We conducted a randomized controlled clinical trial to evaluate the efficacy of a brain-computer interface ( BCI ) -based visual and motor feedback motor imagery therapy system on cognitive, psychological and limb movement in hemiplegic stroke patients. We recruited more than 90 patients and randomly divided them into three groups : conventional treatment group, MI group and MI group based on brain-computer interface. The data set contains the evaluation data of these three groups of patients before and after treatment.


This article provides an introduction to the field of datasets, including their types, characteristics, and applications. Datasets refer to collections of data that have been organized for specific purposes. They can come in various forms, including structured data, unstructured data, and semi-structured data. Each type of dataset has its own unique characteristics and uses. For example, structured data typically includes datasets that have been organized into tables and rows, such as spreadsheets or databases, while unstructured data typically includes text, images, and videos.


This data set contains:


-88 patients


-the noncontrast computed tomography (NCCT) and computed tomography angiography (CTA) performed before thrombectomy.


-the VOI of blood clot for NCCT and CTA.


For each patient NCCT data is marked "2" and CTA is marked "1".


This dataset contains the trained model that accompanies the publication of the same name:

 Anup Tuladhar*, Serena Schimert*, Deepthi Rajashekar, Helge C. Kniep, Jens Fiehler, Nils D. Forkert, "Automatic Segmentation of Stroke Lesions in Non-Contrast Computed Tomography Datasets With Convolutional Neural Networks," in IEEE Access, vol. 8, pp. 94871-94879, 2020, doi:10.1109/ACCESS.2020.2995632. *: Co-first authors



The proposed signals are used  for electromagnetic-based stroke classification.  Six realistic head phantom computed from MRI scans, is surrounded by an antenna array of 16 dipole antennas distributed uniformly around the head. These antennas are deployed in a fixed circular array around the head, at a distance of approximately 2-3 mm from the head. A Gaussian pulse covering the bandwidth from 0:7 to 2 GHz is emitted from each of the antennas, sequentially, while all of the antennas capture the scattered signals. Since 16 antennas were used, there are a total of 256 channel signals (i.e.