Meta-Radiology最新文献

英文中文

MRI-based radiomics for assisting diagnosis, assessment, and treatment of brain metastases in lung cancer 基于mri的放射组学用于肺癌脑转移的辅助诊断、评估和治疗

Meta-Radiology

Pub Date : 2025-07-29 DOI: 10.1016/j.metrad.2025.100169

Lianyu Sui , Huan Meng , Lihong Xing , Yu Zhang , Jianing Wang , Xiaoping Yin

Brain metastases (BMs) are the most prevalent intracranial malignancies. Brain metastases from lung cancer (LC) are particularly common in clinical practice and are strongly associated with poor prognosis and high mortality. Consequently, the precise diagnosis and treatment of BMs are crucial for improving clinical outcomes. Diagnosis primarily relies on radiological data and clinical history. Magnetic resonance imaging (MRI) is widely regarded as the primary imaging technique for diagnosing BMs and assessing prognosis due to its exceptional sensitivity and specificity. Radiomics, a field increasingly empowered by artificial intelligence (AI), is used to assist healthcare professionals in conducting in-depth analyses of medical images, thereby enhancing diagnostic accuracy and personalizing treatment. It utilizes high-throughput feature extraction techniques to derive numerous quantitative imaging characteristics from medical images, which exhibit strong correlations with tumor biology and clinical outcomes. Recent research has demonstrated that MRI-based radiomics applications show great potential at improving the accuracy and efficiency of clinicians in BMs diagnosis, classification, treatment, and prognosis prediction. Radiomics methods can precisely characterize the internal structure and heterogeneity of tumors, thereby providing clinicians with comprehensive decision-support information.The review comprehensively summarizes the latest applications of MRI-based radiomics in BMs, focusing on data segmentation processing and model establishment in order to provide insights into current research in this emerging field. For LC BMs, integrating multi-center, high-quality standardized data with deep learning algorithms and MRI radiomics is crucial for clinical application.

脑转移瘤是最常见的颅内恶性肿瘤。肺癌脑转移在临床实践中尤为常见，且与预后差和高死亡率密切相关。因此，脑转移的准确诊断和治疗对于改善临床结果至关重要。诊断主要依靠放射学资料和临床病史。磁共振成像（MRI）由于其特殊的敏感性和特异性，被广泛认为是诊断脑转移和评估预后的主要成像技术。放射组学是人工智能（AI）日益增强的一个领域，用于协助医疗保健专业人员对医学图像进行深入分析，从而提高诊断准确性和个性化治疗。它利用高通量特征提取技术从医学图像中获得大量定量成像特征，这些特征与肿瘤生物学和临床结果具有很强的相关性。最近的研究表明，基于mri的放射组学应用在提高临床医生在脑转移诊断、分类、治疗和预后预测方面的准确性和效率方面具有巨大的潜力。放射组学方法可以精确表征肿瘤的内部结构和异质性，从而为临床医生提供全面的决策支持信息。本文综述了基于mri的放射组学在脑转移中的最新应用，重点介绍了数据分割处理和模型建立，以期对这一新兴领域的研究现状有所了解。对于LC脑转移来说，将多中心、高质量的标准化数据与深度学习算法和MRI放射组学相结合对于临床应用至关重要。

{"title":"MRI-based radiomics for assisting diagnosis, assessment, and treatment of brain metastases in lung cancer","authors":"Lianyu Sui , Huan Meng , Lihong Xing , Yu Zhang , Jianing Wang , Xiaoping Yin","doi":"10.1016/j.metrad.2025.100169","DOIUrl":"10.1016/j.metrad.2025.100169","url":null,"abstract":"<div><div>Brain metastases (BMs) are the most prevalent intracranial malignancies. Brain metastases from lung cancer (LC) are particularly common in clinical practice and are strongly associated with poor prognosis and high mortality. Consequently, the precise diagnosis and treatment of BMs are crucial for improving clinical outcomes. Diagnosis primarily relies on radiological data and clinical history. Magnetic resonance imaging (MRI) is widely regarded as the primary imaging technique for diagnosing BMs and assessing prognosis due to its exceptional sensitivity and specificity. Radiomics, a field increasingly empowered by artificial intelligence (AI), is used to assist healthcare professionals in conducting in-depth analyses of medical images, thereby enhancing diagnostic accuracy and personalizing treatment. It utilizes high-throughput feature extraction techniques to derive numerous quantitative imaging characteristics from medical images, which exhibit strong correlations with tumor biology and clinical outcomes. Recent research has demonstrated that MRI-based radiomics applications show great potential at improving the accuracy and efficiency of clinicians in BMs diagnosis, classification, treatment, and prognosis prediction. Radiomics methods can precisely characterize the internal structure and heterogeneity of tumors, thereby providing clinicians with comprehensive decision-support information.The review comprehensively summarizes the latest applications of MRI-based radiomics in BMs, focusing on data segmentation processing and model establishment in order to provide insights into current research in this emerging field. For LC BMs, integrating multi-center, high-quality standardized data with deep learning algorithms and MRI radiomics is crucial for clinical application.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 4","pages":"Article 100169"},"PeriodicalIF":0.0,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145475893","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}

引用次数: 0

Fast-RF-Shimming: Accelerate RF shimming in 7T MRI using deep learning 快速射频振荡：使用深度学习加速7T MRI中的射频振荡

Meta-Radiology

Pub Date : 2025-07-08 DOI: 10.1016/j.metrad.2025.100166

Zhengyi Lu , Hao Liang , Ming Lu , Xiao Wang , Xinqiang Yan , Yuankai Huo

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

(B_{1}^{+})

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

B_{1}^{+}

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

B_{1}^{+}

fields. Next, we train a Residual Network (ResNet) to map

B_{1}^{+}

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.

超高场（UHF）磁共振成像（MRI）提供了更高的信噪比（SNR），实现了极高的空间分辨率，有利于临床诊断和高级研究。然而，向更高场的跳跃带来了复杂性，特别是发射射频（RF）场（B1+）的不均匀性，表现为不均匀的翻转角度和图像强度不规则。这些伪影会降低图像质量，阻碍临床应用。传统的射频振荡方法，如最小二乘（MLS）优化，可以有效地缓解B1+非均匀性，但仍然耗时。最近的机器学习方法，包括迭代投影岭回归的RF Shim预测和其他深度学习架构，提出了替代途径。尽管这些方法显示出了希望，但挑战仍然存在，例如长时间的训练、有限的网络复杂性和实际数据需求。在本文中，我们引入了一种称为Fast-RF-Shimming的基于整体学习的框架，与传统的MLS方法相比，该框架的速度提高了5000倍。在初始阶段，我们采用随机初始化的自适应矩估计（Adam）从多通道B1+场中获得所需的参考振荡权值。接下来，我们训练一个残差网络（ResNet）将B1+场直接映射到最终的射频振荡输出，并将置信度参数纳入其损失函数。最后，我们设计了非均匀场检测器（NFD），这是一个可选的后处理步骤，以确保识别极端的非均匀结果。与标准MLS优化的比较评估强调了处理速度和预测精度的显着提高，这表明我们的技术在解决持续非同质性挑战方面显示了一个有希望的解决方案。

{"title":"Fast-RF-Shimming: Accelerate RF shimming in 7T MRI using deep learning","authors":"Zhengyi Lu , Hao Liang , Ming Lu , Xiao Wang , Xinqiang Yan , 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}

引用次数: 0

Investigating the shared genetic architecture between Parkinson's disease and magnetic susceptibility of the substantia nigra 研究帕金森病与黑质磁化率之间的共同遗传结构

Meta-Radiology

Pub Date : 2025-06-12 DOI: 10.1016/j.metrad.2025.100157

Jilian Fu

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 (rg = 0.096, p = 0.032 with LDSC; rg = 0.097, p = 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.

帕金森病（PD）是一种常见且逐渐恶化的神经退行性疾病，严重影响着全世界数百万人。神经影像学研究一致表明，黑质（SN）内的定量易感性图谱（QSM）异常与帕金森病有关。然而，帕金森病和黑质QSM之间的遗传基础仍然没有得到充分的了解。本研究利用PD （N = 501,348）和SN QSM （N = 35273）的最大全基因组关联研究的汇总统计数据，进行遗传多效性分析，以探索全局、局部和变异水平上的遗传重叠。我们观察到SN的PD与QSM在全球范围内具有显著的遗传相关性（rg = 0.096，与LDSC相比p = 0.032; rg = 0.097，与SumHer相比p = 0.048）。局部水平的分析确定了6个基因组区域，显示了与这两种特征的共同关联。在变异水平上，我们发现了SN的PD和QSM共有的12个遗传变异。这些共有的风险变异被映射到33个独特的基因上。我们分析了基于这些共享基因的药物-基因相互作用及其与PD药物的关联。这些发现阐明了SN磁化率与PD发病机制之间的遗传相互作用，揭示了潜在的生物标志物发现和治疗开发的靶点。

{"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}

引用次数: 0

Radiology-GPT: A large language model for radiology 放射学- gpt：用于放射学的大型语言模型

Meta-Radiology

Pub Date : 2025-06-01 DOI: 10.1016/j.metrad.2025.100153

Zhengliang Liu , Yiwei Li , Peng Shu , Aoxiao Zhong , Hanqi Jiang , Yi Pan , Longtao Yang , Chao Ju , Zihao Wu , Chong Ma , Cheng Chen , Sekeun Kim , Haixing Dai , Lin Zhao , Lichao Sun , Dajiang Zhu , Jun Liu , Wei Liu , Dinggang Shen , Quanzheng Li , Xiang Li

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 https://huggingface.co/spaces/allen-eric/radiology-gpt.

我们介绍了放射学- gpt，一个大型放射学语言模型。在放射学领域知识的广泛数据集上使用指令调优方法，与一般语言模型（如StableLM， Dolly和LLaMA）相比，radiology - gpt表现出优越的性能。它在放射学诊断、研究和交流方面表现出显著的多功能性。这项工作为临床NLP的未来发展提供了催化剂。放射学- gpt的成功实施表明，在确保遵守HIPAA等隐私标准的同时，专门为独特的医学专业量身定制的生成大型语言模型具有本地化的潜力。开发个性化的、大规模的语言模型，以满足各种医院的特定需求，是一个很有前景的方向。在这些模型中，会话能力和特定领域知识的融合将促进医疗保健人工智能的未来发展。放射学-gpt的演示可在https://huggingface.co/spaces/allen-eric/radiology-gpt上获得。

{"title":"Radiology-GPT: A large language model for radiology","authors":"Zhengliang Liu , Yiwei Li , Peng Shu , Aoxiao Zhong , Hanqi Jiang , Yi Pan , Longtao Yang , Chao Ju , Zihao Wu , Chong Ma , Cheng Chen , Sekeun Kim , Haixing Dai , Lin Zhao , Lichao Sun , Dajiang Zhu , Jun Liu , Wei Liu , Dinggang Shen , Quanzheng Li , 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}

引用次数: 0

Application of deep learning on automated breast ultrasound: Current developments, challenges, and opportunities 深度学习在自动乳腺超声中的应用：当前的发展、挑战和机遇

Meta-Radiology

Pub Date : 2025-06-01 DOI: 10.1016/j.metrad.2025.100138

Ruixin Wang , Zhiyuan Wang , Yuanming Xiao , Xiaohui Liu , Guoping Tan , Jun Liu

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.

乳腺癌是威胁全世界妇女健康的主要疾病。自动乳腺超声（ABUS）的出现为乳腺癌的早期筛查和诊断提供了新的可能性。同时，由深度学习（DL）驱动的基于人工智能（AI）的计算机辅助诊断（CAD）系统在过去十年中取得了显著进展。与传统的手持式超声（HHUS）不同，ABUS实现了扫描和诊断的分离，增加了对具有重要临床价值的CAD系统的需求。近年来，深度学习已成为人工智能发展的主导力量，在各种医学成像模式的CAD中发挥着至关重要的作用。然而，尽管它在人工智能驱动的医学图像分析中占有突出地位，但仍缺乏对其在ABUS中的应用的全面审查。本文详细分析了这一快速发展领域的最新进展、存在的挑战和未来的研究机会。

引用次数: 0

Multi-task glioma segmentation and IDH mutation and 1p19q codeletion classification via a deep learning model on multimodal MRI 基于多模态MRI的多任务胶质瘤分割、IDH突变和1p19q编码分类

Meta-Radiology

Pub Date : 2025-06-01 DOI: 10.1016/j.metrad.2025.100152

Erin Beate Bjørkeli , Morteza Esmaeili

Objectives

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.

Methods

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.

Results

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.

Conclusion

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.

目的建立一种基于多模态MRI的神经胶质瘤病变同时分割、IDH突变和1p/19q编码状态分类的深度学习模型。方法采用具有编码器-解码器架构的CNN模型进行分割，然后采用全连接层进行分类。该模型使用BraTS 2020数据集（132个已知分子状态的检查，分割80/20）进行训练和验证。4张MRI序列图像（T1, T1ce, T2， FLAIR）进行分析。使用平均Dice Score （mDS）和平均Intersection over Union （mIoU）来评估分割性能。分类采用准确性、敏感性和特异性进行评估。结果该模型在4种模式下均获得了最佳分割效果（mDS验证= 0.73，mIoU验证= 0.62）。在单一模式中，FLAIR表现最好（mDS验证= 0.56，mIoU验证= 0.44）。对于分类，组合四种模式的总体准确率为0.98。然而，IDH和1p19q的分类精度可能受到类别不平衡的限制。结论基于cnn的编码器-解码器模型证明了多模态MRI对胶质瘤精确分割的好处，并在分子亚型分类方面显示出令人鼓舞的结果。未来的工作将集中在解决类别不平衡和探索特征集成以提高分类性能上。

{"title":"Multi-task glioma segmentation and IDH mutation and 1p19q codeletion classification via a deep learning model on multimodal MRI","authors":"Erin Beate Bjørkeli , 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}

引用次数: 0

MRI advances on structural and functional changes in limbic system with premenstrual syndrome 经前期综合征边缘系统结构和功能改变的MRI研究进展

Meta-Radiology

Pub Date : 2025-06-01 DOI: 10.1016/j.metrad.2025.100147

Shan-Shan Li , Gao-Xiong Duan , De-Mao Deng

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 Diagnostic and Statistical Manual of Mental Disorders (DSM-5). 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.

经前综合征（PMS）是一种独特的女性情绪障碍，其特征是在月经周期的黄体期出现一系列周期性的身体、情绪、行为和认知症状，通常伴有严重的功能障碍。经前焦虑症（PMDD）是经前综合症的一种严重形式，在第五版《精神疾病诊断与统计手册》（DSM-5）中被归类为抑郁症的一个亚型。神经影像学研究发现PMS/PMDD患者的边缘系统存在结构和功能异常，特别是杏仁核、下丘脑和海马等区域，这些区域与临床症状密切相关。这些异常可能是经前症候群/经前不悦症的中枢神经机制之一。本文就经前症候群/经前抑郁患者MRI所显示的边缘系统结构和功能变化进行综述，并对相关研究进展进行总结。

引用次数: 0

Response to “Commentary on Ferroptosis, M6A and immune checkpoint-related gene expression in the middle temporal gyrus of the Alzheimer's disease brain” 对《关于阿尔茨海默病大脑颞叶中回中凋亡、M6A和免疫检查点相关基因表达的评论》的回应

Meta-Radiology

Pub Date : 2025-05-19 DOI: 10.1016/j.metrad.2025.100156

Jingwen Hu , Kai Yuan , Suping Cai

引用次数: 0

Commentary on “Ferroptosis, M6A and immune checkpoint-related gene expression in the middle temporal gyrus of the Alzheimer's disease brain” 《阿尔茨海默病大脑颞叶中回中凋亡、M6A及免疫检查点相关基因表达》述评

Meta-Radiology

Pub Date : 2025-05-19 DOI: 10.1016/j.metrad.2025.100155

Ziyu Liu, Suhang Shang

引用次数: 0

Reference ranges of CT quantitative indexes based on paired inspiratory and expiratory chest CT in healthy Chinese adults: A community-based cohort study 基于中国健康成人吸气和呼气胸部CT配对定量指标的参考范围：基于社区的队列研究

Meta-Radiology

Pub Date : 2025-05-02 DOI: 10.1016/j.metrad.2025.100154

Ziwei Zhang , Xiuxiu Zhou , Yi Xia , Qianxi Jin , Yu Guan , Taohu Zhou , Yueze Li , Shiyuan Liu , Li Fan

Purpose

Computed tomography (CT) screening has established itself as the routine method to monitor lung conditions by providing pulmonary structural and functional information. However, the reference ranges of CT indices are still lacking. Therefore, this study aimed to provide reference ranges for CT quantitative indexes in healthy middle-aged and elderly Chinese population.

Methods

A total of 783 healthy Chinese adults attending our hospital for the NELCIN-B3 protocol were enrolled. Paired inspiratory and expiratory chest CT and pulmonary function tests (PFTs) were performed in all subjects, CT indices based on density and parametric response map (PRM) were obtained, and PFTs and CT data were retrospectively collected. The reference range was obtained with the Lambda-Mu-Sigma model. Independent-sample t-test/one-way ANOVA analysis or Mann-Whitney test/Kruskal-Wallis test were conducted to compare mean values between different groups. Spearman correlation analysis was used to evaluate the correlation between spirometric and CT quantitative indices.

Results

A total of 783 healthy subjects (255 men, 67 (63–69) years) were included. The reference ranges of lung volume, the percentage of low attenuation area (LAA (%)), PRM^Emphy (%) and PRM^fSAD (%) concerning age based on gender were established. LAA (%), PRM^Emphy (%) and PRM^fSAD (%) were significant higher in the upper lobes than in the lower lobes. There was a strong positive correlation between PRM^Emphy (%) and PRM^fSAD (%) (r = 0.62, p < 0.001).

Conclusions

We established Chinese reference ranges for CT quantitative indexes in the population aged from 40 to 75 years old.

目的计算机断层扫描（CT）通过提供肺结构和功能信息，已成为监测肺部状况的常规方法。然而，CT指标的参考范围仍然缺乏。因此，本研究旨在为中国健康中老年人群CT定量指标提供参考范围。方法入选我院接受NELCIN-B3方案治疗的中国健康成人783例。对所有受试者进行配对吸气、呼气胸部CT和肺功能测试（PFTs），获得基于密度和参数反应图（PRM）的CT指标，并回顾性收集PFTs和CT数据。参考范围采用Lambda-Mu-Sigma模型得到。采用独立样本t检验/单因素方差分析或Mann-Whitney检验/Kruskal-Wallis检验比较各组间均值。采用Spearman相关分析评价肺活量测定与CT定量指标的相关性。结果共纳入健康受试者783例，其中男性255例，年龄67（63 ~ 69）岁。建立肺体积、低衰减面积百分比（LAA(%)）、PRMEmphy（%）、PRMfSAD（%）与年龄相关的性别参考范围。LAA（%）、PRMEmphy（%）和PRMfSAD（%）在上叶明显高于下叶。PRMEmphy（%）与PRMfSAD（%）呈正相关(r = 0.62, p <；0.001)。结论建立了40 ~ 75岁人群CT定量指标的中文参考范围。

{"title":"Reference ranges of CT quantitative indexes based on paired inspiratory and expiratory chest CT in healthy Chinese adults: A community-based cohort study","authors":"Ziwei Zhang , Xiuxiu Zhou , Yi Xia , Qianxi Jin , Yu Guan , Taohu Zhou , Yueze Li , Shiyuan Liu , Li Fan","doi":"10.1016/j.metrad.2025.100154","DOIUrl":"10.1016/j.metrad.2025.100154","url":null,"abstract":"<div><h3>Purpose</h3><div>Computed tomography (CT) screening has established itself as the routine method to monitor lung conditions by providing pulmonary structural and functional information. However, the reference ranges of CT indices are still lacking. Therefore, this study aimed to provide reference ranges for CT quantitative indexes in healthy middle-aged and elderly Chinese population.</div></div><div><h3>Methods</h3><div>A total of 783 healthy Chinese adults attending our hospital for the NELCIN-B3 protocol were enrolled. Paired inspiratory and expiratory chest CT and pulmonary function tests (PFTs) were performed in all subjects, CT indices based on density and parametric response map (PRM) were obtained, and PFTs and CT data were retrospectively collected. The reference range was obtained with the Lambda-Mu-Sigma model. Independent-sample <em>t</em>-test/one-way ANOVA analysis or Mann-Whitney test/Kruskal-Wallis test were conducted to compare mean values between different groups. Spearman correlation analysis was used to evaluate the correlation between spirometric and CT quantitative indices.</div></div><div><h3>Results</h3><div>A total of 783 healthy subjects (255 men, 67 (63–69) years) were included. The reference ranges of lung volume, the percentage of low attenuation area (LAA (%)), PRM<sup>Emphy</sup> (%) and PRM<sup>fSAD</sup> (%) concerning age based on gender were established. LAA (%), PRM<sup>Emphy</sup> (%) and PRM<sup>fSAD</sup> (%) were significant higher in the upper lobes than in the lower lobes. There was a strong positive correlation between PRM<sup>Emphy</sup> (%) and PRM<sup>fSAD</sup> (%) (r = 0.62, p < 0.001).</div></div><div><h3>Conclusions</h3><div>We established Chinese reference ranges for CT quantitative indexes in the population aged from 40 to 75 years old.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 2","pages":"Article 100154"},"PeriodicalIF":0.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089642","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}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Meta-Radiology

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀