Semantic Instance Segmentation of Kidney Cysts in MR Images: A Fully Automated 3D Approach Developed Through Active Learning.
Semantic Instance Segmentation of Kidney Cysts in MR Images: A Fully Automated 3D Approach Developed Through Active Learning.
复制标题
DOI：
10.1007/s10278-021-00452-3
复制
发表时间：
2021-08
影响因子：
4.4
通讯作者：
Kline TL
中科院分区：
文献类型：
--
作者：
Gregory AV;Anaam DA;Vercnocke AJ;Edwards ME;Torres VE;Harris PC;Erickson BJ;Kline TL
肾总量 (TKV) 是用于监测疾病进展和对常染色体显性多囊肾病 (ADPKD) 患者进行临床试验分类的主要影像学生物标志物。然而，具有相似 TKV 的患者可能具有截然不同的囊性表现和表型。为了量化这些囊性差异，我们开发了第一个针对 MR 图像中肾脏的 3D 语义实例囊肿分割算法。我们将对象检测/定位任务和基于实例的分割任务重新表述为语义分割任务。这使我们能够有效地解决这个独特的成像问题，即使是对于有数千个囊肿的患者也是如此。为此，训练了卷积神经网络 (CNN) 来学习囊肿边缘和囊肿核心。通过将 3D 侵蚀形态学算子应用于图像的上采样版本，将图像从实例囊肿分割转换为语义边缘核心分割。缩小后的包囊标记为核心；侵蚀区域在二维上扩大并标记为边缘。该网络在 30 幅 MR 图像上进行训练，并使用四重交叉验证程序在 10 幅 MR 图像上进行验证。最终的集成模型在初始训练/验证期间未见过的 20 张 MR 图像上进行了测试。将测试集的结果与两个读者的分段进行比较。该模型的囊肿计数平均 R2 值为 0.94，囊肿总体积为 1.00，囊肿指数为 0.94，平均 Dice 系数为 0.85。这些结果证明了在 ADPKD 患者中自动进行囊肿分割的可行性。在线版本包含可在 10.1007/s10278-021-00452-3 获取的补充材料。
Total kidney volume (TKV) is the main imaging biomarker used to monitor disease progression and to classify patients affected by autosomal dominant polycystic kidney disease (ADPKD) for clinical trials. However, patients with similar TKVs may have drastically different cystic presentations and phenotypes. In an effort to quantify these cystic differences, we developed the first 3D semantic instance cyst segmentation algorithm for kidneys in MR images. We have reformulated both the object detection/localization task and the instance-based segmentation task into a semantic segmentation task. This allowed us to solve this unique imaging problem efficiently, even for patients with thousands of cysts. To do this, a convolutional neural network (CNN) was trained to learn cyst edges and cyst cores. Images were converted from instance cyst segmentations to semantic edge-core segmentations by applying a 3D erosion morphology operator to up-sampled versions of the images. The reduced cysts were labeled as core; the eroded areas were dilated in 2D and labeled as edge. The network was trained on 30 MR images and validated on 10 MR images using a fourfold cross-validation procedure. The final ensemble model was tested on 20 MR images not seen during the initial training/validation. The results from the test set were compared to segmentations from two readers. The presented model achieved an averaged R2 value of 0.94 for cyst count, 1.00 for total cyst volume, 0.94 for cystic index, and an averaged Dice coefficient of 0.85. These results demonstrate the feasibility of performing cyst segmentations automatically in ADPKD patients. The online version contains supplementary material available at 10.1007/s10278-021-00452-3.
登录
查看更多内容
影响因子：
13.2
作者：
Alam, Ahsan;Dahl, Neera K.;Bichet, Daniel G.
通讯作者：
Bichet, Daniel G.
DOI：
10.2215/cjn.10360818
发表时间：
2019-06-07
影响因子：
9.8
作者：
Bae, Kyongtae T.;Zhou, Wen;Harris, Peter C.
通讯作者：
Harris, Peter C.
DOI：
10.3174/ajnr.a5742
发表时间：
2018-09
期刊：
AJNR. American journal of neuroradiology
影响因子：
--
作者：
Chang PD;Kuoy E;Grinband J;Weinberg BD;Thompson M;Homo R;Chen J;Abcede H;Shafie M;Sugrue L;Filippi CG;Su MY;Yu W;Hess C;Chow D
通讯作者：
Chow D
影响因子：
5.5
作者：
Couteaux, V;Si-Mohamed, S.;Boussel, L.
通讯作者：
Boussel, L.
影响因子：
13.6
作者：
Harris, Peter C.;Bae, Kyongtae T.;Miller, J. Philip
通讯作者：
Miller, J. Philip