Semantic segmentation of mFISH images using convolutional networks

TL;DR

This paper introduces a convolutional neural network for semantic segmentation of mFISH images, effectively classifying pixels with high accuracy and advancing automated chromosomal analysis.

Contribution

It presents a novel fully convolutional network that leverages spatial and spectral data for end-to-end chromosome classification in mFISH images.

Findings

Achieved 87.41% correct classification ratio on public dataset

Outperformed previous pixel-wise classification methods

Demonstrated potential for improved computer-aided genetic diagnosis

Abstract

Multicolor in situ hybridization (mFISH) is a karyotyping technique used to detect major chromosomal alterations using fluorescent probes and imaging techniques. Manual interpretation of mFISH images is a time consuming step that can be automated using machine learning; in previous works, pixel or patch wise classification was employed, overlooking spatial information which can help identify chromosomes. In this work, we propose a fully convolutional semantic segmentation network for the interpretation of mFISH images, which uses both spatial and spectral information to classify each pixel in an end-to-end fashion. The semantic segmentation network developed was tested on samples extracted from a public dataset using cross validation. Despite having no labeling information of the image it was tested on our algorithm yielded an average correct classification ratio (CCR) of 87.41%. Previously, this level of accuracy was only achieved with state of the art algorithms when classifying pixels from the same image in which the classifier has been trained. These results provide evidence that fully convolutional semantic segmentation networks may be employed in the computer aided diagnosis of genetic diseases with improved performance over the current methods of image analysis.