PFUS1: Premier Pelvic Floor Ultrasound Segmentation Dataset

<pre><br>This dataset comprises pelvic floor ultrasound images in the midsagittal plane, involving segmentation of eight structures, from 110 patients. <br><br>The dataset is structured as follows: at the top level, there is a directory named "data" containing 110 folders, each corresponding to a patient, named "PXXX", where XXX is the patient identifier (from 000 to 109).<br><br>Each patient folder contains two files per image frame: a PNG file with the ultrasound image and a JSON file with the segmentation polygons. Each file is named "frame\_YYY\.png" or "frame\_YYY\.json" respectively, where YYY is the video frame number.<br><br>Each JSON file with the segmentation polygons is structured as a list of eight dictionaries. Each dictionary has two keys: "label" and "pol". The "label" key identifies the organ with a string, and the "pol" key is a list of pairs (x, y) defining the points list of the polygon. An example of a JSON file is shown below:<br><br><br> [<br> { <br> "pol": [[800, 400], [848, 320], ...., [796, 401]],<br> "label": "Levator ani muscle"<br> },<br> { <br> "pol": [[750, 371], [794, 384], ...., [726, 426]],<br> "label": "Rectum"<br> },<br> ...<br> ...<br> ...<br><br> ]</pre>