July 31st, 10:00-12:15 EDT
Speaker: Dr. Mohammad Havaei
Title: Application of Generative Adversarial Networks in Medical Imaging
Abstract: Synthetic medical image generation has a huge potential for improving healthcare through many applications, from data augmentation for training machine learning systems to preserving patient privacy. Conditional Adversarial Generative Networks (cGANs) use a conditioning factor to generate images and have shown great success in recent years. Intuitively, the information in an image can be divided into two parts: 1) content which is presented through the conditioning vector and 2) style which is the undiscovered information missing from the conditioning vector. Current practices in using cGANs for medical image generation, only use a single variable for image generation (i.e., content) and therefore, do not provide much flexibility nor control over the generated image. In this work we propose a methodology to learn from the image itself, disentangled representations of style and content, and use this information to impose control over the generation process. In this framework, style is learned in a fully unsupervised manner, while content is learned through both supervised learning (using the conditioning vector) and unsupervised learning (with the inference mechanism). We undergo two novel regularization steps to ensure content-style disentanglement. First, we minimize the shared information between content and style by introducing a novel application of the gradient reverse layer (GRL); second, we introduce a self-supervised regularization method to further separate information in the content and style variables. We show that in general, two latent variable models achieve better performance and give more control over the generated image. We also show that our proposed model (DRAI) achieves the best disentanglement score and has the best overall performance.
Speaker: Dr. Issam Laradji
Title: A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images
Abstract: In this presentation I will discuss one of our works on COVID-19 Segmentation in CT Images. It will include a brief description of the motivation for using a weakly supervised method for this task, and a description on how this method leverages a consistency-based learning approach to achieve better segmentation results. I will also include a tutorial for running the code and getting results which could help for setting up a codebase or a benchmark for the Hackathon.
Speaker: Dr. Ken Chang
Title: Distributed Deep Learning Techniques for Medical Imaging
Abstract: Vast quantities of data needed to train effective deep learning models are often dispersed across institutions and not easily shared due to ethical, infrastructure, or patient privacy concerns. In this talk, I will discuss distributed training of deep learning models that do not require sharing patient data for multi-institutional collaborative settings.
Speaker: Dr. Issam El Naqa
Title: Future directions in machine learning and their application in healthcare
Abstract: The presentation will discuss current challenges in machine learning and their application to healthcare. Specifically, it will discuss the role of humans and quantum computing in improving machine learning credibility.
Speaker: Dr. Shirin Abbasinejad Enger
Title: McMedHacks 2021 Closing Remarks
Abstract: What McMedHacks offered with its first iteration in 2021, and what to look forward to in 2022!