论文标题
CNN-LSTM结构，用于检测CT扫描中颅内出血
A CNN-LSTM Architecture for Detection of Intracranial Hemorrhage on CT scans
论文作者
论文摘要
我们提出了一种新的方法，将卷积神经网络（CNN）与长期记忆（LSTM）机制相结合，以准确预测计算机内层析成像（CT）扫描中颅内出血。 CNN在LSTM负责链接跨切片的特征时扮演着切片的特征提取器的角色。整个体系结构都是端对端训练的，输入是通过堆叠单个切片的3个不同观看窗口形成的类似RGB的图像。我们在最近的RSNA颅内出血检测挑战和CQ500数据集中验证了该方法。对于RSNA挑战，我们最好的单个模型在排行榜上实现了0.0522的加权日志损失，这与前3％的表现相当，几乎所有这些都利用了集合学习。重要的是，我们的方法概括得很好：在RSNA数据集上训练的模型显着优于2D模型，该模型不考虑切片之间的关系，在CQ500上。我们的代码和模型可在https://github.com/vinbdi-medicalimagingteam/midl2020-cnnlstm-ich上公开避免。
We propose a novel method that combines a convolutional neural network (CNN) with a long short-term memory (LSTM) mechanism for accurate prediction of intracranial hemorrhage on computed tomography (CT) scans. The CNN plays the role of a slice-wise feature extractor while the LSTM is responsible for linking the features across slices. The whole architecture is trained end-to-end with input being an RGB-like image formed by stacking 3 different viewing windows of a single slice. We validate the method on the recent RSNA Intracranial Hemorrhage Detection challenge and on the CQ500 dataset. For the RSNA challenge, our best single model achieves a weighted log loss of 0.0522 on the leaderboard, which is comparable to the top 3% performances, almost all of which make use of ensemble learning. Importantly, our method generalizes very well: the model trained on the RSNA dataset significantly outperforms the 2D model, which does not take into account the relationship between slices, on CQ500. Our codes and models is publicly avaiable at https://github.com/VinBDI-MedicalImagingTeam/midl2020-cnnlstm-ich.
