Background

Liver alignment between series/exams is challenged by dynamic morphology or variability in patient positioning or motion. Image registration can improve image interpretation and lesion co-localization. We assessed the performance of a convolutional neural network algorithm to register cross-sectional liver imaging series and compared its performance to manual image registration.

Methods

Three hundred fourteen patients, including internal and external datasets, who underwent gadoxetate disodium-enhanced magnetic resonance imaging for clinical care from 2011 to 2018, were retrospectively selected. Automated registration was applied to all 2,663 within-patient series pairs derived from these datasets. Additionally, 100 within-patient series pairs from the internal dataset were independently manually registered by expert readers. Liver overlap, image correlation, and intra-observation distances for manual versus automated registrations were compared using paired t tests. Influence of patient demographics, imaging characteristics, and liver uptake function was evaluated using univariate and multivariate mixed models.

Results

Compared to the manual, automated registration produced significantly lower intra-observation distance (p < 0.001) and higher liver overlap and image correlation (p < 0.001). Intra-exam automated registration achieved 0.88 mean liver overlap and 0.44 mean image correlation for the internal dataset and 0.91 and 0.41, respectively, for the external dataset. For inter-exam registration, mean overlap was 0.81 and image correlation 0.41. Older age, female sex, greater inter-series time interval, differing uptake, and greater voxel size differences independently reduced automated registration performance (p ≤ 0.020).

Conclusion

A fully automated algorithm accurately registered the liver within and between examinations, yielding better liver and focal observation co-localization compared to manual registration.

中文翻译：

---

基于全自动卷积神经网络的仿射算法改进了肝胆相 T1 加权 MR 图像上的肝脏配准和病变共定位。

背景

系列/检查之间的肝脏对齐受到患者定位或运动的动态形态或变化的挑战。图像配准可以改善图像解释和病变共定位。我们评估了卷积神经网络算法配准横截面肝脏成像系列的性能，并将其性能与手动图像配准进行了比较。

方法

回顾性选取 2011 年至 2018 年接受钆塞酸二钠增强磁共振成像临床护理的 314 名患者，包括内部和外部数据集。自动配准应用于源自这些数据集的所有 2,663 个患者内部系列对。此外，内部数据集中的 100 个患者内部系列对由专家读者独立手动注册。使用配对t检验比较手动与自动配准的肝脏重叠、图像相关性和观察内距离。使用单变量和多变量混合模型评估患者人口统计、影像特征和肝摄取功能的影响。

结果

与手动相比，自动配准产生显着更低的观察内距离 ( p < 0.001) 和更高的肝脏重叠和图像相关性 ( p < 0.001)。检查内自动配准对于内部数据集实现了 0.88 平均肝脏重叠和 0.44 平均图像相关性，对于外部数据集分别实现了 0.91 和 0.41。对于检查间配准，平均重叠率为 0.81，图像相关性为 0.41。年龄较大、女性、较大的系列间时间间隔、不同的摄取和较大的体素大小差异独立地降低了自动配准性能（p≤0.020 ）。

结论

全自动算法可以在检查期间和检查之间准确地配准肝脏，与手动配准相比，可以实现更好的肝脏和病灶观察共定位。