Current Landscape of Generative Adversarial Networks for Facial Deidentification in Dermatology: Systematic Review and Evaluation
BackgroundDeidentifying facial images is critical for protecting patient anonymity in the era of increasing tools for automatic image analysis in dermatology. ObjectiveThe aim of this paper was to review the current literature in the field of automatic facial deid...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2022-05-01
|
| Series: | JMIR Dermatology |
| Online Access: | https://derma.jmir.org/2022/2/e35497 |
| _version_ | 1797328377978290176 |
|---|---|
| author | Christine Park Hyeon Ki Jeong Ricardo Henao Meenal Kheterpal |
| author_facet | Christine Park Hyeon Ki Jeong Ricardo Henao Meenal Kheterpal |
| author_sort | Christine Park |
| collection | DOAJ |
| description |
BackgroundDeidentifying facial images is critical for protecting patient anonymity in the era of increasing tools for automatic image analysis in dermatology.
ObjectiveThe aim of this paper was to review the current literature in the field of automatic facial deidentification algorithms.
MethodsWe conducted a systematic search using a combination of headings and keywords to encompass the concepts of facial deidentification and privacy preservation. The MEDLINE (via PubMed), Embase (via Elsevier), and Web of Science (via Clarivate) databases were queried from inception to May 1, 2021. Studies of incorrect design and outcomes were excluded during the screening and review process.
ResultsA total of 18 studies reporting on various methodologies of facial deidentification algorithms were included in the final review. The study methods were rated individually regarding their utility for use cases in dermatology pertaining to skin color and pigmentation preservation, texture preservation, data utility, and human detection. Most studies that were notable in the literature addressed feature preservation while sacrificing skin color and texture.
ConclusionsFacial deidentification algorithms are sparse and inadequate for preserving both facial features and skin pigmentation and texture quality in facial photographs. A novel approach is needed to ensure greater patient anonymity, while increasing data access for automated image analysis in dermatology for improved patient care. |
| first_indexed | 2024-03-08T06:50:59Z |
| format | Article |
| id | doaj.art-52f9b5855fd648948728408fe42cff52 |
| institution | Directory Open Access Journal |
| issn | 2562-0959 |
| language | English |
| last_indexed | 2024-03-08T06:50:59Z |
| publishDate | 2022-05-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Dermatology |
| spelling | doaj.art-52f9b5855fd648948728408fe42cff522024-02-03T06:55:15ZengJMIR PublicationsJMIR Dermatology2562-09592022-05-0152e3549710.2196/35497Current Landscape of Generative Adversarial Networks for Facial Deidentification in Dermatology: Systematic Review and EvaluationChristine Parkhttps://orcid.org/0000-0002-0066-366XHyeon Ki Jeonghttps://orcid.org/0000-0001-6680-2012Ricardo Henaohttps://orcid.org/0000-0003-4980-845XMeenal Kheterpalhttps://orcid.org/0000-0002-0460-6400 BackgroundDeidentifying facial images is critical for protecting patient anonymity in the era of increasing tools for automatic image analysis in dermatology. ObjectiveThe aim of this paper was to review the current literature in the field of automatic facial deidentification algorithms. MethodsWe conducted a systematic search using a combination of headings and keywords to encompass the concepts of facial deidentification and privacy preservation. The MEDLINE (via PubMed), Embase (via Elsevier), and Web of Science (via Clarivate) databases were queried from inception to May 1, 2021. Studies of incorrect design and outcomes were excluded during the screening and review process. ResultsA total of 18 studies reporting on various methodologies of facial deidentification algorithms were included in the final review. The study methods were rated individually regarding their utility for use cases in dermatology pertaining to skin color and pigmentation preservation, texture preservation, data utility, and human detection. Most studies that were notable in the literature addressed feature preservation while sacrificing skin color and texture. ConclusionsFacial deidentification algorithms are sparse and inadequate for preserving both facial features and skin pigmentation and texture quality in facial photographs. A novel approach is needed to ensure greater patient anonymity, while increasing data access for automated image analysis in dermatology for improved patient care.https://derma.jmir.org/2022/2/e35497 |
| spellingShingle | Christine Park Hyeon Ki Jeong Ricardo Henao Meenal Kheterpal Current Landscape of Generative Adversarial Networks for Facial Deidentification in Dermatology: Systematic Review and Evaluation JMIR Dermatology |
| title | Current Landscape of Generative Adversarial Networks for Facial Deidentification in Dermatology: Systematic Review and Evaluation |
| title_full | Current Landscape of Generative Adversarial Networks for Facial Deidentification in Dermatology: Systematic Review and Evaluation |
| title_fullStr | Current Landscape of Generative Adversarial Networks for Facial Deidentification in Dermatology: Systematic Review and Evaluation |
| title_full_unstemmed | Current Landscape of Generative Adversarial Networks for Facial Deidentification in Dermatology: Systematic Review and Evaluation |
| title_short | Current Landscape of Generative Adversarial Networks for Facial Deidentification in Dermatology: Systematic Review and Evaluation |
| title_sort | current landscape of generative adversarial networks for facial deidentification in dermatology systematic review and evaluation |
| url | https://derma.jmir.org/2022/2/e35497 |
| work_keys_str_mv | AT christinepark currentlandscapeofgenerativeadversarialnetworksforfacialdeidentificationindermatologysystematicreviewandevaluation AT hyeonkijeong currentlandscapeofgenerativeadversarialnetworksforfacialdeidentificationindermatologysystematicreviewandevaluation AT ricardohenao currentlandscapeofgenerativeadversarialnetworksforfacialdeidentificationindermatologysystematicreviewandevaluation AT meenalkheterpal currentlandscapeofgenerativeadversarialnetworksforfacialdeidentificationindermatologysystematicreviewandevaluation |