RT期刊文章SR电子T1卷积神经网络算法来确定偏侧性癫痫患者癫痫发作:乔摩根富林明神经病学神经学原理研究FD Lippincott Williams &威尔金斯10.1212 SP / WNL。首页0000000000207411 10.1212 / WNL。0000000000207411 A1 Erik Kaestner A1君饶A1艾伦j . Chang A1中艾琳王A1罗宾·M Busch A1西蒙·S·凯勒A1西奥多·红的A1 Daniel L Drane A1特拉维斯Stoub A1 Ezequiel Gleichgerrcht A1莱昂纳多Bonilha A1凯尔Hasenstab A1凯莉麦克唐纳年2023 UL //www.ez-admanager.com/content/early/2023/05/18/WNL.0000000000207411.abstract AB背景和首页目标:诊断放射学的新边疆的包容machine-assisted支持工具,促进细微病变的识别通常人眼不可见。结构神经影像中扮演着重要的角色在癫痫患者病变的鉴别,通常配合癫痫的焦点。这里我们探索潜在的卷积神经网络(CNN)来确定偏侧性癫痫发作的癫痫患者使用t1加权结构核磁共振扫描作为输入。方法:使用一个数据集的359例颞叶癫痫(框架)从7外科中心,我们测试了基于t1影像的CNN能否发作一侧进行分类整合与临床团队共识。CNN与随机模型(相比机会)和海马体积逻辑回归(目前clinically-available措施的比较)。此外,我们利用一个CNN特性可视化技术来识别区域用于分类的病人。结果:在100个运行,CNN模型整合了临床医生偏侧性平均78% (SD = 5.1%)表现最佳的运行模式实现89%的一致性。CNN优于随机模型的100%(51.7%)的平均一致性运行平均提高26.2%,表现优于海马体积模型的85%(71.7%)的平均一致性运行平均提高6.25%。特征可视化地图显示,除了内侧颞叶,地区外侧颞叶,扣带、中央前回辅助分类。Discussion: These extra-temporal lobe features underscore the importance of whole-brain models to highlight areas worthy of clinician scrutiny during temporal lobe epilepsy lateralization. This proof-of-concept study illustrates that a CNN applied to structural MRI data can visually aid clinician-led localization of epileptogenic zone and identify extra-hippocampal regions that may require additional radiological attention.Classification of Evidence: This study provides Class II evidence that in patients with drug-resistant unilateral temporal lobe epilepsy, a convolutional neural network algorithm derived from T1-weighted MR images can correctly classify seizure laterality.

map