Stereo Endoscopic Dataset

<p>This dataset was created based on a clinical procedure named Radical Prostatectomy with lymphadenectomy using da Vinci Xi surgical system (Intuitive Surgical Inc., USA) at European Institute of Oncology (IEO, Milan, Italy).&nbsp;<br> The videos were recorded with a 3D HD video recorder (HVO-3300MT, SONY, Tokyo).</p> <p>The dataset is divided into 6 folders concerning the steps of the procedure:&nbsp;<br> clips<br> dissection<br> irrigation<br> suction<br> suturing<br> traction</p> <p>Each step is then divided into four phases of the procedure:<br> 1 - collapse of the peritoneum<br> 2 - prostate removal<br> 3 - lymphadenectomy&nbsp;<br> 4 - anastomosis</p> <p>Each frame is labeled as follows: Camera_step_NumberOfTheFrame<br> for example, for the first frame, left lens of the Da Vinci endoscope, in the dissection step we have: L_dissection_000000.jpg</p> <p>In the folders, we also provide the text files created on Anvil (ground truth labels), which contain important surgical context information, including the steps, phases and types of surgical instruments.</p> <p>This dataset could be used for:</p> <p>1. Evaluation of surgical scene reconstruction models</p> <p>2.&nbsp;Training of unsupervised learning based networks</p> <p>3. Surgical workflow recognition based on stereo images or point clouds.&nbsp;</p> <p>To know more about this research, please see the manuscript:</p> <p>FRSR: Framework for Real-time Scene Reconstruction in Robot-Assisted Minimally Invasive Surgery.</p> <p>&nbsp;</p>