Medical Faculty, Heidelberg University, Im Neuenheimer Feld 672, 69120, Heidelberg, BW, Germany.
Department of Computer Science, Ulm University of Applied Sciences, Albert-Einstein-Allee 55, 89081, Ulm, BW, Germany.
Int J Comput Assist Radiol Surg. 2022 Sep;17(9):1633-1641. doi: 10.1007/s11548-022-02654-8. Epub 2022 May 23.
Recently, a large number of patients with acute ischemic stroke benefited from the use of thrombectomy, a minimally invasive intervention technique for mechanically removing thrombi from the cerebrovasculature. During thrombectomy, 2D digital subtraction angiography (DSA) image sequences are acquired simultaneously from the posterior-anterior and the lateral view to control whether thrombus removal was successful, and to possibly detect newly occluded areas caused by thrombus fragments split from the main thrombus. However, such new occlusions, which would be treatable by thrombectomy, may be overlooked during the intervention. To prevent this, we developed a deep learning-based approach to automatic classification of DSA sequences into thrombus-free and non-thrombus-free sequences.
We performed a retrospective study based on the single-center DSA data of thrombectomy patients. For classifying the DSA sequences, we applied Long Short-Term Memory or Gated Recurrent Unit networks and combined them with different Convolutional Neural Networks used as feature extractor. These network variants were trained on the DSA data by using five-fold cross-validation. The classification performance was determined on a test data set with respect to the Matthews correlation coefficient (MCC) and the area under the curve (AUC). Finally, we evaluated our models on patient cases, in which overlooking thrombi during thrombectomy had happened.
Depending on the specific model configuration used, we obtained a performance of up to 0.77[Formula: see text]0.94 for the MCC[Formula: see text]AUC, respectively. Additionally, overlooking thrombi could have been prevented in the reported patient cases, as our models would have classified the corresponding DSA sequences correctly.
Our deep learning-based approach to thrombus identification in DSA sequences yielded high accuracy on our single-center test data set. External validation is now required to investigate the generalizability of our method. As demonstrated, using this new approach may help reduce the incident risk of overlooking thrombi during thrombectomy in the future.
最近，大量急性缺血性脑卒中患者受益于血栓切除术，这是一种微创介入技术，可从脑血管系统中机械地清除血栓。在血栓切除术中，同时从前-后位和侧位采集二维数字减影血管造影（DSA）图像序列，以控制血栓清除是否成功，并可能检测到由主要血栓中分离出来的血栓碎片引起的新闭塞区域。然而，这些可能通过血栓切除术治疗的新闭塞可能会在干预过程中被忽视。为了防止这种情况，我们开发了一种基于深度学习的方法，用于自动将 DSA 序列分类为血栓自由和非血栓自由序列。
我们基于血栓切除术患者的单中心 DSA 数据进行了回顾性研究。为了对 DSA 序列进行分类，我们应用了长短期记忆或门控循环单元网络，并将其与作为特征提取器的不同卷积神经网络相结合。这些网络变体通过五折交叉验证在 DSA 数据上进行训练。使用马修斯相关系数（MCC）和曲线下面积（AUC）在测试数据集上确定分类性能。最后，我们在患者病例中评估了我们的模型，其中在血栓切除术中忽视了血栓。
根据使用的具体模型配置，我们获得了高达 0.77[Formula: see text]0.94 的 MCC[Formula: see text]AUC 性能。此外，在报告的患者病例中，忽视血栓的情况本可以得到预防，因为我们的模型会正确地对相应的 DSA 序列进行分类。
我们基于深度学习的方法对 DSA 序列中的血栓识别在我们的单中心测试数据集上取得了很高的准确性。现在需要进行外部验证，以研究我们方法的泛化能力。如所证明的，将来使用这种新方法可能有助于降低在血栓切除术中忽视血栓的事件风险。
