前列腺癌近距离放疗MRI辅助放射外科中盆腔解剖的机器分割
DenseNet201编码器全卷积网络经交叉熵训练后综合分割性能最高,在53例T2或T2/T1加权测试集上微调后前列腺DSC达0.90±0.04。结论认为单一全卷积网络可对不同脉冲序列3D MRI进行机器分割。
要点
- DenseNet201编码器全卷积网络经交叉熵最小化训练获得最高综合分割性能
- 微调后T2/T2-T1加权测试集前列腺DSC为0.90±0.04、膀胱0.96±0.04
- 仅用T2及T2/T1加权训练的全卷积网络对T1加权图像分割性能下降
核心结论
- 对MARS低剂量率前列腺近距离放疗中不同脉冲序列采集的3D MRI,单一全卷积网络可实现前列腺及周围解剖的机器分割。
研究设计与样本
- 深度学习模型由18个具有不同卷积编码器的全卷积网络组成,并构建二维和三维U-Net全卷积网络进行比较。
- 研究比较6种目标函数:交叉熵、Jaccard距离、焦点损失及3种Tversky距离变体。
- 采用像素准确率、Jaccard指数、Dice相似系数、95% Hausdorff距离、相对体积差、Matthews相关系数、精确率、召回率和平均对称表面距离等相似性指标比较模型性能。
主要发现
- 总体而言,采用DenseNet201编码器并通过交叉熵最小化训练的全卷积网络获得最高综合分割性能。
- 在53例T2加权或T2/T1加权3D测试MRI上,模型微调后前列腺、外尿道括约肌、精囊、直肠和膀胱的DSC分别为0.90±0.04、0.70±0.15、0.80±0.12、0.91±0.06和0.96±0.04。
- 在5例T1加权图像上,上述器官的DSC分别为0.82±0.07、0.17±0.15、0.46±0.21、0.87±0.06和0.88±0.05。
- 研究还考察了训练数据量、跳跃连接使用和数据增强对分割性能的影响。
- 研究探讨了仅用T2加权和T2/T1加权图像对比度训练的全卷积网络能否分割T1加权MRI。
关键数值与推荐
- 最高综合分割性能对应DenseNet201编码器全卷积网络联合交叉熵最小化训练。
- T2加权或T2/T1加权3D测试MRI共53例,T1加权图像共5例。
- 微调后T2/T2-T1加权测试集DSC:前列腺0.90±0.04,外尿道括约肌0.70±0.15,精囊0.80±0.12,直肠0.91±0.06,膀胱0.96±0.04。
- T1加权图像DSC:前列腺0.82±0.07,外尿道括约肌0.17±0.15,精囊0.46±0.21,直肠0.87±0.06,膀胱0.88±0.05。
临床怎么用
- 在前列腺癌MARS低剂量率近距离放疗中,可用单一全卷积网络对多脉冲序列3D MRI进行前列腺及周围器官自动分割。
- 对T2加权或T2/T1加权图像,模型微调后前列腺、直肠和膀胱分割DSC较高,外尿道括约肌分割DSC相对较低。
- 对T1加权图像,仅用T2及T2/T1加权训练的全卷积网络分割外尿道括约肌和精囊性能明显下降,临床使用需谨慎。
局限性
- T1加权测试图像仅5例,样本量小。
- 原文未报告训练集与测试集的具体划分方式及外部验证结果。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: To investigate machine segmentation of pelvic anatomy in magnetic resonance imaging (MRI)-assisted radiosurgery (MARS) for prostate cancer using prostate brachytherapy MRIs acquired with different pulse sequences and image contrasts. METHODS AND MATERIALS: Two hundred 3-dimensional (3D) preimplant and postimplant prostate brachytherapy MRI scans were acquired with a T2-weighted sequence, a T2/T1-weighted sequence, or a T1-weighted sequence. One hundred twenty deep machine learning models were trained to segment the prostate, seminal vesicles, external urinary sphincter, rectum, and bladder using the MRI scans acquired with T2-weighted and T2/T1-weighted image contrast. The deep machine learning models consisted of 18 fully convolutional networks (FCNs) with different convolutional encoders. Both 2-dimensional and 3D U-Net FCNs were constructed for comparison. Six objective functions were investigated: cross-entropy, Jaccard distance, focal loss, and 3 variations of Tversky distance. The performance of the models was compared using similarity metrics, including pixel accuracy, Jaccard index, Dice similarity coefficient (DSC), 95% Hausdorff distance, relative volume difference, Matthews correlation coefficient, precision, recall, and average symmetrical surface distance. We selected the highest-performing architecture and investigated how the amount of training data, use of skip connections, and data augmentation affected segmentation performance. In addition, we investigated whether segmentation on T1-weighted MRI was possible with FCNs trained on only T2-weighted and T2/T1-weighted image contrast. RESULTS: Overall, an FCN with a DenseNet201 encoder trained via cross-entropy minimization yielded the highest combined segmentation performance. For the 53 3D test MRI scans acquired with T2-weighted or T2/T1-weighted image contrast, the DSCs of the prostate, external urinary sphincter, seminal vesicles, rectum, and bladder were 0.90 ± 0.04, 0.70 ± 0.15, 0.80 ± 0.12, 0.91 ± 0.06, and 0.96 ± 0.04, respectively, after model fine-tuning. For the 5 T1-weighted images, the DSCs of these organs were 0.82 ± 0.07, 0.17 ± 0.15, 0.46 ± 0.21, 0.87 ± 0.06, and 0.88 ± 0.05, respectively. CONCLUSIONS: Machine segmentation of the prostate and surrounding anatomy on 3D MRIs acquired with different pulse sequences for MARS low-dose-rate prostate brachytherapy is possible with a single FCN.
引用
- Sanders JW, Lewis GD, Thames HD, et al. Machine Segmentation of Pelvic Anatomy in MRI-Assisted Radiosurgery (MARS) for Prostate Cancer Brachytherapy. Int J Radiat Oncol Biol Phys. 2020. PMID: 32634543. doi:10.1016/j.ijrobp.2020.06.076
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。