DeepFoci: Deep Learning-Based Algorithm for Fast Automatic Analysis of DNA Double Strand Break Ionizing Radiation-Induced Foci

• Published in: bioRxiv
• Main Authors: Vicar, Tomas, Gumulec, Jaromir, Kolar, Radim, Kopecna, Olga, Pagáčová, Eva, Falk, Martin
• Format: Paper
• Language: English
• Published: Cold Spring Harbor Cold Spring Harbor Laboratory Press 08.10.2020
• Subjects: Algorithms; Computer programs; Confocal microscopy; Datasets; Deep learning; Deoxyribonucleic acid; DNA; DNA damage; DNA repair; Double-strand break repair; Fibroblasts; Glioblastoma; Head & neck cancer; Histone H2A; Ionizing radiation; Morphometry; Neural networks; p53 Protein; Post-irradiation; Proteins; Radiation therapy; Segmentation; Serine; Tumors
• DOI: 10.1101/2020.10.07.321927

Abstract DNA double-strand breaks, marked by Ionizing Radiation-Induced (Repair) Foci (IRIF), are the most serious DNA lesions, dangerous to human health. IRIF quantification based on confocal microscopy represents the most sensitive and gold standard method in radiation biodosimetry and allows research of DSB induction and repair at the molecular and a single cell level. In this study, we introduce DeepFoci - a deep learning-based fully-automatic method for IRIF counting and its morphometric analysis. DeepFoci is designed to work with 3D multichannel data (trained for 53BP1 and γH2AX) and uses U-Net for the nucleus segmentation and IRIF detection, together with maximally stable extremal region-based IRIF segmentation. The proposed method was trained and tested on challenging datasets consisting of mixtures of non-irradiated and irradiated cells of different types and IRIF characteristics - permanent cell lines (NHDF, U-87) and cell primary cultures prepared from tumors and adjacent normal tissues of head and neck cancer patients. The cells were dosed with 1-4 Gy gamma-rays and fixed at multiple (0-24 h) post-irradiation times. Upon all circumstances, DeepFoci was able to quantify the number of IRIF foci with the highest accuracy among current advanced algorithms. Moreover, while the detection error of DeepFoci remained comparable to the variability between two experienced experts, the software kept its sensitivity and fidelity across dramatically different IRIF counts per nucleus. In addition, information was extracted on IRIF 3D morphometric features and repair protein colocalization within IRIFs. This allowed multiparameter IRIF categorization, thereby refining the analysis of DSB repair processes and classification of patient tumors with a potential to identify specific cell subclones. The developed software improves IRIF quantification for various practical applications (radiotherapy monitoring, biodosimetry, etc.) and opens the door to an advanced DSB focus analysis and, in turn, a better understanding of (radiation) DNA damaging and repair. Highlights * New method for DSB repair focus (IRIF) detection and multi-parameter analysis * Trainable deep learning-based method * Fully automated analysis of multichannel 3D datasets * Trained and tested on extremely challenging datasets (tumor primary cultures) * Comparable to an expert analysis and superb to available methods Figure1 Figure1 * Download figure * Open in new tab Competing Interest Statement The authors have declared no competing interest. Footnotes * https://github.com/tomasvicar/DeepFoci * https://doi.org/10.5281/zenodo.2572450 * Abbreviations 53BP1 P53 Binding Protein 1 CNN Convolutional Neural Network DSB DNA double-strand breaks FOV Field of View GUI Graphical User Interface IRIF Ionizing Radiation-Induced (Repair) Foci MSER Maximally Stable Extremal Region Algorithm NHDF Normal Human Dermal Fibroblasts RAD51 DNA repair protein RAD51 homolog 1 U-87 U-87 Glioblastoma Cell Line γH2AX histone H2AX phosphorylated at serine 139