An Efficient and Accurate Super-Resolution Approach to Low-Field MRI via U-Net Architecture With Logarithmic Loss and L2 Regularization
Low-field (LF) MRI scanners have the power to revolutionize medical imaging by provid- 27 ing a portable and cheaper alternative to high-field MRI scanners. However, such scanners are usu- 28 ally significantly noisier and lower quality than their high-field counterparts. This prevents them 29 from appealing to global markets. The aim of this paper is to improve the SNR and overall image quality of low-field MRI scans (called super-resolution) to improve diagnostic capability and, as a result, make it more accessible. To address this issue, we propose a Nested U-Net neural network architecture super-resolution algorithm that outperforms previously suggested super-resolution deep learning methods with an average PSNR of 78.83 ± 0.01 and SSIM of 0.9551 ± 0.01. Our ANOVA paired t-test and Post-Hoc Tukey test demonstrate significance with a p-value < 0.0001 and no other network demonstrating significance higher than 0.1. We tested our network on artificial noisy downsampled synthetic data from 1500 T1 weighted MRI images through the dataset called the T1- mix. Four board-certified radiologists scored 25 images (100 image ratings total) on the Likert scale (1-5) assessing overall image quality, anatomical structure, and diagnostic confidence across our architecture and other published works (SR DenseNet, Generator Block, SRCNN, etc.). Our algo- rithm outperformed all other works with the highest MOS, 4.4 ± 0.3. We also introduce a new type of loss function called natural log mean squared error (NLMSE), outperforming MSE, MAE, and MSLE on this specific SR task. Additionally, we ran inference on actual Hyperfine scan images with successful qualitative results using a Generator RRDB block. In conclusion, we present a more ac- curate deep learning method for single image super-resolution applied to low-field MRI via a 45 Nested U-Net architecture.
THIRD-LIFE: Real Life Accident Alerting, Live Locations and Notifications to Emergency Service
The country of Nepal, although beautiful, is facing many challenges due to its geography, lying between the towering Himalayas and the vast plains of Terai. The narrow mountain roads, prone to landslides and poor infrastructure, often result in frequent accidents. This situation is worsened by the delayed emergency response, as accidents are often reported much later than the time they occur. In the past ten years, over 15 major bus accidents have killed hundreds of people, and in 2024 alone, more than 80 deaths were reported. In response, the "Third Life" project was developed to improve emergency response time and save lives.The project has two main components: first, a device equipped with GSM (Global System for Mobile Communications), a GPS module (Global Positioning System), a gyroscopic sensor, and a microcontroller to detect accidents in real-time within seconds of the incident. Second, once an accident is detected, live coordinates are sent directly to emergency services and police stations for immediate assistance.This project is not only vital for Nepal but also for countries with similar terrain and infrastructure challenges. The "Third Life" project aims to save many lives that are lost due to delayed reporting, ensuring quicker emergency responses.A tragic example of this was the 2024 Trishuli bus accident, where many lives were lost when the bus plunged into the river. To date, the bus has not been recovered. Our project aims to create a waterproof device that, when connected to a satellite, will send live coordinates to emergency services, ensuring 100% reliability. This device could help locate the bus, which is still missing, within seconds.Ultimately, this initiative offers more than just safety it restores peace of mind and hope for the families of victims, providing them with a chance for a better future despite the tragedy.