Unknown

Dataset Information

0

SHIFT: speedy histological-to-immunofluorescent translation of a tumor signature enabled by deep learning.


ABSTRACT: Spatially-resolved molecular profiling by immunostaining tissue sections is a key feature in cancer diagnosis, subtyping, and treatment, where it complements routine histopathological evaluation by clarifying tumor phenotypes. In this work, we present a deep learning-based method called speedy histological-to-immunofluorescent translation (SHIFT) which takes histologic images of hematoxylin and eosin (H&E)-stained tissue as input, then in near-real time returns inferred virtual immunofluorescence (IF) images that estimate the underlying distribution of the tumor cell marker pan-cytokeratin (panCK). To build a dataset suitable for learning this task, we developed a serial staining protocol which allows IF and H&E images from the same tissue to be spatially registered. We show that deep learning-extracted morphological feature representations of histological images can guide representative sample selection, which improved SHIFT generalizability in a small but heterogenous set of human pancreatic cancer samples. With validation in larger cohorts, SHIFT could serve as an efficient preliminary, auxiliary, or substitute for panCK IF by delivering virtual panCK IF images for a fraction of the cost and in a fraction of the time required by traditional IF.

SUBMITTER: Burlingame EA 

PROVIDER: S-EPMC7566625 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

altmetric image

Publications

SHIFT: speedy histological-to-immunofluorescent translation of a tumor signature enabled by deep learning.

Burlingame Erik A EA   McDonnell Mary M   Schau Geoffrey F GF   Thibault Guillaume G   Lanciault Christian C   Morgan Terry T   Johnson Brett E BE   Corless Christopher C   Gray Joe W JW   Chang Young Hwan YH  

Scientific reports 20201015 1


Spatially-resolved molecular profiling by immunostaining tissue sections is a key feature in cancer diagnosis, subtyping, and treatment, where it complements routine histopathological evaluation by clarifying tumor phenotypes. In this work, we present a deep learning-based method called speedy histological-to-immunofluorescent translation (SHIFT) which takes histologic images of hematoxylin and eosin (H&E)-stained tissue as input, then in near-real time returns inferred virtual immunofluorescenc  ...[more]

Similar Datasets

| S-EPMC6732032 | biostudies-literature
| S-EPMC7400564 | biostudies-literature
| S-EPMC7733499 | biostudies-literature
| S-EPMC9177767 | biostudies-literature
| S-EPMC8418980 | biostudies-literature
| S-EPMC8196406 | biostudies-literature
| S-EPMC8273385 | biostudies-literature
| S-EPMC11310081 | biostudies-literature
| S-EPMC9990908 | biostudies-literature
| S-EPMC8948574 | biostudies-literature