no code implementations • 7 Aug 2023 • Milad Sikaroudi, Maryam Hosseini, Shahryar Rahnamayan, H. R. Tizhoosh
This enables us to derive invariant features from training images without relying on training labels, thereby covering different abstraction levels.
no code implementations • 7 Apr 2023 • Milad Sikaroudi, Mehdi Afshari, Abubakr Shafique, Shivam Kalra, H. R. Tizhoosh
Chen et al. [Chen2022] recently published the article 'Fast and scalable search of whole-slide images via self-supervised deep learning' in Nature Biomedical Engineering.
no code implementations • 21 Aug 2022 • S. Maryam Hosseini, Milad Sikaroudi, Morteza Babaei, H. R. Tizhoosh
Finally, the central server aggregates the results, retrieving the average of models' weights and updating the model without having access to individual hospitals' weights.
no code implementations • 5 Apr 2022 • Milad Sikaroudi, Shahryar Rahnamayan, H. R. Tizhoosh
These variabilities are assumed to cause a domain shift in the images of different hospitals.
1 code implementation • 18 Jan 2021 • Milad Sikaroudi, Benyamin Ghojogh, Fakhri Karray, Mark Crowley, H. R. Tizhoosh
However, a useful task in histopathology embedding is to train an embedding space regardless of the magnification level.
Breast Cancer Histology Image Classification Classification Of Breast Cancer Histology Images +3
1 code implementation • 10 Jul 2020 • Milad Sikaroudi, Benyamin Ghojogh, Fakhri Karray, Mark Crowley, H. R. Tizhoosh
However, sampling from stochastic distributions of data rather than sampling merely from the existing embedding instances can provide more discriminative information.
Dimensionality Reduction Histopathological Image Classification +1
1 code implementation • 4 Jul 2020 • Milad Sikaroudi, Benyamin Ghojogh, Amir Safarpoor, Fakhri Karray, Mark Crowley, H. R. Tizhoosh
We analyze the effect of offline and online triplet mining for colorectal cancer (CRC) histopathology dataset containing 100, 000 patches.
Dimensionality Reduction Histopathological Image Classification +1
1 code implementation • 10 May 2020 • Milad Sikaroudi, Amir Safarpoor, Benyamin Ghojogh, Sobhan Shafiei, Mark Crowley, H. R. Tizhoosh
In this work, we explored the performance of a deep neural network and triplet loss in the area of representation learning.
1 code implementation • 5 Apr 2020 • Benyamin Ghojogh, Milad Sikaroudi, Sobhan Shafiei, H. R. Tizhoosh, Fakhri Karray, Mark Crowley
The FDT and FDC loss functions are designed based on the statistical formulation of the Fisher Discriminant Analysis (FDA), which is a linear subspace learning method.
Classification Of Breast Cancer Histology Images Dimensionality Reduction +3
1 code implementation • 4 Apr 2020 • Benyamin Ghojogh, Milad Sikaroudi, H. R. Tizhoosh, Fakhri Karray, Mark Crowley
We also propose a weighted FDA in the feature space to establish a weighted kernel FDA for both existing and newly proposed weights.