Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
The University of Texas MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences, Houston, TX, USA.
Sci Rep. 2024 Feb 26;14(1):4678. doi: 10.1038/s41598-024-53997-y.
Manual delineation of liver segments on computed tomography (CT) images for primary/secondary liver cancer (LC) patients is time-intensive and prone to inter/intra-observer variability. Therefore, we developed a deep-learning-based model to auto-contour liver segments and spleen on contrast-enhanced CT (CECT) images. We trained two models using 3d patch-based attention U-Net ([Formula: see text] and 3d full resolution of nnU-Net ([Formula: see text] to determine the best architecture ([Formula: see text]. BA was used with vessels ([Formula: see text] and spleen ([Formula: see text] to assess the impact on segment contouring. Models were trained, validated, and tested on 160 ([Formula: see text]), 40 ([Formula: see text]), 33 ([Formula: see text]), 25 (C) and 20 (C) CECT of LC patients. [Formula: see text] outperformed [Formula: see text] across all segments with median differences in Dice similarity coefficients (DSC) ranging 0.03-0.05 (p < 0.05). [Formula: see text], and [Formula: see text] were not statistically different (p > 0.05), however, both were slightly better than [Formula: see text] by DSC up to 0.02. The final model, [Formula: see text], showed a mean DSC of 0.89, 0.82, 0.88, 0.87, 0.96, and 0.95 for segments 1, 2, 3, 4, 5-8, and spleen, respectively on entire test sets. Qualitatively, more than 85% of cases showed a Likert score [Formula: see text] 3 on test sets. Our final model provides clinically acceptable contours of liver segments and spleen which are usable in treatment planning.
基于手动勾画肝脏分段的计算机断层扫描（CT）图像在原发性/继发性肝癌（LC）患者中耗时且易受观察者内/间变异性的影响。因此，我们开发了一种基于深度学习的模型，用于自动勾画增强 CT（CECT）图像上的肝脏和脾脏分段。我们使用基于 3d 补丁的注意力 U-Net（[Formula: see text]和 3d 全分辨率 nnU-Net（[Formula: see text]来训练两个模型，以确定最佳架构（[Formula: see text]。使用血管（[Formula: see text]和脾脏（[Formula: see text]来评估 BA 对分段轮廓的影响。在 160 个（[Formula: see text]）、40 个（[Formula: see text]）、33 个（[Formula: see text]）、25 个（C）和 20 个（C）LC 患者的 CECT 上进行了模型的训练、验证和测试。[Formula: see text]在所有分段中均优于[Formula: see text]，Dice 相似系数（DSC）的中位数差异范围为 0.03-0.05（p < 0.05）。[Formula: see text]和[Formula: see text]之间没有统计学差异（p > 0.05），但 DSC 略高于[Formula: see text]，最高可达 0.02。最终模型[Formula: see text]在整个测试集中分别对分段 1、2、3、4、5-8 和脾脏的平均 DSC 为 0.89、0.82、0.88、0.87、0.96 和 0.95。定性分析表明，测试集中超过 85%的病例获得了 Likert 评分[Formula: see text]3。我们的最终模型提供了可用于治疗计划的临床可接受的肝脏分段和脾脏轮廓。
