Biomedical and Multimedia Information Technology Research Group, School of Computer Science, University of Sydney, Sydney, Australia.
Biomedical and Multimedia Information Technology Research Group, School of Computer Science, University of Sydney, Sydney, Australia.
Comput Methods Programs Biomed. 2019 Mar;170:11-21. doi: 10.1016/j.cmpb.2018.12.031. Epub 2018 Dec 29.
Prostate segmentation on Magnetic Resonance (MR) imaging is problematic because disease changes the shape and boundaries of the gland and it can be difficult to separate the prostate from surrounding tissues. We propose an automated model that extracts and combines multi-level features in a deep neural network to segment prostate on MR images.
Our proposed model, the Propagation Deep Neural Network (P-DNN), incorporates the optimal combination of multi-level feature extraction as a single model. High level features from the convolved data using DNN are extracted for prostate localization and shape recognition, while labeling propagation, by low level cues, is embedded into a deep layer to delineate the prostate boundary.
A well-recognized benchmarking dataset (50 training data and 30 testing data from patients) was used to evaluate the P-DNN. When compared it to existing DNN methods, the P-DNN statistically outperformed the baseline DNN models with an average improvement in the DSC of 3.19%. When compared to the state-of-the-art non-DNN prostate segmentation methods, P-DNN was competitive by achieving 89.9 ± 2.8% DSC and 6.84 ± 2.5 mm HD on training sets and 84.13 ± 5.18% DSC and 9.74 ± 4.21 mm HD on testing sets.
Our results show that P-DNN maximizes multi-level feature extraction for prostate segmentation of MR images.
磁共振成像（MR）上的前列腺分割存在问题，因为疾病会改变腺体的形状和边界，并且很难将前列腺与周围组织分开。我们提出了一种自动化模型，该模型在深度神经网络中提取和组合多层次特征，以分割 MR 图像上的前列腺。
我们提出的模型，即传播深度神经网络（P-DNN），将多层次特征提取的最佳组合合并为单个模型。使用 DNN 对卷积数据进行高级特征提取，用于前列腺定位和形状识别，而低级线索的标签传播则嵌入到深层以描绘前列腺边界。
使用公认的基准数据集（来自患者的 50 个训练数据和 30 个测试数据）来评估 P-DNN。与现有的 DNN 方法相比，P-DNN 在 DSC 上的平均提高了 3.19%，在统计上优于基线 DNN 模型。与最先进的非 DNN 前列腺分割方法相比，P-DNN 在训练集上达到了 89.9 ± 2.8%的 DSC 和 6.84 ± 2.5mmHD，在测试集上达到了 84.13 ± 5.18%的 DSC 和 9.74 ± 4.21mmHD，具有竞争力。
我们的结果表明，P-DNN 最大化了用于 MR 图像前列腺分割的多层次特征提取。
