.7 ± 3.4 cm; malignant group: 6 ± 2.3 cm, P > 0.050). Calcification was present in 80% of the patients with IMT. At the time of diagnosis, two (8.3%) patients were found to have metastasis: one was diagnosed with adenocarcinoma and the other with LELC. Tumors were located peripherally in 18 (75%) patients.

Conclusion: The symptoms associated with lung masses are non-specific. There is no correlation between tumor size and malignancy. The most common tumors observed in this study were IMT and PPB, respectively. IMT is highly associated with calcification.

Clinical significance: Primary lung tumors are rarely seen in children, and they have different histopathological types. Calcification might be an important radiological clue for the diagnosis of IMT, which is the most common lung tumor in children.

Purpose: This meta-analysis aimed to evaluate the diagnostic accuracy of computed tomography (CT) for detecting gastroesophageal varices (GEVs) and identify high-risk GEVs in patients with cirrhosis.

Methods: A comprehensive search of databases identified 28 studies reporting on CT-based diagnosis for GEVs confirmed via endoscopy. Meta-analyses were conducted to calculate pooled sensitivity (SEN) and pooled specificity (SPE), positive likelihood ratio (PLR) and negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and the area under the curve (AUC).

Results: Based on the number of patients (or varices), the pooled SEN, SPE, PLR, NLR, DOR, and AUC of CT-based diagnosis were estimated at 0.91 (0.92), 0.81 (0.45), 4.82 (1.67), 0.11 (0.17), 42.47 (10.26), and 0.93 (0.94), respectively, for any GEV and at 0.89 (0.89), 0.90 (0.79), 8.86 (4.28), 0.12 (0.14), 75.71 (30.19), and 0.95 (0.85), respectively, for high-risk GEVs. Subgroup analyses indicated that CT had a higher diagnostic accuracy for esophageal varices compared with gastric varices (AUC: 0.93 vs. 0.89, P < 0.05), and the 64-slice CT yielded superior SEN compared with 16-slice and <16-slice CT (AUC: 0.97 vs. 0.92 and 0.82, respectively, P < 0.05). Prospective studies demonstrated higher diagnostic accuracy than retrospective studies (AUC: 0.95 vs. 0.90, P < 0.05). Regarding variceal size, a cut-off of 3 mm and 5 mm discriminated between low- and high-risk individuals, respectively, with high diagnostic accuracy (AUC: 0.992 vs. 0.997, P > 0.05).

Conclusion: CT demonstrates promising diagnostic accuracy for identifying gastroesophageal varices and distinguishing high-risk GEVs in patients with cirrhosis. Further research to validate optimal variceal size cut-offs is warranted to enhance clinical utility.

Clinical significance: Such a high diagnostic accuracy of CT scans for predicting varices is clinically meaningful for patients with cirrhosis accompanied by portal hypertension. If high-risk varices are identified at CT scans, early intervention would be helpful to reduce the risk of variceal bleeding.

Purpose: To assess the effectiveness and safety of computed tomography (CT)-guided cryoablation for treating adrenal metastases (AMs).

Methods: This study included 12 patients treated with 13 CT-guided cryoablation procedures for AMs between 2016 and 2020. Patients were selected based on specific criteria, including tumor size ≤5 cm and suitability for surgery. Procedures were performed by expert radiologists, with comprehensive monitoring for complications and regular post-treatment evaluations.

Results: The primary technical success rate was 91.7%, with a secondary success rate of 100% following repeat procedures. Over an 8-24-month follow-up period, local tumor recurrence was observed in 16.7% of patients, and systemic progression occurred in five (41.6%) patients. The average overall survival duration was 26.4 ± 5.6 months.

Conclusion: CT-guided cryoablation is a feasible and effective treatment option for AMs, demonstrating high technical success rates and manageable complications.

Clinical significance: This study highlights CT-guided cryoablation as a promising treatment for AMs, offering a minimally invasive alternative to surgery with good local control and safety profile. Further research, including multi-center studies, is needed to confirm these findings.

Purpose: The use of flow diverter (FD) stents is continually expanding. Aneurysms on arterial bifurcation typically have an undesirable anatomical form, are frequently wide-necked, and include one or more side-branch arteries. In recent years, the off-label use of flow diversion in treating intracranial aneurysms beyond the internal carotid artery has become increasingly popular. This study reports our center's initial experience treating bifurcation aneurysms with FD devices, documenting occlusion outcomes using the O'Kelly-Marotta and modified Cekirge-Saatci scales, as well as the safety of FD usage in bifurcation locations.

Methods: This retrospective, single-center study analyzed a prospectively maintained database of patients with cerebral aneurysms treated endovascularly. The study identified bifurcation aneurysms that were treated between January 2019 and May 2022 by placing an FD device covering the neck of the aneurysm.

Results: Our short series suggests that flow diversion is a viable therapeutic option for bifurcation aneurysms with favorable angiographic outcomes.

Conclusion: In highly selective cases, flow diversion may be considered for treating bifurcation aneurysms in patients who will undergo follow-up examinations in the future.

Clinical significance: Flow diversion has emerged as a valuable technique in the management of bifurcation aneurysms, offering the potential for satisfactory occlusion and long-term outcomes.

Radiomics aims to improve clinical decision making through the use of radiological imaging. However, the field is challenged by reproducibility issues due to variability in imaging and subsequent statistical analysis, which particularly affects the interpretability of the model. In fact, radiomics extracts many highly correlated features that, combined with the small sample sizes often found in radiomics studies, result in high-dimensional datasets. These datasets, which are characterized by containing more features than samples, have different statistical properties than other datasets, thereby complicating their training by machine learning and deep learning methods. This review critically examines the challenges of both reproducibility issues and interpretability, beginning with an overview of the radiomics pipeline, followed by a discussion of the imaging and statistical reproducibility issues. It further highlights how limited model interpretability hinders clinical translation. The discussion concludes that these challenges could be mitigated by following best practices and by creating large, representative, and publicly available datasets.

Purpose: By retrospectively studying the chest computed tomography (CT) data of children with bronchial artery (BA)-pulmonary artery fistula, this study summarizes the characteristic imaging features of the disease and provides imaging support for the diagnosis and clinical treatment of these children.

Methods: Digital subtraction angiography and CT angiography data were collected from 74 children with pulmonary hemorrhage following BA embolization. Bronchial-pulmonary shunt was present in 30 cases.

Results: Of the 74 children with pulmonary hemorrhage in this study, seven exhibited signs of consolidation in the middle lobe of the right lung, and bronchial-pulmonary shunt existed in all of them. A total of 30 children with BA-pulmonary artery shunt (PAS) had BA tortuosity and thickening. Regarding primary BA-PAS, the middle lobe and lower lobe of the right lung were involved in 94.1% (16) of the children. Those with a fistula located in the middle lobe of the right lung accounted for 58.8% (10 cases), of which 40.0% (four cases) presented consolidation. In this study, 41.2% (seven) of the children with primary BA-PAS exhibited no abnormal changes on chest CT, and 58.8% (10 cases) exhibited abnormal changes in the unilateral lung.

Conclusion: For children with pulmonary hemorrhage who have consolidation in the right middle lobe, the formation of BA-PAS should be anticipated. The possibility of primary BA-PAS should not be disregarded in children with pulmonary hemorrhage with tortuosity and dilation of BAs, despite no apparent abnormalities on lung CT, or ground-glass density or consolidation on only one side.

Clinical significance: The chest CT of patients with pulmonary hemorrhage showed consolidation of the right middle lobe of the lung, which was highly likely to indicate BA-PAS.

Purpose: By correcting the effect of tumor size on metabolic activity, the maximum standardized uptake value-to-tumor size (SUV_max:tumor size) ratio on fluorodeoxyglucose F18 positron emission tomography (¹⁸F-FDG PET)/computed tomography (CT) scans can be a prognostic parameter of non-small cell lung cancer (NSCLC). The current study evaluates the prognostic value of SUV_max:tumor size ratio on pretreatment ¹⁸F-FDG PET/CT scans in patients with NSCLC. Furthermore, the SUV_max:tumor size ratio is compared with other established PET parameters.

Methods: This study included 108 patients with NSCLC who underwent pretreatment ¹⁸F-FDG PET/CT scans and curative lung surgery. The associations between the SUV_max:tumor size ratio and other conventional PET parameters were investigated. The recurrence-free survival according to the SUV_max:tumor size ratio was also analyzed. In addition, the SUV_max:tumor size ratio was compared according to postoperative pathologic findings.

Results: In total, 72 (66.7%) of the 108 participants presented with adenocarcinoma (ADC). Nineteen (17.6%) patients experienced recurrence during a median follow-up period of 32.3 months. The median SUV max:tumor size ratio was 2.37 (1.23 for ADCs and 3.90 for other histologic types). The SUV_max:tumor size ratio was associated with SUV_max and mean SUV, as well as metabolic tumor volume and total lesion glycolysis. Patients with an SUV_max:tumor size ratio higher than the median had a worse recurrence outcome than those with an SUV_max:tumor size ratio lower than the median. Participants with ADC who presented with lymphovascular invasion had a higher SUV_max:tumor size ratio than those without. The presence of lymph node metastasis and advanced histologic grade were associated with a high SUV_max:tumor size ratio in patients with ADC.

Conclusion: The SUV_max:tumor size ratio on pretreatment ¹⁸F-FDG PET/CT scans was associated with aggressive tumor behavior and poor outcome in NSCLCs, particularly ADC.

Clinical significance: The SUV_max:tumor size ratio on pretreatment ¹⁸F-FDG PET/CT scans has a prognostic value in patients with NSCLCs, especially ADC.