Healthcare
❯
Biomarker Discovery
❯Research
❯Chromosome segmentation and deep classification
Explainable artificial intelligence for genomic medicine
For:
Doctors of genomic medicine, researchers of genomic medicine, patients
Scope:
To explain the reason and basis behind AI-generated findings in genomic medicine
Goal:
Improved Product Development / R&D
Chromosome segmentation and deep classification
For:
Hospitals, doctors, cytogeneticists, patients
Scope:
Karyotyping of chromosomes is restricted to healthy patients.
Goal:
Improved Product Development / R&D
Chromosome segmentation and deep classification
For:
Hospitals, doctors, cytogeneticists, patientsGoal:
Improved Product Development / R&DProblem addressed
Automating karyotyping of chromosomes in cell spread images.
Segmentation of chromosomes in images by a non-expert crowd.
Scope of use case
Karyotyping of chromosomes is restricted to healthy patients.
Description
Metaphase chromosome analysis is one of the primary
techniques utilized in cytogenetics. Observations of
chromosomal segments or translocations during metaphase
can indicate structural changes in the cell genome, and are
often used for diagnostic purposes. Karyotyping of the
chromosomes micro-photographed under metaphase is
done by characterizing the individual chromosomes in cell
spread images. Currently, considerable effort and time is
spent to manually segment out chromosomes from cell
images, and classify the segmented chromosomes into one of
the twenty-four types, or in the case of diseased cells, to one
of the known translocated types. Segmenting out the
chromosomes in such images can be especially laborious and
is often done manually if there are overlapping
chromosomes in the image that are not easily separable by
image processing techniques. Many techniques have been
proposed to automate the segmentation and classification of
chromosomes from spread images with reasonable accuracy,
but given the criticality of the domain, a human in the loop is
often still required. In this paper, we present a method to
segment out and classify chromosomes for healthy patients
using a combination of crowdsourcing, pre-processing and
deep learning, wherein the non-expert crowd from
CrowdFlower is utilized to segment out the chromosomes
from the cell image, which are then straightened and fed into
a (hierarchical) deep neural network for classification.
Experiments are performed on four hundred healthy patient
images obtained from a hospital. Results are encouraging
and promise to significantly reduce the cognitive burden of
segmenting and karyotyping chromosomes.
Live Video
AI: Perceive