Laryngeal Dataset

The dataset in <em><strong>laryngeal dataset.tar </strong></em>contains 1320 patches of healthy and early-stage cancerous laryngeal tissues. The patches (100x100 pixels) were manually extracted from 33 narrow-band laryngoscopic images of 33 different patients affected by laryngeal spinocellular carcinoma (diagnosed after histopathological examination). Specifically, four tissue classes were considered (330 patches/tissue class): He (healthy tissue), Hbv (tissue with hypertrophic vessels), Le (tissue with leukoplakia) and IPCL (tissue with intrapapillary capillary loops). The dataset was created for testing the method proposed in <em>Moccia, Sara, et al. "Confident texture-based laryngeal tissue classification for early stage diagnosis support." JOURNAL OF MEDICAL IMAGING 4.03 (2017): 1-10.</em> The folder<em> <strong>laryngeal dataset.tar</strong> </em>contains 3 subfolders (FOLD 1, FOLD 2, FOLD 3), which are the 3 folds used for cross-validation purpose in the tissue classification performance assessment. Each subfolder contains 4 folders relative to the four tissue classes, i.e., Le, He, Hbv, IPCL. ---------------------------------------------------------------------------------------------------------------------------------------------------------- If you want to use the dataset, please cite <em>Moccia, Sara, et al. "Confident texture-based laryngeal tissue classification for early stage diagnosis support." JOURNAL OF MEDICAL IMAGING 4.03 (2017): 1-10.</em>