Dataset Information

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

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.

SUBMITTER: Liu X

PROVIDER: S-EPMC8486973 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Allogeneic hematopoietic stem cell transplantation is a curative treatment for numerous hematological malignancies. However, acute graft-versus-host disease (aGvHD) is a major complication affecting 40-70% of all transplant patients, whereby the earliest and most frequent presentation is in the skin. MicroRNAs play a role in varied biological process and have been reported as potential biomarkers for aGvHD. More recently, microRNAs have received added attention as circulatory biomarkers that can be detected in biofluids. In this study, we performed global microRNA expression profiling using a discovery cohort of diagnostic cutaneous aGvHD biopsies (n = 5, stages 1-3) and healthy volunteers (n = 4), in order to identify a signature list of microRNAs that could be used as diagnostic biomarkers for cutaneous aGvHD. Candidate microRNAs (n = 8) were then further investigated in a validation cohort of post-HSCT skin biopsies (n = 17), pre-HSCT skin biopsies (n = 6) and normal controls (n = 6) for their association with aGvHD. Expression of let-7c (p = 0.014), miR-503-5p (p = 0.003), miR-365a-3p (p = 0.02), miR-34a-5p (p < 0.001) and miR-34a-3p (p = 0.006) were significantly differentially expressed between groups and significantly associated with survival outcome in post-HSCT patients (miR-503-5p ROC AUC = 0.83 p = 0.021, Log Rank p = 0.003; miR-34a-3p ROC AUC = 0.93, p = 0.003, Log Rank p = 0.004). There was no association with relapse. A statistical interaction between miR-34a-3p and miR-503-5p (p = 0.016) was diagnostic for aGvHD. Expression levels of the miR-34a-5p protein target p53 were assessed in the epidermis of the skin, and an inverse correlation was identified (r2 = 0.44, p = 0.039). Expression of the validated candidate microRNAs was also assessed at day 28 post-HSCT in the sera of transplant recipients, in order to investigate their potential as circulatory microRNA biomarkers. Expression of miR-503-5p (p = 0.001), miR-34a-5p (p = 0.005), and miR-34a-3p (p = 0.004) was significantly elevated in the sera of patients who developed aGvHD versus no-aGvHD (n = 30) and miR-503-5p was associated with overall survival (OS) (ROC AUC = 0.80, p = 0.04, Log Rank p = 0.041). In conclusion, this investigation reports that microRNA expression levels in clinical skin biopsies, obtained at the time of cutaneous aGvHD onset, show potential as diagnostic biomarkers for aGvHD and as predictive biomarkers for OS. In addition, the same microRNAs can be detected in the circulation and show predictive association with post-HSCT outcomes.

Dataset Information

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets