Artificial intelligence-assisted identification of skin lesions associated with chronic venous insufficiency
Ko Eun Kim, Jin Cheol Na, SangJun Song, Jiehyun Jeon, Seungjun Baek, Beom Suk Kim · 2027
Read Artificial intelligence-assisted identification of skin lesions associated with chronic venous insufficiency by Ko Eun Kim, Jin Cheol Na, SangJun Song, Jiehyun Jeon, Seungjun Baek, Beom Suk Kim (2027) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13634074.txt.
Description
Ko Eun Kim and five co-authors built an artificial intelligence tool in two thousand twenty-six to sort skin lesions linked to poor vein flow in the legs. Such lesions can look much like other skin diseases or inflamed blood vessels. A correct call early can speed referral and cut the need for invasive tests.
The team used six hundred seventy-seven dermoscopic images from two hundred forty-eight patients, all confirmed by biopsy. Images fell into three groups: vein-related lesions, common inflamed skin diseases, and vasculitis. Their Swin Transformer model beat the other models they tested, with strong scores for each group. Most errors came where patterns overlapped, such as purple spots shared by two conditions. Errors also leaned toward the lower-risk call.
Catalog record
| CREATOR | Ko Eun Kim, Jin Cheol Na, SangJun Song, Jiehyun Jeon, Seungjun Baek, Beom Suk Kim |
|---|---|
| YEAR | 2027 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |