Baseline Photos and Confident Annotation Improve Automated Detection of Cutaneous Graft-Versus-Host Disease

Authors

Xiaoqi Liu^{1, 2, 3,} , Kelsey Parks^{1, 3,} , Inga Saknite^3, , Tahsin Reasat^2, , Austin D. Cronin^{1, 3}, Lee E. Wheless^{1, 3,} , Benoit M. Dawant², Eric R. Tkaczyk^{1, 3, 4, *,}

¹Department of Veterans Affairs, Tennessee Valley Healthcare System, Dermatology Service, 1310 24th Avenue South, Nashville, TN 37212-2637, USA

²Department of Electrical Engineering and Computer Science, Vanderbilt University, 361 Jacobs Hall, Nashville, TN 37235-1662, USA

³Vanderbilt Dermatology Translational Research Clinic (VDTRC.org), Department of Dermatology, Vanderbilt University Medical Center, 719 Thompson Lane, One Hundred Oaks Suite 26300, Nashville, TN 37204, USA

⁴Department of Biomedical Engineering, Vanderbilt University, Nashville, TN, USA

^*Corresponding author. Email: eric.tkaczyk@vumc.org

DOI

10.2991/chi.k.210704.001How to use a DOI?

Keywords

Cutaneous erythema; chronic graft-versus-host disease; change detection; longitudinal photos; baseline photos; computer vision; convolutional neural networks

Abstract

Cutaneous erythema is used in diagnosis and response assessment of cutaneous chronic graft-versus-host disease (cGVHD). The development of objective erythema evaluation methods remains a challenge. We used a pre-trained neural network to segment cGVHD erythema by detecting changes relative to a patient’s registered baseline photo. We fixed this change detection algorithm on human annotations from a single photo pair, by using either a traditional approach or by marking definitely affected (“Do Not Miss”, DNM) and definitely unaffected skin (“Do Not Include”, DNI). The fixed algorithm was applied to each of the remaining 47 test photo pairs from six follow-up sessions of one patient. We used both the Dice index and the opinion of two board-certified dermatologists to evaluate the algorithm performance. The change detection algorithm correctly assigned 80% of the pixels, regardless of whether it was fixed on traditional (median accuracy: 0.77, interquartile range 0.62–0.87) or DNM/DNI segmentations (0.81, 0.65–0.89). When the algorithm was fixed on markings by different annotators, the DNM/DNI achieved more consistent outputs (median Dice indices: 0.94–0.96) than the traditional method (0.73–0.81). Compared to viewing only rash photos, the addition of baseline photos improved the reliability of dermatologists’ scoring. The inter-rater intraclass correlation coefficient increased from 0.19 (95% confidence interval lower bound: 0.06) to 0.51 (lower bound: 0.35). In conclusion, a change detection algorithm accurately assigned erythema in longitudinal photos of cGVHD. The reliability was significantly improved by exclusively using confident human segmentations to fix the algorithm. Baseline photos improved the agreement among two dermatologists in assessing algorithm performance.

Copyright

© 2021 International Academy for Clinical Hematology. Publishing services by Atlantis Press International B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Xiaoqi Liu
AU  - Kelsey Parks
AU  - Inga Saknite
AU  - Tahsin Reasat
AU  - Austin D. Cronin
AU  - Lee E. Wheless
AU  - Benoit M. Dawant
AU  - Eric R. Tkaczyk
PY  - 2021
DA  - 2021/07/15
TI  - Baseline Photos and Confident Annotation Improve Automated Detection of Cutaneous Graft-Versus-Host Disease
JO  - Clinical Hematology International
SP  - 108
EP  - 115
VL  - 3
IS  - 3
SN  - 2590-0048
UR  - https://doi.org/10.2991/chi.k.210704.001
DO  - 10.2991/chi.k.210704.001
ID  - Liu2021
ER  -