Automated segmentation of multiparametric magnetic resonance images for cerebral AVM radiosurgery planning: a deep learning approach.
Automated segmentation of multiparametric magnetic resonance images for cerebral AVM radiosurgery planning: a deep learning approach.
复制标题
DOI：
10.1038/s41598-021-04466-3
复制
发表时间：
2022-01-17
影响因子：
4.6
通讯作者：
Hattangadi-Gluth JA
中科院分区：
文献类型：
--
作者：
Simon AB;Hurt B;Karunamuni R;Kim GY;Moiseenko V;Olson S;Farid N;Hsiao A;Hattangadi-Gluth JA
脑动静脉畸形（AVM）的立体定向放射手术计划由于不同成像方式下AVM病灶外观的变化而变得复杂。我们开发了一种深度学习方法，从AVM患者的多个高分辨率磁共振成像/血管造影（MRI/MRA）序列中自动分割脑血管解剖图，目的是促进目标描绘。23例AVM患者接受了放射外科评估并进行了多参数MRI/MRA。采用半自动化和手动混合方法标记动脉、静脉、脑实质、脑脊液（CSF）和栓塞血管的MRI/ mra。接下来，这些标签被用来训练一个卷积神经网络来执行这个任务。17例患者（6362片）的影像用于训练，6例患者（1224片）的影像用于验证。采用骰子相似系数（DSC）评价性能。动脉、静脉、脑实质和脑脊液的分类效果较好，验证图像集的dsc分别为0.86、0.91、0.98和0.91。栓塞血管的表现较低，DSC为0.75。这证明了多参数MRI/MRA可以生成准确、高分辨率的脑血管解剖图的原理证明。它们在放射外科计划中的应用的临床验证是有保证的。
Stereotactic radiosurgery planning for cerebral arteriovenous malformations (AVM) is complicated by the variability in appearance of an AVM nidus across different imaging modalities. We developed a deep learning approach to automatically segment cerebrovascular-anatomical maps from multiple high-resolution magnetic resonance imaging/angiography (MRI/MRA) sequences in AVM patients, with the goal of facilitating target delineation. Twenty-three AVM patients who were evaluated for radiosurgery and underwent multi-parametric MRI/MRA were included. A hybrid semi-automated and manual approach was used to label MRI/MRAs with arteries, veins, brain parenchyma, cerebral spinal fluid (CSF), and embolized vessels. Next, these labels were used to train a convolutional neural network to perform this task. Imaging from 17 patients (6362 image slices) was used for training, and 6 patients (1224 slices) for validation. Performance was evaluated by Dice Similarity Coefficient (DSC). Classification performance was good for arteries, veins, brain parenchyma, and CSF, with DSCs of 0.86, 0.91, 0.98, and 0.91, respectively in the validation image set. Performance was lower for embolized vessels, with a DSC of 0.75. This demonstrates the proof of principle that accurate, high-resolution cerebrovascular-anatomical maps can be generated from multiparametric MRI/MRA. Clinical validation of their utility in radiosurgery planning is warranted.
登录
查看更多内容
影响因子：
5.7
作者：
Sherer, Michael, V;Lin, Diana;Elguindi, Sharif;Duke, Simon;Tan, Li-Tee;Cacicedo, Jon;Dahele, Max;Gillespie, Erin F.
通讯作者：
Gillespie, Erin F.
影响因子：
4.1
作者：
BROWN, RD;WIEBERS, DO;MACIUNAS, RJ
通讯作者：
MACIUNAS, RJ
影响因子：
5.5
作者：
Geibprasert, Sasikhan;Pongpech, Sirintara;Krings, Timo
通讯作者：
Krings, Timo
影响因子：
4.8
作者：
Rubin, Benjamin A.;Brunswick, Andrew;Kondziolka, Douglas
通讯作者：
Kondziolka, Douglas
影响因子：
4.3
作者：
Avadiappan, Sivakami;Payabvash, Seyedmehdi;Lupo, Janine M.
通讯作者：
Lupo, Janine M.