Dataset Information

Non-Expert Markings of Active Chronic Graft-Versus-Host Disease Photographs: Optimal Metrics of Training Effects.

ABSTRACT: Lack of reliable measures of cutaneous chronic graft-versus-host disease (cGVHD) remains a significant challenge. Non-expert assistance in marking photographs of active disease could aid the development of automated segmentation algorithms, but validated metrics to evaluate training effects are lacking. We studied absolute and relative error of marked body surface area (BSA), redness, and the Dice index as potential metrics of non-expert improvement. Three non-experts underwent an extensive training program led by a board-certified dermatologist to mark cGVHD in photographs. At the end of the 4-month training, the dermatologist confirmed that each trainee had learned to accurately mark cGVHD. The trainees' inter- and intra-rater intraclass correlation coefficient estimates were "substantial" to "almost perfect" for both BSA and total redness. For fifteen 3D photos of patients with cGVHD, the trainees' median absolute (relative) BSA error compared to expert marking dropped from 20 cm² (29%) pre-training to 14 cm² (24%) post-training. Total redness error decreased from 122 a*·cm² (26%) to 95 a*·cm² (21%). By contrast, median Dice index did not reflect improvement (0.76 to 0.75). Both absolute and relative BSA and redness errors similarly and stably reflected improvements from this training program, which the Dice index failed to capture.

SUBMITTER: Parks K

PROVIDER: S-EPMC9984572 | biostudies-literature | 2023 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Non-Expert Markings of Active Chronic Graft-Versus-Host Disease Photographs: Optimal Metrics of Training Effects.

Parks Kelsey K Liu Xiaoqi X Reasat Tahsin T Khera Zain Z Baker Laura X LX Chen Heidi H Chen Heidi H Dawant Benoit M BM Saknite Inga I Tkaczyk Eric R ER

Journal of digital imaging 20221107 1

Lack of reliable measures of cutaneous chronic graft-versus-host disease (cGVHD) remains a significant challenge. Non-expert assistance in marking photographs of active disease could aid the development of automated segmentation algorithms, but validated metrics to evaluate training effects are lacking. We studied absolute and relative error of marked body surface area (BSA), redness, and the Dice index as potential metrics of non-expert improvement. Three non-experts underwent an extensive trai ...[more]

PMID: 36344635

Similar Datasets

Project description:Allogeneic hematopoietic cell transplantation (allo-HCT) is an essential therapeutic modality for patients with hematological malignancies and other blood disorders. Unfortunately, acute graft-versus-host disease (aGVHD) remains a major source of morbidity and mortality following allo-HCT, which limits its use in a broader spectrum of patients. Chronic graft-versus-host disease (cGVHD) also remains the most common long-term complication of allo-HCT, occurring in reportedly 30-70% of patients surviving more than 100 days. Chronic GVHD is also the leading cause of non-relapse mortality (NRM) occurring more than 2 years after HCT for malignant disease. Graft versus tumor (GVT) is a major component of the overall beneficial effects of allogeneic HCT in the treatment of hematological malignancies. Better understanding of GVHD pathogenesis is important to identify new therapeutic targets for GVHD prevention and therapy. Emerging data suggest opposing roles for different T cell subsets, e.g., IFN-γ producing CD4+ and CD8+ T cells (Th1 and Tc1), IL-4 producing T cells (Th2 and Tc2), IL-17 producing T cells (Th17 and Tc17), IL-9 producing T cells (Th9 and Tc9), IL-22 producing T cells (Th22), T follicular helper cells (Tfh), regulatory T-cells (Treg) and tissue resident memory T cells (Trm) in GVHD and GVT etiology. In this review, we first summarize the general description of the cytokine signals that promote the differentiation of T cell subsets and the roles of these T cell subsets in the pathogenesis of GVHD. Next, we extensively explore preclinical findings of T cell subsets in both GVHD/GVT animal models and humans. Finally, we address recent findings about the roles of T-cell subsets in clinical GVHD and current strategies to modulate T-cell differentiation for treating and preventing GVHD in patients. Further exploring and outlining the immune biology of T-cell differentiation in GVHD that will provide more therapeutic options for maintaining success of allo-HCT.

Dataset Information

Non-Expert Markings of Active Chronic Graft-Versus-Host Disease Photographs: Optimal Metrics of Training Effects.

Publications

Non-Expert Markings of Active Chronic Graft-Versus-Host Disease Photographs: Optimal Metrics of Training Effects.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets