Questions about the DDTI dataset #215

In version v1（MedSegDiff）, the dataset description states:

"We evaluated the performance of our method for glaucoma, thyroid cancer, and melanoma diagnosis on the REFUGE-2 dataset (Fang et al., 2022), BraTs-2021 dataset (Baid et al., 2021), and DDTI dataset (Pedraza et al., 2015), which contain 1200, 2000, and 8046 samples, respectively."

Does this mean that the DDTI dataset used here contains 8046 images? Why is it that the DDTI dataset I found only has 637 images?