Ren Huipeng, Ren Chengjuan, Guo Ziyu, Zhang Guangnan, Luo Xiaohui, Ren Zhuanqin, Tian Hongzhe, Li Wei, Yuan Hao, Hao Lele, Wang Jiacheng, Zhang Ming
Department of Medical Imaging, First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
Department of Medical Imaging, Baoji Central Hospital, Baoji, China.
Front Oncol. 2023 Apr 19;13:1095353. doi: 10.3389/fonc.2023.1095353. eCollection 2023.
To develop an accurate and automatic segmentation model based on convolution neural network to segment the prostate and its lesion regions.
Of all 180 subjects, 122 healthy individuals and 58 patients with prostate cancer were included. For each subject, all slices of the prostate were comprised in the DWIs. A novel DCNN is proposed to automatically segment the prostate and its lesion regions. This model is inspired by the U-Net model with the encoding-decoding path as the backbone, importing dense block, attention mechanism techniques, and group norm-Atrous Spatial Pyramidal Pooling. Data augmentation was used to avoid overfitting in training. In the experimental phase, the data set was randomly divided into a training (70%), testing set (30%). four-fold cross-validation methods were used to obtain results for each metric.
The proposed model achieved in terms of Iou, Dice score, accuracy, sensitivity, 95% Hausdorff Distance, 86.82%,93.90%, 94.11%, 93.8%,7.84 for the prostate, 79.2%, 89.51%, 88.43%,89.31%,8.39 for lesion region in segmentation. Compared to the state-of-the-art models, FCN, U-Net, U-Net++, and ResU-Net, the segmentation model achieved more promising results.
The proposed model yielded excellent performance in accurate and automatic segmentation of the prostate and lesion regions, revealing that the novel deep convolutional neural network could be used in clinical disease treatment and diagnosis.
基于卷积神经网络开发一种准确的自动分割模型，用于分割前列腺及其病变区域。
在180名受试者中，纳入122名健康个体和58名前列腺癌患者。对于每个受试者，DWIs中包含前列腺的所有切片。提出了一种新颖的深度卷积神经网络（DCNN）来自动分割前列腺及其病变区域。该模型以具有编码-解码路径的U-Net模型为基础，引入了密集块、注意力机制技术和组归一化空洞空间金字塔池化。在训练中使用数据增强来避免过拟合。在实验阶段，将数据集随机分为训练集（70%）、测试集（30%）。采用四重交叉验证方法来获得每个指标的结果。
所提出的模型在分割前列腺时，交并比（IoU）、骰子系数、准确率、灵敏度、95%豪斯多夫距离分别达到86.82%、93.90%、94.11%、93.8%、7.84；在分割病变区域时，分别为79.2%、89.51%、88.43%、89.31%、8.39。与当前最先进的模型全卷积网络（FCN）、U-Net、U-Net++和残差U-Net相比，该分割模型取得了更有前景的结果。
所提出的模型在前列腺及其病变区域的准确自动分割方面表现出色，表明这种新颖的深度卷积神经网络可用于临床疾病的治疗和诊断。
