Radiology最新文献

{"title":"Time-Dependent Diffusion MRI Helps Predict Molecular Subtypes and Treatment Response to Neoadjuvant Chemotherapy in Breast Cancer.","authors":"Xiaoxia Wang, Ruicheng Ba, Yao Huang, Ying Cao, Huifang Chen, Hanshan Xu, Hesong Shen, Daihong Liu, Haiping Huang, Ting Yin, Dan Wu, Jiuquan Zhang","doi":"10.1148/radiol.240288","DOIUrl":"10.1148/radiol.240288","url":null,"abstract":"<p><p>Background Time-dependent diffusion MRI has the potential to help characterize tumor cell properties; however, to the knowledge of the authors, its usefulness for breast cancer diagnosis and prognostic evaluation is unknown. Purpose To investigate the clinical value of time-dependent diffusion MRI-based microstructural mapping for noninvasive prediction of molecular subtypes and pathologic complete response (pCR) in participants with breast cancer. Materials and Methods Participants with invasive breast cancer who underwent pretreatment with time-dependent diffusion MRI between February 2021 and May 2023 were prospectively enrolled. Four microstructural parameters were estimated using the IMPULSED method (a form of time-dependent diffusion MRI), along with three apparent diffusion coefficient (ADC) measurements and a relative ADC diffusion-weighted imaging parameter. Multivariable logistic regression analysis was used to identify parameters associated with each molecular subtype and pCR. A predictive model based on associated parameters was constructed, and its performance was assessed using the area under the receiver operating characteristic curve (AUC) and compared by using the DeLong test. The time-dependent diffusion MRI parameters were validated based on correlation with pathologic measurements. Results The analysis included 408 participants with breast cancer (mean age, 51.9 years ± 9.1 [SD]). Of these, 221 participants were administered neoadjuvant chemotherapy and 54 (24.4%) achieved pCR. The time-dependent diffusion MRI parameters showed reasonable performance in helping to identify luminal A (AUC, 0.70), luminal B (AUC, 0.78), and triple-negative breast cancer (AUC, 0.72) subtypes and high performance for human epidermal growth factor receptor 2 <i>(HER2)</i>-enriched breast cancer (AUC, 0.85), outperforming ADC measurements (all <i>P</i> < .05). Progesterone receptor status (odds ratio [OR], 0.08; <i>P</i> = .02), <i>HER2</i> status (OR, 3.36; <i>P</i> = .009), and the cellularity index (OR, 0.01; <i>P</i> = .02) were independently associated with the odds of achieving pCR. The combined model showed high performance for predicting pCR (AUC, 0.88), outperforming ADC measurements and the clinical-pathologic model (AUC, 0.73 and 0.79, respectively; <i>P</i> < .001). The time-dependent diffusion MRI-estimated parameters correlated well with the pathologic measurements (<i>n</i> = 100; <i>r</i> = 0.67-0.81; <i>P</i> < .001). Conclusion Time-dependent diffusion MRI-based microstructural mapping was an effective method for helping to predict molecular subtypes and pCR to neoadjuvant chemotherapy in participants with breast cancer. © RSNA, 2024 <i>Supplemental material is available for this article.</i> See also the editorial by Partridge and Xu in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e240288"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142473375","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":"Intersystem and Interoperator Agreement of US Attenuation Coefficient for Quantifying Liver Steatosis.","authors":"Giovanna Ferraioli, Davide Roccarina, Richard G Barr","doi":"10.1148/radiol.240162","DOIUrl":"10.1148/radiol.240162","url":null,"abstract":"<p><p>Background The extent of liver steatosis can be assessed using US attenuation coefficient (AC) algorithms currently implemented in several US systems. However, little is known about intersystem and interoperator variability in measurements. Purpose To assess intersystem and interoperator agreement in US AC measurements for fat quantification in individuals with varying degrees of liver steatosis and to assess the correlation of each manufacturer's AC algorithm results with MRI proton density fat fraction (PDFF). Materials and Methods This prospective study was conducted at Southwoods Imaging, Youngstown, Ohio, September 30-October 1, 2023. Two operators independently obtained AC measurements using eight US systems equipped with an AC algorithm from different manufacturers. On the same day, MRI PDFF measurement was performed by a different operator. Correlation between US AC and MRI PDFF was assessed using a mixed-effects model. Agreement between systems and operators was evaluated using the intraclass correlation coefficient (ICC). Results Twenty-six individuals (mean age, 55.4 years ± 10.7 [SD]; 16 female participants) were evaluated. The correlation of US AC with MRI PDFF was high for five AC algorithms (<i>r</i> range, 0.70-0.86), moderate for two (<i>r</i> = 0.62 for both), and poor for one (<i>r</i> = 0.47). In pairwise comparisons, none of the pairs of systems achieved excellent agreement (overall ICC = 0.33 [95% CI: 0.15, 0.52]). One pair showed good agreement (ICC = 0.79 [95% CI: 0.66, 0.87]), eight pairs showed moderate agreement (ICC range, 0.50 [95% CI: 0.22, 0.69] to 0.73 [95% CI: 0.49, 0.85]), and 19 pairs showed poor agreement (ICC range, 0.11 [95% CI: -0.06, 0.37] to 0.48 [95% CI: 0.20, 0.67]). Interoperator agreement on AC value was excellent for the Samsung Medison algorithm (ICC = 0.90 [95% CI: 0.80, 0.96]), good for the Siemens Healthineers (ICC = 0.76 [95% CI: 0.54, 0.89]) and Canon Medical Systems (ICC = 0.76 [95% CI: 0.16, 0.92]) algorithms, and moderate for the remaining algorithms (ICC range, 0.50 [95% CI: 0.16, 0.73] to 0.74 [95% CI: 0.51, 0.88]). The mean AC value obtained by the two operators did not differ for any system except the system from Canon Medical Systems. Conclusion There was substantial variability in AC values obtained with different US systems, precluding interchangeability between systems for liver steatosis diagnosis and follow-up imaging. Interoperator agreement ranged from moderate to excellent. © RSNA, 2024 <i>Supplemental material is available for this article.</i> See also the editorial by Han in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e240162"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142522826","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":"Large Language and Emerging Multimodal Foundation Models: Boundless Opportunities.","authors":"Reza Forghani","doi":"10.1148/radiol.242508","DOIUrl":"https://doi.org/10.1148/radiol.242508","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"34 1","pages":"e242508"},"PeriodicalIF":19.7,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142385577","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":"The Radiologist at the Forefront of Management of Ovarian and Adnexal Lesions.","authors":"Laure S Fournier","doi":"10.1148/radiol.242545","DOIUrl":"https://doi.org/10.1148/radiol.242545","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"5 1","pages":"e242545"},"PeriodicalIF":19.7,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142385532","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":"A Decade of Contrast-enhanced Mammography: Expanding Screening to Women at Intermediate or High Risk for Breast Cancer.","authors":"Marc B I Lobbes","doi":"10.1148/radiol.241970","DOIUrl":"https://doi.org/10.1148/radiol.241970","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e241970"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142352721","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":"Comparing Commercial and Open-Source Large Language Models for Labeling Chest Radiograph Reports.","authors":"Felix J Dorfner, Liv Jürgensen, Leonhard Donle, Fares Al Mohamad, Tobias R Bodenmann, Mason C Cleveland, Felix Busch, Lisa C Adams, James Sato, Thomas Schultz, Albert E Kim, Jameson Merkow, Keno K Bressem, Christopher P Bridge","doi":"10.1148/radiol.241139","DOIUrl":"10.1148/radiol.241139","url":null,"abstract":"<p><p>Background Rapid advances in large language models (LLMs) have led to the development of numerous commercial and open-source models. While recent publications have explored OpenAI's GPT-4 to extract information of interest from radiology reports, there has not been a real-world comparison of GPT-4 to leading open-source models. Purpose To compare different leading open-source LLMs to GPT-4 on the task of extracting relevant findings from chest radiograph reports. Materials and Methods Two independent datasets of free-text radiology reports from chest radiograph examinations were used in this retrospective study performed between February 2, 2024, and February 14, 2024. The first dataset consisted of reports from the ImaGenome dataset, providing reference standard annotations from the MIMIC-CXR database acquired between 2011 and 2016. The second dataset consisted of randomly selected reports created at the Massachusetts General Hospital between July 2019 and July 2021. In both datasets, the commercial models GPT-3.5 Turbo and GPT-4 were compared with open-source models that included Mistral-7B and Mixtral-8 × 7B (Mistral AI), Llama 2-13B and Llama 2-70B (Meta), and Qwen1.5-72B (Alibaba Group), as well as CheXbert and CheXpert-labeler (Stanford ML Group), in their ability to accurately label the presence of multiple findings in radiograph text reports using zero-shot and few-shot prompting. The McNemar test was used to compare F1 scores between models. Results On the ImaGenome dataset (<i>n</i> = 450), the open-source model with the highest score, Llama 2-70B, achieved micro F1 scores of 0.97 and 0.97 for zero-shot and few-shot prompting, respectively, compared with the GPT-4 F1 scores of 0.98 and 0.98 (<i>P</i> > .99 and < .001 for superiority of GPT-4). On the institutional dataset (<i>n</i> = 500), the open-source model with the highest score, an ensemble model, achieved micro F1 scores of 0.96 and 0.97 for zero-shot and few-shot prompting, respectively, compared with the GPT-4 F1 scores of 0.98 and 0.97 (<i>P</i> < .001 and > .99 for superiority of GPT-4). Conclusion Although GPT-4 was superior to open-source models in zero-shot report labeling, few-shot prompting with a small number of example reports closely matched the performance of GPT-4. The benefit of few-shot prompting varied across datasets and models. © RSNA, 2024 <i>Supplemental material is available for this article.</i></p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e241139"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11535875/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142522822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pearls and Pitfalls for LLMs 2.0.","authors":"Merel Huisman, Felipe Kitamura, Tessa S Cook, Keith D Hentel, Jonathan Elias, George Shih, Linda Moy","doi":"10.1148/radiol.242512","DOIUrl":"10.1148/radiol.242512","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e242512"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11535876/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142522827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting Recurrence after Sublobar Resection in Patients with Lung Adenocarcinoma Using Preoperative Chest CT Scans.","authors":"Jae Kwang Yun, Ji Yong Kim, Yura Ahn, Mi Young Kim, Geon Dong Lee, Sehoon Choi, Yong-Hee Kim, Dong Kwan Kim, Seung-Il Park, Hyeong Ryul Kim","doi":"10.1148/radiol.233244","DOIUrl":"10.1148/radiol.233244","url":null,"abstract":"<p><p>Background Sublobar resection for lung cancer is usually guided by cutoff values for consolidation size (maximal diameter of the solid tumor component) and consolidation-to-tumor ratio (CTR). The effects of these factors as continuous variables and the reason for established cutoffs are, to the knowledge of the authors, unexplored. Purpose To quantitatively assess the predictive value of CTR and consolidation size for cancer recurrence risk after sublobar resection in clinical stage IA lung adenocarcinoma. Materials and Methods This retrospective study reviewed sublobar resection for clinical stage IA lung adenocarcinoma performed between January 2010 and December 2019. A restricted cubic spline function verified linearity by estimating recurrence probabilities using CTR and consolidation size obtained on preoperative CT scans. Statistical analyses included a Cox proportional hazards model to identify risk factors for cancer recurrence and the Cochran-Armitage trend test for the association between CTR and consolidation size. Results Of 1032 enrolled patients (age, 63.9 years ± 9.9 [SD]; 464 male patients), 523 (50.7%) and 509 (49.3%) underwent wedge resection and segmentectomy, respectively. Among patients with a CTR between 1% and 50% (<i>n</i> = 201), 187 (93.0%) had a consolidation size of less than or equal to 10 mm (<i>P</i> < .001). There was a positive association between the risk of recurrence with CTR and consolidation size (<i>r</i>² = 0.727; <i>P</i> < .001). The recurrence rate showed the greatest increase when CTR was greater than 50% or consolidation size was greater than 10 mm. Specifically, the recurrence rate increased from 2.1% (three of 146) at 26%-50% CTR to 8.3% (nine of 108) at 51%-75% CTR, and from 4.4% (eight of 183) for 6-10-mm consolidation size to 11.9% (23 of 194) for 11-15-mm consolidation size. The probability of recurrence exhibited linearity and increased with CTR and consolidation size. Conclusion Cancer recurrence risk after sublobar resection for stage IA adenocarcinoma consistently rises with CTR and consolidation size. Current guideline cutoffs for sublobar resection remain clinically relevant given observed recurrence rates. © RSNA, 2024 <i>Supplemental material is available for this article.</i></p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e233244"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142522828","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":"Cellular Characterization of Breast Cancer Using Microstructural Diffusion MRI.","authors":"Savannah C Partridge, Junzhong Xu","doi":"10.1148/radiol.242268","DOIUrl":"10.1148/radiol.242268","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e242268"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11535873/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142473347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the Performance and Bias of Natural Language Processing Tools in Labeling Chest Radiograph Reports.","authors":"Samantha M Santomartino, John R Zech, Kent Hall, Jean Jeudy, Vishwa Parekh, Paul H Yi","doi":"10.1148/radiol.232746","DOIUrl":"10.1148/radiol.232746","url":null,"abstract":"<p><p>Background Natural language processing (NLP) is commonly used to annotate radiology datasets for training deep learning (DL) models. However, the accuracy and potential biases of these NLP methods have not been thoroughly investigated, particularly across different demographic groups. Purpose To evaluate the accuracy and demographic bias of four NLP radiology report labeling tools on two chest radiograph datasets. Materials and Methods This retrospective study, performed between April 2022 and April 2024, evaluated chest radiograph report labeling using four NLP tools (CheXpert [rule-based], RadReportAnnotator [RRA; DL-based], OpenAI's GPT-4 [DL-based], cTAKES [hybrid]) on a subset of the Medical Information Mart for Intensive Care (MIMIC) chest radiograph dataset balanced for representation of age, sex, and race and ethnicity (<i>n</i> = 692) and the entire Indiana University (IU) chest radiograph dataset (<i>n</i> = 3665). Three board-certified radiologists annotated the chest radiograph reports for 14 thoracic disease labels. NLP tool performance was evaluated using several metrics, including accuracy and error rate. Bias was evaluated by comparing performance between demographic subgroups using the Pearson χ² test. Results The IU dataset included 3665 patients (mean age, 49.7 years ± 17 [SD]; 1963 female), while the MIMIC dataset included 692 patients (mean age, 54.1 years ± 23.1; 357 female). All four NLP tools demonstrated high accuracy across findings in the IU and MIMIC datasets, as follows: CheXpert (92.6% [47 516 of 51 310], 90.2% [8742 of 9688]), RRA (82.9% [19 746 of 23 829], 92.2% [2870 of 3114]), GPT-4 (94.3% [45 586 of 48 342], 91.6% [6721 of 7336]), and cTAKES (84.7% [43 436 of 51 310], 88.7% [8597 of 9688]). RRA and cTAKES had higher accuracy (<i>P</i> < .001) on the MIMIC dataset, while CheXpert and GPT-4 had higher accuracy on the IU dataset. Differences (<i>P</i> < .001) in error rates were observed across age groups for all NLP tools except RRA on the MIMIC dataset, with the highest error rates for CheXpert, RRA, and cTAKES in patients older than 80 years (mean, 15.8% ± 5.0) and the highest error rate for GPT-4 in patients 60-80 years of age (8.3%). Conclusion Although commonly used NLP tools for chest radiograph report annotation are accurate when evaluating reports in aggregate, demographic subanalyses showed significant bias, with poorer performance in older patients. © RSNA, 2024 <i>Supplemental material is available for this article.</i> See also the editorial by Cai in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e232746"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11535863/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142473351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}