Deep convolutional neural network-based segmentation and classification of difficult to define metastatic spinal lesions in 3D CT data
Deep convolutional neural network-based segmentation and classification of difficult to define metastatic spinal lesions in 3D CT data
复制标题
DOI：
10.1016/j.media.2018.07.008
复制
发表时间：
2018-10-01
影响因子：
10.9
通讯作者：
Gavelli, Giampaolo
中科院分区：
文献类型：
--
作者：
Chmelik, Jiri;Jakubicek, Roman;Gavelli, Giampaolo
本文的目的是解决的分割和分类的抒情性和坐骨神经转移性病变，很难通过使用脊柱三维计算机断层扫描（CT）图像从高度病理影响的情况下获得的定义。由于病变是不明确的，因此很难找到相关的图像特征，使检测和分类的病变的纹理和形状分析的经典方法，这个问题是解决了自动特征提取提供的深度卷积神经网络（CNN）。我们的主要贡献是：（i）单独的CNN架构，以及取决于患者数据和扫描协议的预处理步骤-它使得能够与不同类型的CT扫描一起工作;（ii）中轴变换（MAT）后处理，用于利用基于随机森林（RF）的元分析对分割的病变候选者进行形状简化;以及（iii）所提出的方法在全脊柱CT上的可用性（颈椎、胸椎、腰椎），在其他已发表的方法中没有处理我们提出的方法已经在我们自己的数据集上进行了测试，由两个相互独立的放射科医生注释，并与其他已发表的方法进行了比较。这项工作是正在进行的复杂项目的一部分，涉及脊柱分析和脊柱病变纵向研究。(C)2018 Elsevier B. V.版权所有。
This paper aims to address the segmentation and classification of lyric and sclerotic metastatic lesions that are difficult to define by using spinal 3D Computed Tomography (CT) images obtained from highly pathologically affected cases. As the lesions are ill-defined and consequently it is difficult to find relevant image features that would enable detection and classification of lesions by classical methods of texture and shape analysis, the problem is solved by automatic feature extraction provided by a deep Convolutional Neural Network (CNN). Our main contributions are: (i) individual CNN architecture, and pre-processing steps that are dependent on a patient data and a scan protocol - it enables work with different types of CT scans; (ii) medial axis transform (MAT) post-processing for shape simplification of segmented lesion candidates with Random Forest (RF) based meta-analysis; and (iii) usability of the proposed method on whole-spine CTs (cervical, thoracic, lumbar), which is not treated in other published methods (they work with thoracolumbar segments of spine only).Our proposed method has been tested on our own dataset annotated by two mutually independent radiologists and has been compared to other published methods. This work is part of the ongoing complex project dealing with spine analysis and spine lesion longitudinal studies. (C) 2018 Elsevier B.V. All rights reserved.