top of page

Open Science

Image by Tobias Fischer

The AIMLab. has a culture and longstanding record for opening access to datasets. These resources have already been visited by thousands of researchers and been cited by dozens.

Open datasets

The SHDB-AF dataset contains raw Holter ECG recordings from 100 unique patients with paroxysmal atrial fibrillation, all of which have been manually annotated at the beat level by a cardiology fellow. Those annotations include (1) AF, (2) atrial flutter, (3) atrial tachycardia, and (4) other supraventricular tachycardias.

​

Tsutsui, K., Biton Brimer, S., & Behar, J. (2024). SHDB-AF: a Japanese Holter ECG database of atrial fibrillation (version 1.0.0). PhysioNet.

Leuven-Haifa High-Resolution Fundus Image Dataset for Retinal Blood Vessel Segmentation and Glaucoma Diagnosis

The Leuven-Haifa dataset contains 240 disc-centered fundus images of 224 unique patients. Among those 75 patients have normal tension glaucoma, 63 patients have high tension glaucoma, 30 patients have other eye diseases and 56 are healthy controls.

​

Van Eijgen, J., Fhima, J., Billen Moulin-Romsée, MI. et al. "Leuven-Haifa High-Resolution Fundus Image Dataset for Retinal Blood Vessel Segmentation and Glaucoma Diagnosis." Sci Data 11, 257 (2024)

The Non-Invasive Fetal ECG Arrhythmia Database (NIFEA DB) provides a series of fetal arrhythmias recordings (n=12) and a number of control normal rhythm recordings (n=14) performed using the non-invasive fetal electrocardiography (NI-FECG) technique.

​

Behar, Joachim A., et al. "Noninvasive fetal electrocardiography for the detection of fetal arrhythmias." Prenatal diagnosis 39.3 (2019): 178-187s

bottom of page