Unsupervised Detection of Rare Events in Liquid Biopsy Assays

This dataset contains immunofluorescence microscopy images of blood samples used to develop a deep generative model for unsupervised rare cell detection. The samples consist of peripheral blood from normal donors spiked with cancer-related cells.Images are provided as <code>.jpg</code> files at a resolution of 1362×1004 pixels. Each microscopy image is divided into 2,304 tiles, with filenames following the format <code>Tile{tile_number_id}.jpg</code>. The tile IDs are organized by fluorescence channel as follows:Tiles <b>1–2304</b>: DAPI channelTiles <b>2305–4608</b>: PanCK channelTiles <b>4609–6912</b>: CD45/31 channelTiles <b>9217–11520</b>: Vimentin channelCorresponding tiles across channels share the same spatial location in the original image. For example, tiles 1, 2305, 4609, and 9217 represent the DAPI, PanCK, CD45/31, and Vimentin channels, respectively, for the same field of view.