Zobrazeno 1 - 10
of 554
pro vyhledávání: '"Jacob Mathews"'
Diffusion models (DPMs) have demonstrated remarkable performance in image generation, often times outperforming other generative models. Since their introduction, the powerful noise-to-image denoising pipeline has been extended to various discriminat
Externí odkaz:
http://arxiv.org/abs/2407.12952
Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology. This review paper provides a comprehensive overview of recent advances in DL for MRI reconstructi
Externí odkaz:
http://arxiv.org/abs/2404.15692
Publikováno v:
Indian Journal of Anaesthesia, Vol 62, Iss 7, Pp 538-544 (2018)
Background and Aims: Obstructive sleep apnoea (OSA) is largely undiagnosed in surgical population. Airway-related complication account for 35% of anaesthesia-related deaths and OSA patients have higher occurrence of difficult intubation (DIT). The ai
Externí odkaz:
https://doaj.org/article/ea7e3b3932134d4393ee4d687dca8c78
Autor:
Chand, Jyothi Rikhab, Jacob, Mathews
End-to-End (E2E) unrolled optimization frameworks show promise for Magnetic Resonance (MR) image recovery, but suffer from high memory usage during training. In addition, these deterministic approaches do not offer opportunities for sampling from the
Externí odkaz:
http://arxiv.org/abs/2402.05422
Publikováno v:
Journal of Applied Hematology, Vol 9, Iss 3, Pp 101-103 (2018)
Patients with thalassemia are known to have an increased risk of immune-mediated illness. This increased risk may be due to a genetic predisposition or underlying immunological abnormalities. The clinical presentation of these immune-mediated illness
Externí odkaz:
https://doaj.org/article/a09057bb4faa42cdad9742d72f10d9dd
Diffusion models have shown impressive performance for image generation, often times outperforming other generative models. Since their introduction, researchers have extended the powerful noise-to-image denoising pipeline to discriminative tasks, in
Externí odkaz:
http://arxiv.org/abs/2312.12649
The recovery of magnetic resonance (MR) images from undersampled measurements is a key problem that has seen extensive research in recent years. Unrolled approaches, which rely on end-to-end training of convolutional neural network (CNN) blocks withi
Externí odkaz:
http://arxiv.org/abs/2312.00386
We propose an unsupervised deep learning algorithm for the motion-compensated reconstruction of 5D cardiac MRI data from 3D radial acquisitions. Ungated free-breathing 5D MRI simplifies the scan planning, improves patient comfort, and offers several
Externí odkaz:
http://arxiv.org/abs/2309.04552
Autor:
Chand, Jyothi Rikhab, Jacob, Mathews
We introduce multi-scale energy models to learn the prior distribution of images, which can be used in inverse problems to derive the Maximum A Posteriori (MAP) estimate and to sample from the posterior distribution. Compared to the traditional singl
Externí odkaz:
http://arxiv.org/abs/2305.04775
Purpose: The aim of this work is to introduce a single model-based deep network that can provide high-quality reconstructions from undersampled parallel MRI data acquired with multiple sequences, acquisition settings and field strengths. Methods: A s
Externí odkaz:
http://arxiv.org/abs/2304.11238