Jacqueline Scheicher, Peter Riley, Karen Dobeli, Paul Yielder, Giovanni Mandarano
Background
Prostate cancer is one of the most common diagnosed cancers globally, with early detection crucial for reducing mortality and morbidity. However existing screening methods have limitations, such as invasiveness and patient discomfort. Spectral detector computed tomography (SDCT) could be an alternative or complementary test for prostate cancer diagnosis because of its material decomposition capabilities. The purpose of this experimental study was to explore the capability of SDCT to accurately measure zinc (Zn) and magnesium (Mg) levels in solutions that simulate clinically relevant concentrations of these elements.
Methods
Solutions of zinc and magnesium chloride (50–1200 μg/g) were prepared in 10 mL test tubes and scanned using SDCT. A region of interest was selected, and average effective atomic numbers (Z-effective [Z-eff]) were obtained using IntelliSpace Discovery. Linear regression assessed the relationship between concentration and Z-eff, with p < 0.05. Regression lines, R2 values, and 95% prediction intervals evaluated measurement variability and precision.
Results
A strong positive correlation was observed between Zn concentration and Z-eff (R2 = 0.99), with the regression equation Z-eff = 7.17 + 0.0010 × concentration. Similarly, Mg concentration demonstrated a positive correlation with Z-eff (R2 = 0.97), with the regression equation Z-eff = 7.14 + 0.0002 × concentration. The 95% prediction interval showed minimal variability in the data.
Conclusions
SDCT effectively differentiates between Zn and Mg within clinically relevant concentration ranges, providing a foundation for further research into its clinical application for prostate cancer diagnosis.
{"title":"Exploring the Capability of Spectral Detector Computed Tomography to Identify Zinc and Magnesium in the Prostate Gland: A Proof-of-Concept Study","authors":"Jacqueline Scheicher, Peter Riley, Karen Dobeli, Paul Yielder, Giovanni Mandarano","doi":"10.1002/ird3.70039","DOIUrl":"https://doi.org/10.1002/ird3.70039","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Prostate cancer is one of the most common diagnosed cancers globally, with early detection crucial for reducing mortality and morbidity. However existing screening methods have limitations, such as invasiveness and patient discomfort. Spectral detector computed tomography (SDCT) could be an alternative or complementary test for prostate cancer diagnosis because of its material decomposition capabilities. The purpose of this experimental study was to explore the capability of SDCT to accurately measure zinc (Zn) and magnesium (Mg) levels in solutions that simulate clinically relevant concentrations of these elements.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Solutions of zinc and magnesium chloride (50–1200 μg/g) were prepared in 10 mL test tubes and scanned using SDCT. A region of interest was selected, and average effective atomic numbers (<i>Z</i>-effective [<i>Z</i>-eff]) were obtained using IntelliSpace Discovery. Linear regression assessed the relationship between concentration and <i>Z</i>-eff, with <i>p</i> < 0.05. Regression lines, <i>R</i><sup>2</sup> values, and 95% prediction intervals evaluated measurement variability and precision.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>A strong positive correlation was observed between Zn concentration and <i>Z</i>-eff (<i>R</i><sup>2</sup> = 0.99), with the regression equation <i>Z</i>-eff = 7.17 + 0.0010 × concentration. Similarly, Mg concentration demonstrated a positive correlation with <i>Z</i>-eff (<i>R</i><sup>2</sup> = 0.97), with the regression equation <i>Z</i>-eff = 7.14 + 0.0002 × concentration. The 95% prediction interval showed minimal variability in the data.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>SDCT effectively differentiates between Zn and Mg within clinically relevant concentration ranges, providing a foundation for further research into its clinical application for prostate cancer diagnosis.</p>\u0000 </section>\u0000 </div>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 5","pages":"362-369"},"PeriodicalIF":0.0,"publicationDate":"2025-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.70039","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145385179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
<p>This special issue of <i>iR</i><i>ADIOLOGY</i> on the application of instruments and equipment in medical imaging documents the groundbreaking strides to develop optimal imaging modalities, particularly X-ray, ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and single-photon emission computed tomography (SPECT), to diagnose, treat, cure, and ultimately prevent medical disorders. This special issue continues the outstanding contributions of prior special issues on ultra-high field MRI [<span>1</span>], ultra-high field MRI in the theranostics of mental disorders [<span>2</span>], artificial intelligence in medical imaging [<span>3</span>], imaging of fetuses, children, and mothers [<span>4</span>], and the use of large language models in radiology [<span>5</span>] to provide readers updates on the state-of-the-art of the application of instruments and equipment in medical imaging to utilize the promising hardware available for optimal interventions in medicine.</p><p>This editorial will focus specifically on the means that novel application of instruments and equipment in molecular medical imaging provide the framework for breakthroughs in neuropsychiatric disorders. Medical molecular imaging constitutes a crucial component of the path to identify the abnormalities in anatomy and physiology that lead to the correct diagnosis of neuropsychiatric and other disorders and the utilization of preventive medicine to formulate a comprehensive treatment plan to target the specific needs of each individual patient. Innovations in the development of instruments, equipment, and other hardware, provide the means for optimal visualization of the structure and function of the nervous system and other organ systems in health and disease. The state-of-the-art descriptions of instruments and equipment reported in this special issue constitute the foundation for providers to incorporate precision medicine to construct comprehensive treatments plans to tailor interventions for the unique needs of each individual patient. This editorial will focus on groundbreaking investigations utilizing innovative medical molecular imaging tools (CT, micro positron emission tomograpy/computed tomography [microPET/CT] [<span>6</span>], MRI, and PET) for neuropsychiatric disorders, including human immunodeficiency virus (HIV) infections [<span>7</span>] and Parkinson's disease (PD) [<span>8</span>].</p><p>People with infections with the HIV may develop a spectrum of disorders including cognitive dysfunction. The causes of cognitive impairment among older HIV seropositive (HIV+) individuals may overlap with causes among elderly HIV seronegative (HIV−) individuals without HIV infections. Providers are then faced with the urgent need to determine if cognitive function in people who are HIV+ is due to other infections, malignancies, and other conditions requiring immediate interventions. Additionally, providers also must cons
{"title":"Breakthroughs in the Application of Instruments and Equipment in Medical Molecular Imaging to Neuropsychiatric Disorders","authors":"James Robert Brašić, Ali Cahid Civelek","doi":"10.1002/ird3.70038","DOIUrl":"https://doi.org/10.1002/ird3.70038","url":null,"abstract":"<p>This special issue of <i>iR</i><i>ADIOLOGY</i> on the application of instruments and equipment in medical imaging documents the groundbreaking strides to develop optimal imaging modalities, particularly X-ray, ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and single-photon emission computed tomography (SPECT), to diagnose, treat, cure, and ultimately prevent medical disorders. This special issue continues the outstanding contributions of prior special issues on ultra-high field MRI [<span>1</span>], ultra-high field MRI in the theranostics of mental disorders [<span>2</span>], artificial intelligence in medical imaging [<span>3</span>], imaging of fetuses, children, and mothers [<span>4</span>], and the use of large language models in radiology [<span>5</span>] to provide readers updates on the state-of-the-art of the application of instruments and equipment in medical imaging to utilize the promising hardware available for optimal interventions in medicine.</p><p>This editorial will focus specifically on the means that novel application of instruments and equipment in molecular medical imaging provide the framework for breakthroughs in neuropsychiatric disorders. Medical molecular imaging constitutes a crucial component of the path to identify the abnormalities in anatomy and physiology that lead to the correct diagnosis of neuropsychiatric and other disorders and the utilization of preventive medicine to formulate a comprehensive treatment plan to target the specific needs of each individual patient. Innovations in the development of instruments, equipment, and other hardware, provide the means for optimal visualization of the structure and function of the nervous system and other organ systems in health and disease. The state-of-the-art descriptions of instruments and equipment reported in this special issue constitute the foundation for providers to incorporate precision medicine to construct comprehensive treatments plans to tailor interventions for the unique needs of each individual patient. This editorial will focus on groundbreaking investigations utilizing innovative medical molecular imaging tools (CT, micro positron emission tomograpy/computed tomography [microPET/CT] [<span>6</span>], MRI, and PET) for neuropsychiatric disorders, including human immunodeficiency virus (HIV) infections [<span>7</span>] and Parkinson's disease (PD) [<span>8</span>].</p><p>People with infections with the HIV may develop a spectrum of disorders including cognitive dysfunction. The causes of cognitive impairment among older HIV seropositive (HIV+) individuals may overlap with causes among elderly HIV seronegative (HIV−) individuals without HIV infections. Providers are then faced with the urgent need to determine if cognitive function in people who are HIV+ is due to other infections, malignancies, and other conditions requiring immediate interventions. Additionally, providers also must cons","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 5","pages":"327-329"},"PeriodicalIF":0.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.70038","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145385060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Transthyretin amyloidosis (ATTR), a rare systemic disorder characterized by misfolded transthyretin (TTR) protein aggregation, predominantly affects the heart and peripheral nervous system. Central nervous system (CNS) involvement in ATTR, especially widespread leptomeningeal amyloidosis (LA), is exceedingly rare. Early diagnosis of CNS-predominant ATTR is difficult due to nonspecific symptoms and low awareness. This study adopted a dual-methodology: A single-case analysis of a CNS-predominant hereditary ATTR(CNS-ATTR) patient at a tertiary referral center and a systematic literature review following PRISMA guidelines. PubMed and Embase were systematically searched from the start to March 2025 using controlled vocabulary (MeSH/Emtree terms) and Boolean operators for reported CNS-involved ATTR cases. A systematic review of 79 CNS-ATTR cases revealed universal leptomeningeal enhancement on magnetic resonance imaging (MRI) (77/79, 97%) and cerebrospinal fluid (CSF) protein elevation (66/79, 84%). The index case (p. Gly73Ala) showed diffuse leptomeningeal enhancement, grade 3 PYP uptake, and CSF protein 1.88 g/L. In summary, LA associated with ATTR is extremely scarce. A four-tiered, protocolbased diagnostic algorithm is crucial for patients with unexplained leptomeningeal disorders.
{"title":"Central Nervous System Involvement as the Initial Manifestation of Transthyretin Amyloidosis: A Case Report and Literature Review","authors":"Fen Li, Mingsheng Wan, Benjian Sun, Lijia Zou, Huan Yang, Jing Li, Si Chen","doi":"10.1002/ird3.70026","DOIUrl":"https://doi.org/10.1002/ird3.70026","url":null,"abstract":"<p>Transthyretin amyloidosis (ATTR), a rare systemic disorder characterized by misfolded transthyretin (TTR) protein aggregation, predominantly affects the heart and peripheral nervous system. Central nervous system (CNS) involvement in ATTR, especially widespread leptomeningeal amyloidosis (LA), is exceedingly rare. Early diagnosis of CNS-predominant ATTR is difficult due to nonspecific symptoms and low awareness. This study adopted a dual-methodology: A single-case analysis of a CNS-predominant hereditary ATTR(CNS-ATTR) patient at a tertiary referral center and a systematic literature review following PRISMA guidelines. PubMed and Embase were systematically searched from the start to March 2025 using controlled vocabulary (MeSH/Emtree terms) and Boolean operators for reported CNS-involved ATTR cases. A systematic review of 79 CNS-ATTR cases revealed universal leptomeningeal enhancement on magnetic resonance imaging (MRI) (77/79, 97%) and cerebrospinal fluid (CSF) protein elevation (66/79, 84%). The index case (p. Gly73Ala) showed diffuse leptomeningeal enhancement, grade 3 PYP uptake, and CSF protein 1.88 g/L. In summary, LA associated with ATTR is extremely scarce. A four-tiered, protocolbased diagnostic algorithm is crucial for patients with unexplained leptomeningeal disorders.</p>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 5","pages":"388-396"},"PeriodicalIF":0.0,"publicationDate":"2025-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.70026","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145385091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
<p>This editorial introduces a special issue dedicated to the technical advancements in medical imaging. Medical imaging is an essential component of modern medicine, enabling the detection and analysis of structures and functions within the human body. Among the key imaging modalities are X-ray, ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and single-photon emission computed tomography. Each of these technologies plays a vital role in diagnostics and research, and their continued development drives progress in diagnostic imaging and related disciplines.</p><p>This special issue invites submissions on the following: (1) Applications of recent advancements in imaging instruments and equipment. (2) Integration of imaging devices with molecular imaging and nuclear medicine approaches. (3) The role of instrumentation and radiomics in systemic diseases. (4) Case studies highlighting diagnostic and therapeutic use of imaging technologies.</p><p>Modern diagnostics rely significantly on imaging modalities such as CT, MRI, PET, and optical imaging. Each has witnessed transformative technical advances, enhancing clinical precision and diagnostic roles.</p><p>CT imaging remains pivotal due to ongoing innovations such as photon-counting detector (PCD) technology. Unlike traditional CT scanners, PCD converts X-ray photons directly into electrical signals, offering resolutions down to 0.2 mm. This high resolution enables clear visualization of intricate structures, such as inner ear bones. PCD inherently provides spectral imaging, delivering simultaneous multi-energy data. These advances yield lower radiation doses (30%–50% reduction), significantly reduced noise, and rapid scan times. AI-driven software enhances image reconstruction, facilitating clearer, lower-dose images. CT's strengths lie in rapid anatomical assessment, crucial in emergencies for trauma or acute neurological conditions. It is vital in lung cancer screening, cardiac imaging (via electrocardiograph-gated CT angiography), and dual-energy CT's material characterization. Globally, approximately 375 million scans occur annually, reflecting widespread integration and increasing adoption, particularly in middle-income regions. Photon-counting CT, recently approved, represents a trend toward spectral imaging becoming routine, whereas AI facilitates workflow efficiency.</p><p>MRI, known for exceptional soft tissue contrast, has advanced significantly with ultrahigh field systems like 7 Tesla MRI. These scanners offer superior resolution and sensitivity, critical in neurological imaging for detecting minute lesions and microvascular changes. Hardware advancements include parallel transmit technology to improve image uniformity at ultrahigh fields and digital gradient coils for rapid, high-resolution imaging. Techniques such as parallel imaging and compressed sensing have significantly shortened scan durations, and AI further reduces acqu
{"title":"The Expanding Role of Instruments and Equipment in Medical Imaging","authors":"Arturo Chiti","doi":"10.1002/ird3.70029","DOIUrl":"https://doi.org/10.1002/ird3.70029","url":null,"abstract":"<p>This editorial introduces a special issue dedicated to the technical advancements in medical imaging. Medical imaging is an essential component of modern medicine, enabling the detection and analysis of structures and functions within the human body. Among the key imaging modalities are X-ray, ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and single-photon emission computed tomography. Each of these technologies plays a vital role in diagnostics and research, and their continued development drives progress in diagnostic imaging and related disciplines.</p><p>This special issue invites submissions on the following: (1) Applications of recent advancements in imaging instruments and equipment. (2) Integration of imaging devices with molecular imaging and nuclear medicine approaches. (3) The role of instrumentation and radiomics in systemic diseases. (4) Case studies highlighting diagnostic and therapeutic use of imaging technologies.</p><p>Modern diagnostics rely significantly on imaging modalities such as CT, MRI, PET, and optical imaging. Each has witnessed transformative technical advances, enhancing clinical precision and diagnostic roles.</p><p>CT imaging remains pivotal due to ongoing innovations such as photon-counting detector (PCD) technology. Unlike traditional CT scanners, PCD converts X-ray photons directly into electrical signals, offering resolutions down to 0.2 mm. This high resolution enables clear visualization of intricate structures, such as inner ear bones. PCD inherently provides spectral imaging, delivering simultaneous multi-energy data. These advances yield lower radiation doses (30%–50% reduction), significantly reduced noise, and rapid scan times. AI-driven software enhances image reconstruction, facilitating clearer, lower-dose images. CT's strengths lie in rapid anatomical assessment, crucial in emergencies for trauma or acute neurological conditions. It is vital in lung cancer screening, cardiac imaging (via electrocardiograph-gated CT angiography), and dual-energy CT's material characterization. Globally, approximately 375 million scans occur annually, reflecting widespread integration and increasing adoption, particularly in middle-income regions. Photon-counting CT, recently approved, represents a trend toward spectral imaging becoming routine, whereas AI facilitates workflow efficiency.</p><p>MRI, known for exceptional soft tissue contrast, has advanced significantly with ultrahigh field systems like 7 Tesla MRI. These scanners offer superior resolution and sensitivity, critical in neurological imaging for detecting minute lesions and microvascular changes. Hardware advancements include parallel transmit technology to improve image uniformity at ultrahigh fields and digital gradient coils for rapid, high-resolution imaging. Techniques such as parallel imaging and compressed sensing have significantly shortened scan durations, and AI further reduces acqu","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 5","pages":"325-326"},"PeriodicalIF":0.0,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.70029","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145385048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Caiyun Xu, Jing Peng, Jinyan Chen, Lixia Zhang, Jing Wang
Ovarian cancer (OC) is the most lethal gynecological malignancy. Diagnosis usually occurs late, and even with the most effective treatment relapses are frequent. Early diagnosis and precise staging are critical for achieving better treatment outcomes and prognoses. Conventional imaging methods such as ultrasound (US), computed tomography (CT), and magnetic resonance imaging (MRI) are the main imaging techniques supporting management decisions. However, advancements in molecular imaging have made positron emission tomography/computed tomography (PET/CT) a promising noninvasive imaging option for better management of OC. The literature provides evidence indicating that fluorine-18-fluorodeoxyglucose (18F-FDG) PET/CT (FDG-PET/CT) is effective in primary tumor diagnosis, staging, prognosis evaluation, treatment response assessment, and relapse surveillance. Looking ahead, significant attention should be paid to tracers beyond FDG, integrated PET/MRI, dynamic PET, and artificial intelligence (AI)-based radiomics. This review examines the application of PET/CT in OC management at each disease stage and discusses its future potential.
{"title":"Positron Emission Tomography/Computed Tomography in Ovarian Cancer: Current Status and Future Potential","authors":"Caiyun Xu, Jing Peng, Jinyan Chen, Lixia Zhang, Jing Wang","doi":"10.1002/ird3.70034","DOIUrl":"https://doi.org/10.1002/ird3.70034","url":null,"abstract":"<p>Ovarian cancer (OC) is the most lethal gynecological malignancy. Diagnosis usually occurs late, and even with the most effective treatment relapses are frequent. Early diagnosis and precise staging are critical for achieving better treatment outcomes and prognoses. Conventional imaging methods such as ultrasound (US), computed tomography (CT), and magnetic resonance imaging (MRI) are the main imaging techniques supporting management decisions. However, advancements in molecular imaging have made positron emission tomography/computed tomography (PET/CT) a promising noninvasive imaging option for better management of OC. The literature provides evidence indicating that fluorine-18-fluorodeoxyglucose (<sup>18</sup>F-FDG) PET/CT (FDG-PET/CT) is effective in primary tumor diagnosis, staging, prognosis evaluation, treatment response assessment, and relapse surveillance. Looking ahead, significant attention should be paid to tracers beyond FDG, integrated PET/MRI, dynamic PET, and artificial intelligence (AI)-based radiomics. This review examines the application of PET/CT in OC management at each disease stage and discusses its future potential.</p>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 5","pages":"337-352"},"PeriodicalIF":0.0,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.70034","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145384962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ogechukwu Ngwu-Hyacinth, Aaron Alford, Caleb S. Rowe, Ryan Willoughby, S. Abdollah Mirbozorgi, Steven A. Rothenberg, Jesse Jones, Abin Sajan, Venkatesh P. Krishnasamy, Mark Bolding
Ultrasmall superparamagnetic iron oxide nanoparticles (usSPIONs) are promising alternatives to gadolinium-based contrast agents for positive contrast enhancement in magnetic resonance imaging (MRI). Unlike larger SPIONs that primarily function as T2/T2* negative contrast agents, usSPIONs with core diameters below 5 nm can effectively shorten T1 relaxation times, producing bright signals in T1-weighted images. This distinct behavior stems from their unique magnetic properties, including single-domain configurations, surface spin canting, and rapid Néel relaxation dynamics, which are particularly enhanced at low magnetic field strengths. The biocompatibility of iron oxide, efficient renal clearance pathways, and versatility for surface functionalization offer potential advantages over gadolinium-based agents, especially regarding safety concerns related to nephrogenic systemic fibrosis and gadolinium deposition. These nanoparticles show particular promise for applications in low-field MRI, vascular imaging, targeted molecular imaging, and theranostic platforms. Although challenges remain in optimizing synthesis methods for consistent production of monodisperse usSPIONs with tailored surface chemistry, ongoing research continues to advance their potential for clinical translation. This review explores the mechanisms, synthesis approaches, applications, and future perspectives of usSPIONs as positive contrast agents in MRI.
{"title":"Ultrasmall Superparamagnetic Iron Oxide Nanoparticles as Positive Contrast Agents in Low-Field Magnetic Resonance Imaging","authors":"Ogechukwu Ngwu-Hyacinth, Aaron Alford, Caleb S. Rowe, Ryan Willoughby, S. Abdollah Mirbozorgi, Steven A. Rothenberg, Jesse Jones, Abin Sajan, Venkatesh P. Krishnasamy, Mark Bolding","doi":"10.1002/ird3.70035","DOIUrl":"https://doi.org/10.1002/ird3.70035","url":null,"abstract":"<p>Ultrasmall superparamagnetic iron oxide nanoparticles (usSPIONs) are promising alternatives to gadolinium-based contrast agents for positive contrast enhancement in magnetic resonance imaging (MRI). Unlike larger SPIONs that primarily function as T2/T2* negative contrast agents, usSPIONs with core diameters below 5 nm can effectively shorten T1 relaxation times, producing bright signals in T1-weighted images. This distinct behavior stems from their unique magnetic properties, including single-domain configurations, surface spin canting, and rapid Néel relaxation dynamics, which are particularly enhanced at low magnetic field strengths. The biocompatibility of iron oxide, efficient renal clearance pathways, and versatility for surface functionalization offer potential advantages over gadolinium-based agents, especially regarding safety concerns related to nephrogenic systemic fibrosis and gadolinium deposition. These nanoparticles show particular promise for applications in low-field MRI, vascular imaging, targeted molecular imaging, and theranostic platforms. Although challenges remain in optimizing synthesis methods for consistent production of monodisperse usSPIONs with tailored surface chemistry, ongoing research continues to advance their potential for clinical translation. This review explores the mechanisms, synthesis approaches, applications, and future perspectives of usSPIONs as positive contrast agents in MRI.</p>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 5","pages":"372-387"},"PeriodicalIF":0.0,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.70035","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145385181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiaofeng Dou, Congcong Yu, Chenxi Xue, Jing Wang, Chentao Jin, Yan Zhong, Rui Zhou, Xiaohui Zhang, Hong Zhang
Background
Vascular thrombus is a common complication in cancer patients and can be classified as benign or neoplastic based on tumor cell presence. Conventional imaging modalities provide anatomical information but exhibit limited specificity in distinguishing neoplastic from benign thrombi, prompting the evaluation of 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography/computed tomography ([18F]FDG PET/CT), which leverages metabolic differences for improved differentiation. In this study, the efficacy of [18F]FDG PET/CT for differentiating neoplastic thrombus from benign thrombus was evaluated in patients with malignant tumors.
Methods
Sixty-five patients with histologically or clinically confirmed neoplastic or benign thrombus who underwent [18F]FDG PET/CT were retrospectively enrolled. Both visual and semi-quantitative analyses of the PET/CT scans were conducted. The difference in maximum standardized uptake value (SUVmax) between neoplastic and benign thrombus was assessed using a t-test. Furthermore, receiver operating characteristics (ROC) analysis was performed to determine the optimal SUVmax threshold for differentiating neoplastic from benign thrombus.
Results
Within the cohort, 55 patients were diagnosed with neoplastic thrombus and 10 patients with benign thrombus. In the visual analysis, the sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of [18F]FDG PET/CT for diagnosing neoplastic thrombus were 96.4%, 90.0%, 98.1%, 81.8%, and 95.4%, respectively. In the semi-quantitative analysis, the sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy for diagnosing neoplastic thrombus were 96.4%, 100%, 100%, 83.3%, and 96.9%, respectively. The normalized SUVmax of neoplastic thrombus was significantly higher than that of benign thrombus (10.11 ± 5.32 vs. 2.21 ± 0.51, p < 0.001). The area under the ROC curves for visual assessment and semi-quantitative analysis were 0.932 and 0.993, respectively. There was no statistically significant difference observed between these two assessment methods (p = 0.317).
Conclusions
[18F]FDG PET/CT is capable of differentiating neoplastic thrombus from benign thrombus. Both visual and semi-quantitative analyses demonstrated high diagnostic s
{"title":"The Value of [18F]FDG PET/CT for Differentiating Neoplastic From Benign Thrombus","authors":"Xiaofeng Dou, Congcong Yu, Chenxi Xue, Jing Wang, Chentao Jin, Yan Zhong, Rui Zhou, Xiaohui Zhang, Hong Zhang","doi":"10.1002/ird3.70036","DOIUrl":"https://doi.org/10.1002/ird3.70036","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Vascular thrombus is a common complication in cancer patients and can be classified as benign or neoplastic based on tumor cell presence. Conventional imaging modalities provide anatomical information but exhibit limited specificity in distinguishing neoplastic from benign thrombi, prompting the evaluation of 2-deoxy-2-[<sup>18</sup>F]fluoro-D-glucose positron emission tomography/computed tomography ([<sup>18</sup>F]FDG PET/CT), which leverages metabolic differences for improved differentiation. In this study, the efficacy of [<sup>18</sup>F]FDG PET/CT for differentiating neoplastic thrombus from benign thrombus was evaluated in patients with malignant tumors.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Sixty-five patients with histologically or clinically confirmed neoplastic or benign thrombus who underwent [<sup>18</sup>F]FDG PET/CT were retrospectively enrolled. Both visual and semi-quantitative analyses of the PET/CT scans were conducted. The difference in maximum standardized uptake value (SUV<sub>max</sub>) between neoplastic and benign thrombus was assessed using a <i>t</i>-test. Furthermore, receiver operating characteristics (ROC) analysis was performed to determine the optimal SUV<sub>max</sub> threshold for differentiating neoplastic from benign thrombus.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Within the cohort, 55 patients were diagnosed with neoplastic thrombus and 10 patients with benign thrombus. In the visual analysis, the sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of [<sup>18</sup>F]FDG PET/CT for diagnosing neoplastic thrombus were 96.4%, 90.0%, 98.1%, 81.8%, and 95.4%, respectively. In the semi-quantitative analysis, the sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy for diagnosing neoplastic thrombus were 96.4%, 100%, 100%, 83.3%, and 96.9%, respectively. The normalized SUV<sub>max</sub> of neoplastic thrombus was significantly higher than that of benign thrombus (10.11 ± 5.32 vs. 2.21 ± 0.51, <i>p</i> < 0.001). The area under the ROC curves for visual assessment and semi-quantitative analysis were 0.932 and 0.993, respectively. There was no statistically significant difference observed between these two assessment methods (<i>p</i> = 0.317).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>[<sup>18</sup>F]FDG PET/CT is capable of differentiating neoplastic thrombus from benign thrombus. Both visual and semi-quantitative analyses demonstrated high diagnostic s","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 5","pages":"353-361"},"PeriodicalIF":0.0,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.70036","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145385180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A 48-year-old woman complained with repeated vomiting and pallor over 3 months. Laboratory results revealed a decrease in hemoglobin (80 g/L, reference range > 110 g/L), and no other findings (including tumor markers) were abnormal. Next, abdomen computed tomography (CT) revealed a duodenal mass, which may be malignant. To further define the nature and stage of the lesion, the patient underwent 18F-flurodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) scan. The maximum intensity projection (MIP) image (Figure 1a) demonstrated a high radioactivity (arrow) in the middle abdomen. The axial (Figure 1b), coronal (Figure 1c), and sagittal (Figure 1d) images of the abdomen displayed a solid lesion (arrow) with the size of 61 mm × 34 mm and a SUVmax of 15.6 in the horizontal part of the duodenum. In addition, peripheral lymph nodes with the maximum size of 8 mm × 5 mm showing mild FDG activity (SUVmax: 2.0) were noted (images not shown). The patient received surgical resection of the duodenal lesion (Figure 2a) and peripheral lymph nodes. Pathological examination (Figure 2b, hematoxylin–eosin staining and original magnification: ×100) from the duodenal specimen showed tumor cells arranged in nests with formation of keratin pearls. Immunohistochemistry indicated positive staining for P40 (Figure 2c, original magnification: ×100). These findings were consistent with a diagnosis of duodenal squamous cell carcinoma (SCC). Besides, peripheral lymph node metastases were also confirmed.
SCC of the duodenum is extremely rare and is more likely to represent metastasis from primary SCC originating in other sites, such as the head and neck, lungs, or cervix. Only occasional cases of primary SCC of the duodenum have been reported in the literature. There are four possible pathogenesis of primary duodenal SCC: (1) malignant transformation of heterotopic squamous epithelium; (2) pluripotential stem cells differentiate to malignant squamous cells; (3) squamous metaplasia malignant change due to chronic mucosal damage; and (4) adenocarcinoma transformed into adenosquamous carcinoma and eventually to SCC. Surgery might be the cornerstone in the management of such kind disease. Given the value of the differentiation of metastatic or primary duodenal SCC for treatment options and prognosis, establishing a correct diagnosis is essential. Traditionally, CT scanning has been the major imaging modality for diagnosing abdominal malignancies, which is not particularly sensitive for detecting duodenal malignancies. Increased FDG uptake in the duodenum is not uncommon, but it is usually physiological or inflammation-related. However, our case suggests that duodenal malignancy should be considered in the differential diagnosis when focal abnormal FDG uptake is present in the duodenum, especially when accompanied by a corresponding mass-like lesion on CT imaging. Furthermore, in this case, whole bo
48岁女性主诉反复呕吐、面色苍白3个多月。实验室结果显示血红蛋白下降（80 g/L，参考范围110 g/L），其他未见异常（包括肿瘤标志物）。腹部电脑断层扫描显示一十二指肠肿块，可能为恶性。为了进一步明确病变的性质和分期，患者接受了18f -氟脱氧葡萄糖正电子发射断层扫描/计算机断层扫描（18F-FDG PET/CT）。最大强度投影（MIP）图像（图1a）显示腹部中部有高放射性（箭头）。腹部轴位（图1b）、冠状位（图1c）和矢状位（图1d）显示一实性病变（箭头），大小为61 mm × 34 mm，十二指肠水平部分SUVmax为15.6。此外，外周淋巴结最大大小为8 mm × 5 mm，显示轻度FDG活性（SUVmax: 2.0）（图像未显示）。患者接受手术切除十二指肠病变（图2a）和周围淋巴结。十二指肠标本病理检查（图2b，苏木精-伊红染色和原始放大：×100）显示肿瘤细胞呈巢状排列，形成角蛋白珍珠。免疫组织化学显示P40阳性染色（图2c，原始放大：×100）。这些结果与十二指肠鳞状细胞癌（SCC）的诊断一致。此外，外周淋巴结转移也被证实。十二指肠鳞状细胞癌极为罕见，更有可能是原发于其他部位的鳞状细胞癌的转移，如头颈部、肺部或子宫颈。文献中只报道过偶有十二指肠原发SCC的病例。原发性十二指肠鳞状细胞癌的发病机制可能有四种：(1)异位鳞状上皮的恶性转化；(2)多能干细胞向恶性鳞状细胞分化；(3)慢性黏膜损伤所致的鳞状皮化生恶性改变；(4)腺癌转化为腺鳞癌，最终转化为鳞状细胞癌。手术可能是治疗这类疾病的基石。鉴于转移性或原发性十二指肠鳞状细胞癌的鉴别对治疗方案和预后的价值，建立正确的诊断是至关重要的。传统上，CT扫描是诊断腹部恶性肿瘤的主要成像方式，对十二指肠恶性肿瘤的检测并不特别敏感。十二指肠FDG摄取增加并不罕见，但通常是生理性的或与炎症有关。然而，我们的病例表明，当十二指肠出现局灶性异常FDG摄取时，特别是在CT图像上伴有相应的肿块样病变时，应考虑十二指肠恶性肿瘤。此外，在本病例中，全身18F-FDG PET/CT有助于区分原发性十二指肠肿瘤和转移灶，并有助于识别转移灶和临床分期。此外，原发性十二指肠鳞状细胞癌应与十二指肠腺癌、淋巴瘤、神经内分泌癌和胃肠道间质瘤鉴别。胡银婷：写作——原稿（主笔）。雷江：写作——审编（主笔）。本研究经广东省人民医院伦理委员会批准（批准文号：KY2023-020-01）。由于本报告的追溯性，我们放弃了知情同意。作者声明无利益冲突。
{"title":"Primary Duodenal Squamous Cell Carcinoma on 18F-Flurodeoxyglucose Positron Emission Tomography/Computed Tomography","authors":"Yinting Hu, Lei Jiang","doi":"10.1002/ird3.70032","DOIUrl":"https://doi.org/10.1002/ird3.70032","url":null,"abstract":"<p>A 48-year-old woman complained with repeated vomiting and pallor over 3 months. Laboratory results revealed a decrease in hemoglobin (80 g/L, reference range > 110 g/L), and no other findings (including tumor markers) were abnormal. Next, abdomen computed tomography (CT) revealed a duodenal mass, which may be malignant. To further define the nature and stage of the lesion, the patient underwent <sup>18</sup>F-flurodeoxyglucose positron emission tomography/computed tomography (<sup>18</sup>F-FDG PET/CT) scan. The maximum intensity projection (MIP) image (Figure 1a) demonstrated a high radioactivity (arrow) in the middle abdomen. The axial (Figure 1b), coronal (Figure 1c), and sagittal (Figure 1d) images of the abdomen displayed a solid lesion (arrow) with the size of 61 mm × 34 mm and a SUV<sub>max</sub> of 15.6 in the horizontal part of the duodenum. In addition, peripheral lymph nodes with the maximum size of 8 mm × 5 mm showing mild FDG activity (SUV<sub>max</sub>: 2.0) were noted (images not shown). The patient received surgical resection of the duodenal lesion (Figure 2a) and peripheral lymph nodes. Pathological examination (Figure 2b, hematoxylin–eosin staining and original magnification: ×100) from the duodenal specimen showed tumor cells arranged in nests with formation of keratin pearls. Immunohistochemistry indicated positive staining for P40 (Figure 2c, original magnification: ×100). These findings were consistent with a diagnosis of duodenal squamous cell carcinoma (SCC). Besides, peripheral lymph node metastases were also confirmed.</p><p>SCC of the duodenum is extremely rare and is more likely to represent metastasis from primary SCC originating in other sites, such as the head and neck, lungs, or cervix. Only occasional cases of primary SCC of the duodenum have been reported in the literature. There are four possible pathogenesis of primary duodenal SCC: (1) malignant transformation of heterotopic squamous epithelium; (2) pluripotential stem cells differentiate to malignant squamous cells; (3) squamous metaplasia malignant change due to chronic mucosal damage; and (4) adenocarcinoma transformed into adenosquamous carcinoma and eventually to SCC. Surgery might be the cornerstone in the management of such kind disease. Given the value of the differentiation of metastatic or primary duodenal SCC for treatment options and prognosis, establishing a correct diagnosis is essential. Traditionally, CT scanning has been the major imaging modality for diagnosing abdominal malignancies, which is not particularly sensitive for detecting duodenal malignancies. Increased FDG uptake in the duodenum is not uncommon, but it is usually physiological or inflammation-related. However, our case suggests that duodenal malignancy should be considered in the differential diagnosis when focal abnormal FDG uptake is present in the duodenum, especially when accompanied by a corresponding mass-like lesion on CT imaging. Furthermore, in this case, whole bo","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 4","pages":"315-317"},"PeriodicalIF":0.0,"publicationDate":"2025-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.70032","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144910069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pradosh Kumar Sarangi, Pratisruti Hui, Himel Mondal, Debasish Swapnesh Kumar Nayak, M. Sarthak Swarup, Ishan, Swaha Panda
Background
Plain language summary (PLS) are essential for making scientific research accessible to a broader audience. With the increasing capabilities of large language models (LLMs), there is the potential to automate the generation of PLS from complex scientific abstracts. This study assessed the performance of six LLM chatbots: ChatGPT, Claude, Copilot, Gemini, Meta AI, and Perplexity, in generating PLS from radiology research abstracts.
Methods
A total of 100 radiology abstracts were collected from PubMed. Six LLM chatbots were tasked with generating PLS for each abstract. Two expert radiologists independently evaluated the generated summaries for accuracy and readability, with their average scores being used for comparisons. Additionally, the Flesch–Kincaid (FK) grade level and Flesch reading ease score were applied to objectively assess readability.
Results
Comparisons of LLM-generated PLS revealed variations in both accuracy and readability across the models. Accuracy was highest for ChatGPT (4.94 ± 0.18) followed by Claude (4.75 ± 0.31). Readability was highest for ChatGPT (4.83 ± 0.27) followed by Perplexity (4.82 ± 0.29). The Flesch reading ease score was highest for Claude (62.53 ± 10.98) and lowest for ChatGPT (40.10 ± 11.24).
Conclusion
LLM chatbots show promise in the generation of PLS, but performance varies significantly between models in terms of both accuracy and readability. This study highlights the potential of LLMs to aid in science communication but underscores the need for careful model selection and human oversight.
通俗易懂的语言摘要（PLS）对于让更广泛的受众了解科学研究是必不可少的。随着大型语言模型（llm）功能的不断增强，从复杂的科学摘要中自动生成PLS具有潜力。本研究评估了六个LLM聊天机器人的性能：ChatGPT， Claude, Copilot, Gemini， Meta AI和Perplexity，从放射学研究摘要中生成PLS。方法从PubMed中收集放射学摘要100篇。六个LLM聊天机器人的任务是为每个摘要生成PLS。两名放射科专家独立评估了生成的摘要的准确性和可读性，并使用他们的平均分进行比较。此外，采用Flesch - kincaid （FK）年级水平和Flesch阅读轻松度评分客观评价可读性。结果llm生成的PLS的比较揭示了模型之间准确性和可读性的差异。ChatGPT的准确率最高（4.94±0.18），其次是Claude（4.75±0.31）。ChatGPT的可读性最高（4.83±0.27），其次是Perplexity（4.82±0.29）。Claude的Flesch阅读轻松评分最高（62.53±10.98），ChatGPT的最低（40.10±11.24）。LLM聊天机器人在PLS生成方面表现出很大的潜力，但在准确性和可读性方面，不同模型的性能差异很大。这项研究强调了法学硕士帮助科学传播的潜力，但也强调了谨慎选择模式和人为监督的必要性。
{"title":"Evaluating the Capability of Large Language Model Chatbots for Generating Plain Language Summaries in Radiology","authors":"Pradosh Kumar Sarangi, Pratisruti Hui, Himel Mondal, Debasish Swapnesh Kumar Nayak, M. Sarthak Swarup, Ishan, Swaha Panda","doi":"10.1002/ird3.70030","DOIUrl":"https://doi.org/10.1002/ird3.70030","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Plain language summary (PLS) are essential for making scientific research accessible to a broader audience. With the increasing capabilities of large language models (LLMs), there is the potential to automate the generation of PLS from complex scientific abstracts. This study assessed the performance of six LLM chatbots: ChatGPT, Claude, Copilot, Gemini, Meta AI, and Perplexity, in generating PLS from radiology research abstracts.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>A total of 100 radiology abstracts were collected from PubMed. Six LLM chatbots were tasked with generating PLS for each abstract. Two expert radiologists independently evaluated the generated summaries for accuracy and readability, with their average scores being used for comparisons. Additionally, the Flesch–Kincaid (FK) grade level and Flesch reading ease score were applied to objectively assess readability.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Comparisons of LLM-generated PLS revealed variations in both accuracy and readability across the models. Accuracy was highest for ChatGPT (4.94 ± 0.18) followed by Claude (4.75 ± 0.31). Readability was highest for ChatGPT (4.83 ± 0.27) followed by Perplexity (4.82 ± 0.29). The Flesch reading ease score was highest for Claude (62.53 ± 10.98) and lowest for ChatGPT (40.10 ± 11.24).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>LLM chatbots show promise in the generation of PLS, but performance varies significantly between models in terms of both accuracy and readability. This study highlights the potential of LLMs to aid in science communication but underscores the need for careful model selection and human oversight.</p>\u0000 </section>\u0000 </div>","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 4","pages":"289-294"},"PeriodicalIF":0.0,"publicationDate":"2025-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.70030","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144910059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
<p>Rapid advancements in artificial intelligence (AI) technology have resulted in the emergence of state-of-the-art large language models (LLMs) such as ChatGPT and GPT-4. Originally designed for natural language processing, these models are now being applied to increasingly broader domains, particularly in medical image processing [<span>1</span>]. Concurrently, the rise of such models has introduced innovative tools into medical image processing and diagnosis, profoundly shaping the future trajectory of this field. These tools not only enhance diagnostic accuracy and efficiency, but also alleviate substantial repetitive workloads for clinicians [<span>2</span>]. To address the critical needs for transparency, reproducibility, and clinical reliability in biomedical AI research, Gallifant et al. [<span>3</span>] proposed Transparent Reporting of a prediction model for Individual Prognosis or Diagnosis-LLM, an extension to the Transparent Reporting of a prediction model for Individual Prognosis or Diagnosis + artificial intelligence statement. In a domain-specific innovation, Liu et al. [<span>4</span>] developed Radiology-GPT through training and fine-tuning on a massive radiology knowledge corpus. In comparison with general-purpose LLMs, this specialized model demonstrated superior performance, validating the feasibility of creating localized generative models for specific medical specialties. Complementing this work, Yuan et al. [<span>5</span>] systematically evaluated the capabilities of the advanced multimodal model ChatGPT-4V for diagnosing brain tumors on 7T magnetic resonance imaging (MRI) data. Their study established a benchmark framework for ultra-high field imaging AI applications, propelling the progress of precision medicine and intelligent diagnostics.</p><p>This special issue on ChatGPT and GPT-4 includes four recent studies that cover applications of different LLMs, such as Meta LLaMA 3.1, ChatGPT, Claude, Gemini, and LLaVA, in various medical scenarios. Yuan et al. [<span>6</span>] deeply explored the application of the Transformer architecture in natural language processing of chest X-ray reports, finding that this architecture holds significant potential in medical text processing. However, computational efficiency and ethical compliance require optimization, and future integration with multimodal data is needed to enhance diagnostic accuracy. Lotfian et al. [<span>7</span>] evaluated the performance of the open-source model LLaMA 3.1 in thoracic imaging diagnostics using 126 multiple-choice questions. The model achieved an overall accuracy of 61.1%, with excellent performance in intensive care (90%) and terminology recognition (83.3%) but weaker results in basic imaging (40%) and lung cancer diagnosis (33.3%). This assessment demonstrates the potential of open-source models like LLaMA 3.1 while highlighting the need for domain-specific fine-tuning to improve stability as well as the need to balance open-source flexibility wit
人工智能（AI）技术的快速发展导致了ChatGPT和GPT-4等最先进的大型语言模型（llm）的出现。这些模型最初是为自然语言处理而设计的，现在正被应用于越来越广泛的领域，特别是在医学图像处理领域。同时，这些模型的兴起为医学图像处理和诊断引入了创新工具，深刻地塑造了该领域的未来轨迹。这些工具不仅提高了诊断的准确性和效率，还减轻了临床医生的大量重复性工作量。为了解决生物医学人工智能研究中对透明度、可重复性和临床可靠性的关键需求，Gallifant等人提出了个体预后或诊断预测模型的透明报告- llm，这是对个体预后或诊断预测模型的透明报告+人工智能声明的扩展。在特定领域的创新中，Liu等人通过对大量放射学知识语料库进行培训和微调，开发了radiology - gpt。与通用llm相比，该专业模型表现出优越的性能，验证了为特定医学专业创建本地化生成模型的可行性。Yuan等人（[5]）系统地评估了先进的多模态模型ChatGPT-4V在7T磁共振成像（MRI）数据上诊断脑肿瘤的能力。他们的研究为超高场成像人工智能应用建立了基准框架，推动了精准医疗和智能诊断的进步。本期关于ChatGPT和GPT-4的特刊包括四项最新研究，涵盖了Meta LLaMA 3.1、ChatGPT、Claude、Gemini和LLaVA等不同llm在各种医疗场景中的应用。Yuan等人[6]深入探索了Transformer架构在胸部x光报告自然语言处理中的应用，发现该架构在医学文本处理中具有巨大的潜力。然而，计算效率和道德合规需要优化，未来需要与多模态数据集成以提高诊断准确性。Lotfian等人用126道选择题评估了开源模型LLaMA 3.1在胸部影像诊断中的性能。该模型的总体准确率为61.1%，在重症监护（90%）和术语识别（83.3%）方面表现优异，但在基础影像学（40%）和肺癌诊断（33.3%）方面表现较差。该评估显示了像LLaMA 3.1这样的开源模型的潜力，同时强调了在临床应用中需要对特定领域进行微调以提高稳定性，以及需要平衡开源灵活性和专有模型可靠性。Sarangi等人比较了六种模型，包括ChatGPT、Claude和Gemini，评估了它们为100篇放射学摘要生成的简单语言摘要的准确性和可读性（Flesch-Kincaid指标）。他们发现ChatGPT的准确率最高，而Claude在可读性方面表现最好。然而，手工审查是必要的，以确保准确性和避免误解或遗漏的技术术语。除了关注这些法学硕士的表现外，我们还关心医疗保健提供者对他们的态度。Lecler等人认为，这些llm不会取代放射科医生，而是作为辅助工具来提高诊断效率和准确性，需要两者之间的协同工作。He et al.[10]通过访谈调查发现，67.4%-94.3%的受访者认为AI可以提高临床准确性，64%的受访者认为AI可以提高效率。他们还发现，71.1%的人认为人工智能不会对工作保障产生重大影响，由于人工智能的帮助，一些居民更倾向于选择放射学作为职业。只有55.6%的受访者熟悉人工智能，而超过80%的受访者支持将人工智能纳入住院医师培训课程。同时，Perera et al. b[11]主张将ChatGPT整合到放射学培训中，培养医生与AI协作的能力，同时加强批判性思维。为了促进放射科医师对LLM的采用，Kim等人证明了10分钟的结构化LLM教程显著提高了放射科住院医师在脑MRI鉴别诊断方面的表现和信心。这种低成本的教育干预措施可以作为促进法学硕士在医学中安全有效应用的关键策略。ChatGPT和GPT-4等llm对医学成像的发展产生了深远的影响。 特别是在大数据的背景下，这些模型和技术正在推动医学成像从“经验驱动”模式向“数据驱动”模式的转变。以ChatGPT为代表的llm将迎来医学影像发展的新阶段，并将其提升到新的高度。博高：审稿编辑（主笔）。欧卫华：写作——原稿（主笔）。作者没有什么可报告的。作者没有什么可报告的。本文属于特刊(SI) - ChatGPT/GPT-4在放射学中的应用。作为该杂志的执行总编辑和SI的客座编辑，为了尽量减少偏见，Bo Gao教授被排除在与本文发表相关的所有编辑决策之外。作为SI的客座编辑，为了尽量减少偏见，欧卫华教授也被排除在与本文发表与否相关的所有编辑决策之外。
{"title":"Applications and Implications of ChatGPT and GPT-4 in Radiology","authors":"Bo Gao, Weihua Ou","doi":"10.1002/ird3.70031","DOIUrl":"https://doi.org/10.1002/ird3.70031","url":null,"abstract":"<p>Rapid advancements in artificial intelligence (AI) technology have resulted in the emergence of state-of-the-art large language models (LLMs) such as ChatGPT and GPT-4. Originally designed for natural language processing, these models are now being applied to increasingly broader domains, particularly in medical image processing [<span>1</span>]. Concurrently, the rise of such models has introduced innovative tools into medical image processing and diagnosis, profoundly shaping the future trajectory of this field. These tools not only enhance diagnostic accuracy and efficiency, but also alleviate substantial repetitive workloads for clinicians [<span>2</span>]. To address the critical needs for transparency, reproducibility, and clinical reliability in biomedical AI research, Gallifant et al. [<span>3</span>] proposed Transparent Reporting of a prediction model for Individual Prognosis or Diagnosis-LLM, an extension to the Transparent Reporting of a prediction model for Individual Prognosis or Diagnosis + artificial intelligence statement. In a domain-specific innovation, Liu et al. [<span>4</span>] developed Radiology-GPT through training and fine-tuning on a massive radiology knowledge corpus. In comparison with general-purpose LLMs, this specialized model demonstrated superior performance, validating the feasibility of creating localized generative models for specific medical specialties. Complementing this work, Yuan et al. [<span>5</span>] systematically evaluated the capabilities of the advanced multimodal model ChatGPT-4V for diagnosing brain tumors on 7T magnetic resonance imaging (MRI) data. Their study established a benchmark framework for ultra-high field imaging AI applications, propelling the progress of precision medicine and intelligent diagnostics.</p><p>This special issue on ChatGPT and GPT-4 includes four recent studies that cover applications of different LLMs, such as Meta LLaMA 3.1, ChatGPT, Claude, Gemini, and LLaVA, in various medical scenarios. Yuan et al. [<span>6</span>] deeply explored the application of the Transformer architecture in natural language processing of chest X-ray reports, finding that this architecture holds significant potential in medical text processing. However, computational efficiency and ethical compliance require optimization, and future integration with multimodal data is needed to enhance diagnostic accuracy. Lotfian et al. [<span>7</span>] evaluated the performance of the open-source model LLaMA 3.1 in thoracic imaging diagnostics using 126 multiple-choice questions. The model achieved an overall accuracy of 61.1%, with excellent performance in intensive care (90%) and terminology recognition (83.3%) but weaker results in basic imaging (40%) and lung cancer diagnosis (33.3%). This assessment demonstrates the potential of open-source models like LLaMA 3.1 while highlighting the need for domain-specific fine-tuning to improve stability as well as the need to balance open-source flexibility wit","PeriodicalId":73508,"journal":{"name":"iRadiology","volume":"3 4","pages":"259-260"},"PeriodicalIF":0.0,"publicationDate":"2025-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ird3.70031","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144910324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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