Automated density-based counting of FISH amplification signals for HER2 status assessment. (May 2019)

• Record Type: Journal Article
• Authors: Höfener, Henning; Homeyer, André; Förster, Mareike; Drieschner, Norbert; Schildhaus, Hans-Ulrich; Hahn, Horst K.
• Is Part Of: Computer methods and programs in biomedicine. Volume 173(2019)
• Page Start: 77
• Page End: 85
• Publication Date: 2019-05
• Subjects: Fluorescence in situ hybridization -- HER2 -- Deep learning -- Histology -- Image analysis; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2019.03.006
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A density-based deep-learning approach for quantification of FISH amplification signals is presented. The approach analyzes images efficiently and more accurately than compared approaches. The presented method is robust against uncertainty in training annotations. Abstract: Background: Automated image analysis can make quantification of FISH signals in histological sections more efficient and reproducible. Current detection-based methods, however, often fail to accurately quantify densely clustered FISH signals. Methods: We propose a novel density-based approach to quantifying FISH signals. Instead of detecting individual signals, this approach quantifies FISH signals in terms of the integral over a density map predicted by Deep Learning. We apply the density-based approach to the task of counting and determining ratios of ERBB2 and CEN17 signals and compare it to common detection-based and area-based approaches. Results: The ratios determined by our approach were strongly correlated with results obtained by manual annotation of individual FISH signals (Pearson's r = 0.907). In addition, they were highly consistent with cutoff-scores determined by a pathologist (balanced concordance = 0.971). The density-based approach generally outperformed the other approaches. Its superiority was particularly evident in the presence of dense signal clusters. Conclusions: The presented approach enables accurate and efficient automated quantification of FISH signals. Since signals in clusters can hardly be detected individually even by human observers, the density-based quantification performs better than detection-based approaches.