Meta-Radiology最新文献

{"title":"Advances in neuroimaging applications of quantitative susceptibility mapping","authors":"Shuxin Ma ,&nbsp;Wencan Fu ,&nbsp;Chao Chai ,&nbsp;Huiying Wang ,&nbsp;Ke Lv ,&nbsp;Chenxi Zhao ,&nbsp;E. Mark Haacke ,&nbsp;Sagar Buch ,&nbsp;Shuang Xia","doi":"10.1016/j.metrad.2025.100148","DOIUrl":"10.1016/j.metrad.2025.100148","url":null,"abstract":"<div><div>This review article delves into the advancements of quantitative susceptibility mapping (QSM) in neuroimaging, highlighting its utility in detecting and quantifying magnetic susceptibility differences in tissues, particularly for paramagnetic substances like iron and diamagnetic substances such as calcifications in the brain. QSM has revolutionized the diagnosis and monitoring of neurodegenerative diseases by enabling the precise measurement of brain iron deposition and blood oxygen saturation. The review is partitioned into three sections. The first section underscores QSM's role in clinical applications related to microhemorrhages, cerebral amyloidosis, intracranial hematomas, and cerebrovascular malformations. The second section focuses on QSM's application in mapping iron content in neurodegenerative diseases such as Parkinson's disease and Alzheimer's disease. The final section discusses QSM's potential in assessing stroke by measuring oxygen saturation. The article also outlines the basic theory and development of QSM, emphasizing the importance of echo time selection for accurate QSM results. Challenges in clinical applications and future directions, including the integration of AI technology for image reconstruction and data analysis, are also discussed. QSM's ability to differentiate between microbleeds and calcifications, assess dynamic susceptibility changes in intracranial hematomas, and guide thrombolytic strategies in acute cerebrovascular disease is highlighted. The review concludes by emphasizing the need for further optimization of QSM algorithms and the expansion of its applications in biomedical imaging.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 3","pages":"Article 100148"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cardiac ECV mapping: Underlying concepts and clinical applications","authors":"Guo-Jun Zhu ,&nbsp;Simran Qureshi ,&nbsp;Ward Hedges ,&nbsp;Chong-Wen Wu ,&nbsp;Lian-Ming Wu","doi":"10.1016/j.metrad.2025.100168","DOIUrl":"10.1016/j.metrad.2025.100168","url":null,"abstract":"<div><div>Myocardial Extracellular volume fraction (ECV) mapping, based on cardiac magnetic resonance (CMR), is a crucial technique for assessing myocardial histological changes by evaluating extracellular matrix expansion. In recent years, cardiac ECV mapping has gained significant attention in both basic research and clinical settings, particularly for its role in myocardial fibrosis and other cardiovascular diseases. This review explores the measurement of ECV mapping, its diagnostic and prognostic value in ischemic and non-ischemic cardiovascular diseases, and emerging advancements in ECV mapping techniques.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 3","pages":"Article 100168"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent analysis of chest X-ray based on multi-modal instruction tuning","authors":"Junjie Yao ,&nbsp;Junhao Wang ,&nbsp;Zhenxiang Xiao ,&nbsp;Xinlin Hao ,&nbsp;Xi Jiang","doi":"10.1016/j.metrad.2025.100172","DOIUrl":"10.1016/j.metrad.2025.100172","url":null,"abstract":"<div><div>Chest X-ray plays a crucial role in the screening and diagnosis of chest diseases. Due to the complexity of pathological manifestations and limitations of radiologists' experience, the accuracy and efficiency of diagnosing chest diseases need to be further improved. In recent years, deep learning has made significant progress in chest X-ray image analysis, while existing methods mainly rely on uni-modal visual information, overlooking the prior knowledge related to disease category descriptions embedded in medical text data, making it challenging to fully understand the deep semantics of chest X-ray images. To address these challenges, inspired by the Instruction-ViT model, we adopt instruction tuning techniques to integrate medical textual information into the fine-tuning process of the visual model. Furthermore, a contrastive learning loss is employed to align textual and visual features, thereby enhancing the model's capacity to understand and differentiate complex pathological patterns. Experimental results demonstrate that the model integrating medical text information outperforms uni-modal models in various evaluation metrics, confirming that with instruction tuning, our model can effectively utilize medical text as prior knowledge to improve the performance of visual models in chest disease diagnosis. Furthermore, we conduct an interpretability analysis of the model's decision-making process, revealing that the regions attended to by the model highly correspond to the radiographic manifestations of different diseases, demonstrating the model's interpretability to a certain degree.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 3","pages":"Article 100172"},"PeriodicalIF":0.0,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144904346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dopamine receptor- and noradrenaline transporter-related disruptions are associated with depression and cognitive performance in COVID-19 survivors","authors":"Yao Wang ,&nbsp;Ziwei Yang ,&nbsp;Xiao Liang ,&nbsp;Lin Wu ,&nbsp;Chengsi Wu ,&nbsp;Jiankun Dai ,&nbsp;Yuan Cao ,&nbsp;Xianjun Zeng ,&nbsp;Meng Li ,&nbsp;Fuqing Zhou","doi":"10.1016/j.metrad.2025.100170","DOIUrl":"10.1016/j.metrad.2025.100170","url":null,"abstract":"<div><h3>Purpose</h3><div>This study aims to explore the relationships between neural activity, neurovascular coupling (NVC), and neurotransmitter receptors, and to investigate their association with emotion and cognition in COVID-19 survivors.</div></div><div><h3>Materials and methods</h3><div>A total of 42 COVID-19 survivors and 30 matched healthy controls (HCs) were recruited. Regional homogeneity (ReHo) and functional connectivity strength (FCS) were calculated -to assess local and global neural activity, respectively. Cerebral blood flow (CBF) was characterized as brain perfusion. Regional NVC was evaluated using CBF/ReHo and CBF/FCS ratios at the voxel level. Neurotransmitter receptor maps were derived from the JuSpace toolbox, which integrates positron emission tomography (PET) and single-photon emission computed tomography (SPECT) data from healthy populations. These maps included 16 receptor/transporters, such as dopamine, serotonin, norepinephrine and glutamate receptors, among others. Spatial correlations between neural activity, NVC and neurotransmitter receptor maps were subsequently analyzed in COVID-19 survivors.</div></div><div><h3>Results</h3><div>Whether examining neural activity or NVC, COVID-19 survivors primariily exhibiteddecreased ReHo or CBF/ReHo pattern compared to HC. Moreover, the neurotransmitter receptor distributions showed strong associations exclusively with local neural activity (e.g., ReHo) and NVC (e.g., CBF/ReHo) in COVID-19 survivors. Specifically, the spatial pattern of ReHo correlated with dopamine receptors, glutamate receptors, and noradrenaline transporters, but the CBF/ReHo correlated only with dopamine receptors. Importantly, the correlation coefficients between ReHo and dopamine receptors or noradrenaline transporters were associated with cognitive performance in COVID-19 survivors. Conversely, the correlation coefficients between CBF/ReHo and dopamine were correlated with depression in COVID-19 survivors.</div></div><div><h3>Conclusion</h3><div>COVID-19 survivors exhibit disruptions in local neural activity and NVC related to dopamine receptors and noradrenaline transporters. These alterations are associated with depression and cognitive impairment, suggesting a potential molecular basis for impaired neural and neurovascular function.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 3","pages":"Article 100170"},"PeriodicalIF":0.0,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144841975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fast-RF-Shimming: Accelerate RF shimming in 7T MRI using deep learning","authors":"Zhengyi Lu ,&nbsp;Hao Liang ,&nbsp;Ming Lu ,&nbsp;Xiao Wang ,&nbsp;Xinqiang Yan ,&nbsp;Yuankai Huo","doi":"10.1016/j.metrad.2025.100166","DOIUrl":"10.1016/j.metrad.2025.100166","url":null,"abstract":"<div><div>Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) offers an elevated signal-to-noise ratio (SNR), enabling exceptionally high spatial resolution that benefits both clinical diagnostics and advanced research. However, the jump to higher fields introduces complications, particularly transmit radiofrequency (RF) field <span><math><mrow><mo>(</mo><mrow><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></mrow><mo>)</mo></mrow></math></span> inhomogeneities, manifesting as uneven flip angles and image intensity irregularities. These artifacts can degrade image quality and impede broader clinical adoption. Traditional RF shimming methods, such as Magnitude Least Squares (MLS) optimization, effectively mitigate <span><math><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></math></span> inhomogeneity, but remain time-consuming. Recent machine learning approaches, including RF Shim Prediction by Iteratively Projected Ridge Regression and other deep learning architectures, suggest alternative pathways. Although these approaches show promise, challenges such as extensive training periods, limited network complexity, and practical data requirements persist. In this paper, we introduce a holistic learning-based framework called Fast-RF-Shimming, which achieves a 5000 ​× ​speed-up compared to the traditional MLS method. In the initial phase, we employ random-initialized Adaptive Moment Estimation (Adam) to derive the desired reference shimming weights from multi-channel <span><math><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></math></span> fields. Next, we train a Residual Network (ResNet) to map <span><math><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></math></span> fields directly to the ultimate RF shimming outputs, incorporating the confidence parameter into its loss function. Finally, we design Non-uniformity Field Detector (NFD), an optional post-processing step, to ensure the extreme non-uniform outcomes are identified. Comparative evaluations with standard MLS optimization underscore notable gains in both processing speed and predictive accuracy, which indicates that our technique shows a promising solution for addressing persistent inhomogeneity challenges.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 3","pages":"Article 100166"},"PeriodicalIF":0.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144757832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigating the shared genetic architecture between Parkinson's disease and magnetic susceptibility of the substantia nigra","authors":"Jilian Fu","doi":"10.1016/j.metrad.2025.100157","DOIUrl":"10.1016/j.metrad.2025.100157","url":null,"abstract":"<div><div>Parkinson's disease (PD) is a common and progressively deteriorating neurodegenerative disorder thatprofoundly affects millions of individuals worldwide. Neuroimaging research has consistently demonstrated abnormalities in quantitative susceptibility mapping (QSM) within the substantia nigra (SN) that are associated with Parkinson's disease. However, the genetic underpinnings shared between Parkinson's disease and QSM of substantia nigra remain inadequately understood. Here, genetic pleiotropic analyses were conducted to explore genetic overlap at global, local, and variant levels byleveraging summary statistics from the largest genome-wide association studies for PD (N ​= ​501,348) and QSM of SN (N ​= ​35,273). We observed a significant global genetic correlation between PD and QSM of SN (<em>rg</em> ​= ​0.096, <em>p</em> ​= ​0.032 with LDSC; <em>rg</em> ​= ​0.097, <em>p</em> ​= ​0.048 with SumHer). Local-level analysis identified six genomic regions showing shared associations with the two traits. At the variant level, we found 12 genetic variants shared by PD and QSM of SN. These shared risk variants were mapped to 33 unique genes. We analyzed drug-gene interactions based on these shared genes and their associations with PD medications. These findings elucidate the genetic interplay between SN magnetic susceptibility and PD pathogenesis, revealing potential biomarker discovery and targets for therapeutic development.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 3","pages":"Article 100157"},"PeriodicalIF":0.0,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144886605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radiology-GPT: A large language model for radiology","authors":"Zhengliang Liu ,&nbsp;Yiwei Li ,&nbsp;Peng Shu ,&nbsp;Aoxiao Zhong ,&nbsp;Hanqi Jiang ,&nbsp;Yi Pan ,&nbsp;Longtao Yang ,&nbsp;Chao Ju ,&nbsp;Zihao Wu ,&nbsp;Chong Ma ,&nbsp;Cheng Chen ,&nbsp;Sekeun Kim ,&nbsp;Haixing Dai ,&nbsp;Lin Zhao ,&nbsp;Lichao Sun ,&nbsp;Dajiang Zhu ,&nbsp;Jun Liu ,&nbsp;Wei Liu ,&nbsp;Dinggang Shen ,&nbsp;Quanzheng Li ,&nbsp;Xiang Li","doi":"10.1016/j.metrad.2025.100153","DOIUrl":"10.1016/j.metrad.2025.100153","url":null,"abstract":"<div><div>We introduce Radiology-GPT, a large language model for radiology. Using an instruction tuning approach on an extensive dataset of radiology domain knowledge, Radiology-GPT demonstrates superior performance compared to general language models such as StableLM, Dolly, and LLaMA. It exhibits significant versatility in radiological diagnosis, research, and communication. This work serves as a catalyst for future developments in clinical NLP. The successful implementation of Radiology-GPT is indicative of the potential of localizing generative large language models, specifically tailored for distinctive medical specialties, while ensuring adherence to privacy standards such as HIPAA. The prospect of developing individualized, large-scale language models that cater to specific needs of various hospitals presents a promising direction. The fusion of conversational competence and domain-specific knowledge in these models is set to foster future development in healthcare AI. A demo of Radiology-GPT is available at <span><span>https://huggingface.co/spaces/allen-eric/radiology-gpt</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 2","pages":"Article 100153"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of deep learning on automated breast ultrasound: Current developments, challenges, and opportunities","authors":"Ruixin Wang ,&nbsp;Zhiyuan Wang ,&nbsp;Yuanming Xiao ,&nbsp;Xiaohui Liu ,&nbsp;Guoping Tan ,&nbsp;Jun Liu","doi":"10.1016/j.metrad.2025.100138","DOIUrl":"10.1016/j.metrad.2025.100138","url":null,"abstract":"<div><div>Breast cancer is a major disease threatening the health of women worldwide. The advent of automated breast ultrasound (ABUS) has provided new possibilities for the early screening and diagnosis of breast cancer. Concurrently, artificial intelligence (AI)-based computer-aided diagnosis (CAD) systems, driven by deep learning (DL), have advanced significantly over the past decade. Unlike traditional handheld ultrasound (HHUS), ABUS enables the separation of scanning and diagnosis, increasing the demand for CAD systems that hold significant clinical value. In recent years, DL has become a dominant force in AI development, playing a crucial role in CAD for across various medical imaging modalities. However, despite its prominence in AI-driven medical image analysis, a comprehensive review of its applications in ABUS is still lacking. This paper provides a detailed analysis of the latest advancements, existing challenges, and future research opportunities in this rapidly evolving field.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 2","pages":"Article 100138"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144279891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-task glioma segmentation and IDH mutation and 1p19q codeletion classification via a deep learning model on multimodal MRI","authors":"Erin Beate Bjørkeli ,&nbsp;Morteza Esmaeili","doi":"10.1016/j.metrad.2025.100152","DOIUrl":"10.1016/j.metrad.2025.100152","url":null,"abstract":"<div><h3>Objectives</h3><div>To develop a deep learning model for simultaneous segmentation of glioma lesions and classification of IDH mutation and 1p/19q codeletion status using multimodal MRI.</div></div><div><h3>Methods</h3><div>We employed a CNN model with Encoder-Decoder architecture for segmentation, followed by fully connected layers for classification. The model was trained and validated using the BraTS 2020 dataset (132 examinations with known molecular status, split 80/20). Four MRI sequences iamges (T1, T1ce, T2, FLAIR) were used for analysis. Segmentation performance was evaluated using mean Dice Score (mDS) and mean Intersection over Union (mIoU). Classification was assessed using accuracy, sensitivity, and specificity.</div></div><div><h3>Results</h3><div>The model achieved the best segmentation performance with all four modalities (mDS validation ​= ​0.73, mIoU validation ​= ​0.62). Among single modalities, FLAIR performed best (mDS validation ​= ​0.56, mIoU validation ​= ​0.44). For classification, the combined four modalities achieved an overall accuracy of 0.98. However, classification precision for IDH and 1p19q was potentially limited by class imbalance.</div></div><div><h3>Conclusion</h3><div>Our CNN-based Encoder-Decoder model demonstrates the benefit of multimodal MRI for accurate glioma segmentation and shows promising results for molecular subtype classification. Future work will focus on addressing class imbalance and exploring feature integration to enhance classification performance.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 2","pages":"Article 100152"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MRI advances on structural and functional changes in limbic system with premenstrual syndrome","authors":"Shan-Shan Li ,&nbsp;Gao-Xiong Duan ,&nbsp;De-Mao Deng","doi":"10.1016/j.metrad.2025.100147","DOIUrl":"10.1016/j.metrad.2025.100147","url":null,"abstract":"<div><div>Premenstrual Syndrome (PMS) is a unique emotional disorder in women, characterized by a series of cyclical physical, emotional, behavioral, and cognitive symptoms that occur during the luteal phase of the menstrual cycle, often accompanied by significant functional impairment. Premenstrual Dysphoric Disorder (PMDD) is a severe form of PMS and is classified as a subtype of depressive disorders in the fifth edition of the <em>Diagnostic and Statistical Manual of Mental Disorders</em> (<em>DSM-5)</em>. Neuroimaging studies have revealed structural and functional abnormalities in the limbic system of PMS/PMDD patients, particularly in areas such as the amygdala, hypothalamus, and hippocampus, which are closely related to clinical symptoms. These abnormalities may represent one of the central nervous mechanisms underlying PMS/PMDD. This review focuses on the structural and functional changes in the limbic system of PMS/PMDD patients as revealed by MRI, and summarizes the relevant research progress.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 2","pages":"Article 100147"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144269987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}