Deep Learning-Based 3D U-Net Cerebral Aneurysm Detection

2021 ◽  
pp. 31-38
Author(s):  
Matthias Ivantsits ◽  
Jan-Martin Kuhnigk ◽  
Markus Huellebrand ◽  
Titus Kuehne ◽  
Anja Hennemuth
Keyword(s):  
Deep Learning ◽  
Cerebral Aneurysm ◽  
Aneurysm Detection

Deep learning for automated cerebral aneurysm detection on computed tomography images

2020 ◽  
Vol 15 (4) ◽  
pp. 715-723 ◽  
Author(s):  
Xilei Dai ◽  
Lixiang Huang ◽  
Yi Qian ◽  
Shuang Xia ◽  
Winston Chong ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Cerebral Aneurysm ◽  
Computed Tomography Images ◽  
Aneurysm Detection

Using convolutional neural network and long short time memory to automatically detect aneurysm on 2D DSA images (Preprint)

2021 ◽  
Author(s):  
JunHua Liao ◽  
LunXin Liu ◽  
HaiHan Duan ◽  
YunZhi Huang ◽  
LiangXue Zhou ◽  
...  
Keyword(s):  
Deep Learning ◽  
Intracranial Aneurysm ◽  
Spatial Information ◽  
Diagnostic System ◽  
Two Stage ◽  
Regional Localization ◽  
Detection Stage ◽  
Aneurysm Detection ◽  
Sensitivity Specificity ◽  
Computation Load

BACKGROUND It is hard to distinguish cerebral aneurysm from overlap vessels based on the 2D DSA images, for its lack the spatial information. OBJECTIVE The aim of this study is to construct a deep learning diagnostic system to improve the ability of detecting the PCoA aneurysm on 2D-DSA images and validate the efficiency of deep learning diagnostic system in 2D-DSA aneurysm detecting. METHODS We proposed a two stage detecting system. First, we established the regional localization stage (RLS) to automatically locate specific detection region of raw 2D-DSA sequences. And then, in the intracranial aneurysm detection stage (IADS) ,we build three different frames, RetinaNet, RetinaNet+LSTM, Bi-input+RetinaNet+LSTM, to detect the aneurysms. Each of the frame had fivefold cross-validation scheme. The area under curve (AUC), the receiver operating characteristic (ROC) curve, and mean average precision (mAP) were used to validate the efficiency of different frames. The sensitivity, specificity and accuracy were used to identify the ability of different frames. RESULTS 255 patients with PCoA aneurysms and 20 patients without aneurysm were included in this study. The best results of AUC of the RetinaNet, RetinaNet+LSTM, and Bi-input+RetinaNet+LSTM were 0.95, 0.96, and 0.97, respectively. The sensitivity of the RetinaNet, RetinaNet+LSTM, and Bi-input+RetinaNet+LSTM were 81.65% (59.40% to 94.76%), 87.91% (64.24% to 98.27%), 84.50% (69.57% to 93.97%), respectively. The specificity of the RetinaNet, RetinaNet+LSTM, and Bi-input+RetinaNet+LSTM were 88.89% (66.73% to 98.41%), 88.12% (66.06% to 98.08%), and 88.50% (74.44% to 96.39%), respectively. The accuracy of the RetinaNet, RetinaNet+LSTM, and Bi-input+RetinaNet+LSTM were 92.71% (71.29% to 99.54%), 89.42% (68.13% to 98.49%), and 91.00% (77.63% to 97.72%), respectively. CONCLUSIONS Two stage aneurysm detecting system can reduce time cost and the computation load. According to our results, more spatial and temporal information can help improve the performance of the frames, so that Bi-input+RetinaNet+LSTM has the best performance compared to other frames. And our study can demonstrate that our system was feasible to assist doctor to detect intracranial aneurysm on 2D-DSA images.

scholarly journals Prediction of Cerebral Aneurysm Hemodynamics With Porous-Medium Models of Flow-Diverting Stents via Deep Learning

2021 ◽  
Vol 12 ◽  
Author(s):  
Gaoyang Li ◽  
Xiaorui Song ◽  
Haoran Wang ◽  
Siwei Liu ◽  
Jiayuan Ji ◽  
...  
Keyword(s):  
Porous Medium ◽  
Deep Learning ◽  
Cerebral Aneurysm ◽  
Stent Placement ◽  
Point Cloud ◽  
Computational Cost ◽  
Learning Method ◽  
Method Error ◽  
Complex Operation ◽  
Before And After

The interventional treatment of cerebral aneurysm requires hemodynamics to provide proper guidance. Computational fluid dynamics (CFD) is gradually used in calculating cerebral aneurysm hemodynamics before and after flow-diverting (FD) stent placement. However, the complex operation (such as the construction and placement simulation of fully resolved or porous-medium FD stent) and high computational cost of CFD hinder its application. To solve these problems, we applied aneurysm hemodynamics point cloud data sets and a deep learning network with double input and sampling channels. The flexible point cloud format can represent the geometry and flow distribution of different aneurysms before and after FD stent (represented by porous medium layer) placement with high resolution. The proposed network can directly analyze the relationship between aneurysm geometry and internal hemodynamics, to further realize the flow field prediction and avoid the complex operation of CFD. Statistical analysis shows that the prediction results of hemodynamics by our deep learning method are consistent with the CFD method (error function <13%), but the calculation time is significantly reduced 1,800 times. This study develops a novel deep learning method that can accurately predict the hemodynamics of different cerebral aneurysms before and after FD stent placement with low computational cost and simple operation processes.

Cerebral Aneurysm Detection and Analysis Challenge 2020 (CADA)

2021 ◽  
pp. 3-17 ◽  
Author(s):  
Matthias Ivantsits ◽  
Leonid Goubergrits ◽  
Jan-Martin Kuhnigk ◽  
Markus Huellebrand ◽  
Jan Brüning ◽  
...  
Keyword(s):  
Cerebral Aneurysm ◽  
Aneurysm Detection

scholarly journals Clinically Applicable Deep Learning for Intracranial Aneurysm Detection in Computed Tomography Angiography Images: A Comprehensive Multicohort Study

2020 ◽  
Author(s):  
Zhao Shi ◽  
Chongchang Miao ◽  
Chengwei Pan ◽  
Xue Chai ◽  
Xiu Li Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Intracranial Aneurysm ◽  
High Confidence ◽  
Common Life ◽  
Bone Removal ◽  
Life Threatening ◽  
Diagnosis Tool ◽  
Aneurysm Detection ◽  
A Prospective Study ◽  
Human Burden

AbstractIntracranial aneurysm is a common life-threatening disease. CTA is recommended as a standard diagnosis tool, while the interpretation is time-consuming and challenging. We presented a novel deep-learning-based framework trained on 1,177 DSA verified bone-removal CTA cases. The framework had excellent tolerance to the influence of occult cases of CTA-negative but DSA-positive aneurysms, image quality, and manufacturers. Simulated real-world studies were conducted in consecutive internal and external cohorts, achieving improved sensitivity and negative predictive value than radiologists. A specific cohort of suspected acute ischemic stroke was employed and found 96.8% predicted-negative cases can be trusted with high confidence, leading to reducing in human burden. A prospective study is warranted to determine whether the algorithm could improve patients’ care in comparison to radiologists’ assessment.

scholarly journals Automated Aneurysm Detection: Emerging from the Shallow End of the Deep Learning Pool

Radiology ◽  
2021 ◽  
Vol 298 (1) ◽  
pp. 164-165
Author(s):  
David F. Kallmes ◽  
Bradley J. Erickson
Keyword(s):  
Deep Learning ◽  
Aneurysm Detection

A Method Towards Cerebral Aneurysm Detection in Clinical Settings

2019 ◽  
pp. 8-15 ◽  
Author(s):  
Sarada Prasad Dakua ◽  
Julien Abinahed ◽  
Abdulla Al-Ansari ◽  
Pablo Garcia Bermejo ◽  
Ayaman Zakaria ◽  
...  
Keyword(s):  
Cerebral Aneurysm ◽  
Clinical Settings ◽  
Aneurysm Detection
Sign in / Sign up

Export Citation Format

Share Document