Abstract:
We present a novel method to segment
instances of glandular structures from colon histopathology
images. We use a structure learning approach which
represents local spatial configurations of class labels, capturing
structural information normally ignored by slidingwindow
methods. This allows us to reveal different spatial
structures of pixel labels (e.g., locations between adjacent
glands, or far from glands), and to identify correctly
neighboring glandular structures as separate instances.
Exemplars of label structures are obtained via clustering
and used to train support vector machine classifiers. The
label structures predicted are then combined and postprocessed
to obtain segmentationmaps.We combine handcrafted,
multi-scale image features with features computed
by a deep convolutional network trained to map images to
segmentation maps. We evaluate the proposed method on
the public domain GlaS data set, which allows extensive
comparisons with recent, alternative methods. Using the
GlaS contest protocol, ourmethod achieves the overall best
performance.
