Due to low or missing tumor-cell SOX10 positivity, precision for normal cells was markedly reduced in lymph-node and organ metastases compared with primary melanomas ( p < 0.001). For primary melanomas, precision of annotation was 100% (95%CI, 99% to 100%) for tumor cells and 99% (95%CI, 98% to 100%) for normal cells. Based on 1,221,367 annotated nuclei, a convolutional neural network for calculating tumor burden (CNN TB) was developed. Because images were aligned, annotations of SOX10 image analysis were directly transferred to H&E stains of the training set. H&E stains of primary and metastatic melanoma ( N = 77) were digitized, re-stained with SOX10, and re-scanned.
We aimed to optimize and evaluate computer-assisted annotation based on digital dual stains of the same tissue section. This may form a labor-intensive task involving highly skilled pathologists. Deep learning for the analysis of H&E stains requires a large annotated training set.
0 kommentar(er)
