Digital Pathology

Benyamin Ghojogh

Dr. Benyamin Ghojogh (graduated)

PhD. Electrical and Computer Engineering, University of Waterloo
MSc. Electrical Engineering, Sharif University of Technology
B.Eng, Electrical Engineering, Amirkabir University of Technology

Beyamin is a postdoctoral scholar student working on theoretical and applied advances in manifold learning, data reduction and dimensionality...

Read more about Benyamin Ghojogh (graduated)
Sikaroudi, M. et al., Accepted. Offline versus Online Triplet Mining based on Extreme Distances of Histopathology Patches. In International Conference on Intelligent Systems and Computer Vision (ISCV 2020) . Fez-Morrocco (virtual): IEEE., p. 8. Available at: https://arxiv.org/abs/2007.02200. Preprint
We analyze the effect of offline and online triplet mining for colorectal cancer (CRC) histopathology dataset containing 100,000 patches. We consider the extreme, i.e., farthest and nearest patches with respect to a given anchor, both in online and offline mining. While many works focus solely on how to select the triplets online (batch-wise), we also study the effect of extreme distances and neighbor patches before training in an offline fashion. We analyze the impacts of extreme cases for offline versus online mining, including easy positive, batch semi-hard, and batch hard triplet mining as well as the neighborhood component analysis loss, its proxy version, and distance weighted sampling. We also investigate online approaches based on extreme distance and comprehensively compare the performance of offline and online mining based on the data patterns and explain offline mining as a tractable generalization of the online mining with large mini-batch size. As well, we discuss the relations of different colorectal tissue types in terms of extreme distances. We found that offline mining can generate a better statistical representation of the population by working on the whole dataset.
Sikaroudi, M. et al., 2020. Supervision and Source Domain Impact on Representation Learning: A Histopathology Case Study. In International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'20). 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'20): IEEE Engineering in Medicine and Biology Society. Available at: https://embs.papercept.net/conferences/scripts/rtf/EMBC20_ContentListWeb_1.html#moat2-15_02. Conference Description

As many algorithms depend on a suitable representation of data, learning unique features is considered a crucial task. Although supervised techniques using deep neural networks have boosted the performance of representation learning, the need for a large set of labeled data limits the application of such methods. As an example, high-quality delineations of regions of interest in the field of pathology is a tedious and time-consuming task due to the large image dimensions. In this work, we explored the performance of a deep neural network and triplet loss in the area of representation learning. We investigated the notion of similarity and dissimilarity in pathology whole-slide images and compared different setups from unsupervised and semi-supervised to supervised learning in our experiments. Additionally, different approaches were tested, applying few-shot learning on two publicly available pathology image datasets. We achieved high accuracy and generalization when the learned representations were applied to two different pathology datasets.