论著摘要 |【AI-PET】巨噬细胞肌筋膜炎中大脑的18F-FDG PET:一种基于SVN的个体化方法(双语版)

2018-02-26 12:22:37 admin
标签:   人工智能 巨噬细胞肌筋膜炎 脑代谢轮廓 支持向量机 18F-FDG-PET

Cerebral 18F-FDG PET in macrophagic myofasciitis: An individual SVM-based approach.

发表日期: 2017.07.13   来源:PLoS One. 2017 Jul 13;12(7):e0181152.

作者:

Blanc-Durand P11, Van Der Gucht A11, Guedj E2,3,42,3,4, Abulizi M11 , Aoun-Sebaiti M5,65,6, Lerman L11, Verger A77, Authier FJ5,8,95,8,9, Itti E1,101,10.

作者介绍:

1. Department of Nuclear Medicine, H. Mondor Hospital, Assistance Publique-Hôpitaux de Paris/Paris-Est University, Créteil, France.

2. Department of Nuclear Medicine, La Timone Hospital, Assistance Publique-Hôpitaux de Marseille, Marseille, France.

3. Aix-Marseille University, INT, CNRS UMR 7289, Marseille, France.

4. Aix-Marseille University, CERIMED, Marseille, France.

5. INSERM U955-Team 10, Créteil, France.

6. Department of Neurology, H. Mondor Hospital, Assistance Publique-Hôpitaux de Paris/Paris-Est University, Créteil, France.

7. CHU Nancy, Nuclear Medecine & Nancyclotep Experimental Imaging Platform, Nancy, France.

8. Department of Pathology, H. Mondor Hospital, Assistance Publique-Hôpitaux de Paris/Paris-Est University, Créteil, France.

9. Reference Center for Neuromuscular Disorders, H. Mondor Hospital, Assistance Publique-Hôpitaux de Paris, Créteil, France.

10. INSERM U955-GRC Amyloid Research Institute, Créteil, France.

摘要

Abstact

介绍

巨噬细胞肌筋膜炎(MMF)是一种新兴的具有特定的肌病改变的疾病。已经报道了MMF患者的一种特殊的脑葡萄糖基础代谢率减退的空间模式,这其中涉及到枕颞皮质和小脑; 然而,在常规的扫描显示中并没有系统地出现完整的模式,并根据患者的认知情况分出不同程度的严重性。目标是生成和评估支持向量机(SVM)程序,以分类健康患者或MMF患者的18F-FDG大脑轮廓。

Introduction

Macrophagic myofasciitis (MMF) is an emerging condition with highly specific myopathological alterations. A peculiar spatial pattern of a cerebral glucose hypometabolism involving occipito-temporal cortex and cerebellum have been reported in patients with MMF; however, the full pattern is not systematically present in routine interpretation of scans, and with varying degrees of severity depending on the cognitive profile of patients. Aim was to generate and evaluate a support vector machine (SVM) procedure to classify patients between healthy or MMF 18F-FDG brain profiles.

方法

回顾性分析了119名MMF患者和64名健康受试者的18F-FDG PET脑图像。整体分成两组,一个训练组(100 MMF,44个健康受试者)和一个测试组(19个MMF,20个健康受试者)。使用来自统计参数图(SPM)的t图执行维度缩小,并且在训练集上训练具有线性核的SVM。为了评估SVM分类器的性能,计算了灵敏度(Se),特异度(Sp),阳性预测值(PPV),阴性预测值(NPV)和准确度(Acc)的值。

Methods

18F-FDG PET brain images of 119 patients with MMF and 64 healthy subjects were retrospectively analyzed. The whole-population was divided into two groups; a training set (100 MMF, 44 healthy subjects) and a testing set (19 MMF, 20 healthy subjects). Dimensionality reduction was performed using a t-map from statistical parametric mapping (SPM) and a SVM with a linear kernel was trained on the training set. To evaluate the performance of the SVM classifier, values of sensitivity (Se), specificity (Sp), positive predictive value (PPV), negative predictive value (NPV) and accuracy (Acc) were calculated.

结果

训练集的SPM12分析显示已经报道的涉及枕颞叶和额叶-顶叶皮质,边缘系统和小脑的基础代谢减退。支持向量机程序基于训练集产生的t检验,将测试集中的MMF患者正确地分类得到的Se,Sp,PPV,NPV和Acc为:89%,85%,85%,89%和87%。

Results

The SPM12 analysis on the training set exhibited the already reported hypometabolism pattern involving occipito-temporal and fronto-parietal cortices, limbic system and cerebellum. The SVM procedure, based on the t-test mask generated from the training set, correctly classified MMF patients of the testing set with following Se, Sp, PPV, NPV and Acc: 89%, 85%, 85%, 89%, and 87%.

结论

我们开发了一个独特的原创方法,包括一个使用18F-FDG-PET将患者分类为健康或MMF脑代谢轮廓的支持向量机。机器学习算法有望用于计算机辅助诊断,但是需要在前瞻性群组中进一步验证。

Conclusions

We developed an original and individual approach including a SVM to classify patients between healthy or MMF metabolic brain profiles using 18F-FDG-PET. Machine learning algorithms are promising for computer-aided diagnosis but will need further validation in prospective cohorts.

阅读原文:PMID: 28704562  PMCID: PMC5509294  DOI: 10.1371/journal.pone.0181152


慧影医疗科技(北京)有限公司

地点:北京市海淀区中关村东升科技园B2-C103

电话:400-890-9020

邮箱:radcloud@huiyihuiying.com

关闭
图片
图片