[口头报告]The automatic evaluation of steno-occlusive change on Moyamoya patients Using 3D Coordinate Attention Residual Networks - 报告详情

The automatic evaluation of steno-occlusive change on Moyamoya patients Using 3D Coordinate Attention Residual Networks
编号:60 访问权限:仅限参会人 更新:2021-10-30 18:36:15 浏览:173次 口头报告

报告开始:2021年11月13日 15:00 (Asia/Shanghai)

报告时间:15min

所在会议:[PS1] Plenary Session 1 [AI1] Workshop on AI

演示文件

提示:该报告下的文件权限为仅限参会人,您尚未登录,暂时无法查看。

摘要
Moyamoya is a specific chronic cerebrovascular occlusive disorder that is characterized by progressive bilateral stenosis of the terminal portion of the internal carotid artery and its main branches. The surgical procedure of intracranial and extracranial vascular reconstruction can reduce symptoms and lower the risk of complication. The surgery threshold depends on the preoperative brain vascular imaging evaluation whose accuracy is greatly influenced by the radiologist. This study aims to achieve a preoperative deep learning-based evaluation of moyamoya patients by distinguishing between stenosis and normal MCA. The deep learning model with fine-tuning was developed using 3D Coordinate Attention Residual Networks (CA-ResNet). A total of 50 patients with moyamoya disease and 50 normal controls were enrolled. The preoperative Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) was performed in all patients. For each patient, a region with 60mm thickness was extracted based on the reference points on MCA. The 3D CA-ResNet was trained based on sub-volumes  patches from selected regions and was tested using patch-based and patient-based methods. The performance of 3D CA-ResNet was compared with those of conventional networks including 3D ResNet and 3D Visual Geometry Group (VGG), where the Area Under the Curve (AUC) and classification accuracy were used as evaluation indicators. The final experiments showed the expected results in distinguishing between patients with moyamoya disease and normal controls. Specifically, the values of AUC and accuracy were 0.94 and 0.89 for patch-based and only one patient was misdiagnosed for patient-based testing in 3D CA-ResNet, respectively. In addition, the AUC value of 3D CA-ResNet was higher than the counterparts of conventional 3D ResNet or 3D VGG for patch-based testing (3D CA-ResNet: 0.94 vs. 3D ResNet: 0.85; 3D CA-ResNet: 0.94 vs. 3D VGG: 0.84). Besides, Gradient-weighted Class Activation Mapping based on heatmap was used to provide visual clues related to vascular stenosis location on MCA. The results indicated that all the three models above are able to differentially diagnose moyamoya disease from clinical TOF-MRA data, and the 3D CA-ResNet outperforms 3D ResNet and 3D VGG in evaluating vascular steno-occlusive change on moyamoya patients.
 
关键字
Moyamoya,Convolution neural network; Deep learning; Image classification,cerebrovascular stenosis
报告人
泽茹 张
北京大学

Master student major in medical imaging technique of Peking University

稿件作者
泽茹 张 北京大学
冰 吴 解放军总医院第七医学中心
一托 王 解放军总医院第七医学中心
帅 周 石家庄市人民医院
兆同 李 北京大学
嵩 高 北京大学
喆 王 北京大学
发表评论
验证码 看不清楚,更换一张
全部评论

倒计时

  • 00

  • 00

  • 00

  • 00

重要日期

摘要提交日期:

2021/08/31

2021/10/25

全文投稿日期:  

2021/09/15

2021/10/25

录取通知日期: 

2021/09/30

2021/11/01

会议日期:   2021-11-12-2021-11-14

联系我们

杨巾英 13675518597
智德波 15056085235
高嵩 13121880288
曹乐 15910809908
会议邮箱: icmipe2021@ustc.edu.cn