Pub Date : 2025-07-01Epub Date: 2024-08-23DOI: 10.1053/j.semnuclmed.2024.07.002
Pierre Courault , Luc Zimmer , Sophie Lancelot
At present, spinal cord imaging primarily uses magnetic resonance imaging (MRI) or computed tomography (CT), but the greater sensitivity of positron emission tomography (PET) techniques and the development of new radiotracers are paving the way for a new approach. The substantial rise in publications on PET radiotracers for spinal cord exploration indicates a growing interest in the functional and molecular imaging of this organ. The present review aimed to provide an overview of the various radiotracers used in this indication, in preclinical and clinical settings. Firstly, we outline spinal cord anatomy and associated target pathologies. Secondly, we present the state-of-the-art of spinal cord imaging techniques used in clinical practice, with their respective strengths and limitations. Thirdly, we summarize the literature on radiotracers employed in functional PET imaging of the spinal cord. In conclusion, we propose criteria for an ideal radiotracer for molecular spinal cord imaging, emphasizing the relevance of multimodal hybrid cameras, and particularly the benefits of PET-MRI integration.
目前，脊髓成像主要使用磁共振成像（MRI）或计算机断层扫描（CT），但正电子发射断层扫描（PET）技术更高的灵敏度和新型放射性racer的开发正在为新方法铺平道路。有关正电子发射计算机断层成像（PET）放射性核素用于脊髓探查的论文大量增加，表明人们对这一器官的功能和分子成像越来越感兴趣。本综述旨在概述临床前和临床环境中用于该适应症的各种放射性核素。首先，我们概述了脊髓解剖结构和相关靶点病理。其次，我们介绍了临床实践中使用的最先进的脊髓成像技术，以及它们各自的优势和局限性。第三，我们总结了脊髓功能 PET 成像中使用的放射性racer 的文献。最后，我们提出了用于脊髓分子成像的理想放射性示踪剂的标准，强调了多模态混合相机的相关性，尤其是 PET-MRI 集成的优势。
{"title":"Toward Functional PET Imaging of the Spinal Cord","authors":"Pierre Courault , Luc Zimmer , Sophie Lancelot","doi":"10.1053/j.semnuclmed.2024.07.002","DOIUrl":"10.1053/j.semnuclmed.2024.07.002","url":null,"abstract":"<div><div>At present, spinal cord imaging primarily uses magnetic resonance imaging (MRI) or computed tomography (CT), but the greater sensitivity of positron emission tomography (PET) techniques and the development of new radiotracers are paving the way for a new approach. The substantial rise in publications on PET radiotracers for spinal cord exploration indicates a growing interest in the functional and molecular imaging of this organ. The present review aimed to provide an overview of the various radiotracers used in this indication, in preclinical and clinical settings. Firstly, we outline spinal cord anatomy and associated target pathologies. Secondly, we present the state-of-the-art of spinal cord imaging techniques used in clinical practice, with their respective strengths and limitations. Thirdly, we summarize the literature on radiotracers employed in functional PET imaging of the spinal cord. In conclusion, we propose criteria for an ideal radiotracer for molecular spinal cord imaging, emphasizing the relevance of multimodal hybrid cameras, and particularly the benefits of PET-MRI integration.</div></div>","PeriodicalId":21643,"journal":{"name":"Seminars in nuclear medicine","volume":"55 4","pages":"Pages 629-643"},"PeriodicalIF":4.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142056460","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}
Pub Date : 2025-05-01Epub Date: 2025-02-10DOI: 10.1053/j.semnuclmed.2025.01.006
Leonor Lopes MD , Alejandro Lopez-Montes PhD , Yizhou Chen MSc , Pia Koller MSc , Narendra Rathod PhD , August Blomgren MSc , Federico Caobelli MD , Axel Rominger PhD , Kuangyu Shi PhD , Robert Seifert MD
Nuclear medicine has continuously evolved since its beginnings, constantly improving the diagnosis and treatment of various diseases. The integration of artificial intelligence (AI) is one of the latest revolutionizing chapters, promising significant advancements in diagnosis, prognosis, segmentation, image quality enhancement, and theranostics. Early AI applications in nuclear medicine focused on improving diagnostic accuracy, leveraging machine learning algorithms for disease classification and outcome prediction. Advances in deep learning, including convolutional and more recently transformer-based neural networks, have further enabled more precise diagnosis and image segmentation as well as low-dose imaging, and patient-specific dosimetry for personalized treatment. Generative AI, driven by large language models and diffusion techniques, is now allowing the process, interpretation, and generation of complex medical language and images. Despite these achievements, challenges such as data scarcity, heterogeneity, and ethical concerns remain barriers to clinical translation. Addressing these issues through interdisciplinary collaboration will pave the way for a broader adoption of AI in nuclear medicine, potentially enhancing patient care and optimizing diagnosis and therapeutic outcomes.
{"title":"The Evolution of Artificial Intelligence in Nuclear Medicine","authors":"Leonor Lopes MD , Alejandro Lopez-Montes PhD , Yizhou Chen MSc , Pia Koller MSc , Narendra Rathod PhD , August Blomgren MSc , Federico Caobelli MD , Axel Rominger PhD , Kuangyu Shi PhD , Robert Seifert MD","doi":"10.1053/j.semnuclmed.2025.01.006","DOIUrl":"10.1053/j.semnuclmed.2025.01.006","url":null,"abstract":"<div><div>Nuclear medicine has continuously evolved since its beginnings, constantly improving the diagnosis and treatment of various diseases. The integration of artificial intelligence (AI) is one of the latest revolutionizing chapters, promising significant advancements in diagnosis, prognosis, segmentation, image quality enhancement, and theranostics. Early AI applications in nuclear medicine focused on improving diagnostic accuracy, leveraging machine learning algorithms for disease classification and outcome prediction. Advances in deep learning, including convolutional and more recently transformer-based neural networks, have further enabled more precise diagnosis and image segmentation as well as low-dose imaging, and patient-specific dosimetry for personalized treatment. Generative AI, driven by large language models and diffusion techniques, is now allowing the process, interpretation, and generation of complex medical language and images. Despite these achievements, challenges such as data scarcity, heterogeneity, and ethical concerns remain barriers to clinical translation. Addressing these issues through interdisciplinary collaboration will pave the way for a broader adoption of AI in nuclear medicine, potentially enhancing patient care and optimizing diagnosis and therapeutic outcomes.</div></div>","PeriodicalId":21643,"journal":{"name":"Seminars in nuclear medicine","volume":"55 3","pages":"Pages 313-327"},"PeriodicalIF":4.6,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143400013","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}
Pub Date : 2025-05-01Epub Date: 2024-06-08DOI: 10.1053/j.semnuclmed.2024.05.005
Geoffrey M. Currie , K. Elizabeth Hawk , Eric M. Rohren
Generative artificial intelligence (AI) algorithms for both text-to-text and text-to-image applications have seen rapid and widespread adoption in the general and medical communities. While limitations of generative AI have been widely reported, there remain valuable applications in patient and professional communities. Here, the limitations and biases of both text-to-text and text-to-image generative AI are explored using purported applications in medical imaging as case examples. A direct comparison of the capabilities of four common text-to-image generative AI algorithms is reported and recommendations for the most appropriate use, DALL-E 3, justified. The risks use and biases are outlined, and appropriate use guidelines framed for use of generative AI in nuclear medicine.
Generative AI text-to-text and text-to-image generation includes inherent biases, particularly gender and ethnicity, that could misrepresent nuclear medicine. The assimilation of generative AI tools into medical education, image interpretation, patient education, health promotion and marketing in nuclear medicine risks propagating errors and amplification of biases. Mitigation strategies should reside inside appropriate use criteria and minimum standards for quality and professionalism for the application of generative AI in nuclear medicine.
{"title":"Generative Artificial Intelligence Biases, Limitations and Risks in Nuclear Medicine: An Argument for Appropriate Use Framework and Recommendations","authors":"Geoffrey M. Currie , K. Elizabeth Hawk , Eric M. Rohren","doi":"10.1053/j.semnuclmed.2024.05.005","DOIUrl":"10.1053/j.semnuclmed.2024.05.005","url":null,"abstract":"<div><div>Generative artificial intelligence (AI) algorithms for both text-to-text and text-to-image applications have seen rapid and widespread adoption in the general and medical communities. While limitations of generative AI have been widely reported, there remain valuable applications in patient and professional communities. Here, the limitations and biases of both text-to-text and text-to-image generative AI are explored using purported applications in medical imaging as case examples. A direct comparison of the capabilities of four common text-to-image generative AI algorithms is reported and recommendations for the most appropriate use, DALL-E 3, justified. The risks use and biases are outlined, and appropriate use guidelines framed for use of generative AI in nuclear medicine.</div><div>Generative AI text-to-text and text-to-image generation includes inherent biases, particularly gender and ethnicity, that could misrepresent nuclear medicine. The assimilation of generative AI tools into medical education, image interpretation, patient education, health promotion and marketing in nuclear medicine risks propagating errors and amplification of biases. Mitigation strategies should reside inside appropriate use criteria and minimum standards for quality and professionalism for the application of generative AI in nuclear medicine.</div></div>","PeriodicalId":21643,"journal":{"name":"Seminars in nuclear medicine","volume":"55 3","pages":"Pages 423-436"},"PeriodicalIF":4.6,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141293683","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}
Pub Date : 2025-05-01Epub Date: 2025-03-22DOI: 10.1053/j.semnuclmed.2025.02.012
Margarita Kirienko , Lara Cavinato , Martina Sollini
Infectious and inflammatory diseases represent a global challenge. Delayed diagnosis and treatment lead to death, disabilities and impairment of the quality of life. The detection of low-grade inflammation and occult infections remains challenging. Nuclear medicine techniques are well established in the assessment of the severity and extent of the disease. However, high-level expertise is required to process and interpret the images. Additionally, the workflows are frequently time consuming. Artificial intelligence (AI)-based techniques can be efficiently applied in this setting. We reviewed the literature to assess the state of the application of AI in nuclear medicine imaging in infectious and inflammatory diseases. We included 22 studies, which applied AI-based methods for any of the steps of their workflow. In this review we report and critically discuss the state-of-the-art knowledge on the application of AI models in Infection and Inflammation nuclear medicine imaging.
{"title":"Infection and Inflammation in Nuclear Medicine Imaging: The Role of Artificial Intelligence","authors":"Margarita Kirienko , Lara Cavinato , Martina Sollini","doi":"10.1053/j.semnuclmed.2025.02.012","DOIUrl":"10.1053/j.semnuclmed.2025.02.012","url":null,"abstract":"<div><div>Infectious and inflammatory diseases represent a global challenge. Delayed diagnosis and treatment lead to death, disabilities and impairment of the quality of life. The detection of low-grade inflammation and occult infections remains challenging. Nuclear medicine techniques are well established in the assessment of the severity and extent of the disease. However, high-level expertise is required to process and interpret the images. Additionally, the workflows are frequently time consuming. Artificial intelligence (AI)-based techniques can be efficiently applied in this setting. We reviewed the literature to assess the state of the application of AI in nuclear medicine imaging in infectious and inflammatory diseases. We included 22 studies, which applied AI-based methods for any of the steps of their workflow. In this review we report and critically discuss the state-of-the-art knowledge on the application of AI models in Infection and Inflammation nuclear medicine imaging.</div></div>","PeriodicalId":21643,"journal":{"name":"Seminars in nuclear medicine","volume":"55 3","pages":"Pages 396-405"},"PeriodicalIF":4.6,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143693178","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}
Pub Date : 2025-05-01Epub Date: 2025-03-29DOI: 10.1053/j.semnuclmed.2025.03.003
Alireza Safarian MD , Seyed Ali Mirshahvalad MD, MPH, FEBNM, FANMB , Abolfazl Farbod MD , Hadi Nasrollahi MSc , Christian Pirich MD, PhD , Mohsen Beheshti MD, FEBNM, FASNC
The advent of sophisticated image analysis techniques has facilitated the extraction of increasingly complex data, such as radiomic features, from various imaging modalities, including [18F]FDG PET/CT, a well-established cornerstone of oncological imaging. Furthermore, the use of artificial intelligence (AI) algorithms has shown considerable promise in enhancing the interpretation of these quantitative parameters. Additionally, AI-driven models enable the integration of parameters from multiple imaging modalities along with clinical data, facilitating the development of comprehensive models with significant clinical impact.
However, challenges remain regarding standardization and validation of the AI-powered models, as well as their implementation in real-world clinical practice. The variability in imaging acquisition protocols, segmentation methods, and feature extraction approaches across different institutions necessitates robust harmonization efforts to ensure reproducibility and clinical utility. Moreover, the successful translation of AI models into clinical practice requires prospective validation in large cohorts, as well as seamless integration into existing workflows to assess their ability to enhance clinicians’ performance.
This review aims to provide an overview of the literature and highlight three key applications: diagnostic impact, prediction of treatment response, and long-term patient prognostication. In the first part, we will focus on head and neck, lung, breast, gastroesophageal, colorectal, and gynecological malignancies.
{"title":"Artificial intelligence for tumor [18F]FDG-PET imaging: Advancement and future trends—part I","authors":"Alireza Safarian MD , Seyed Ali Mirshahvalad MD, MPH, FEBNM, FANMB , Abolfazl Farbod MD , Hadi Nasrollahi MSc , Christian Pirich MD, PhD , Mohsen Beheshti MD, FEBNM, FASNC","doi":"10.1053/j.semnuclmed.2025.03.003","DOIUrl":"10.1053/j.semnuclmed.2025.03.003","url":null,"abstract":"<div><div>The advent of sophisticated image analysis techniques has facilitated the extraction of increasingly complex data, such as radiomic features, from various imaging modalities, including [<sup>18</sup>F]FDG PET/CT, a well-established cornerstone of oncological imaging. Furthermore, the use of artificial intelligence (AI) algorithms has shown considerable promise in enhancing the interpretation of these quantitative parameters. Additionally, AI-driven models enable the integration of parameters from multiple imaging modalities along with clinical data, facilitating the development of comprehensive models with significant clinical impact.</div><div>However, challenges remain regarding standardization and validation of the AI-powered models, as well as their implementation in real-world clinical practice. The variability in imaging acquisition protocols, segmentation methods, and feature extraction approaches across different institutions necessitates robust harmonization efforts to ensure reproducibility and clinical utility. Moreover, the successful translation of AI models into clinical practice requires prospective validation in large cohorts, as well as seamless integration into existing workflows to assess their ability to enhance clinicians’ performance.</div><div>This review aims to provide an overview of the literature and highlight three key applications: diagnostic impact, prediction of treatment response, and long-term patient prognostication. In the first part, we will focus on head and neck, lung, breast, gastroesophageal, colorectal, and gynecological malignancies.</div></div>","PeriodicalId":21643,"journal":{"name":"Seminars in nuclear medicine","volume":"55 3","pages":"Pages 328-344"},"PeriodicalIF":4.6,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143753825","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}
Pub Date : 2025-05-01Epub Date: 2025-03-11DOI: 10.1053/j.semnuclmed.2025.02.007
James Cairns BMBS, MSc, FRCR , Russell Frood MBChB, PhD, FRCR , Chirag Patel MBBS, FRCR , Andrew Scarsbrook BMBS, PhD, FRCR
Malignant lymphomas encompass a range of malignancies with incidence rising globally, particularly with age. In younger populations, Hodgkin and Burkitt lymphomas predominate, while older populations more commonly experience subtypes such as diffuse large B-cell, follicular, marginal zone, and mantle cell lymphomas. Positron emission tomography/computed tomography (PET/CT) using [18F] fluorodeoxyglucose (FDG) is the gold standard for staging, treatment response assessment, and prognostication in lymphoma. However, interpretation of PET/CT is complex, time-consuming, and reliant on expert imaging specialists, exacerbating challenges associated with workforce shortages worldwide. Artificial intelligence (AI) offers transformative potential across multiple aspects of PET/CT imaging in this setting.
AI applications in appointment planning have demonstrated utility in reducing nonattendance rates and improving departmental efficiency. Advanced reconstruction techniques leveraging convolutional neural networks (CNNs) enable reduced injected activities of radiopharmaceutical and patient dose whilst maintaining diagnostic accuracy, particularly benefiting younger patients requiring multiple scans. Automated segmentation tools, predominantly using 3D U-Net architectures, have improved quantification of metrics such as total metabolic tumour volume (TMTV) and total lesion glycolysis (TLG), facilitating prognostication and treatment stratification. Despite these advancements, challenges remain, including variability in segmentation performance, impact on Deauville Score interpretation, and standardization of TMTV/TLG measurements. Emerging large language models (LLMs) also show promise in enhancing PET/CT reporting, converting free-text reports into structured formats, and improving patient communication.
Further research is required to address limitations such as AI-induced errors, physiological uptake differentiation, and the integration of AI models into clinical workflows. With robust validation and harmonization, AI integration could significantly enhance lymphoma care, improving diagnostic precision, workflow efficiency, and patient outcomes.
{"title":"The Role of AI in Lymphoma: An Update","authors":"James Cairns BMBS, MSc, FRCR , Russell Frood MBChB, PhD, FRCR , Chirag Patel MBBS, FRCR , Andrew Scarsbrook BMBS, PhD, FRCR","doi":"10.1053/j.semnuclmed.2025.02.007","DOIUrl":"10.1053/j.semnuclmed.2025.02.007","url":null,"abstract":"<div><div>Malignant lymphomas encompass a range of malignancies with incidence rising globally, particularly with age. In younger populations, Hodgkin and Burkitt lymphomas predominate, while older populations more commonly experience subtypes such as diffuse large B-cell, follicular, marginal zone, and mantle cell lymphomas. Positron emission tomography/computed tomography (PET/CT) using [<sup>18</sup>F] fluorodeoxyglucose (FDG) is the gold standard for staging, treatment response assessment, and prognostication in lymphoma. However, interpretation of PET/CT is complex, time-consuming, and reliant on expert imaging specialists, exacerbating challenges associated with workforce shortages worldwide. Artificial intelligence (AI) offers transformative potential across multiple aspects of PET/CT imaging in this setting.</div><div>AI applications in appointment planning have demonstrated utility in reducing nonattendance rates and improving departmental efficiency. Advanced reconstruction techniques leveraging convolutional neural networks (CNNs) enable reduced injected activities of radiopharmaceutical and patient dose whilst maintaining diagnostic accuracy, particularly benefiting younger patients requiring multiple scans. Automated segmentation tools, predominantly using 3D U-Net architectures, have improved quantification of metrics such as total metabolic tumour volume (TMTV) and total lesion glycolysis (TLG), facilitating prognostication and treatment stratification. Despite these advancements, challenges remain, including variability in segmentation performance, impact on Deauville Score interpretation, and standardization of TMTV/TLG measurements. Emerging large language models (LLMs) also show promise in enhancing PET/CT reporting, converting free-text reports into structured formats, and improving patient communication.</div><div>Further research is required to address limitations such as AI-induced errors, physiological uptake differentiation, and the integration of AI models into clinical workflows. With robust validation and harmonization, AI integration could significantly enhance lymphoma care, improving diagnostic precision, workflow efficiency, and patient outcomes.</div></div>","PeriodicalId":21643,"journal":{"name":"Seminars in nuclear medicine","volume":"55 3","pages":"Pages 377-386"},"PeriodicalIF":4.6,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143606405","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}
Pub Date : 2025-05-01Epub Date: 2024-11-19DOI: 10.1053/j.semnuclmed.2024.10.005
K Elizabeth Hawk , Geoffrey M Currie
Artificial intelligence (AI) has rapidly reshaped the global practice of nuclear medicine. Through this shift, the integration of AI into nuclear medicine education, clinical practice, and research has a significant impact on workforce diversity. While AI in nuclear medicine has the potential to be a powerful tool to improve clinical, research and educational practice, and to enhance patient care, careful examination of the impact of each AI tool needs to be undertaken with respect to the impact on, among other factors, diversity in the nuclear medicine workforce. Some AI tools can be used to specifically drive inclusivity and diversity of the workforce by supporting women and underrepresented minorities. Other tools, however, have the potential to negatively impact minority groups, leading to a widening of the diversity gap. This manuscript explores how various AI solutions have the potential to both negatively and positively affect diversity in the nuclear medicine workforce.
{"title":"Artificial Intelligence and Workforce Diversity in Nuclear Medicine","authors":"K Elizabeth Hawk , Geoffrey M Currie","doi":"10.1053/j.semnuclmed.2024.10.005","DOIUrl":"10.1053/j.semnuclmed.2024.10.005","url":null,"abstract":"<div><div>Artificial intelligence (AI) has rapidly reshaped the global practice of nuclear medicine. Through this shift, the integration of AI into nuclear medicine education, clinical practice, and research has a significant impact on workforce diversity. While AI in nuclear medicine has the potential to be a powerful tool to improve clinical, research and educational practice, and to enhance patient care, careful examination of the impact of each AI tool needs to be undertaken with respect to the impact on, among other factors, diversity in the nuclear medicine workforce. Some AI tools can be used to specifically drive inclusivity and diversity of the workforce by supporting women and underrepresented minorities. Other tools, however, have the potential to negatively impact minority groups, leading to a widening of the diversity gap. This manuscript explores how various AI solutions have the potential to both negatively and positively affect diversity in the nuclear medicine workforce.</div></div>","PeriodicalId":21643,"journal":{"name":"Seminars in nuclear medicine","volume":"55 3","pages":"Pages 437-449"},"PeriodicalIF":4.6,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142682260","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}
[18F]FDG PET/CT is a powerful imaging modality of high performance in multiple myeloma (MM) and is considered the appropriate method for assessing treatment response in this disease. On the other hand, due to the heterogeneous and sometimes complex patterns of bone marrow infiltration in MM, the interpretation of PET/CT can be particularly challenging, hampering interobserver reproducibility and limiting the diagnostic and prognostic ability of the modality. Although many approaches have been developed to address the issue of standardization, none can yet be considered a standard method for interpretation or objective quantification of PET/CT. Therefore, advanced diagnostic quantification approaches are needed to support and potentially guide the management of MM. In recent years, radiomics has emerged as an innovative method for high-throughput mining of image-derived features for clinical decision making, which may be particularly helpful in oncology. In addition, machine learning and deep learning, both subfields of artificial intelligence (AI) closely related to the radiomics process, have been increasingly applied to automated image analysis, offering new possibilities for a standardized evaluation of imaging modalities such as CT, PET/CT and MRI in oncology. In line with this, the initial but steadily growing literature on the application of radiomics and AI-based methods in the field of [18F]FDG PET/CT in MM has already yielded encouraging results, offering a potentially reliable tool towards optimization and standardization of interpretation in this disease. The main results of these studies are presented in this review.
[18F]FDG正电子发射计算机断层显像/计算机断层扫描（PET/CT）是多发性骨髓瘤（MM）中一种功能强大的成像模式，被认为是评估该疾病治疗反应的适当方法。另一方面，由于多发性骨髓瘤骨髓浸润的异质性和有时复杂的模式，PET/CT 的判读尤其具有挑战性，妨碍了观察者之间的可重复性，限制了该模式的诊断和预后能力。尽管已开发出许多方法来解决标准化问题，但还没有一种方法可被视为 PET/CT 解释或客观量化的标准方法。因此，需要先进的诊断量化方法来支持和指导 MM 的治疗。近年来，放射组学已成为一种创新方法，可高通量挖掘图像特征，用于临床决策，这可能对肿瘤学特别有帮助。此外，机器学习和深度学习这两个与放射组学过程密切相关的人工智能（AI）子领域已越来越多地应用于自动图像分析，为肿瘤学中 CT、PET/CT 和 MRI 等成像模式的标准化评估提供了新的可能性。因此，关于放射组学和基于人工智能的方法在 MM 的 [18F]FDG PET/CT 领域的应用的文献虽然刚刚起步，但在稳步增长，已经取得了令人鼓舞的成果，为该疾病的解释优化和标准化提供了潜在的可靠工具。本综述介绍了这些研究的主要成果。
{"title":"Radiomics and Artificial Intelligence Landscape for [18F]FDG PET/CT in Multiple Myeloma","authors":"Christos Sachpekidis MD , Hartmut Goldschmidt MD , Lars Edenbrandt MD , Antonia Dimitrakopoulou-Strauss MD","doi":"10.1053/j.semnuclmed.2024.11.005","DOIUrl":"10.1053/j.semnuclmed.2024.11.005","url":null,"abstract":"<div><div>[<sup>18</sup>F]FDG PET/CT is a powerful imaging modality of high performance in multiple myeloma (MM) and is considered the appropriate method for assessing treatment response in this disease. On the other hand, due to the heterogeneous and sometimes complex patterns of bone marrow infiltration in MM, the interpretation of PET/CT can be particularly challenging, hampering interobserver reproducibility and limiting the diagnostic and prognostic ability of the modality. Although many approaches have been developed to address the issue of standardization, none can yet be considered a standard method for interpretation or objective quantification of PET/CT. Therefore, advanced diagnostic quantification approaches are needed to support and potentially guide the management of MM. In recent years, radiomics has emerged as an innovative method for high-throughput mining of image-derived features for clinical decision making, which may be particularly helpful in oncology. In addition, machine learning and deep learning, both subfields of artificial intelligence (AI) closely related to the radiomics process, have been increasingly applied to automated image analysis, offering new possibilities for a standardized evaluation of imaging modalities such as CT, PET/CT and MRI in oncology. In line with this, the initial but steadily growing literature on the application of radiomics and AI-based methods in the field of [<sup>18</sup>F]FDG PET/CT in MM has already yielded encouraging results, offering a potentially reliable tool towards optimization and standardization of interpretation in this disease. The main results of these studies are presented in this review.</div></div>","PeriodicalId":21643,"journal":{"name":"Seminars in nuclear medicine","volume":"55 3","pages":"Pages 387-395"},"PeriodicalIF":4.6,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142824486","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}
Pub Date : 2025-05-01Epub Date: 2025-02-25DOI: 10.1053/j.semnuclmed.2025.01.008
Yizhou Chen MA, M. Eng. , Xiaoliang Shao MD , Kuangyu Shi PhD , Axel Rominger MD, PhD , Federico Caobelli PD, MD, FEBNM
Breast cancer is one of the most common types of cancer affecting women worldwide. Artificial intelligence (AI) is transforming breast cancer imaging by enhancing diagnostic capabilities across multiple imaging modalities including mammography, digital breast tomosynthesis, ultrasound, magnetic resonance imaging, and nuclear medicines techniques. AI is being applied to diverse tasks such as breast lesion detection and classification, risk stratification, molecular subtyping, gene mutation status prediction, and treatment response assessment, with emerging research demonstrating performance levels comparable to or potentially exceeding those of radiologists. The large foundation models are showing remarkable potential in different breast cancer imaging tasks. Self-supervised learning gives an insight into data inherent correlation, and federated learning is an alternative way to maintain data privacy. While promising results have been obtained so far, data standardization from source, large-scale annotated multimodal datasets, and extensive prospective clinical trials are still needed to fully explore and validate deep learning's clinical utility and address the legal and ethical considerations, which will ultimately determine its widespread adoption in breast cancer care. We hereby provide a review of the most up-to-date knowledge on AI in breast cancer imaging.
{"title":"AI in Breast Cancer Imaging: An Update and Future Trends","authors":"Yizhou Chen MA, M. Eng. , Xiaoliang Shao MD , Kuangyu Shi PhD , Axel Rominger MD, PhD , Federico Caobelli PD, MD, FEBNM","doi":"10.1053/j.semnuclmed.2025.01.008","DOIUrl":"10.1053/j.semnuclmed.2025.01.008","url":null,"abstract":"<div><div>Breast cancer is one of the most common types of cancer affecting women worldwide. Artificial intelligence (AI) is transforming breast cancer imaging by enhancing diagnostic capabilities across multiple imaging modalities including mammography, digital breast tomosynthesis, ultrasound, magnetic resonance imaging, and nuclear medicines techniques. AI is being applied to diverse tasks such as breast lesion detection and classification, risk stratification, molecular subtyping, gene mutation status prediction, and treatment response assessment, with emerging research demonstrating performance levels comparable to or potentially exceeding those of radiologists. The large foundation models are showing remarkable potential in different breast cancer imaging tasks. Self-supervised learning gives an insight into data inherent correlation, and federated learning is an alternative way to maintain data privacy. While promising results have been obtained so far, data standardization from source, large-scale annotated multimodal datasets, and extensive prospective clinical trials are still needed to fully explore and validate deep learning's clinical utility and address the legal and ethical considerations, which will ultimately determine its widespread adoption in breast cancer care. We hereby provide a review of the most up-to-date knowledge on AI in breast cancer imaging.</div></div>","PeriodicalId":21643,"journal":{"name":"Seminars in nuclear medicine","volume":"55 3","pages":"Pages 358-370"},"PeriodicalIF":4.6,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143516707","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}
Pub Date : 2025-05-01Epub Date: 2025-02-17DOI: 10.1053/j.semnuclmed.2025.01.004
Harrison J. Howell BS , Jeremy P. McGale MA , Aurélie Choucair MD , Dorsa Shirini MD, MBA , Nicolas Aide MD, PhD , Michael A. Postow MD , Lucy Wang BA , Mickael Tordjman MD , Egesta Lopci MD, PhD , Augustin Lecler MD, PhD , Stéphane Champiat MD, PhD , Delphine L. Chen MD , Désirée Deandreis MD , Laurent Dercle MD, PhD
Artificial intelligence (AI) has become a pivotal tool for medical image analysis, significantly enhancing drug discovery through improved diagnostics, staging, prognostication, and response assessment. At a high level, AI-driven image analysis enables the quantification and synthesis of previously qualitative imaging characteristics, facilitating the identification of novel disease-specific biomarkers, patient risk stratification, prognostication, and adverse event prediction. In addition, AI can assist in response assessment by capturing changes in imaging “phenotype” over time, allowing for optimized treatment plans based on real-time analysis. Integrating this emerging technology into drug discovery pipelines has the potential to accelerate the identification and development of new pharmaceuticals by assisting in target identification and patient selection, as well as reducing the incidence, and therefore cost, of failed trials through high-throughput, reproducible, and data-driven insights. Continued progress in AI applications will shape the future of medical imaging, ultimately fostering more efficient, accurate, and tailored drug discovery processes. Herein, we offer a comprehensive overview of how AI enhances medical imaging to inform drug development and therapeutic strategies.
{"title":"Artificial Intelligence for Drug Discovery: An Update and Future Prospects","authors":"Harrison J. Howell BS , Jeremy P. McGale MA , Aurélie Choucair MD , Dorsa Shirini MD, MBA , Nicolas Aide MD, PhD , Michael A. Postow MD , Lucy Wang BA , Mickael Tordjman MD , Egesta Lopci MD, PhD , Augustin Lecler MD, PhD , Stéphane Champiat MD, PhD , Delphine L. Chen MD , Désirée Deandreis MD , Laurent Dercle MD, PhD","doi":"10.1053/j.semnuclmed.2025.01.004","DOIUrl":"10.1053/j.semnuclmed.2025.01.004","url":null,"abstract":"<div><div>Artificial intelligence (AI) has become a pivotal tool for medical image analysis, significantly enhancing drug discovery through improved diagnostics, staging, prognostication, and response assessment. At a high level, AI-driven image analysis enables the quantification and synthesis of previously qualitative imaging characteristics, facilitating the identification of novel disease-specific biomarkers, patient risk stratification, prognostication, and adverse event prediction. In addition, AI can assist in response assessment by capturing changes in imaging “phenotype” over time, allowing for optimized treatment plans based on real-time analysis. Integrating this emerging technology into drug discovery pipelines has the potential to accelerate the identification and development of new pharmaceuticals by assisting in target identification and patient selection, as well as reducing the incidence, and therefore cost, of failed trials through high-throughput, reproducible, and data-driven insights. Continued progress in AI applications will shape the future of medical imaging, ultimately fostering more efficient, accurate, and tailored drug discovery processes. Herein, we offer a comprehensive overview of how AI enhances medical imaging to inform drug development and therapeutic strategies.</div></div>","PeriodicalId":21643,"journal":{"name":"Seminars in nuclear medicine","volume":"55 3","pages":"Pages 406-422"},"PeriodicalIF":4.6,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143449799","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号