Semantic segmentation of mFISH images using convolutional networks
This work addresses the time-consuming manual interpretation of mFISH images for genetic disease diagnosis, offering an incremental improvement over previous methods that overlooked spatial information.
The authors tackled the problem of automating the interpretation of mFISH images for karyotyping by proposing a fully convolutional semantic segmentation network that uses spatial and spectral information, achieving an average correct classification ratio of 87.41% on a public dataset without requiring labeling of test images.
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.