A Review of Automatic Hair Removal in Dermoscopy Images: From Image Processing to Deep Learning.
Early melanoma detection is made possible by dermoscopy, but automated analysis and clinical evaluation are often hampered by hair artifacts in images. Although hair removal is critical for accurate diagnosis, it has frequently been treated as a minor preprocessing step rather than a separate resear...
| Publicado en: | Journal of Imaging Informatics in Medicine pp. 1 - 21 |
|---|---|
| Autores principales: | , , , , , , , |
| Formato: | Journal Article |
| Publicado: |
Springer Nature
Apr2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=192783073&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 192783073 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 29482925 NR3A jtl: Journal of Imaging Informatics in Medicine issn: 29482925 maglogo: N pubinfo: dt: Apr2026 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 192783073 10.1007/s10278-026-01950-y 192783073 ppf: 1 ppct: 20 formats: tig: atl: A Review of Automatic Hair Removal in Dermoscopy Images: From Image Processing to Deep Learning. aug: au: Bardou, Dalal Bouaziz, Hamida Lv, Laishui Bounezra, Mourad Vajdi, Ahmadreza Zhang, Ting Abbas, Fayçal Malah, Mehdi affil: LMIA Lab, Department of Computer Science, Abbes Laghrour University of Khenchela sug: ab: Early melanoma detection is made possible by dermoscopy, but automated analysis and clinical evaluation are often hampered by hair artifacts in images. Although hair removal is critical for accurate diagnosis, it has frequently been treated as a minor preprocessing step rather than a separate research focus. This review provides the first thorough investigation into automatic hair removal in dermoscopy images. We categorize and evaluate existing techniques, from conventional image processing to more recent deep learning (DL) architectures, such as generative models and hybrid approaches. This review covers literature published from 1990 to 2025, highlighting the advancements made over the past three decades and the current state of research. Finally, future research directions and challenges are discussed. pubtype: Academic Journal doctype: Journal Article ougenre: Unknown language: English refInfo: holdings: @attributes: islocal: N |
|---|