MRI Slice

MRI slice analysis focuses on extracting meaningful information from individual 2D slices of 3D MRI scans, aiming to improve diagnostic accuracy and efficiency across various medical applications. Current research emphasizes automated segmentation techniques using deep learning models like U-Nets, convolutional neural networks (CNNs), transformers, and generative adversarial networks (GANs) to analyze features within slices and even synthesize missing data or improve resolution. These advancements are crucial for streamlining tasks such as body composition analysis, brain tumor detection, and dementia diagnosis, ultimately leading to faster and more accurate clinical workflows. Furthermore, research explores methods to harmonize data across multiple sites and scanners, improving the reliability and generalizability of findings.

Papers

March 23, 2022

Biceph-Net: A robust and lightweight framework for the diagnosis of Alzheimer's disease using 2D-MRI scans and deep similarity learning
A. H. Rashid, A. Gupta, J. Gupta, M. Tanveer
Convolutional Neural Network Alzheimer'S Disease Medical Diagnosis MRI Slice Lightweight Framework B Scan Deep Similarity

November 5, 2021

Segmentation of 2D Brain MR Images
Angad Ripudaman Singh Bajwa
Segmentation Based Approach Brain Tumor Segmentation Brain Tumor MRI Slice Medical Image Processing

MRI Slice

Papers

Biceph-Net: A robust and lightweight framework for the diagnosis of Alzheimer's disease using 2D-MRI scans and deep similarity learning

Segmentation of 2D Brain MR Images