Department of Neurosurgery, Shanghai Pudong Hospital, Fudan University Pudong Medical Center, Pudong, Shanghai 201399, China.
J Healthc Eng. 2022 Feb 18;2022:8507773. doi: 10.1155/2022/8507773. eCollection 2022.
A common and most basic brain tumor is glioma that is exceptionally dangerous to health of various patients. A glioma segmentation, which is primarily magnetic resonance imaging (MRI) oriented, is considered as one of common tools developed for doctors. These doctors use this system to examine, analyse, and diagnose appearance of the glioma's outward for both patients, i.e., indoor and outdoor. In the literature, a widely utilized approach for the segmentation of glioma is the deep learning-oriented method. To cope with this issue, a segmentation of glioma approach, i.e., primarily on the convolution neural networks, is developed in this manuscript. A DM-DA-enabled cascading approach for the segmentation of glioma, which is 2DResUnet-enabled model, is reported to resolve the problem of spatial data acquisition of insufficient 3D specifically in the 2D full CNN along with the core issue of memory consumption of 3D full CNN. For gliomas segmentation at various stages, we have utilized multiscale fusion approach, attention, segmentation, and DenseBlock. Moreover, for reducing three dimensionalities of the Unet model, a sampling of fixed region is used along with multisequence data of the glioma image. Finally, the CNN model has the ability of producing a better segmentation of tumor preferably with minimum possible memory. The proposed model has used BraTS18 and BraTS17 benchmark data sets for fivefold cross-validation (local) and online evaluation preferably official, respectively. Evaluation results have verified that edema's Dice Score preferable average, enhancement, and core areas of the segmentation of the glioma with DM-DA-Unet perform exceptionally well on the validation set of BraTS17. Finally, average sensitivity was observed to be high as well, which is approximately closer to the best segmentation model and its effect on the validation set of BraTS1 and has segmented gliomas accurately.
一种常见且最基本的脑部肿瘤是神经胶质瘤，它对各种患者的健康都非常危险。一种主要基于磁共振成像（MRI）的神经胶质瘤分割被认为是医生开发的常用工具之一。这些医生使用该系统来检查、分析和诊断患者室内外的神经胶质瘤的外观。在文献中，一种广泛使用的神经胶质瘤分割方法是基于深度学习的方法。为了解决这个问题，本文提出了一种主要基于卷积神经网络的神经胶质瘤分割方法。报告了一种基于 DM-DA 的级联分割方法，即 2DResUnet 模型，用于解决 3D 全卷积神经网络中空间数据采集不足的问题，特别是在 2D 全卷积神经网络中，以及 3D 全卷积神经网络的核心问题，即内存消耗。为了在不同阶段对神经胶质瘤进行分割，我们使用了多尺度融合方法、注意力机制、分割和 DenseBlock。此外，为了降低 U 型网络模型的三维性，使用了固定区域的采样和神经胶质瘤图像的多序列数据。最后，该 CNN 模型具有生成更好的肿瘤分割的能力，最好是在最小的可能内存下。该模型使用了 BraTS18 和 BraTS17 基准数据集进行五折交叉验证（本地）和在线评估（官方）。评估结果验证了 DM-DA-Unet 在 BraTS17 验证集上对水肿的 Dice 得分、增强和核心区域的分割效果非常好。最后，观察到平均灵敏度也很高，这与最佳分割模型及其对 BraTS1 验证集的影响非常接近，并准确地分割了神经胶质瘤。
