Hua Xiong, Ping Yin, Weiqiang Luo, Yihui Li, Sicong Wang
{"title":"基于多参数磁共振成像的颅内孤立性纤维瘤/脑膜血管瘤和脑膜瘤鉴别放射组学模型","authors":"Hua Xiong, Ping Yin, Weiqiang Luo, Yihui Li, Sicong Wang","doi":"10.4103/neurol-india.NI_213_20","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Although the imaging findings of intracranial solitary fibrous tumor (SFT)/hemangiopericytoma (HPC) and meningioma are similar, their treatment and prognosis are quite different. Accurate preoperative identification of these two types of tumors is crucial for individualized treatment.</p><p><strong>Objective: </strong>The aim of this study was to develop a radiomics model for the differentiation of intracranial SFT/HPC and meningioma based on multiparametric magnetic resonance imaging (mpMRI).</p><p><strong>Material and methods: </strong>A total of 99 patients from July 2012 to July 2018 with histologically and immunohistochemically confirmed SFT/HPC (n = 40) or meningiomas (n = 59) were retrospectively analyzed. A total of 1118 features were extracted based on its image shape, intensity and texture features. The logistic regression (LR) and multi-layer artificial neural network (ANN) classifiers were used to classify SFT/HPC and meningioma. The predictive performance was calculated using receiver operating characteristic curves (ROC).</p><p><strong>Results: </strong>We found significant difference in terms of sex between the SFT/HPC and meningioma group (χ2= 4.829, P < 0.05), but no significant difference was found in age (P > 0.05). The most significant radiomics features included five shape and four first-order level features. For the LR classifier, the prediction accuracy of SFT/HPC was 71.0% and meningioma was 78.7%. For the ANN classifier, the prediction accuracy of SFT/HPC was 83.9% and meningioma was 80.9%. Both of the two classifiers achieved a high accuracy rate, but ANN was better.</p><p><strong>Conclusions: </strong>Radiomics features, especially when combined with an ANN classifier, can provide satisfactory performance in distinguishing SFT/HPC and meningioma.</p>","PeriodicalId":19429,"journal":{"name":"Neurology India","volume":null,"pages":null},"PeriodicalIF":0.9000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Radiomics Model for the Differentiation of Intracranial Solitary Fibrous Tumor/Hemangiopericytoma and Meningioma Based on Multiparametric Magnetic Resonance Imaging.\",\"authors\":\"Hua Xiong, Ping Yin, Weiqiang Luo, Yihui Li, Sicong Wang\",\"doi\":\"10.4103/neurol-india.NI_213_20\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Although the imaging findings of intracranial solitary fibrous tumor (SFT)/hemangiopericytoma (HPC) and meningioma are similar, their treatment and prognosis are quite different. Accurate preoperative identification of these two types of tumors is crucial for individualized treatment.</p><p><strong>Objective: </strong>The aim of this study was to develop a radiomics model for the differentiation of intracranial SFT/HPC and meningioma based on multiparametric magnetic resonance imaging (mpMRI).</p><p><strong>Material and methods: </strong>A total of 99 patients from July 2012 to July 2018 with histologically and immunohistochemically confirmed SFT/HPC (n = 40) or meningiomas (n = 59) were retrospectively analyzed. A total of 1118 features were extracted based on its image shape, intensity and texture features. The logistic regression (LR) and multi-layer artificial neural network (ANN) classifiers were used to classify SFT/HPC and meningioma. The predictive performance was calculated using receiver operating characteristic curves (ROC).</p><p><strong>Results: </strong>We found significant difference in terms of sex between the SFT/HPC and meningioma group (χ2= 4.829, P < 0.05), but no significant difference was found in age (P > 0.05). The most significant radiomics features included five shape and four first-order level features. For the LR classifier, the prediction accuracy of SFT/HPC was 71.0% and meningioma was 78.7%. For the ANN classifier, the prediction accuracy of SFT/HPC was 83.9% and meningioma was 80.9%. Both of the two classifiers achieved a high accuracy rate, but ANN was better.</p><p><strong>Conclusions: </strong>Radiomics features, especially when combined with an ANN classifier, can provide satisfactory performance in distinguishing SFT/HPC and meningioma.</p>\",\"PeriodicalId\":19429,\"journal\":{\"name\":\"Neurology India\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.9000,\"publicationDate\":\"2024-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neurology India\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.4103/neurol-india.NI_213_20\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/8/31 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q4\",\"JCRName\":\"NEUROSCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neurology India","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.4103/neurol-india.NI_213_20","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/8/31 0:00:00","PubModel":"Epub","JCR":"Q4","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
引用次数: 0
摘要
背景:尽管颅内单发纤维瘤(SFT)/脑膜血管瘤(HPC)和脑膜瘤的影像学表现相似,但它们的治疗和预后却截然不同。术前准确识别这两类肿瘤对于个体化治疗至关重要:本研究旨在建立一个基于多参数磁共振成像(mpMRI)的放射组学模型,用于区分颅内SFT/HPC和脑膜瘤:回顾性分析了2012年7月至2018年7月期间经组织学和免疫组化证实为SFT/HPC(n = 40)或脑膜瘤(n = 59)的99例患者。根据图像形状、强度和纹理特征,共提取了1118个特征。采用逻辑回归(LR)和多层人工神经网络(ANN)分类器对 SFT/HPC 和脑膜瘤进行分类。使用接收器操作特征曲线(ROC)计算预测性能:我们发现 SFT/HPC 组和脑膜瘤组在性别方面有明显差异(χ2= 4.829,P <0.05),但在年龄方面无明显差异(P >0.05)。最重要的放射组学特征包括五个形状特征和四个一阶水平特征。在 LR 分类器中,SFT/HPC 的预测准确率为 71.0%,脑膜瘤为 78.7%。对于 ANN 分类器,SFT/HPC 的预测准确率为 83.9%,脑膜瘤为 80.9%。两种分类器都达到了较高的准确率,但 ANN 更胜一筹:结论:放射组学特征,尤其是与 ANN 分类器相结合时,可在区分 SFT/HPC 和脑膜瘤方面提供令人满意的性能。
A Radiomics Model for the Differentiation of Intracranial Solitary Fibrous Tumor/Hemangiopericytoma and Meningioma Based on Multiparametric Magnetic Resonance Imaging.
Background: Although the imaging findings of intracranial solitary fibrous tumor (SFT)/hemangiopericytoma (HPC) and meningioma are similar, their treatment and prognosis are quite different. Accurate preoperative identification of these two types of tumors is crucial for individualized treatment.
Objective: The aim of this study was to develop a radiomics model for the differentiation of intracranial SFT/HPC and meningioma based on multiparametric magnetic resonance imaging (mpMRI).
Material and methods: A total of 99 patients from July 2012 to July 2018 with histologically and immunohistochemically confirmed SFT/HPC (n = 40) or meningiomas (n = 59) were retrospectively analyzed. A total of 1118 features were extracted based on its image shape, intensity and texture features. The logistic regression (LR) and multi-layer artificial neural network (ANN) classifiers were used to classify SFT/HPC and meningioma. The predictive performance was calculated using receiver operating characteristic curves (ROC).
Results: We found significant difference in terms of sex between the SFT/HPC and meningioma group (χ2= 4.829, P < 0.05), but no significant difference was found in age (P > 0.05). The most significant radiomics features included five shape and four first-order level features. For the LR classifier, the prediction accuracy of SFT/HPC was 71.0% and meningioma was 78.7%. For the ANN classifier, the prediction accuracy of SFT/HPC was 83.9% and meningioma was 80.9%. Both of the two classifiers achieved a high accuracy rate, but ANN was better.
Conclusions: Radiomics features, especially when combined with an ANN classifier, can provide satisfactory performance in distinguishing SFT/HPC and meningioma.
期刊介绍:
Neurology India (ISSN 0028-3886) is Bi-monthly publication of Neurological Society of India. Neurology India, the show window of the progress of Neurological Sciences in India, has successfully completed 50 years of publication in the year 2002. ‘Neurology India’, along with the Neurological Society of India, has grown stronger with the passing of every year. The full articles of the journal are now available on internet with more than 20000 visitors in a month and the journal is indexed in MEDLINE and Index Medicus, Current Contents, Neuroscience Citation Index and EMBASE in addition to 10 other indexing avenues.
This specialty journal reaches to about 2000 neurologists, neurosurgeons, neuro-psychiatrists, and others working in the fields of neurology.