Dataset Open Access


Sara Moccia; Gabriele Omodeo Vanone; Elena De Momi; Leonardo S. Mattos

Citation Style Language JSON Export

  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.1162784", 
  "author": [
      "family": "Sara Moccia"
      "family": "Gabriele Omodeo Vanone"
      "family": "Elena De Momi"
      "family": "Leonardo S. Mattos"
  "issued": {
    "date-parts": [
  "abstract": "<p>The&nbsp;<strong>NBI-InfFrames </strong>dataset<strong>&nbsp;</strong>aims to provide the surgical data science&nbsp;community with a&nbsp;labeled dataset for the identification of informative endoscopic video&nbsp;frames.&nbsp;</p>\n\n<p>It&nbsp;is&nbsp;composed&nbsp;of 720&nbsp;video frames. The frames are manually&nbsp;extracted and labeled from 18 narrow-band laryngoscopic videos of 18 different patients affected by laryngeal spinocellular carcinoma (diagnosed after histopathological examination).&nbsp;</p>\n\n<p>The frames include 180 informative (<strong>I</strong>) video frames, 180 blurred (<strong>B</strong>)&nbsp;frames, 180 frames with saliva or specular reflections (<strong>S</strong>) and 180 underexposed (<strong>U</strong>) frames.</p>\n\n<p>The dataset was created for testing the method proposed in S. Moccia, et al. &quot;<em>Learning-based classification of informative laryngoscopic frames.</em>&quot; COMPUTER METHODS AND PROGRAM IN BIOMEDICINE, (accepted for publication).</p>\n\n<p>The folder<em>&nbsp;<strong></strong>&nbsp;</em>contains 3 subfolders (FOLD1, FOLD2, FOLD3), which are the 3 folds used for cross-validation purpose in the frame&nbsp;classification performance assessment. Data separation in the folds is performed both at image- and patient-level.</p>\n\n<p>Each subfolder contains 4 folders relative to the four frame classes, i.e., <strong>I</strong>, <strong>B</strong>, <strong>S</strong> and <strong>U</strong>.</p>", 
  "title": "NBI-InfFrames", 
  "type": "dataset", 
  "id": "1162784"
All versions This version
Views 1,7361,734
Downloads 1,0221,022
Data volume 175.2 GB175.2 GB
Unique views 1,5671,565
Unique downloads 615615


Cite as