Difficulty Translation in Histopathology Images
This work addresses the need for better training data in histopathology image analysis, though it is incremental as it adapts existing image translation methods to a specific domain.
The paper tackled the problem of generating more challenging histopathology images for classification by proposing a difficulty translation model, which successfully produced images that were harder for both human pathologists and machine learning classifiers to classify, and using these images as augmented data improved classifier performance on independent test sets.
The unique nature of histopathology images opens the door to domain-specific formulations of image translation models. We propose a difficulty translation model that modifies colorectal histopathology images to be more challenging to classify. Our model comprises a scorer, which provides an output confidence to measure the difficulty of images, and an image translator, which learns to translate images from easy-to-classify to hard-to-classify using a training set defined by the scorer. We present three findings. First, generated images were indeed harder to classify for both human pathologists and machine learning classifiers than their corresponding source images. Second, image classifiers trained with generated images as augmented data performed better on both easy and hard images from an independent test set. Finally, human annotator agreement and our model's measure of difficulty correlated strongly, implying that for future work requiring human annotator agreement, the confidence score of a machine learning classifier could be used as a proxy.