Search

Your search keyword '"Hashmi, Anam"' showing total 14 results
Start Over Author "Hashmi, Anam"
14 results on '"Hashmi, Anam"'

1. Accelerating Cardiac MRI Reconstruction with CMRatt: An Attention-Driven Approach

Author

Hashmi, Anam, Dietlmeier, Julia, Curran, Kathleen M., and O'Connor, Noel E.

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Cine cardiac magnetic resonance (CMR) imaging is recognised as the benchmark modality for the comprehensive assessment of cardiac function. Nevertheless, the acquisition process of cine CMR is considered as an impediment due to its prolonged scanning time. One commonly used strategy to expedite the acquisition process is through k-space undersampling, though it comes with a drawback of introducing aliasing effects in the reconstructed image. Lately, deep learning-based methods have shown remarkable results over traditional approaches in rapidly achieving precise CMR reconstructed images. This study aims to explore the untapped potential of attention mechanisms incorporated with a deep learning model within the context of the CMR reconstruction problem. We are motivated by the fact that attention has proven beneficial in downstream tasks such as image classification and segmentation, but has not been systematically analysed in the context of CMR reconstruction. Our primary goal is to identify the strengths and potential limitations of attention algorithms when integrated with a convolutional backbone model such as a U-Net. To achieve this, we benchmark different state-of-the-art spatial and channel attention mechanisms on the CMRxRecon dataset and quantitatively evaluate the quality of reconstruction using objective metrics. Furthermore, inspired by the best performing attention mechanism, we propose a new, simple yet effective, attention pipeline specifically optimised for the task of cardiac image reconstruction that outperforms other state-of-the-art attention methods. The layer and model code will be made publicly available., Comment: This paper has been submitted for the 32nd European Signal Processing Conference EUSIPCO 2024 in Lyon

Published
2024

2. Cardiac MRI Reconstruction from Undersampled K-Space Using Double-Stream IFFT and a Denoising GNA-UNET Pipeline

Author

Dietlmeier, Julia, Garcia-Cabrera, Carles, Hashmi, Anam, Curran, Kathleen M., O’Connor, Noel E., Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Camara, Oscar, editor, Puyol-Antón, Esther, editor, Sermesant, Maxime, editor, Suinesiaputra, Avan, editor, Tao, Qian, editor, Wang, Chengyan, editor, and Young, Alistair, editor

Published
2024
Full Text
View/download PDF

5. An Automated System for Epileptic Seizure Detection Using EEG

Author

Khan, Bilal Alam, Hashmi, Anam, Farooq, Omar, Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, Kolhe, Mohan L., editor, Tiwari, Shailesh, editor, Trivedi, Munesh C., editor, and Mishra, Krishn K., editor

Published
2020
Full Text
View/download PDF

10. Cardiac MRI reconstruction from undersampled k-space using double-stream IFFT and a denoising GNA-UNET pipeline

Author

Dietlmeier, Julia, Garcia-Cabrera, Carles, Hashmi, Anam, Curran, Kathleen M., O'Connor, Noel E., Dietlmeier, Julia, Garcia-Cabrera, Carles, Hashmi, Anam, Curran, Kathleen M., and O'Connor, Noel E.

Abstract

In this work, we approach the problem of cardiac Magnetic Resonance Imaging (MRI) image reconstruction from undersampled k-space. This is an inherently ill-posed problem leading to a variety of noise and aliasing artifacts if not appropriately addressed. We propose a two-step double-stream processing pipeline that first reconstructs a noisy sample from the undersampled k-space (frequency domain) using the inverse Fourier transform. Second, in the spatial domain we train a denoising GNA-UNET (enhanced by Group Normalization and Attention layers) on the noisy aliased and fully sampled image data using the Mean Square Error loss function. We achieve competitive results on the leaderboard and show that the algorithmic combination proposed is effective in high-quality MRI reconstruction from undersampled cardiac long-axis and short-axis complex k-space data.

Published
2023

14. FUNCTIONAL GAIT ASSESSMENT IN RIGHT VERSUS LEFT HEMISPHERE LESION PATIENTS OF STROKE IN LAHORE, PAKISTAN

Author

Samia zafar, Riaz Hashmi, Anam Naz, Maryam Shabbir, Naveed Arshad, Iram Shafee, Bilal Umar, Umer Maqsood, Hafiz Sheraz Arshad

Abstract

Background: Stroke is a prevalent condition that causes major morbidities and disabilities in individuals. Stroke results in disturbing the patient's functional status of life to a great extent. Different treatment strategies for stroke patients with respect to site of hemispheric lesion are least considered by researchers and clinicians. The disabilities related to left and right hemispheric lesion are also less under discussion. Regaining walking ability in stroke patients is somehow linked with site of hemispheric lesion and this ability is a big goal of all rehabilitation institutes.Objectives: To compare the functional gait among left and right hemisphere lesion patients of stroke.Methodology: This cross sectional comparative study included 126 patients among them 63 were with right and 63 were with the left sided hemispheric lesion. This study was conducted from December 2016 to May 2017. Convenience sampling was done and subjects were selected from different hospitals and rehabilitation centers of Lahore, Pakistan on the basis of inclusion & exclusion criteria after taking informed consent. Functional gait assessment scale is a unique measure with its clinical usefulness, ascertain demonstrable qualities for assessing functional gait performance and disturbance related to balance in stroke patients. FGA is suggested for its psychometric properties because it efficiently detect decrease in functional gait during walking by performing different walking tasks. It is a observational test with excellent validity, consistency and reliability with least ceiling effects. The descriptive statistical data was analyzed using SPSS v20. Means and Standard deviations was calculated and Independent sample t-test was used for comparison of functional gait between left and right hemispheric lesion patients. P-value ≤ .05 was taken statistically significant.Results: Mean difference of functional gait assessment scores in Group A was 12.56±2.595 and in Group B was 15.59±4.172 with p-value of Conclusion: Our study concludes that a significant difference is present between the two groups. The finding from this study gave us understanding that ambulatory functions differ with respect to site of hemisphere lesion. The site of hemisphere lesion impact on patient's functional gait has statistically significant. The patients had their stroke on left side hemisphere more prone to balance and gait impairment as compared to right hemisphere lesion patients expressed from the study population. So, these differences in deficits caused by left & right CVAs must be taken into account in various physical therapy approaches. Key Words: Hemispheric lesion, Stroke, Disabilities, Functional gait assessment scale (FGA), Walking abilities, Stroke rehabilitation, Gait.

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results