FHRMA dataset for FS detection (FHRMA dataset for fetal heart rate false signal detection)

FHRMA is an open-source project for Fetal Heart Rate Morphological Analysis containing Matlab source code and datasets. As a sub-project, it includes a deep learning method and dataset for automatic identification of the maternal heart rate (MHR) and, more generally, false signals (FSs) on fetal heart rate (FHR) recordings. The challenge concerns particularly the FHR signal recorded with Doppler sensors, on which MHR interference and other FSs are particularly common, but the dataset also includes FHR recorded with scalp-ECG. The training and validation dataset contained 1030 expert-annotated periods (mean duration: 36 min) from 635 recordings. Labels consist of annotating each time sample as either 1: False signal; 0: True signal, or -1: do not know or irrelevant. 

Test datasets are also available, but the test dataset annotations are not available on an open-access basis. Researchers who want to evaluate their models will have to send their results for evaluation; hence, a competition has been opened. 

As a baseline method and to help get started, a GRU-based model coded in Python/tensorflow is available. 

More details on the dataset, the problem description and the open-source method are available in: [Use of Deep Learning to Detect the Maternal Heart Rate andFalse Signals on Fetal Heart Rate Recordings] (https://www.mdpi.com/2079-6374/12/9/691)