OCT-MoS, a dataset of mouse skin squamous cell carcinoma stages by full-field optical coherence tomography
The incidence of cutaneous squamous cell carcinoma (SCC) has increased in recent years, while it remains as an understudied subject. Current methods for the diagnose of skin cancer are either invasive, present a low resolution, or images that are difficult to interpret. Full-field optical coherence tomography (FF-OCT) has proven its potential as a non-invasive imaging technique of epithelial tissue. The sub-micrometer resolution offered by FF-OCT is able to show fine features such as cell nuclei, blood vessels, and fibrous structures in the dermis. However, not many physicians are familiar with the images derived from this technique. Using a well-known mouse model of SCC, we acquired volumetric data from skin samples at different stages of the disease using our home-made FF-OCT system. We present OCT-Mouse Skin (OCT-MoS) dataset, a curated dataset of 3400 annotated tomograms distributed into four classes, representing different stages in the development of SCC: normal, dysplasia, papilloma, and SCC. This dataset has a high potential for reuse in areas such as cancer research, medical training, image processing, and deep learning.
Calderon-Delgado M, Lin MY, Tjiu JW, Huang SL
Browse Data in IDR
idr0098-huang-octmos/experimentA ()
idr0098-huang-octmos/experimentB ()
BioFile Finder
BioFile Finder is a tool for filtering, sorting and grouping tabular data. Each table below is loaded from IDR as a Parquet file, with each row representing an image. Images can be selected in BioFile Finder and the "Download" link will open them in the IDR viewer.
idr0098-huang-octmos ( , parquet: )
experimentA ( , parquet: )
experimentB ( , parquet: )
Download
To download original image files in your browser, you can access original data.
Download as JSON.
For more download options, including bulk download using Globus or FTP clients, see the IDR Data download page.
Copyright: Calderon-Delgado et al
Data Publisher: University of Dundee
