A novel deep learning based model called Multi-Planar Spatial Convolutional Neural Network (MPS-CNN) is proposed for effective, automated segmentation of different sub-regions viz. peritumoral edema (ED), necrotic core (NCR), enhancing and non-enhancing tumor core (ET/NET), from multi-modal MR images of the brain. An encoder-decoder type CNN model is designed for pixel-wise segmentation of the tumor along three anatomical planes (axial, sagittal, and coronal) at the slice level. These are then combined, by incorporating a consensus fusion strategy with a fully connected Conditional Random Field (CRF) based post-refinement, to produce the final volumetric segmentation of the tumor and its constituent sub-regions. Concepts, such as spatial-pooling and unpooling are used to preserve the spatial locations of the edge pixels, for reducing segmentation error around the boundaries. A new aggregated loss function is also developed for effectively handling data imbalance. The MPS-CNN is trained and validated on the recent Multimodal Brain Tumor Segmentation Challenge (BraTS) 2018 dataset. The Dice scores obtained for the validation set for whole tumor (WT :NCR/NE +ET +ED), tumor core (TC:NCR/NET +ET), and enhancing tumor (ET) are 0.90216, 0.87247, and 0.82445. The proposed MPS-CNN is found to perform the best (based on leaderboard scores) for ET and TC segmentation tasks, in terms of both the quantitative measures (viz. Dice and Hausdorff). In case of the WT segmentation it also achieved the second highest accuracy, with a score which was only 1% less than that of the best performing method.

中文翻译：

---

脑肿瘤中新颖的体积子区域分割


提出了一种基于深度学习的新型模型，称为多平面空间卷积神经网络（MPS-CNN），用于对不同子区域进行有效、自动的分割。来自大脑多模态 MR 图像的瘤周水肿 (ED)、坏死核心 (NCR)、增强和非增强肿瘤核心 (ET/NET)。编码器-解码器型 CNN 模型设计用于在切片级别沿三个解剖平面（轴向、矢状和冠状）对肿瘤进行像素级分割。然后，通过将共识融合策略与基于完全连接的条件随机场 (CRF) 的后细化相结合，将它们组合起来，以产生肿瘤及其组成子区域的最终体积分割。空间池化和反池化等概念用于保留边缘像素的空间位置，以减少边界周围的分割误差。还开发了新的聚合损失函数来有效处理数据不平衡。 MPS-CNN 在最近的多模式脑肿瘤分割挑战 (BraTS) 2018 数据集上进行了训练和验证。整个肿瘤 (WT:NCR/NE +ET +ED)、肿瘤核心 (TC:NCR/NET +ET) 和增强肿瘤 (ET) 验证集获得的 Dice 分数分别为 0.90216、0.87247 和 0.82445。研究发现，就定量指标（即 Dice 和 Hausdorff）而言，所提出的 MPS-CNN 在 ET 和 TC 分割任务中表现最佳（基于排行榜分数）。在 WT 分割的情况下，它也达到了第二高的准确度，其分数仅比最佳执行方法低 1%。