PathOlOgics_RBCs

The PathOlOgics_RBCs datasets are structured within two directories: "PathOlOgics_RBCs Patches" and "PathOlOgics_RBCs Cells" Inside the "PathOlOgics_RBCs Patches" directory, there exist 25 folders, each designated for the patches from every slide/smear, aggregating a total of 47,366 source images/patches. The count of patches within the 25 slides/smears folders is as follows: 1690, 1709, 2697, 2403, 1905, 1803, 2964, 3049, 2464, 2080, 1894, 1852, 2590, 2263, 3328, 983, 1066, 935, 1131, 1237, 1874, 1393, 1277, 1199 and 1580, respectively. The naming convention for each patch consists of two components: the corresponding slide/smear number followed by the unique patch number. The distribution of slides/smears to their respective staining and scanning sources is as follows: the first source comprises slides 1, 5, 6, 8, and 25; the second source includes slides 2, 3, 4, 7, 9, and 11; the third source encompasses slides 14, 15, 19, 20, 22, 23, and 24; and the fourth source consists of slides 10, 12, 13, 16, 17, 18, and 21.<br>The second root directory, "PathOlOgics_RBCs Cells", is systematically structured into three primary folders: "Cropped images”, "Masks”, and "Segmented images”. Within each of these primary folders, there are nine subfolders, meticulously dedicated to each RBCs class, encompassing the following counts of cells: "Angled cells: 24,187", "Borderline ovalocytes: 35,540”, "Burr cells: 8,948”, "Fragmented RBCs: 7,186”, "Ovalocytes: 55,348”, "Rounded RBCs: 46,346”, "Teardrops: 16,298”, "Three-overlapping RBCs: 15,577”, and "Two-overlapping RBCs: 31,360”. Each of the total 240,790 cells is represented by its own cropped image, mask, and segmented image, all subjected to meticulous processing and individual scrutiny by the hematologists directly, ensuring adherence to rigorous scientific standards. Samples for every class were collected from each slide/smear. The naming scheme for the cropped image, mask, and segmented image of every cell adheres to a consistent format, starting with the slide/smear number, followed by the unique patch number, and concluding with the XYWH notation, accurately specifying the position on the patch. All these images are conveniently stored in the ".jpg" format.