IEEE Trans Med Imaging. 2019 May;38(5):1185-1196. doi: 10.1109/TMI.2018.2881110. Epub 2018 Nov 13.
The findings of splenomegaly, abnormal enlargement of the spleen, is a non-invasive clinical biomarker for liver and spleen diseases. Automated segmentation methods are essential to efficiently quantify splenomegaly from clinically acquired abdominal magnetic resonance imaging (MRI) scans. However, the task is challenging due to: 1) large anatomical and spatial variations of splenomegaly; 2) large inter- and intra-scan intensity variations on multi-modal MRI; and 3) limited numbers of labeled splenomegaly scans. In this paper, we propose the Splenomegaly Segmentation Network (SS-Net) to introduce the deep convolutional neural network (DCNN) approaches in multi-modal MRI splenomegaly segmentation. Large convolutional kernel layers were used to address the spatial and anatomical variations, while the conditional generative adversarial networks were employed to leverage the segmentation performance of SS-Net in an end-to-end manner. A clinically acquired cohort containing both T1-weighted (T1w) and T2-weighted (T2w) MRI splenomegaly scans was used to train and evaluate the performance of multi-atlas segmentation (MAS), 2D DCNN networks, and a 3-D DCNN network. From the experimental results, the DCNN methods achieved superior performance to the state-of-the-art MAS method. The proposed SS-Net method has achieved the highest median and mean Dice scores among the investigated baseline DCNN methods.
脾肿大的发现，即脾脏异常增大，是肝脏和脾脏疾病的一种非侵入性临床生物标志物。自动分割方法对于从临床获得的腹部磁共振成像（MRI）扫描中有效地量化脾肿大至关重要。然而，由于以下原因，这项任务具有挑战性：1）脾肿大的解剖和空间变化很大；2）多模态 MRI 上的强度变化很大；3）标记的脾肿大扫描数量有限。在本文中，我们提出了脾肿大分割网络（SS-Net），以将深度卷积神经网络（DCNN）方法引入多模态 MRI 脾肿大分割中。使用大卷积核层来解决空间和解剖学变化问题，同时利用条件生成对抗网络以端到端的方式利用 SS-Net 的分割性能。使用包含 T1 加权（T1w）和 T2 加权（T2w）MRI 脾肿大扫描的临床采集队列来训练和评估多图谱分割（MAS）、2D DCNN 网络和 3D DCNN 网络的性能。从实验结果来看，DCNN 方法的性能优于最先进的 MAS 方法。所提出的 SS-Net 方法在研究的基线 DCNN 方法中实现了最高的中位数和平均 Dice 分数。
