SearchSkip to Search Results
For cancer research, a powerful imaging modality for both preclinical (where the focus is on imaging small animals) and clinical (where the focus is on imaging human subjects) applications should be inexpensive, portable, noninvasive, safe, and capable of measuring a myriad of information....
Vadim Bulitko, Sean Caulfield, Astrid Ensslin, Daniel Evans, Gillian Harvey, Scott Smallwood, Daniel Laforest, Brad Necyk, Marilène Oliver, Aidan Rowe, Isabelle Van Grimde, Jonathan Garfinkel, Tess Heinricks, Marilene Oliver, Blaine Campbell
DYSCORPIA: Future Intersections of the Body and Technology was a two-year interdisciplinary research project that brought together scholars from art and design, music, digital and medical humanities, radiology, computer science and contemporary dance in order to question what it means not to know...
Accurate information is the foundation of correct clinical diagnoses. Physicians are increasingly relying on new devices and tools to improve the quality of information used in their decision making. Wrong, misleading, or hard to interpret data can prevent patients from receiving proper...
Extending Differentiable Programming to include Non-differentiable Modules using Differentiable Bypass for Combining Convolutional Neural Networks and Dynamic Programming into an End-to-end Trainable FrameworkDownload
Differentiable Programming is the paradigm where different functions or modules are combined into a unified pipeline with the purpose of applying end-to-end learning or optimization. A natural impediment is the non-differentiability characteristic of many modules. This thesis proposes a new way...
Image Registration with Homography: A Refresher with Differentiable Mutual Information, Ordinary Differential Equation and Complex Matrix ExponentialDownload
This work presents a novel method of tackling the task of image registration. Our algorithm uses a differentiable form of Mutual Information implemented via a neural network called MINE. An important property of neural networks is them being differentiable, which allows them to be used as a loss...
Ultrasound imaging is a safe, affordable and reliable diagnostic tool widely used in medical professions. While 2D ultrasound imaging is used extensively in clinical environments, 3D ultrasound imaging has not yet seen wide clinical acceptance. This is partly due to the practical limitations on...
Quantitative relaxation mapping allows for direct non-invasive tissue quantification with removal of variations arising from RF fields and non-uniform coil sensitivity profiles. T2 may be quantified using multi-echo spin echo sequences; however, in practical imaging situations, imperfect...
Image texture is defined as visual patterns appearing in images. The powerful perceptive capability of texture features has made texture analysis a major research topic in computer vision and image processing. Texture features are used to detect defective products in factories, to understand...