Radiological classification of dementia from anatomical MRI assisted by machine learning-derived maps
Radiological classification of dementia from anatomical MRI assisted by machine learning-derived maps
复制标题
DOI：
10.1016/j.neurad.2020.04.004
复制
发表时间：
2021-11-01
影响因子：
3.5
通讯作者：
Colliot, Olivier
中科院分区：
文献类型：
--
作者：
Chague, Pierre;Marro, Beatrice;Colliot, Olivier
背景和目的。- 目前正在开发许多人工智能工具，以帮助通过磁共振成像（MRI）诊断痴呆症。然而，这些工具到目前为止还难以整合到临床常规工作流程中。在这项工作中，我们提出了一种新的简单的方法来使用它们，并评估其效用，以提高诊断的准确性。材料和方法。- 我们研究了34例早发性阿尔茨海默病（EOAD），49例晚发性AD（LOAD），39例额颞叶痴呆（FTD）和24例抑郁症患者，这些患者来自预先存在的队列EAD-AD。使用3D T1 MRI训练支持向量机（SVM）自动分类器，以区分：LOAD与抑郁、FTD与LOAD、EOAD与抑郁、EOAD与FTD。我们提取了SVM权重图，这是分类器用于做出决策的判别性萎缩模式的三维表示，我们打印了这些地图的海报。4名放射科医师（2名高级神经放射科医师和2名非专业初级放射科医师）使用3D T1 MRI对4个诊断对进行了视觉分类。分类进行了两次：首先使用标准放射学阅读，然后使用SVM权重图作为指导。结果- 在FTD与EOAD的病例中，两名初级放射科医生使用权重图显著提高了诊断性能。诊断准确率提高10分以上。结论- 该工具可以提高初级放射科医生的诊断准确性，并可以集成到临床常规工作流程中。(c)2020 Elsevier Masson SAS。All rights reserved.
Background and purpose. - Many artificial intelligence tools are currently being developed to assist diag-nosis of dementia from magnetic resonance imaging (MRI). However, these tools have so far been difficult to integrate in the clinical routine workflow. In this work, we propose a new simple way to use them and assess their utility for improving diagnostic accuracy. Materials and methods. - We studied 34 patients with early-onset Alzheimer's disease (EOAD), 49 with late-onset AD (LOAD), 39 with frontotemporal dementia (FTD) and 24 with depression from the pre-existing cohort CLIN-AD. Support vector machine (SVM) automatic classifiers using 3D T1 MRI were trained to distinguish: LOAD vs. Depression, FTD vs. LOAD, EOAD vs. Depression, EOAD vs. FTD. We extracted SVM weight maps, which are tridimensional representations of discriminant atrophy patterns used by the classifier to take its decisions and we printed posters of these maps. Four radiologists (2 senior neuroradiologists and 2 unspecialized junior radiologists) performed a visual classification of the 4 diagnostic pairs using 3D T1 MRI. Classifications were performed twice: first with standard radiological reading and then using SVM weight maps as a guide. Results. - Diagnostic performance was significantly improved by the use of the weight maps for the two junior radiologists in the case of FTD vs. EOAD. Improvement was over 10 points of diagnostic accuracy. Conclusion. - This tool can improve the diagnostic accuracy of junior radiologists and could be integrated in the clinical routine workflow. (c) 2020 Elsevier Masson SAS. All rights reserved.