Deep learning-based tool to analyze I-FISH spots in consecutive sections of heterogeneously amplified neuroblastoma tumors

Autoren F. Kromp
S. Taschner-Mandl
M. Ambros
M. Berneder
Lukas Fischer
M. Feuerstein
A. Hanbury
I. Ambros
P. Ambros
Editoren
Titel Deep learning-based tool to analyze I-FISH spots in consecutive sections of heterogeneously amplified neuroblastoma tumors
Typ sonst
Ort ANR2018 - Advances in Neuroblastoma Research, San Francisco, California, May 9-12, 2018.
Monat May
Jahr 2018
SCCH ID# 18049
Abstract

Interphase-fluorescence in situ hybridization (I-FISH) is a robust and powerful method to detect chromo­somal aberrations and rearrangements at single-cell resolution. In neuroblastoma diagnostics, FISH is widely used to detect the stratifying MYCN amplification (MNA). Recently, the alternative lengthening of telomeres (ALT) detected by telomere I-FISH has been attracting a lot of attention. While MNA is defined by a ≥4-fold increased number of FISH spots over the reference probe, ALT detection is complicated by highly varying spot sizes and strong intensity differences. The enormous power of I-FISH to resolve intra-tumor heteroge­neity (ITH) can be fully exploited by simultaneous quantitative analysis and visualization of spot features in consecutive tissue sections, ensuring efficient quantification of I-FISH spots for diagnostic purposes and allowing insights into the spatial ITH and clonal evolution in neuroblastomas.