Salanitri Federica Proietto, Bellitto Giovanni, Irmakci Ismail, Palazzo Simone, Bagci Ulas, Spampinato Concetto
PeRCeiVe Lab, University of Catania, Catania, Italy.
CE, Ege University, Izmir, Turkey.
Mach Learn Med Imaging. 2021 Sep;12966:238-247. doi: 10.1007/978-3-030-87589-3_25. Epub 2021 Sep 21.
We propose a novel 3D fully convolutional deep network for automated pancreas segmentation from both MRI and CT scans. More specifically, the proposed model consists of a 3D encoder that learns to extract volume features at different scales; features taken at different points of the encoder hierarchy are then sent to multiple 3D decoders that individually predict intermediate segmentation maps. Finally, all segmentation maps are combined to obtain a unique detailed segmentation mask. We test our model on both CT and MRI imaging data: the publicly available NIH Pancreas-CT dataset (consisting of 82 contrast-enhanced CTs) and a private MRI dataset (consisting of 40 MRI scans). Experimental results show that our model outperforms existing methods on CT pancreas segmentation, obtaining an average Dice score of about 88%, and yields promising segmentation performance on a very challenging MRI data set (average Dice score is about 77%). Additional control experiments demonstrate that the achieved performance is due to the combination of our 3D fully-convolutional deep network and the hierarchical representation decoding, thus substantiating our architectural design.
我们提出了一种新颖的3D全卷积深度网络，用于从MRI和CT扫描中自动分割胰腺。具体而言，所提出的模型由一个3D编码器组成，该编码器学习提取不同尺度的体积特征；然后，将在编码器层次结构的不同点获取的特征发送到多个3D解码器，这些解码器分别预测中间分割图。最后，将所有分割图组合起来以获得唯一的详细分割掩码。我们在CT和MRI成像数据上测试了我们的模型：公开可用的NIH胰腺CT数据集（由82个增强CT组成）和一个私人MRI数据集（由40次MRI扫描组成）。实验结果表明，我们的模型在CT胰腺分割方面优于现有方法，平均Dice分数约为88%，并且在极具挑战性的MRI数据集上产生了有前景的分割性能（平均Dice分数约为77%）。额外的对照实验表明，所取得的性能归因于我们的3D全卷积深度网络和分层表示解码的结合，从而证实了我们的架构设计。
