Radiology最新文献

{"title":"Deep Learning to Simulate Contrast-Enhanced MRI for Evaluating Suspected Prostate Cancer.","authors":"Hongyan Huang, Junyang Mo, Zhiguang Ding, Xuehua Peng, Ruihao Liu, Danping Zhuang, Yuzhong Zhang, Genwen Hu, Bingsheng Huang, Yingwei Qiu","doi":"10.1148/radiol.240238","DOIUrl":"https://doi.org/10.1148/radiol.240238","url":null,"abstract":"<p><p>Background Multiparametric MRI, including contrast-enhanced sequences, is recommended for evaluating suspected prostate cancer, but concerns have been raised regarding potential contrast agent accumulation and toxicity. Purpose To evaluate the feasibility of generating simulated contrast-enhanced MRI from noncontrast MRI sequences using deep learning and to explore their potential value for assessing clinically significant prostate cancer using Prostate Imaging Reporting and Data System (PI-RADS) version 2.1. Materials and Methods Male patients with suspected prostate cancer who underwent multiparametric MRI were retrospectively included from three centers from April 2020 to April 2023. A deep learning model (pix2pix algorithm) was trained to synthesize contrast-enhanced MRI scans from four noncontrast MRI sequences (T1-weighted imaging, T2-weighted imaging, diffusion-weighted imaging, and apparent diffusion coefficient maps) and then tested on an internal and two external datasets. The reference standard for model training was the second postcontrast phase of the dynamic contrast-enhanced sequence. Similarity between simulated and acquired contrast-enhanced images was evaluated using the multiscale structural similarity index. Three radiologists independently scored T2-weighted and diffusion-weighted MRI with either simulated or acquired contrast-enhanced images using PI-RADS, version 2.1; agreement was assessed with Cohen κ. Results A total of 567 male patients (mean age, 66 years ± 11 [SD]) were divided into a training test set (<i>n</i> = 244), internal test set (<i>n</i> = 104), external test set 1 (<i>n</i> = 143), and external test set 2 (<i>n</i> = 76). Simulated and acquired contrast-enhanced images demonstrated high similarity (multiscale structural similarity index: 0.82, 0.71, and 0.69 for internal test set, external test set 1, and external test set 2, respectively) with excellent reader agreement of PI-RADS scores (Cohen κ, 0.96; 95% CI: 0.94, 0.98). When simulated contrast-enhanced imaging was added to biparametric MRI, 34 of 323 (10.5%) patients were upgraded to PI-RADS 4 from PI-RADS 3. Conclusion It was feasible to generate simulated contrast-enhanced prostate MRI using deep learning. The simulated and acquired contrast-enhanced MRI scans exhibited high similarity and demonstrated excellent agreement in assessing clinically significant prostate cancer based on PI-RADS, version 2.1. © RSNA, 2025 <i>Supplemental material is available for this article.</i> See also the editorial by Neji and Goh in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 1","pages":"e240238"},"PeriodicalIF":12.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142979743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synthetic CT Demonstrates Multiple Enchondromas in Ollier Syndrome.","authors":"Pranjal Rai, Amit Kumar Janu","doi":"10.1148/radiol.241650","DOIUrl":"https://doi.org/10.1148/radiol.241650","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 1","pages":"e241650"},"PeriodicalIF":12.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142954072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incorporating Lymph Node Size at CT as an N1 Descriptor in Clinical N Staging for Lung Cancer.","authors":"Yura Ahn, Sang Min Lee, Jooae Choe, Se Hoon Choi, Kyung-Hyun Do, Joon Beom Seo","doi":"10.1148/radiol.241603","DOIUrl":"https://doi.org/10.1148/radiol.241603","url":null,"abstract":"<p><p>Background The ninth edition of the TNM classification for lung cancer revised the N2 categorization, improving patient stratification, but prognostic heterogeneity remains for the N1 category. Purpose To define the optimal size cutoff for a bulky lymph node (LN) on CT scans and to evaluate the prognostic value of bulky LN in the clinical N staging of lung cancer. Materials and Methods This retrospective study analyzed patients who underwent lobectomy or pneumonectomy for lung cancer between January 2013 and December 2021, divided into development (2016-2021) and validation (2013-2015) cohorts. The optimal threshold for a bulky LN was defined based on the short-axis diameter of the largest clinically positive LN at CT. Prognostic differences according to presence of bulky LN in cN1 category for overall survival (OS) were evaluated using multivariable Cox analysis. Survival discrimination was assessed using the Harrell concordance index (C-index). Results A total of 3426 patients (mean age, 64.0 years ± 9.3 [SD]; 1837 male) and 1327 patients (mean age, 63.0 years ± 9.7; 813 male) were included in the development and validation cohorts, respectively. The cutoff size for a bulky LN was established at 15 mm, and the presence of bulky LN was an independent risk factor for OS (hazard ratio [HR], 1.54; 95% CI: 1.10, 2.16; <i>P</i> = .01). In the development and validation cohorts, the cN1-bulky group had higher mortality risk than the cN1-nonbulky group (HR, 2.82 [95% CI: 1.73, 4.58; <i>P</i> < .001]; 2.29 [95% CI: 1.34, 3.92; <i>P</i> = .002], respectively). The bulky LN descriptor improved prognostic discrimination within the cN1 category compared with the current staging (C-index from 0.50 to 0.60 and to 0.58 in the development and validation cohorts [<i>P</i> < .001, <i>P</i> = .006], respectively]). Conclusion Defining bulky LN with a size cutoff of 15 mm was an effective descriptor in the clinical staging of N1 lung cancer. © RSNA, 2025 <i>Supplemental material is available for this article.</i> See also the editorial by Horst in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 1","pages":"e241603"},"PeriodicalIF":12.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143010693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Consideration of Thermal Ablation for Secondary Hyperparathyroidism in Patients with Chronic Kidney Disease.","authors":"Joseph J Gemmete","doi":"10.1148/radiol.243288","DOIUrl":"https://doi.org/10.1148/radiol.243288","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 1","pages":"e243288"},"PeriodicalIF":12.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142954066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Privacy-ensuring Open-weights Large Language Models Are Competitive with Closed-weights GPT-4o in Extracting Chest Radiography Findings from Free-Text Reports.","authors":"Sebastian Nowak, Benjamin Wulff, Yannik C Layer, Maike Theis, Alexander Isaak, Babak Salam, Wolfgang Block, Daniel Kuetting, Claus C Pieper, Julian A Luetkens, Ulrike Attenberger, Alois M Sprinkart","doi":"10.1148/radiol.240895","DOIUrl":"https://doi.org/10.1148/radiol.240895","url":null,"abstract":"<p><p>Background Large-scale secondary use of clinical databases requires automated tools for retrospective extraction of structured content from free-text radiology reports. Purpose To share data and insights on the application of privacy-preserving open-weights large language models (LLMs) for reporting content extraction with comparison to standard rule-based systems and the closed-weights LLMs from OpenAI. Materials and Methods In this retrospective exploratory study conducted between May 2024 and September 2024, zero-shot prompting of 17 open-weights LLMs was preformed. These LLMs with model weights released under open licenses were compared with rule-based annotation and with OpenAI's GPT-4o, GPT-4o-mini, GPT-4-turbo, and GPT-3.5-turbo on a manually annotated public English chest radiography dataset (Indiana University, 3927 patients and reports). An annotated nonpublic German chest radiography dataset (18 500 reports, 16 844 patients [10 340 male; mean age, 62.6 years ± 21.5 {SD}]) was used to compare local fine-tuning of all open-weights LLMs via low-rank adaptation and 4-bit quantization to bidirectional encoder representations from transformers (BERT) with different subsets of reports (from 10 to 14 580). Nonoverlapping 95% CIs of macro-averaged F1 scores were defined as relevant differences. Results For the English reports, the highest zero-shot macro-averaged F1 score was observed for GPT-4o (92.4% [95% CI: 87.9, 95.9]); GPT-4o outperformed the rule-based CheXpert [Stanford University] (73.1% [95% CI: 65.1, 79.7]) but was comparable in performance to several open-weights LLMs (top three: Mistral-Large [Mistral AI], 92.6% [95% CI: 88.2, 96.0]; Llama-3.1-70b [Meta AI], 92.2% [95% CI: 87.1, 95.8]; and Llama-3.1-405b [Meta AI]: 90.3% [95% CI: 84.6, 94.5]). For the German reports, Mistral-Large (91.6% [95% CI: 90.5, 92.7]) had the highest zero-shot macro-averaged F1 score among the six other open-weights LLMs and outperformed the rule-based annotation (74.8% [95% CI: 73.3, 76.1]). Using 1000 reports for fine-tuning, all LLMs (top three: Mistral-Large, 94.3% [95% CI: 93.5, 95.2]; OpenBioLLM-70b [Saama]: 93.9% [95% CI: 92.9, 94.8]; and Mixtral-8×22b [Mistral AI]: 93.8% [95% CI: 92.8, 94.7]) achieved significantly higher macro-averaged F1 score than did BERT (86.7% [95% CI: 85.0, 88.3]); however, the differences were not relevant when 2000 or more reports were used for fine-tuning. Conclusion LLMs have the potential to outperform rule-based systems for zero-shot \"out-of-the-box\" structuring of report databases, with privacy-ensuring open-weights LLMs being competitive with closed-weights GPT-4o. Additionally, the open-weights LLM outperformed BERT when moderate numbers of reports were used for fine-tuning. Published under a CC BY 4.0 license. <i>Supplemental material is available for this article.</i> See also the editorial by Gee and Yao in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 1","pages":"e240895"},"PeriodicalIF":12.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142979764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of Multimodal Prompt Elements on Diagnostic Performance of GPT-4V in Challenging Brain MRI Cases.","authors":"Severin Schramm, Silas Preis, Marie-Christin Metz, Kirsten Jung, Benita Schmitz-Koep, Claus Zimmer, Benedikt Wiestler, Dennis M Hedderich, Su Hwan Kim","doi":"10.1148/radiol.240689","DOIUrl":"https://doi.org/10.1148/radiol.240689","url":null,"abstract":"<p><p>Background Studies have explored the application of multimodal large language models (LLMs) in radiologic differential diagnosis. Yet, how different multimodal input combinations affect diagnostic performance is not well understood. Purpose To evaluate the impact of varying multimodal input elements on the accuracy of OpenAI's GPT-4 with vision (GPT-4V)-based brain MRI differential diagnosis. Materials and Methods Sixty brain MRI cases with a challenging yet verified diagnosis were selected. Seven prompt groups with variations of four input elements (image without modifiers [I], annotation [A], medical history [H], and image description [D]) were defined. For each MRI case and prompt group, three identical queries were performed using an LLM-based search engine (Perplexity AI, powered by GPT-4V). The accuracy of LLM-generated differential diagnoses was rated using a binary and a numeric scoring system and analyzed using a χ² test and a Kruskal-Wallis test. Results were corrected for false-discovery rate with use of the Benjamini-Hochberg procedure. Regression analyses were performed to determine the contribution of each input element to diagnostic performance. Results The prompt group containing I, A, H, and D as input exhibited the highest diagnostic accuracy (124 of 180 responses [69%]). Significant differences were observed between prompt groups that contained D among their inputs and those that did not. Unannotated (I) (four of 180 responses [2.2%]) or annotated radiologic images alone (I and A) (two of 180 responses [1.1%]) yielded very low diagnostic accuracy. Regression analyses confirmed a large positive effect of D on diagnostic accuracy (odds ratio [OR], 68.03; <i>P</i> < .001), as well as a moderate positive effect of H (OR, 4.18; <i>P</i> < .001). Conclusion The textual description of radiologic image findings was identified as the strongest contributor to the performance of GPT-4V in brain MRI differential diagnosis, followed by the medical history; unannotated or annotated images alone yielded very low diagnostic performance. © RSNA, 2025 <i>Supplemental material is available for this article.</i></p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 1","pages":"e240689"},"PeriodicalIF":12.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143010692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"US-Guided Thermal Ablation for Secondary Hyperparathyroidism: A Prospective Multicenter Study.","authors":"Yang Liu, Cheng-Zhong Peng, Hui-Hui Chai, Lin-Xue Qian, Song-Song Wu, Ming-An Yu, Shui-Ping Li, Jian-Tang Zhang, Yue Shan, Fang-Yi Liu, Chong-Bing Sun, Zhi-Wei Yang, Rui Zhang, Ying Che, Shu-Hang Gao, Jie Yu, Ping Liang","doi":"10.1148/radiol.233104","DOIUrl":"10.1148/radiol.233104","url":null,"abstract":"<p><p>Background Interest in microwave ablation (MWA) and radiofrequency ablation (RFA) use for treating secondary hyperparathyroidism (SHPT) is rising; however, ablation outcomes in patients with SHPT are not well characterized. Purpose To assess the response of parathyroid hormone (PTH), calcium, phosphorus, and alkaline phosphatase (ALP) levels to US-guided parathyroid MWA and RFA and the safety of these treatments in participants with SHPT. Materials and Methods This prospective multicenter cohort study, conducted from September 2017 to March 2022, included participants with SHPT. The primary end point was the proportion of participants achieving the target PTH level (≤585 pg/mL). The secondary end points included PTH, calcium, phosphorus, and ALP levels before ablation and time points for follow-up assessments after ablation (2 hours, 1 day, 1 month, 3 months, and 6 months, and then every 6 months) and complications and technical success rates. Mixed-effects logistic regression models were used to identify factors associated with treatment failure. Results A total of 215 participants (median age, 53 years [IQR, 43-60 years]; 109 [50.7%] male participants) were evaluated, and 183 (85.1%) achieved target PTH levels. Compared with baseline levels, there was an 85.9%, 6.3%, 15.3%, and 37.4% reduction in PTH, calcium, phosphorus, and ALP levels at 24 months after ablation, respectively. For major complications, one (0.5%) participant experienced persistent hoarseness, and severe hypocalcemia (<1.87 mmol/L) was present in 74 (34.4%) participants. After adjustments, predictors associated with treatment failure included the preablation PTH level (adjusted odds ratio [OR], 3.78; 95% CI: 1.19, 12.04; <i>P</i> = .03), maximum tumor volume (adjusted OR, 5.02; 95% CI: 1.74, 14.53; <i>P</i> = .003), and number of glands ablated (adjusted OR, 0.32; 95% CI: 0.11, 0.98; <i>P</i> = .046). The prediction model showed good discrimination ability in the development and validation cohorts (area under the receiver operating characteristic curve, 0.78 [95% CI: 0.66, 0.90] and 0.73 [95% CI: 0.55, 0.91], respectively). Conclusion US-guided thermal ablation techniques were effective and safe treatments in participants with SHPT because they effectively reduced PTH, calcium, phosphorus, and ALP levels. © RSNA, 2025 <i>Supplemental material is available for this article.</i> See also the editorial by Gemmete in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 1","pages":"e233104"},"PeriodicalIF":12.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142954073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Deep Learning-Based Detection and Segmentation of Lung Tumors at CT.","authors":"Mehr Kashyap, Xi Wang, Neil Panjwani, Mohammad Hasan, Qin Zhang, Charles Huang, Karl Bush, Alexander Chin, Lucas K Vitzthum, Peng Dong, Sandra Zaky, Billy W Loo, Maximilian Diehn, Lei Xing, Ruijiang Li, Michael F Gensheimer","doi":"10.1148/radiol.233029","DOIUrl":"https://doi.org/10.1148/radiol.233029","url":null,"abstract":"<p><p><i>\"Just Accepted\" papers have undergone full peer review and have been accepted for publication in <i>Radiology: Artificial Intelligence</i>. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content.</i> Background Detection and segmentation of lung tumors on CT scans are critical for monitoring cancer progression, evaluating treatment responses, and planning radiation therapy; however, manual delineation is labor-intensive and subject to physician variability. Purpose To develop and evaluate an ensemble deep learning model for automating identification and segmentation of lung tumors on CT scans. Materials and Methods A retrospective study was conducted between July 2019 and November 2024 using a large dataset of CT simulation scans and clinical lung tumor segmentations from radiotherapy plans. This dataset was used to train a 3D U-Net-based, image-multiresolution ensemble model to detect and segment lung tumors on CT scans. Model performance was evaluated on internal and external test sets composed of CT simulation scans and lung tumor segmentations from two affiliated medical centers, including single primary and metastatic lung tumors. Performance metrics included sensitivity, specificity, false positive rate, and Dice similarity coefficient (DSC). Model-predicted tumor volumes were compared with physician-delineated volumes. Group comparisons were made with Wilcoxon signed-rank test or one-way ANOVA. P < 0.05 indicated statistical significance. Results The model, trained on 1,504 CT scans with clinical lung tumor segmentations, achieved 92% sensitivity (92/100) and 82% specificity (41/50) in detecting lung tumors on the combined 150-CT scan test set. For a subset of 100 CT scans with a single lung tumor each, the model achieved a median model-physician DSC of 0.77 (IQR: 0.65-0.83) and an interphysician DSC of 0.80 (IQR: 0.72-0.86). Segmentation time was shorter for the model than for physicians (mean 76.6 vs. 166.1-187.7 seconds; p<0.001). Conclusion Routinely collected radiotherapy data were useful for model training. The key strengths of the model include a 3D U-Net ensemble approach for balancing volumetric context with resolution, robust tumor detection and segmentation performance, and the ability to generalize to an external site.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 1","pages":"e233029"},"PeriodicalIF":12.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143010649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Building Rome: TNM Lung Cancer Staging and an Illustration of the Scientific Method.","authors":"Carolyn Horst","doi":"10.1148/radiol.243715","DOIUrl":"https://doi.org/10.1148/radiol.243715","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 1","pages":"e243715"},"PeriodicalIF":12.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143010652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Challenges and Advances in Management of Acute Isolated Extracranial Internal Carotid Artery Occlusions.","authors":"Badih Junior Daou, Neeraj Chaudhary","doi":"10.1148/radiol.243753","DOIUrl":"https://doi.org/10.1148/radiol.243753","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"314 1","pages":"e243753"},"PeriodicalIF":12.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143010653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}