State Key Laboratory of Marine Resource Utilization in South China Sea, School of information and Communication Engineering, Hainan University, Haikou, China.
College of Electronics and Information Engineering, Guangdong Ocean University, Zhanjiang, China.
Med Phys. 2023 Feb;50(2):906-921. doi: 10.1002/mp.15895. Epub 2022 Dec 31.
Automatic segmentation of prostate magnetic resonance (MR) images is crucial for the diagnosis, evaluation, and prognosis of prostate diseases (including prostate cancer). In recent years, the mainstream segmentation method for the prostate has been converted to convolutional neural networks. However, owing to the complexity of the tissue structure in MR images and the limitations of existing methods in spatial context modeling, the segmentation performance should be improved further.
In this study, we proposed a novel 3D pyramid pool Unet that benefits from the pyramid pooling structure embedded in the skip connection (SC) and the deep supervision (DS) in the up-sampling of the 3D Unet. The parallel SC of the conventional 3D Unet network causes low-resolution information to be sent to the feature map repeatedly, resulting in blurred image features. To overcome the shortcomings of the conventional 3D Unet, we merge each decoder layer with the feature map of the same scale as the encoder and the smaller scale feature map of the pyramid pooling encoder. This SC combines the low-level details and high-level semantics at two different levels of feature maps. In addition, pyramid pooling performs multifaceted feature extraction on each image behind the convolutional layer, and DS learns hierarchical representations from comprehensive aggregated feature maps, which can improve the accuracy of the task.
Experiments on 3D prostate MR images of 78 patients demonstrated that our results were highly correlated with expert manual segmentation. The average relative volume difference and Dice similarity coefficient of the prostate volume area were 2.32% and 91.03%, respectively.
Quantitative experiments demonstrate that, compared with other methods, the results of our method are highly consistent with the expert manual segmentation.
前列腺磁共振（MR）图像的自动分割对于前列腺疾病（包括前列腺癌）的诊断、评估和预后至关重要。近年来，前列腺的主流分割方法已转为卷积神经网络。然而，由于 MR 图像中组织结构的复杂性以及现有方法在空间上下文建模方面的局限性，分割性能仍需进一步提高。
本研究提出了一种新颖的 3D 金字塔池化 U-Net，该网络受益于嵌入在 skip connection（SC）中的金字塔池化结构和 3D U-Net 上采样中的深度监督（DS）。传统 3D U-Net 网络的并行 SC 会导致低分辨率信息被重复发送到特征图，从而导致图像特征模糊。为了克服传统 3D U-Net 的缺点，我们将每个解码器层与编码器和金字塔池化编码器的较小尺度特征图的相同尺度的特征图合并。这种 SC 将两个不同层次的特征图的低层次细节和高层次语义结合在一起。此外，金字塔池化在卷积层后面的每张图像上进行多方面的特征提取，DS 从综合聚合特征图中学习分层表示，这可以提高任务的准确性。
对 78 例前列腺 3D MR 图像的实验表明，我们的结果与专家手动分割高度相关。前列腺体积区域的平均相对体积差异和 Dice 相似系数分别为 2.32%和 91.03%。
定量实验表明，与其他方法相比，我们的方法结果与专家手动分割高度一致。
