论文标题
来自CT的自动胸腔器官 - 在风险分割的多个分辨率剩余网络
Multiple resolution residual network for automatic thoracic organs-at-risk segmentation from CT
论文作者
论文摘要
我们从计算机断层扫描（CT）图像中实施并评估了多个正常器官 - 风险（OAR）分割的多个分辨率残差网络（MRRN），用于胸腔放射治疗（RT）计划。我们的方法同时结合了通过剩余连接在多个图像分辨率和特征级别计算的特征流。随着图像通过各种功能级别，每个级别的功能流将更新。我们使用206个对肺癌患者进行了35例扫描术进行验证以验证左右肺，心脏，食管和脊髓的肺癌患者训练了方法。从开源AAPM胸腔自动分割挑战数据集对60张CT扫描进行了测试。使用骰子相似系数（DSC）测量性能。我们的方法在诸如食管等难以分段的结构中的大挑战中优于表现最佳的方法，并在所有其他结构中取得了可比的结果。使用我们的方法的中位DSC为左右肺的0.97（IQR]：0.97-0.98），心脏为0.93（IQR：0.93-0.95），为0.78（IQR：0.76-0.80），食管的中位数为0.78（iqr：0.76-0.80），食管和0.88（IQR：0.88（IQR：0.88）（IQR：0.88（IQR：0.88）。
We implemented and evaluated a multiple resolution residual network (MRRN) for multiple normal organs-at-risk (OAR) segmentation from computed tomography (CT) images for thoracic radiotherapy treatment (RT) planning. Our approach simultaneously combines feature streams computed at multiple image resolutions and feature levels through residual connections. The feature streams at each level are updated as the images are passed through various feature levels. We trained our approach using 206 thoracic CT scans of lung cancer patients with 35 scans held out for validation to segment the left and right lungs, heart, esophagus, and spinal cord. This approach was tested on 60 CT scans from the open-source AAPM Thoracic Auto-Segmentation Challenge dataset. Performance was measured using the Dice Similarity Coefficient (DSC). Our approach outperformed the best-performing method in the grand challenge for hard-to-segment structures like the esophagus and achieved comparable results for all other structures. Median DSC using our method was 0.97 (interquartile range [IQR]: 0.97-0.98) for the left and right lungs, 0.93 (IQR: 0.93-0.95) for the heart, 0.78 (IQR: 0.76-0.80) for the esophagus, and 0.88 (IQR: 0.86-0.89) for the spinal cord.
