Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images

Abstract

Automatic and accurate Gleason grading of histopathology tissue slides is crucial for prostate cancer diagnosis, treatment, and prognosis. Usually, histopathology tissue slides from different institutions show heterogeneous appearances because of different tissue preparation and staining procedures, thus the predictable model learned from one domain may not be applicable to a new domain directly. Here we propose to adopt unsupervised domain adaptation to transfer the discriminative knowledge obtained from the source domain to the target domain with-out requiring labeling of images at the target domain. The adaptation is achieved through adversarial training to find an invariant feature space along with the proposed Siamese architecture on the target domain to add a regularization that is appropriate for the whole-slide images. We validate the method on two prostate cancer datasets and obtain significant classification improvement of Gleason scores as compared with the baseline models.

Generative adversarial network in medical imaging: A review

“…Furthermore, Madani et al (2018b) have also shown that the adversarial loss can reduce domain overfitting by simply supplying unlabeled test domain images to the discriminator in identifying cardiac abnormalities in chest Xray. A similar work in addressing domain variance in whole slide images (WSI) has been conducted by Ren et al (2018).…”

AI in Medical Imaging Informatics: Current Challenges and Future Directions

“…Prediction models had been investigated as a means for reliably learning from one domain to map into a new domain directly. This was accomplished by introducing unsupervised domain adaptation to transfer the discriminative knowledge obtained from the source domain to the target domain without requiring re-labeling images at the target domain [183]. This paper has focused on analysis of Hematoxylin and Eosin (H&E) stained tissue images.…”

Deep Learning in the Biomedical Applications: Recent and Future Status

“…In bioimaging histology applications, to classify the newly given prostate datasets into low and high Gleason grade, an adversarial training is used to minimize the distribution discrepancy at the feature space, with the loss function adopted from the GAN [289]. In [290], a cascaded of refinement GANs for phase contrast microscopy image super-resolution is proposed.…”