Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
185eP A multi-module AI assistant for personalized breast cancer patient education and decision support
0
Zitationen
2
Autoren
2025
Jahr
Abstract
compared their mean estimated staining intensities.At the cell level, per-cell coexpression was estimated by locating nearest-neighbor cells in co-registered slides and averaging their staining intensities.Multi-resolution correlation analysis enabled quantitative evaluation of the new assay. Results:The results showed good concordancewith Pearson correlations of 0.81, 0.94 and 0.98 at the patch-level, between the estimated translucent chromogenic monoplex and triplex IHC staining intensities and the corresponding estimated DAB IHC staining intensities across the tested protein-chromogen combinations. Conclusions:The proposed co-registration approach enables quantitative assessment of biomarker measurement reliability by comparing translucent chromogenic multiplex assays with DAB monoplex assays.It also facilitates novel assay development by providing a systematic, quantitative framework for evaluating different chromogen combinations and staining sequences.
Ähnliche Arbeiten
A survey on deep learning in medical image analysis
2017 · 13.940 Zit.
pROC: an open-source package for R and S+ to analyze and compare ROC curves
2011 · 13.773 Zit.
Dermatologist-level classification of skin cancer with deep neural networks
2017 · 13.487 Zit.
A survey on Image Data Augmentation for Deep Learning
2019 · 12.079 Zit.
QuPath: Open source software for digital pathology image analysis
2017 · 8.403 Zit.