Fuyao Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Fuyao Chen has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Eric R. Tkaczyk
Vanderbilt University Medical Center
4 shared publications - Austin Cronin
Dermatology Service, Department of Veterans Affairs Tennessee Valley Healthcare System Nashville Tennessee USA
2 shared publications - Inga Saknite
University of Latvia
2 shared publications Alexis Hood
Vanderbilt Dermatology Translational Research Clinic, Department of Dermatology Vanderbilt University Medical Center Nashville Tennessee USA
1 shared publication- Andrew J. McNeil
Department of Electrical and Computer Engineering, Vanderbilt University, Tennessee, USA
1 shared publication Ari Kukkonen
Revenio Group Vantaa Finland
1 shared publication
Latest Publications
- 10 April 2023
- Published by Wiley in Journal of Biophotonics
- Vol. 16 (7) , e202300009
Hyperspectral imaging to accurately segment skin erythema and hyperpigmentation in cutaneous chronic graft‐versus‐host disease
In 51 lesions from 15 patients with the inflammatory skin condition chronic graft‐versus‐host‐disease, hyperspectral imaging accurately delineated active erythema and post‐inflammatory hyperpigmentation. The method was validated by dermatologist‐approved confident delineations of only definitely affected and definitely unaffected areas in photographs. A prototype hyperspectral imaging system acquired a 2.5 × 3.5 cm2 area of skin at 120 wavelengths in the 450–850 nm range. Unsupervised extraction of unknown absorbers by endmember analysis achieved a comparable accuracy to that of supervised extraction of known absorbers (melanin, hemoglobin) by chromophore mapping: 0.78 (IQR: 0.39–0.85) vs. 0.83 (0.53–0.91) to delineate erythema and 0.74 (0.57–0.87) vs. 0.73 (0.52–0.84) to delineate hyperpigmentation. Both algorithms achieved higher specificity than sensitivity. Whereas a trained human confidently marked a median of 7% of image pixels, unsupervised and supervised algorithms delineated a median of 14% and 27% pixels. Hyperspectral imaging could overcome a fundamental practice gap of distinguishing active from inactive manifestations of inflammatory skin disease.
- 10 April 2023
- Published by Wiley in Journal of Biophotonics
- Vol. 16 (7) , e202300009
Hyperspectral imaging to accurately segment skin erythema and hyperpigmentation in cutaneous chronic graft‐versus‐host disease
In 51 lesions from 15 patients with the inflammatory skin condition chronic graft‐versus‐host‐disease, hyperspectral imaging accurately delineated active erythema and post‐inflammatory hyperpigmentation. The method was validated by dermatologist‐approved confident delineations of only definitely affected and definitely unaffected areas in photographs. A prototype hyperspectral imaging system acquired a 2.5 × 3.5 cm2 area of skin at 120 wavelengths in the 450–850 nm range. Unsupervised extraction of unknown absorbers by endmember analysis achieved a comparable accuracy to that of supervised extraction of known absorbers (melanin, hemoglobin) by chromophore mapping: 0.78 (IQR: 0.39–0.85) vs. 0.83 (0.53–0.91) to delineate erythema and 0.74 (0.57–0.87) vs. 0.73 (0.52–0.84) to delineate hyperpigmentation. Both algorithms achieved higher specificity than sensitivity. Whereas a trained human confidently marked a median of 7% of image pixels, unsupervised and supervised algorithms delineated a median of 14% and 27% pixels. Hyperspectral imaging could overcome a fundamental practice gap of distinguishing active from inactive manifestations of inflammatory skin disease.
- 24 March 2022
- Published by Wiley in British Journal of Haematology
- Vol. 197 (6) , e69-e72
Artificial intelligence recognition of cutaneous chronic graft‐versus‐host disease by a deep learning neural network
- 24 March 2022
- Published by Wiley in British Journal of Haematology
- Vol. 197 (6) , e69-e72
Artificial intelligence recognition of cutaneous chronic graft‐versus‐host disease by a deep learning neural network
- Open Access
- 24 June 2021
- Published by Elsevier in JID Innovations
- Vol. 1 (3)
Optimal Biomechanical Parameters for Measuring Sclerotic Chronic Graft-Versus-Host Disease
- 24 June 2021
- Published by Elsevier in JID Innovations
- Vol. 1 (3)
Open AccessOptimal Biomechanical Parameters for Measuring Sclerotic Chronic Graft-Versus-Host Disease
- 4 September 2019
- Published by Springer Nature
- p. 733-743
Non-uniformity of Porous Band in Steel-Concrete Interface and Its Influence on Formation of Corrosion Products
- 4 September 2019
- Published by Springer Nature
- p. 733-743
Non-uniformity of Porous Band in Steel-Concrete Interface and Its Influence on Formation of Corrosion Products
- 20 February 2019
- Published by Wiley in Skin Research and Technology
- Vol. 25 (4) , 572-577
Crowdsourcing to delineate skin affected by chronic graft‐vs‐host disease
Background: Estimating the extent of affected skin is an important unmet clinical need both for research and practical management in many diseases. In particular, cutaneous burden of chronic graft‐vs‐host disease (cGVHD) is a primary outcome in many trials. Despite advances in artificial intelligence and 3D photography, progress toward reliable automated techniques is hindered by limited expert time to delineate cGVHD patient images. Crowdsourcing may have potential to provide the requisite expert‐level data.Materials and methods: Forty‐one three‐dimensional photographs of three cutaneous cGVHD patients were delineated by a board‐certified dermatologist. 410 two‐dimensional projections of the raw photos were each annotated by seven crowd workers, whose consensus performance was compared to the expert.Results: The consensus delineation by four of seven crowd workers achieved the highest agreement with the expert, measured by a median Dice index of 0.7551 across all 410 images, outperforming even the best worker from the crowd (Dice index 0.7216). For their internal agreement, crowd workers achieved a median Fleiss's kappa of 0.4140 across the images. The time a worker spent marking an image had only weak correlation with the surface area marked, and very low correlation with accuracy. Percent of pixels selected by the consensus exhibited good correlation (Pearson R = 0.81) with the patient's affected surface area.Conclusion: Crowdsourcing may be an efficient method for obtaining demarcations of affected skin, on par with expert performance. Crowdsourced data generally agreed with the current clinical standard of percent body surface area to assess cGVHD severity in the skin.
- 20 February 2019
- Published by Wiley in Skin Research and Technology
- Vol. 25 (4) , 572-577
Crowdsourcing to delineate skin affected by chronic graft‐vs‐host disease
Background: Estimating the extent of affected skin is an important unmet clinical need both for research and practical management in many diseases. In particular, cutaneous burden of chronic graft‐vs‐host disease (cGVHD) is a primary outcome in many trials. Despite advances in artificial intelligence and 3D photography, progress toward reliable automated techniques is hindered by limited expert time to delineate cGVHD patient images. Crowdsourcing may have potential to provide the requisite expert‐level data.Materials and methods: Forty‐one three‐dimensional photographs of three cutaneous cGVHD patients were delineated by a board‐certified dermatologist. 410 two‐dimensional projections of the raw photos were each annotated by seven crowd workers, whose consensus performance was compared to the expert.Results: The consensus delineation by four of seven crowd workers achieved the highest agreement with the expert, measured by a median Dice index of 0.7551 across all 410 images, outperforming even the best worker from the crowd (Dice index 0.7216). For their internal agreement, crowd workers achieved a median Fleiss's kappa of 0.4140 across the images. The time a worker spent marking an image had only weak correlation with the surface area marked, and very low correlation with accuracy. Percent of pixels selected by the consensus exhibited good correlation (Pearson R = 0.81) with the patient's affected surface area.Conclusion: Crowdsourcing may be an efficient method for obtaining demarcations of affected skin, on par with expert performance. Crowdsourced data generally agreed with the current clinical standard of percent body surface area to assess cGVHD severity in the skin.