Browsing by Subject "Multi-modal"

Now showing 1 - 2 of 2

Open Access
Novel deep learning algorithms for multi-modal medical image synthesis
(2023-08) Dalmaz, Onat
Multi-modal medical imaging is a powerful tool for diagnosis and treatment of various diseases, as it provides complementary information about tissue morphology and function. However, acquiring multiple images from different modalities or contrasts is often impractical or impossible due to various factors such as scan time, cost, and patient comfort. Medical image translation has emerged as a promising solution to synthesize target-modality images given source-modality images. Ability to synthesize unavailable images enhance the ubiquity and utility of multi-modal protocols while decreasing examination costs and toxicity exposure such as ionizing radiation and contrast agents. Existing medical image translation methods prominently rely on generative adversarial networks (GANs) with convolutional neural networks (CNNs) backbones. CNNs are designed to perform local processing with compact filters, and this inductive bias is prone to limited contextual sensitivity. Meanwhile, GANs suffer from limited sample fidelity and diversity due to one-shot sampling and implicit characterization of the image distribution. To overcome the challenges with CNN based GAN models, in this thesis, first ResViT was introduced that leverages novel aggregated residual transformer (ART) blocks that synergistically fuse representations from convolutional and transformer modules. Then SynDiff is introduced, a conditional diffusion model that progressively maps noise and source images onto the target image via large diffusion steps and adversarial projections, capturing a direct correlate of the image distribution and improving sample quality and speed. ResViT provides a unified implementation to avoid the need to rebuild separate synthesis models for varying source-target modality configurations, whereas SynDiff enables unsupervised training on unpaired datasets via a cycle-consistent architecture. ResViT and SynDiff was demonstrated on synthesizing missing sequences in multi-contrast MRI, and CT images from MRI, and their state-of-the-art performance in medical image translation was shown.
Open Access
A simulation model for military deployment
(IEEE, 2007) Yıldırım, Uğur Z.; Sabuncuoğlu, İhsan; Tansel, Barbaros
The Deployment Planning Problem (DPP) for military units may in general be defined as the problem of planning the movement of geographically dispersed military units from their home bases to their final destinations using different transportation assets and a multimodal transportation network while obeying the constraints of a time-phased force deployment data describing the movement requirements for troops and equipment. Our main contribution is to develop a GISbased, object-oriented, loosely-coupled, modular, platformindependent, multi-modal and medium-resolution discrete event simulation model to test the feasibility of deployment scenarios. While our simulation model is not a panacea for all, it allows creation and testing the feasibility of a given scenario under stochastic conditions and can provide insights into potential outcomes in a matter of a few hours.