The mitral valve is the largest valve of the heart and regulates the blood flow between the left atrium and the left ventricle. It is composed by two leaflets, the anterior and the posterior leaflet, that are attached to a fibrous ring known as the mitral annulus. In healthy patients, the left atrium contracts during diastole and the blood flows through the open MV into the left ventricle while it is dilating.

Echocardiography is a medical imaging technique that produces 2D pictures and videos of the heart using ultrasound waves generated by a transducer, scattered and reflected by biological tissues and read by a detector. Echocardiography is the standard imaging tool in the clinical routine to perform the diagnosis of most of heart diseases and dysfunctions, including MV diseases.

Mitral valve segmentation specifies a crucial first step to establish a machine learning pipeline that can support practitioners in performing multiple tasks including the diagnosis of mitral valve diseases, surgical planning, and intra-operative procedures. **Therefore, this task will be concerned with the segmentation of the mitral valve in echocardiography videos.**

The training set consists of 65 videos in which the mitral valve is labeled in three different frames in each video. Additionally, a bounding box surrounding the mitral valve is provided for each video. The test set consists of 20 videos. For each video in the test set the mitral valve should be segmented for **all** frames.