Table 2.
Annotator | GNB-I | GNB-II | NB-I | NB-II | NB-III | NB-IV | NC-I | NC-II | NC-III | TS | Overall |
---|---|---|---|---|---|---|---|---|---|---|---|
Biol. exp. | 0.853 | 0.781 | 0.883 | 0.932 | 0.802 | 0.946 | 0.969 | 0.869 | 0.969 | 0.895 | 0.890 |
Annot. exp. | 0.877 | 0.849 | 0.896 | 0.892 | 0.888 | 0.957 | 0.969 | 0.928 | 0.973 | 0.895 | 0.912 |
Annot. exp.: annotation expert, Biol. exp.: expert biologist, GNB-I: ganglioneuroblastoma tissue sections, GNB-II: ganglioneuroblastoma tissue sections with a low signal-to-noise ratio, NB-I: neuroblastoma bone marrow cytospin preparations, NB-II: neuroblastoma cell line preparations with different magnifications, NB-III: neuroblastoma cell line preparations with different magnifications and imaged with LSM modalities, NB-IV: neuroblastoma tumor touch imprints, NC-I: normal cells (HaCaT) cytospin preparations, NC-II: normal cells (HaCaT) with low signal-to-noise ratio, NC-III: normal cells (HaCaT) grown on slide, TS: other tissue sections (neuroblastoma, Wilms tumor). Bold values set the baseline for machine learning-based image segmentation methods.