American Journal of Roentgenology最新文献

{"title":"Professional Pathways: Training-Pediatric Imaging, an <i>AJR</i> Podcast Series (Episode 3).","authors":"Raisa Amiruddin, Amy R Mehollin-Ray","doi":"10.2214/AJR.25.33866","DOIUrl":"https://doi.org/10.2214/AJR.25.33866","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145076712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"What it Takes to Tackle the Hottest Topic-Radiology Trailblazers, an <i>AJR</i> Podcast Series (Episode 3).","authors":"Lindsey Negrete, Amy Maduram, Kate Hanneman","doi":"10.2214/AJR.25.33827","DOIUrl":"https://doi.org/10.2214/AJR.25.33827","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spectral Photon-Counting Detector Coronary CTA With Reduced Radiation and Contrast Media Doses in Inflammation-Associated Coronary Artery Disease: A Prospective Study.","authors":"Cheng Xu, Yue Sun, Liang Wang, Limiao Zou, Ming Wang, Lu Lin, Yun Wang, Xiaonan Sun, Xiaoying Liu, Xianbo Yu, Christianne Leidecker, Lun Wang, Yifan Liu, Hao Qian, Ran Tian, Rozemarijn Vliegenthart, Zhenyu Liu, Yining Wang","doi":"10.2214/AJR.25.33493","DOIUrl":"https://doi.org/10.2214/AJR.25.33493","url":null,"abstract":"<p><p><b>Background:</b> Patients with inflammation-associated coronary artery disease (CAD) may exhibit rapid progression and require regular coronary imaging. <b>Objectives:</b> To evaluate the diagnostic performance of spectral photon-counting detector (PCD) coronary CTA with reduced radiation and contrast media doses for detecting coronary stenosis and in-stent restenosis in patients with inflammation-associated CAD. <b>Methods:</b> This prospective study enrolled patients with inflammation-associated CAD from January 2023 to March 2024. Participants underwent spectral PCD coronary CTA using prospectively ECG-triggered sequential acquisition and an individualized low-dose contrast media protocol. Virtual monoenergetic images (VMI) at 55 keV and polychromatic (T3D) images were reconstructed with matching parameters, including 0.4-mm slice thickness. Two readers independently assessed subjective (5-point Likert scales) and objective image quality measures; readers also assessed images for obstructive stenosis and in-stent restenosis (both ≥50%) in patients with invasive coronary angiography (ICA) available as reference. <b>Results:</b> The analysis included 63 patients (mean age, 50.4±11.5 years; 45 women, 18 men). Median contrast media volume was 28.0 mL. Median DLP was 165.0 mG·cm. The 55-keV VMI, compared with T3D, showed better (p<.05) overall image quality, diagnostic confidence, SNR, and CNR in all three assessed vessels (e.g., right circumflex artery for reader 1: overall image quality of 4.5 vs 4.1, CNR of 12.1 vs 9.9). Diagnostic performance using ICA as reference was evaluated in 40 patients with 132 lesions and 75 stents. The 55-keV VMI, compared to T3D, demonstrated higher (p<.05) per-lesion accuracy for obstructive stenosis (reader 1: 96.2% vs 84.1%; reader 2: 97.0% vs 86.4%); these differences in accuracy were also observed for both readers for noncalcified and partly calcified plaques, lesions in mid and distal segments, and patients with BMI ≥24. The 55-keV VMI and T3D showed no significant difference (p>.05) in accuracy for in-stent restenosis (reader 1: 97.3% vs 96.0%; reader 2: 96.0% vs 94.7%). <b>Conclusions:</b> Spectral PCD coronary CTA, obtained using low radiation and contrast media doses and reconstructed using 55-keV VMI, demonstrated excellent diagnostic accuracy in detecting obstructive stenosis and in-stent restenosis in patients with inflammation-associated CAD. <b>Clinical Impact:</b> The proposed protocol could be used to guide clinical decision-making in inflammation-associated CAD.</p>","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MRI at 0.55 T for Assessment of Pancreatic Intraductal Papillary Mucinous Neoplasms: An Intraindividual Comparison Versus 1.5-T and 3-T MRI.","authors":"Radhika Rajeev, Vikas Gulani, Mishal Mendiratta-Lala, Erica B Stein, Benjamin M Mervak, Shane A Wells, Reve Chahine, Tayson Lin, Nikita Consul, Matheos Yosef, Shokoufeh Khalatbari, Maria Masotti, Chamila Perera, Nicole Seiberlich, Hero K Hussain","doi":"10.2214/AJR.25.33252","DOIUrl":"10.2214/AJR.25.33252","url":null,"abstract":"<p><p><b>Background:</b> Mid-field (0.55-T) MRI may offer an alternative to higher field strengths for pancreatic intraductal papillary mucinous neoplasms (IPMNs) surveillance given high-quality MRCP sequences enabled by longer T2 relaxation times and greater patient comfort resulting from a larger bore and reduced acoustic noise. However, SNR is lower at 0.55 T. <b>Objective:</b> To compare pancreatic IPMN assessment between MRI performed at 0.55 T versus at higher field strengths in terms of cyst feature characterization, image quality, and diagnostic confidence. <b>Methods:</b> This retrospective study included 35 patients (median age, 70 years; 25 female, 10 male) with a pancreatic IPMN who underwent abdominal MRI both at 0.55 T (performed between April 8, 2022 and November 15, 2023) and at 1.5 or 3 T (hereafter, 1.5/3 T) within a 13-month interval. Seven radiologists independently reviewed examinations for cyst characteristics as well as for image quality and diagnostic confidence (1-10 scales; 10=highest scores). <b>Results:</b> Across readers, agreement between 0.55 T and 1.5/3 T was excellent for IPMN type (Gwet's agreement coefficient 1 [Gwet's AC1], 0.87), presence of pancreatic duct dilation (Gwet's AC1, 0.94), cyst size (intraclass correlation coefficient, 0.96), diameter of diameter ducts (intraclass correlation coefficient, 0.99), and all five assessed suspicious cyst features (enhancing mural nodule <5 mm, enhancing mural nodule ≥5 mm, thickened enhancing walls/septae, abrupt pancreatic duct caliber change with upstream atrophy, enlarged peripancreatic lymph nodes, Gwet's AC1, 0.88-0.99); and was moderate for multifocality (Gwet's AC1, 0.62) and cyst location (Gwet's AC1, 0.55). Across readers, 0.55-T examinations, compared with 1.5/3-T examinations, showed lower mean image quality (7.5±1.7 vs 8.6±1.3, p<.001) and lower mean diagnostic confidence (8±1.7 vs 8.7±1.3; p<.001). However, all 0.55-T and 1.5/3-T examinations were considered diagnostic (diagnostic confidence ≥5) by all readers. One patient developed IPMN-related malignancy, which corresponded to a 5-mm enhancing mural nodule identified by one reader, who identified this finding at both field strengths. <b>Conclusion:</b> Agreement for suspicious cyst features was excellent at both field strengths. All 0.55-T examinations were considered diagnostic. <b>Clinical Impact:</b> The findings may help guide the application of 0.55-T MRI in longitudinal surveillance of pancreatic IPMNs and inform relevant technical improvement efforts.</p>","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Closing in on the Properties of Subsolid Nodules by Habitat Imaging.","authors":"Takuma Usuzaki","doi":"10.2214/AJR.25.33803","DOIUrl":"https://doi.org/10.2214/AJR.25.33803","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Central Tumor Location in Predicting Prognosis of Lung Adenocarcinoma: Implications for Clinical Practice.","authors":"Yeqing Zhu","doi":"10.2214/AJR.25.33848","DOIUrl":"https://doi.org/10.2214/AJR.25.33848","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Out-of-the-Box Large Language Models for Detecting and Classifying Critical Findings in Radiology Reports Using Various Prompt Strategies.","authors":"Ish A Talati, Juan M Zambrano Chaves, Avisha Das, Imon Banerjee, Daniel L Rubin","doi":"10.2214/AJR.25.33469","DOIUrl":"10.2214/AJR.25.33469","url":null,"abstract":"<p><p><b>Background:</b> The increasing complexity and volume of radiology reports present challenges for timely critical findings communication. <b>Purpose:</b> To evaluate the performance of two out-of-the-box LLMs in detecting and classifying critical findings in radiology reports using various prompt strategies. <b>Methods:</b> The analysis included 252 radiology reports of varying modalities and anatomic regions extracted from the MIMIC-III database, divided into a prompt engineering tuning set of 50 reports, a holdout test set of 125 reports, and a pool of 77 remaining reports used as examples for few-shot prompting. An external test set of 180 chest radiography reports was extracted from the CheXpert Plus database. Reports were manually reviewed to identify critical findings and classify such findings into one of three categories (true critical finding, known/expected critical finding, equivocal critical finding). Following prompt engineering using various prompt strategies, a final prompt for optimal true critical findings detection was selected. Two general-purpose LLMs, GPT-4 and Mistral-7B, processed reports in the test sets using the final prompt. Evaluation included automated text similarity metrics (BLEU-1, ROUGE-F1, G-Eval) and manual performance metrics (precision, recall). <b>Results:</b> For true critical findings, zero-shot, few-shot static (five examples), and few-shot dynamic (five examples) prompting yielded BLEU-1 of 0.691, 0.778, and 0.748; ROUGE-F1 of 0.706, 0.797, and 0.773; and G-Eval of 0.428, 0.573, and 0.516. Precision and recall for true critical findings, known/expected critical findings, and equivocal critical findings, in the holdout test set for GPT-4 were 90.1% and 86.9%, 80.9% and 85.0%, and 80.5% and 94.3%; in the holdout test set for Mistral-7B were 75.6% and 77.4%, 34.1% and 70.0%, and 41.3% and 74.3%; in the external test set for GPT-4 were 82.6% and 98.3%, 76.9% and 71.4%, and 70.8% and 85.0%; and in the external test set for Mistral-7B were 75.0% and 93.1%, 33.3% and 92.9%, and 34.0% and 80.0%. <b>Conclusion:</b> Out-of-the-box LLMs were used to detect and classify arbitrary numbers of critical findings in radiology reports. The optimal model for true critical findings entailed a few-shot static approach. <b>Clinical Impact:</b> The study shows a role of contemporary general-purpose models in adapting to specialized medical tasks using minimal data annotation.</p>","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Montgomery Gland Enhancement on Contrast-Enhanced Mammography.","authors":"Rodrigo Alcantara, Chiara Bozzola","doi":"10.2214/AJR.25.33709","DOIUrl":"https://doi.org/10.2214/AJR.25.33709","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Tumor Localization Algorithm: A Valuable Tool for Defining Central Lung Adenocarcinoma and Guiding Prognosis.","authors":"Tao Ouyang","doi":"10.2214/AJR.25.33841","DOIUrl":"https://doi.org/10.2214/AJR.25.33841","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radiologist in the Loop: Advancing Artificial Intelligence in Radiology Through Active Learning.","authors":"Andrew D Chung","doi":"10.2214/AJR.25.33799","DOIUrl":"10.2214/AJR.25.33799","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144978991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}