Augmented Mitotic Cell Count using Field Of Interest Proposal
This addresses variability in histopathological prognostication for neoplasia, but it is incremental as it builds on existing deep learning methods for region selection.
The paper tackled the problem of high variability in tumor grading due to arbitrary selection of regions for mitotic count by proposing an algorithmic approach that uses a deep convolutional network to estimate mitotic activity and select optimal regions. The result was a correlation of r=0.936 in mitotic count estimate on a test set of 10 whole slide images.
Histopathological prognostication of neoplasia including most tumor grading systems are based upon a number of criteria. Probably the most important is the number of mitotic figures which are most commonly determined as the mitotic count (MC), i.e. number of mitotic figures within 10 consecutive high power fields. Often the area with the highest mitotic activity is to be selected for the MC. However, since mitotic activity is not known in advance, an arbitrary choice of this region is considered one important cause for high variability in the prognostication and grading. In this work, we present an algorithmic approach that first calculates a mitotic cell map based upon a deep convolutional network. This map is in a second step used to construct a mitotic activity estimate. Lastly, we select the image segment representing the size of ten high power fields with the overall highest mitotic activity as a region proposal for an expert MC determination. We evaluate the approach using a dataset of 32 completely annotated whole slide images, where 22 were used for training of the network and 10 for test. We find a correlation of r=0.936 in mitotic count estimate.