Hi everyone, I’m currently working on a skin disease segmentation\/classification project and I’m having a hard time finding a suitable dataset.<\/p>\n
I’m looking for a dataset that ideally has the skin lesion image with its corresponding binary segmentation masks (doesn’t need to be a mask as long as it has annotations) and disease labels.<\/p>\n
Most of the datasets I’ve found so far, such as ISIC, are heavily focused on melanoma and other cancerous skin lesions. I’m looking for something more focused on common\/non-cancerous skin conditions like acne, eczema, psoriasis, rosacea etc. <\/p>\n
It doesn’t necessarily have to contain all of these diseases, but having a good variety of common conditions would be great.<\/p>\n
I’ve found classification datasets like DermNet that contain several common conditions, but they don’t seem to provide the pixel-level binary masks I need for segmentation.<\/p>\n
If anyone knows of a dataset, research project, or even multiple datasets that could be combined to achieve this, I’d really appreciate it!<\/p>\n<\/div>\n
submitted by \/u\/Tamago_111 <\/a>
[link]<\/a><\/span> [comments]<\/a><\/span><\/p>
