首页 > 最新文献

Radiology最新文献

英文 中文
Comparing Commercial and Open-Source Large Language Models for Labeling Chest Radiograph Reports. 比较用于标注胸部 X 光片报告的商用和开源大型语言模型。
IF 12.1 1区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-10-01 DOI: 10.1148/radiol.241139
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

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 (n = 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 (P > .99 and < .001 for superiority of GPT-4). On the institutional dataset (n = 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 (P < .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 Supplemental material is available for this article.

背景 大型语言模型(LLM)的快速发展带动了众多商业和开源模型的开发。虽然最近的出版物探讨了 OpenAI 的 GPT-4 从放射学报告中提取感兴趣的信息,但还没有将 GPT-4 与领先的开源模型进行实际比较。目的 比较不同的主流开源 LLM 与 GPT-4 在从胸片报告中提取相关结果的任务。材料和方法 在这项回顾性研究中,使用了 2024 年 2 月 2 日至 2024 年 2 月 14 日期间进行的胸片检查中自由文本放射学报告的两个独立数据集。第一个数据集由 ImaGenome 数据集中的报告组成,提供 2011 年至 2016 年间从 MIMIC-CXR 数据库中获取的参考标准注释。第二个数据集由麻省总医院在 2019 年 7 月至 2021 年 7 月期间随机选择的报告组成。在这两个数据集中,商业模式 GPT-3.5 Turbo 和 GPT-4 与开源模式进行了比较,开源模式包括 Mistral-7B 和 Mixtral-8 × 7B(Mistral AI)、Llama 2-13B 和 Llama 2-70B(Meta)、Qwen1.5-72B(阿里巴巴集团),以及 CheXbert 和 CheXpert-labeler(斯坦福 ML 集团),比较了它们在使用零镜头和少镜头提示时准确标注放射照片文本报告中是否存在多个发现的能力。McNemar 检验用于比较不同模型的 F1 分数。结果 在 ImaGenome 数据集(n = 450)上,得分最高的开源模型 Llama 2-70B 在零镜头和少镜头提示方面的微观 F1 分数分别为 0.97 和 0.97,而 GPT-4 的 F1 分数分别为 0.98 和 0.98(GPT-4 的优越性 P > .99 和 < .001)。在机构数据集(n = 500)中,得分最高的开源模型(即集合模型)在零次和少量提示时的微观 F1 得分分别为 0.96 和 0.97,而 GPT-4 的 F1 得分分别为 0.98 和 0.97(GPT-4 的优越性 P < .001 和 > .99)。结论 虽然 GPT-4 在零次报告标注方面优于开源模型,但使用少量示例报告进行的少量提示与 GPT-4 的性能非常接近。在不同的数据集和模型中,少量提示的优势各不相同。© RSNA, 2024 本文有补充材料。
{"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":null,"pages":null},"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}
引用次数: 0
Pearls and Pitfalls for LLMs 2.0. 法学硕士 2.0 的珍珠与陷阱。
IF 12.1 1区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-10-01 DOI: 10.1148/radiol.242512
Merel Huisman, Felipe Kitamura, Tessa S Cook, Keith D Hentel, Jonathan Elias, George Shih, Linda Moy
{"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":null,"pages":null},"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}
引用次数: 0
Absolute Metabolite Quantification in Individuals with Glioma and Healthy Individuals Using Whole-Brain Three-dimensional MR Spectroscopic and Echo-planar Time-resolved Imaging. 利用全脑三维磁共振光谱和回声平面时间分辨成像对胶质瘤患者和健康人的代谢物进行绝对定量。
IF 12.1 1区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-01 DOI: 10.1148/radiol.232401
Mehran Baboli, Fuyixue Wang, Zijing Dong, Jorg Dietrich, Erik J Uhlmann, Tracy T Batchelor, Daniel P Cahill, Ovidiu C Andronesi

Background: MR spectroscopic imaging (MRSI) can be used to quantify an extended brain metabolic profile but is confounded by changes in tissue water levels due to disease.

Purpose: To develop a fast absolute quantification method for metabolite concentrations combining whole-brain MRSI with echo-planar time-resolved imaging (EPTI) relaxometry in individuals with glioma and healthy individuals.

Materials and methods: In this prospective study performed from August 2022 to August 2023, using internal water as concentration reference, the MRSI-EPTI quantification method was compared with the conventional method using population-average literature relaxation values. Healthy participants and participants with mutant IDH1 gliomas underwent imaging at 3 T with a 32-channel coil. Real-time navigated adiabatic spiral three-dimensional MRSI scans were acquired in approximately 8 minutes and reconstructed with a super-resolution pipeline to obtain brain metabolic images at 2.4-mm isotropic resolution. High-spatial-resolution multiparametric EPTI was performed in 3 minutes, with 1-mm isotropic resolution, to correct the relaxation and proton density of the water reference signal. Bland-Altman analysis and the Wilcoxon signed rank test were used to compare absolute quantifications from the proposed and conventional methods.

Results: Six healthy participants (four male; mean age, 37 years ± 11 [SD]) and nine participants with glioma (six male; mean age, 41 years ± 15; one with wild-type IDH1 and eight with mutant IDH1) were included. In healthy participants, there was good agreement (+4% bias) between metabolic concentrations derived using the two methods, with a CI of plus or minus 26%. In participants with glioma, there was large disagreement between the two methods (+39% bias) and a CI of plus or minus 55%. The proposed quantification method improved tumor contrast-to-noise ratio (median values) for total N-acetyl-aspartate (EPTI: 0.541 [95% CI: 0.217, 0.910]; conventional: 0.484 [95% CI: 0.199, 0.823]), total choline (EPTI: 1.053 [95% CI: 0.681, 1.713]; conventional: 0.940 [95% CI: 0.617, 1.295]), and total creatine (EPTI: 0.745 [95% CI: 0.628, 0.909]; conventional: 0.553 [95% CI: 0.444, 0.828]) (P = .03 for all).

Conclusion: The whole-brain MRSI-EPTI method provided fast absolute quantification of metabolic concentrations with individual-specific corrections at 2.4-mm isotropic resolution, yielding concentrations closer to the true value in disease than the conventional literature-based corrections. © RSNA, 2024 Supplemental material is available for this article.

背景:目的:结合全脑 MRSI 和回声平面时间分辨成像(EPTI)弛豫测量法,为胶质瘤患者和健康人的代谢物浓度开发一种快速绝对量化方法:在这项于 2022 年 8 月至 2023 年 8 月进行的前瞻性研究中,以体内水为浓度参考,将 MRSI-EPTI 定量方法与使用人群平均文献弛豫值的传统方法进行了比较。健康参试者和患有突变 IDH1 胶质瘤的参试者使用 32 通道线圈在 3 T 下进行了成像。实时导航绝热螺旋三维 MRSI 扫描在大约 8 分钟内完成,并通过超分辨率管道重建,获得了 2.4 毫米各向同性分辨率的脑代谢图像。高空间分辨率多参数 EPTI 在 3 分钟内完成,各向同性分辨率为 1 毫米,用于校正水参考信号的弛豫和质子密度。使用Bland-Altman分析和Wilcoxon符号秩检验来比较建议方法和传统方法的绝对定量结果:共纳入六名健康参与者(四名男性;平均年龄为 37 岁 ± 11 [SD])和九名胶质瘤患者(六名男性;平均年龄为 41 岁 ± 15;一名为野生型 IDH1,八名为突变型 IDH1)。在健康参试者中,两种方法得出的代谢浓度具有良好的一致性(+4% 偏差),CI 为正负 26%。在患有胶质瘤的参试者中,两种方法之间的差异较大(偏差+39%),CI 为正负 55%。拟议的量化方法提高了总 N-乙酰天冬氨酸(EPTI:0.541 [95% CI:0.217, 0.910];常规:0.484 [95% CI:0.199, 0.823])、总胆碱(EPTI:1.053[95%CI:0.681,1.713];常规:0.940[95%CI:0.617,1.295])和总肌酸(EPTI:0.745[95%CI:0.628,0.909];常规:0.553[95%CI:0.444,0.828])(P = .03):结论:全脑 MRSI-EPTI 方法在 2.4 毫米各向同性分辨率下对代谢浓度进行了快速绝对量化和个体特异性校正,与传统的基于文献的校正方法相比,该方法得出的代谢浓度更接近疾病的真实值。RSNA, 2024 这篇文章有补充材料。
{"title":"Absolute Metabolite Quantification in Individuals with Glioma and Healthy Individuals Using Whole-Brain Three-dimensional MR Spectroscopic and Echo-planar Time-resolved Imaging.","authors":"Mehran Baboli, Fuyixue Wang, Zijing Dong, Jorg Dietrich, Erik J Uhlmann, Tracy T Batchelor, Daniel P Cahill, Ovidiu C Andronesi","doi":"10.1148/radiol.232401","DOIUrl":"10.1148/radiol.232401","url":null,"abstract":"<p><strong>Background: </strong>MR spectroscopic imaging (MRSI) can be used to quantify an extended brain metabolic profile but is confounded by changes in tissue water levels due to disease.</p><p><strong>Purpose: </strong>To develop a fast absolute quantification method for metabolite concentrations combining whole-brain MRSI with echo-planar time-resolved imaging (EPTI) relaxometry in individuals with glioma and healthy individuals.</p><p><strong>Materials and methods: </strong>In this prospective study performed from August 2022 to August 2023, using internal water as concentration reference, the MRSI-EPTI quantification method was compared with the conventional method using population-average literature relaxation values. Healthy participants and participants with mutant <i>IDH1</i> gliomas underwent imaging at 3 T with a 32-channel coil. Real-time navigated adiabatic spiral three-dimensional MRSI scans were acquired in approximately 8 minutes and reconstructed with a super-resolution pipeline to obtain brain metabolic images at 2.4-mm isotropic resolution. High-spatial-resolution multiparametric EPTI was performed in 3 minutes, with 1-mm isotropic resolution, to correct the relaxation and proton density of the water reference signal. Bland-Altman analysis and the Wilcoxon signed rank test were used to compare absolute quantifications from the proposed and conventional methods.</p><p><strong>Results: </strong>Six healthy participants (four male; mean age, 37 years ± 11 [SD]) and nine participants with glioma (six male; mean age, 41 years ± 15; one with wild-type <i>IDH1</i> and eight with mutant <i>IDH1</i>) were included. In healthy participants, there was good agreement (+4% bias) between metabolic concentrations derived using the two methods, with a CI of plus or minus 26%. In participants with glioma, there was large disagreement between the two methods (+39% bias) and a CI of plus or minus 55%. The proposed quantification method improved tumor contrast-to-noise ratio (median values) for total <i>N</i>-acetyl-aspartate (EPTI: 0.541 [95% CI: 0.217, 0.910]; conventional: 0.484 [95% CI: 0.199, 0.823]), total choline (EPTI: 1.053 [95% CI: 0.681, 1.713]; conventional: 0.940 [95% CI: 0.617, 1.295]), and total creatine (EPTI: 0.745 [95% CI: 0.628, 0.909]; conventional: 0.553 [95% CI: 0.444, 0.828]) (<i>P</i> = .03 for all).</p><p><strong>Conclusion: </strong>The whole-brain MRSI-EPTI method provided fast absolute quantification of metabolic concentrations with individual-specific corrections at 2.4-mm isotropic resolution, yielding concentrations closer to the true value in disease than the conventional literature-based corrections. © RSNA, 2024 <i>Supplemental material is available for this article.</i></p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":null,"pages":null},"PeriodicalIF":12.1,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11449233/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142308491","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}
引用次数: 0
Transforming Lung Cancer Screening with AI: Comprehensive Evaluation and Personalized Medicine Prospects. 用人工智能改变肺癌筛查:综合评估与个性化医疗前景。
IF 19.7 1区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-01 DOI: 10.1148/radiol.242118
Masahiro Yanagawa,Akinori Hata
{"title":"Transforming Lung Cancer Screening with AI: Comprehensive Evaluation and Personalized Medicine Prospects.","authors":"Masahiro Yanagawa,Akinori Hata","doi":"10.1148/radiol.242118","DOIUrl":"https://doi.org/10.1148/radiol.242118","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":null,"pages":null},"PeriodicalIF":19.7,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256227","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}
引用次数: 0
Arterial Tortuosity Syndrome. 动脉扭曲综合征
IF 12.1 1区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-01 DOI: 10.1148/radiol.240181
Brecht Van Berkel, Vincent Sneyers
{"title":"Arterial Tortuosity Syndrome.","authors":"Brecht Van Berkel, Vincent Sneyers","doi":"10.1148/radiol.240181","DOIUrl":"10.1148/radiol.240181","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":null,"pages":null},"PeriodicalIF":12.1,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142294078","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}
引用次数: 0
A Vesical Imaging Reporting and Data System for Contrast-enhanced US. 用于对比增强 US 的膀胱成像报告和数据系统。
IF 19.7 1区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-01 DOI: 10.1148/radiol.241666
Glen R Morrell
{"title":"A Vesical Imaging Reporting and Data System for Contrast-enhanced US.","authors":"Glen R Morrell","doi":"10.1148/radiol.241666","DOIUrl":"https://doi.org/10.1148/radiol.241666","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":null,"pages":null},"PeriodicalIF":19.7,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142165874","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}
引用次数: 0
Generating Synthetic Data for Medical Imaging. 生成医学成像合成数据。
IF 19.7 1区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-01 DOI: 10.1148/radiol.232471
Lennart R Koetzier,Jie Wu,Domenico Mastrodicasa,Aline Lutz,Matthew Chung,W Adam Koszek,Jayanth Pratap,Akshay S Chaudhari,Pranav Rajpurkar,Matthew P Lungren,Martin J Willemink
Artificial intelligence (AI) models for medical imaging tasks, such as classification or segmentation, require large and diverse datasets of images. However, due to privacy and ethical issues, as well as data sharing infrastructure barriers, these datasets are scarce and difficult to assemble. Synthetic medical imaging data generated by AI from existing data could address this challenge by augmenting and anonymizing real imaging data. In addition, synthetic data enable new applications, including modality translation, contrast synthesis, and professional training for radiologists. However, the use of synthetic data also poses technical and ethical challenges. These challenges include ensuring the realism and diversity of the synthesized images while keeping data unidentifiable, evaluating the performance and generalizability of models trained on synthetic data, and high computational costs. Since existing regulations are not sufficient to guarantee the safe and ethical use of synthetic images, it becomes evident that updated laws and more rigorous oversight are needed. Regulatory bodies, physicians, and AI developers should collaborate to develop, maintain, and continually refine best practices for synthetic data. This review aims to provide an overview of the current knowledge of synthetic data in medical imaging and highlights current key challenges in the field to guide future research and development.
用于医学成像任务(如分类或分割)的人工智能(AI)模型需要大量不同的图像数据集。然而,由于隐私和伦理问题,以及数据共享基础设施的障碍,这些数据集非常稀缺且难以收集。人工智能从现有数据中生成的合成医学影像数据可以通过增强和匿名化真实影像数据来应对这一挑战。此外,合成数据还能实现新的应用,包括模式转换、对比度合成和放射科医生的专业培训。然而,合成数据的使用也带来了技术和伦理方面的挑战。这些挑战包括确保合成图像的真实性和多样性,同时保持数据的不可识别性,评估在合成数据上训练的模型的性能和可推广性,以及高昂的计算成本。由于现有法规不足以保证合成图像的安全和道德使用,因此显然需要更新法律和更严格的监督。监管机构、医生和人工智能开发人员应合作开发、维护并不断完善合成数据的最佳实践。本综述旨在概述当前医学影像合成数据方面的知识,并强调该领域当前面临的主要挑战,以指导未来的研究与开发。
{"title":"Generating Synthetic Data for Medical Imaging.","authors":"Lennart R Koetzier,Jie Wu,Domenico Mastrodicasa,Aline Lutz,Matthew Chung,W Adam Koszek,Jayanth Pratap,Akshay S Chaudhari,Pranav Rajpurkar,Matthew P Lungren,Martin J Willemink","doi":"10.1148/radiol.232471","DOIUrl":"https://doi.org/10.1148/radiol.232471","url":null,"abstract":"Artificial intelligence (AI) models for medical imaging tasks, such as classification or segmentation, require large and diverse datasets of images. However, due to privacy and ethical issues, as well as data sharing infrastructure barriers, these datasets are scarce and difficult to assemble. Synthetic medical imaging data generated by AI from existing data could address this challenge by augmenting and anonymizing real imaging data. In addition, synthetic data enable new applications, including modality translation, contrast synthesis, and professional training for radiologists. However, the use of synthetic data also poses technical and ethical challenges. These challenges include ensuring the realism and diversity of the synthesized images while keeping data unidentifiable, evaluating the performance and generalizability of models trained on synthetic data, and high computational costs. Since existing regulations are not sufficient to guarantee the safe and ethical use of synthetic images, it becomes evident that updated laws and more rigorous oversight are needed. Regulatory bodies, physicians, and AI developers should collaborate to develop, maintain, and continually refine best practices for synthetic data. This review aims to provide an overview of the current knowledge of synthetic data in medical imaging and highlights current key challenges in the field to guide future research and development.","PeriodicalId":20896,"journal":{"name":"Radiology","volume":null,"pages":null},"PeriodicalIF":19.7,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142165893","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}
引用次数: 0
Biomarkers for Personalized Neoadjuvant Therapy in Triple-Negative Breast Cancer: Moving Forward. 三阴性乳腺癌个性化新辅助疗法的生物标志物:向前迈进。
IF 12.1 1区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-01 DOI: 10.1148/radiol.242011
Gaiane M Rauch
{"title":"Biomarkers for Personalized Neoadjuvant Therapy in Triple-Negative Breast Cancer: Moving Forward.","authors":"Gaiane M Rauch","doi":"10.1148/radiol.242011","DOIUrl":"10.1148/radiol.242011","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":null,"pages":null},"PeriodicalIF":12.1,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142120455","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}
引用次数: 0
Calcified Osteosarcoma Lung Metastases. 骨肉瘤肺转移钙化
IF 12.1 1区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-01 DOI: 10.1148/radiol.240703
Paolo Spinnato
{"title":"Calcified Osteosarcoma Lung Metastases.","authors":"Paolo Spinnato","doi":"10.1148/radiol.240703","DOIUrl":"10.1148/radiol.240703","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":null,"pages":null},"PeriodicalIF":12.1,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142120456","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}
引用次数: 0
Multimodal Models Are Still a Novice at Radiology Vision. 多模态模型在放射学视野中仍是新手。
IF 12.1 1区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-01 DOI: 10.1148/radiol.242286
Francis Deng
{"title":"Multimodal Models Are Still a Novice at Radiology Vision.","authors":"Francis Deng","doi":"10.1148/radiol.242286","DOIUrl":"10.1148/radiol.242286","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":null,"pages":null},"PeriodicalIF":12.1,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142120460","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}
引用次数: 0
期刊
Radiology
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1