The identification of lacunar infarcts is of great significance in elucidating the pathophysiological mechanism of Cerebral small vessel disease (cSVD).
This paper proposes a semi-automated 3D multi-scale residual convolutional network (3D ResNet) for lacunar infarcts detection.
We make the source code publicly available for researchers for validation and further improvement. The code includes the following files: main, read_data, and DLNetwork.
The paper entitled: "3D Multi-Scale Residual Network Toward Lacunar Infarcts Identification from MR Images with Minimal User Intervention" was submitted to a peer-reviewed journal.
When using our code for research publications, please cite our paper.