Image Segmentation to Distinguish Between Overlapping Human Chromosomes
This work addresses the need for fast and automated segmentation to scale cost-effective medicine and biomedical research, though it appears incremental as it applies a known neural network method to a specific domain problem.
The paper tackled the problem of distinguishing overlapping human chromosomes in medical imaging by applying a customized convolutional neural network for segmentation, achieving intersection over union scores of 94.7% for overlapping regions and 88-94% for non-overlapping regions.
In medicine, visualizing chromosomes is important for medical diagnostics, drug development, and biomedical research. Unfortunately, chromosomes often overlap and it is necessary to identify and distinguish between the overlapping chromosomes. A segmentation solution that is fast and automated will enable scaling of cost effective medicine and biomedical research. We apply neural network-based image segmentation to the problem of distinguishing between partially overlapping DNA chromosomes. A convolutional neural network is customized for this problem. The results achieved intersection over union (IOU) scores of 94.7% for the overlapping region and 88-94% on the non-overlapping chromosome regions.