Multi-Channel Auto-Encoders and a Novel Dataset for Learning Domain Invariant Representations of Histopathology Images
This addresses domain shift issues in automated histopathology pipelines, which is a domain-specific incremental improvement for medical imaging applications.
The paper tackles domain shift in histopathology image analysis by extending a dual-channel auto-encoder to a multi-channel version (MCAE) and creating a synthetic dataset with CycleGANs, resulting in MCAE outperforming the StaNoSA method by 5 percentage-points in f1-score on a tissue classification task.
Domain shift is a problem commonly encountered when developing automated histopathology pipelines. The performance of machine learning models such as convolutional neural networks within automated histopathology pipelines is often diminished when applying them to novel data domains due to factors arising from differing staining and scanning protocols. The Dual-Channel Auto-Encoder (DCAE) model was previously shown to produce feature representations that are less sensitive to appearance variation introduced by different digital slide scanners. In this work, the Multi-Channel Auto-Encoder (MCAE) model is presented as an extension to DCAE which learns from more than two domains of data. Additionally, a synthetic dataset is generated using CycleGANs that contains aligned tissue images that have had their appearance synthetically modified. Experimental results show that the MCAE model produces feature representations that are less sensitive to inter-domain variations than the comparative StaNoSA method when tested on the novel synthetic data. Additionally, the MCAE and StaNoSA models are tested on a novel tissue classification task. The results of this experiment show the MCAE model out performs the StaNoSA model by 5 percentage-points in the f1-score. These results show that the MCAE model is able to generalise better to novel data and tasks than existing approaches by actively learning normalised feature representations.