当前位置: X-MOL 学术Neuroinformatics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Towards Automated Brain Aneurysm Detection in TOF-MRA: Open Data, Weak Labels, and Anatomical Knowledge
Neuroinformatics ( IF 3 ) Pub Date : 2022-08-18 , DOI: 10.1007/s12021-022-09597-0
Tommaso Di Noto 1 , Guillaume Marie 1 , Sebastien Tourbier 1 , Yasser Alemán-Gómez 1, 2 , Oscar Esteban 1 , Guillaume Saliou 1 , Meritxell Bach Cuadra 3 , Patric Hagmann 1 , Jonas Richiardi 1
Affiliation  

Brain aneurysm detection in Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) has undergone drastic improvements with the advent of Deep Learning (DL). However, performances of supervised DL models heavily rely on the quantity of labeled samples, which are extremely costly to obtain. Here, we present a DL model for aneurysm detection that overcomes the issue with “weak” labels: oversized annotations which are considerably faster to create. Our weak labels resulted to be four times faster to generate than their voxel-wise counterparts. In addition, our model leverages prior anatomical knowledge by focusing only on plausible locations for aneurysm occurrence. We first train and evaluate our model through cross-validation on an in-house TOF-MRA dataset comprising 284 subjects (170 females / 127 healthy controls / 157 patients with 198 aneurysms). On this dataset, our best model achieved a sensitivity of 83%, with False Positive (FP) rate of 0.8 per patient. To assess model generalizability, we then participated in a challenge for aneurysm detection with TOF-MRA data (93 patients, 20 controls, 125 aneurysms). On the public challenge, sensitivity was 68% (FP rate = 2.5), ranking 4th/18 on the open leaderboard. We found no significant difference in sensitivity between aneurysm risk-of-rupture groups (p = 0.75), locations (p = 0.72), or sizes (p = 0.15). Data, code and model weights are released under permissive licenses. We demonstrate that weak labels and anatomical knowledge can alleviate the necessity for prohibitively expensive voxel-wise annotations.



中文翻译:

TOF-MRA 中的脑动脉瘤自动化检测:开放数据、弱标签和解剖学知识

随着深度学习 (DL) 的出现,飞行时间磁共振血管造影 (TOF-MRA) 中的脑动脉瘤检测得到了显着改进。然而,有监督的 DL 模型的性能在很大程度上依赖于标记样本的数量,而这些样本的获取成本非常高。在这里,我们提出了一个用于动脉瘤检测的 DL 模型,它克服了“弱”标签的问题:创建速度相当快的超大注释。我们的弱标签的生成速度是体素对应标签的四倍。此外,我们的模型通过仅关注动脉瘤发生的合理位置来利用先前的解剖学知识。我们首先通过对包含 284 名受试者(170 名女性/127 名健康对照者/157 名患有 198 个动脉瘤的患者)的内部 TOF-MRA 数据集进行交叉验证来训练和评估我们的模型。在这个数据集上,我们最好的模型达到了 83% 的灵敏度,每个患者的假阳性 (FP) 率为 0.8。为了评估模型的普遍性,我们随后参加了使用 TOF-MRA 数据进行动脉瘤检测的挑战(93 名患者、20 名对照组、125 个动脉瘤)。在公开挑战中,敏感度为 68%(FP 率 = 2.5),在公开排行榜上排名第 4/18。我们发现动脉瘤破裂风险组之间的敏感性没有显着差异(然后我们参加了使用 TOF-MRA 数据进行动脉瘤检测的挑战(93 名患者、20 名对照组、125 个动脉瘤)。在公开挑战中,敏感度为 68%(FP 率 = 2.5),在公开排行榜上排名第 4/18。我们发现动脉瘤破裂风险组之间的敏感性没有显着差异(然后我们参加了使用 TOF-MRA 数据进行动脉瘤检测的挑战(93 名患者、20 名对照组、125 个动脉瘤)。在公开挑战中,敏感度为 68%(FP 率 = 2.5),在公开排行榜上排名第 4/18。我们发现动脉瘤破裂风险组之间的敏感性没有显着差异(p  = 0.75)、位置 ( p  = 0.72) 或大小 ( p  = 0.15)。数据、代码和模型权重在宽松许可下发布。我们证明弱标签和解剖学知识可以减轻昂贵的体素注释的必要性。

更新日期:2022-08-19
down
wechat
bug