Medical Imaging

Use of Machine Learning for challenges in medical imaging.

DOMAINS | digital-pathology | proj-alzheimers

PEOPLE | aishwarya | lauramccrackin | benyaminghojgh | markcrowley

METHODS | SSIM | PCA | LDA | RDA | QQE | GLLE

This project spans multiple modalities of medical imaging and multiple types of modelling to empower medical experts.

Alzheimer’s Classification - learning predictive classification models for diffusion MRI data to provide decision support for degenerative brain diseases using Deep Neural Network methods currently only used for 2D image classification. This domain is challenging due to the 3D structure of the data as well as the non-visual properties which do not necessarily carry over from other domains.

Digital Pathology - In this dataset we have looked at NLP methods for analyzing medical reports, Deep Learning methods for classifying images, and Manifold Learning methods to extract compact embeddings for using in classifiers and search engines.

Our Papers on Medical Imaging

  1. Analysis of Language Embeddings for Classification of Unstructured Pathology Reports
    Allada, Aishwarya Krishna, Wang, Yuanxin, Jindal, Veni, Babee, Morteza, Tizhoosh, H.R., and Crowley, Mark
    In International Conference of the IEEE Engineering in Medicine and Biology Society 2021
  2. Magnification Generalization for Histopathology Image Embedding
    Sikaroudi, Milad, Ghojogh, Benyamin, Karray, Fakhri, Crowley, Mark, and Tizhoosh, H. R.
    In IEEE International Symposium on Biomedical Imaging (ISBI) 2021
  3. Batch-Incremental Triplet Sampling for Training Triplet Networks Using Bayesian Updating Theorem
    Sikaroudi, Milad, Ghojogh, Benyamin, Karray, Fakhri, Crowley, Mark, and Tizhoosh, H. R.
    In 25th International Conference on Pattern Recognition (ICPR) 2021
  4. Offline versus Online Triplet Mining based on Extreme Distances of Histopathology Patches
    Sikaroudi, Milad, Ghojogh, Benyamin, Safarpoor, Amir, Karray, Fakhri, Crowley, Mark, and Tizhoosh, H. R.
    In 15th International Symposium on Visual Computing (ISCV 2020) 2020
  5. Quantile–Quantile Embedding for distribution transformation and manifold embedding with ability to choose the embedding distribution
    Ghojogh, Benyamin, Karray, Fakhri, and Crowley, Mark
    Machine Learning with Applications (MLWA) 2021
  6. Supervision and Source Domain Impact on Representation Learning: A Histopathology Case Study
    Sikaroudi, Milad, Safarpoor, Amir, Ghojogh, Benyamin, Shafiei, Sobhan, Crowley, Mark, and Tizhoosh, HR
    In International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’20) 2020
  7. Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks
    Ghojogh, Benyamin, Sikaroudi, Milad, Shafiei, Sobhan, Tizhoosh, H.R., Karray, Fakhri, and Crowley, Mark
    In IEEE International Joint Conference on Neural Networks (IJCNN) 2020
  8. Weighted Fisher Discriminant Analysis in the Input and Feature Spaces
    Ghojogh, Benyamin, Sikaroudi, Milad, Tizhoosh, H.R., Karray, Fakhri, and Crowley, Mark
    In International Conference on Image Analysis and Recognition (ICIAR-2020) 2020
  9. Application of probabilistically-weighted graphs to image-based diagnosis of Alzheimer’s disease using diffusion MRI
    Maryam, Syeda, McCrackin, Laura, Crowley, Mark, Rathi, Yogesh, and Michailovich, Oleg
    In Proceedings of SPIE 101324, Medical Imaging 2017 : Computer-Aided Diagnosis 2017