Systemic therapies, encompassing conventional chemotherapy, targeted therapy, and immunotherapy, alongside radiotherapy and thermal ablation, are the covered treatments.
In the Editorial Comment section, Hyun Soo Ko's discussion on this article is available. This article's abstract is available in Chinese (audio/PDF) and Spanish (audio/PDF) translation formats. In cases of acute pulmonary embolism (PE), prompt initiation of anticoagulation therapy is paramount for maximizing patient outcomes. To assess the impact of AI-driven reordering of radiologist worklists on report generation timelines for CT pulmonary angiography (CTPA) scans exhibiting acute pulmonary embolism (PE). In a single-center, retrospective study, patients who underwent CT pulmonary angiography (CTPA) were examined, both pre- (between October 1, 2018, and March 31, 2019) and post- (between October 1, 2019 and March 31, 2020) implementation of an AI tool, that re-prioritized CTPA examinations featuring acute PE detection to the top of the radiologist's reading list. By utilizing the timestamps from both the EMR and dictation system, we were able to ascertain examination wait time (from examination completion to report initiation), read time (from report initiation to report availability), and report turnaround time (the combined wait and read times). A comparison of reporting times for positive PE findings was conducted, referencing the final radiology reports, across the specified periods. PF-06873600 purchase In the study, 2501 examinations were carried out on 2197 patients (average age 57.417 years, comprising 1307 females and 890 males), which included 1166 pre-AI and 1335 post-AI examinations. During the period before AI, the incidence of acute pulmonary embolism, as per radiology reports, was 151% (201 out of 1335). The post-AI period saw a decreased incidence to 123% (144 cases out of 1166). In the post-AI epoch, the AI device adjusted the ranking of 127% (148 divided by 1166) of the examinations. Following the introduction of AI, PE-positive examination reports exhibited a noticeably shorter mean turnaround time (476 minutes) compared to the pre-AI period (599 minutes), demonstrating a difference of 122 minutes (95% confidence interval: 6-260 minutes). Pre-AI, routine-priority examinations had a wait time of 437 minutes, significantly longer than the 153 minutes post-AI (mean difference, 284 minutes; 95% CI, 22–647 minutes) during standard operational hours. However, this decrease in wait time was not observed for urgent or stat-priority examinations. The application of AI to reprioritize worklists achieved a reduction in the time required to complete and provide reports, particularly for PE-positive CPTA examinations. AI-powered diagnostic support for radiologists could potentially enable earlier intervention strategies for acute pulmonary embolism.
Chronic pelvic pain (CPP), a significant health concern linked to reduced quality of life, has often had its origins in pelvic venous disorders (PeVD), previously referred to by vague terms like pelvic congestion syndrome, which have historically been underdiagnosed. Progress in this area has led to improved clarity in defining PeVD, and the evolution of algorithms for PeVD workup and treatment has also brought new insights into the underlying causes of pelvic venous reservoirs and their associated symptoms. Endovascular stenting of common iliac venous compression, alongside ovarian and pelvic vein embolization, are presently options for managing PeVD. The efficacy and safety of both treatments have been consistently demonstrated in patients with CPP of venous origin, irrespective of age. Heterogeneity in current PeVD therapeutic protocols is substantial, owing to the limited availability of prospective, randomized studies and the ongoing refinement of factors impacting treatment success; upcoming clinical trials are projected to deepen our understanding of the venous-origin CPP and to evolve the algorithms for managing PeVD. The AJR Expert Panel's narrative review on PeVD delivers a current perspective, encompassing its classification, diagnostic evaluation, endovascular procedures, symptom management strategies in persistent or recurring cases, and prospective research directions.
Although Photon-counting detector (PCD) CT has demonstrated its capability for radiation dose reduction and image quality enhancement in adult chest CT examinations, its potential in pediatric CT scans remains understudied. Comparing PCD CT and EID CT in children undergoing high-resolution chest CT (HRCT), this study evaluates radiation dose, objective picture quality and patient-reported image quality. A retrospective analysis encompassed 27 children (median age 39 years; 10 females, 17 males) who underwent PCD CT between March 1, 2022, and August 31, 2022, and an additional 27 children (median age 40 years; 13 females, 14 males) who had EID CT scans between August 1, 2021, and January 31, 2022; all chest HRCTs were clinically indicated. By considering age and water-equivalent diameter, patients were matched in the two groups. The parameters of the radiation dose were documented. To obtain objective measurements of lung attenuation, image noise, and signal-to-noise ratio (SNR), an observer designated specific regions of interest (ROIs). Using a 5-point Likert scale (with 1 representing the highest quality), two radiologists independently performed subjective evaluations of overall image quality and motion artifacts. The data from the groups were compared. PF-06873600 purchase Results from PCD CT showed a lower median CTDIvol (0.41 mGy) than EID CT (0.71 mGy), with a statistically significant difference (P < 0.001) apparent in the comparison. A substantial difference was found between the DLP values (102 vs 137 mGy*cm, p = .008) and size-specific dose estimates (82 vs 134 mGy, p < .001). The mAs values exhibited a substantial difference (480 compared to 2020, P < 0.001). PCD CT and EID CT demonstrated no appreciable variation in right upper lobe (RUL) lung attenuation (-793 vs -750 HU, P = .09), right lower lobe (RLL) lung attenuation (-745 vs -716 HU, P = .23), RUL image noise (55 vs 51 HU, P = .27), RLL image noise (59 vs 57 HU, P = .48), RUL signal-to-noise ratio (SNR) (-149 vs -158, P = .89), or RLL SNR (-131 vs -136, P = .79). PCD CT and EID CT demonstrated no appreciable difference in median overall image quality according to reader 1 (10 vs 10, P = .28), nor reader 2 (10 vs 10, P = .07). Similarly, median motion artifact scores exhibited no significant disparity for reader 1 (10 vs 10, P = .17), nor reader 2 (10 vs 10, P = .22). PCD CT procedures resulted in a marked reduction in radiation dose, showing no noteworthy difference in objective or subjective image quality when compared against EID CT. These data concerning PCD CT's performance in children provide a broader understanding, highlighting its suitability for routine application.
Artificial intelligence (AI) models, large language models (LLMs) like ChatGPT, are advanced systems uniquely designed for the purpose of processing and understanding human language. Improved radiology reporting and increased patient engagement are attainable through LLM-powered automation of clinical history and impression generation, the creation of easily comprehensible patient reports, and the provision of pertinent questions and answers regarding radiology report findings. While LLMs excel in many tasks, the inherent possibility of errors necessitates human review to safeguard patient well-being.
The background setting. Clinically applicable AI tools analyzing image studies should exhibit resilience to anticipated variations in examination settings. With the objective in mind. The current investigation sought to assess the functionality of automated AI abdominal CT body composition tools in a heterogeneous group of external CT scans performed outside the authors' hospital network and to identify possible sources of tool malfunction. Different methods will be employed to complete this task effectively. In this retrospective study, 8949 patients (4256 men and 4693 women; average age, 55.5 ± 15.9 years) underwent 11,699 abdominal CT scans at 777 diverse external institutions. These scans, acquired with 83 different scanner models from six manufacturers, were later transferred to the local Picture Archiving and Communication System (PACS) for clinical applications. Three automated AI systems independently evaluated body composition, taking into account bone attenuation, the amount and attenuation of muscle tissue, and the amounts of visceral and subcutaneous fat. For each examination, a single axial series was assessed. The empirical reference ranges established the benchmark for judging the technical adequacy of the tool's output values. Possible causes for failures, defined as tool output not conforming to the reference range, were determined through a focused review. This JSON schema produces a list containing sentences. Across 11431 of 11699 examinations, all three tools performed within acceptable technical standards. In 268 examinations (representing 23% of the total), a minimum of one tool performed poorly. Individual adequacy percentages for bone, muscle, and fat tools were 978%, 991%, and 989%, respectively. Due to an anisotropic image processing error—specifically, incorrect voxel dimensions in the DICOM header—81 of 92 (88%) examinations failed across all three tools. Every instance of this error resulted in a failure of all three tools. PF-06873600 purchase Anisometry errors consistently caused the most tool failures, with pronounced effects on bone (316%), muscle (810%), and fat (628%) tissues. A singular manufacturer produced 79 of 81 (97.5%) scanners with anisometry errors, and even more strikingly, 80 of the 81 (98.8%) flawed scanners were of the same specific model. Analysis of 594% of bone tool failures, 160% of muscle tool failures, and 349% of fat tool failures yielded no causative factors. As a result, High technical adequacy rates were observed in a heterogeneous set of external CT examinations for the automated AI body composition tools, supporting their potential for broader application and generalizability.