Novelty Detection Based Discriminative Multiple Instance Feature Mining to Classify NSCLC PD-L1 Status on HE-Stained Histopathological Images

It is crucial to analyze HE-stained histopathological whole slide images (WSIs) to classify PD-L1 status for non-small cell lung cancer (NSCLC) patients, due to the expensive immunohistochemical examination performed in practical clinics. Usually, a multiple instance learning (MIL) framework is applied to resolve the classification problems of WSIs. However? existing MIL methods cannot perform well in PD-L1 status classification, due to unlearnable instance features and challenging instances that contain weak visual differences. To address this problem, we propose a novelty detection based discriminative multiple instance feature mining method. It contains a trainable instance feature encoder, learning effective information from the on-hand dataset to reduce the domain difference problem, and a novelty detection based instance feature mining mechanism, selecting typical instances to train the encoder for mining more discriminative instance features. We evaluate the proposed method on a private NSCLC PD-L1 dataset and the widely used public Camelyon16 [1] dataset that is targeted for breast cancer identification. The experimental results show that the proposed method is not only effective in predicting the status of NSCLC PD-L1 but also generalized well in the public data set.