View Proposal

---

Proposer

Medhdhar Salem Ali Muthanna Al- Gaashani

Title

Intelligent Medical Image Analysis Using Deep Learning

Goal

Description

This project explores deep learning techniques for medical image analysis, with a focus on tasks such as image classification and segmentation. Students will use a public medical imaging dataset, preprocess and augment the data, and implement suitable deep learning models such as Convolutional Neural Networks (CNNs), U-Net, or Transformer-based architectures. The models will be trained and evaluated using appropriate performance metrics, and their accuracy, efficiency, and limitations will be compared. Results will be visualized and analyzed to understand where different models perform well or fail.

Resources

Ronneberger et al. (2015), U-Net: Convolutional Networks for Biomedical Image Segmentation — https://arxiv.org/abs/1505.04597 ; Chen et al. (2021), TransUNet — https://arxiv.org/abs/2102.04306 ; Cao et al. (2021), Swin-Unet — https://arxiv.org/abs/2105.05537 ; A Survey on Deep Learning in Medical Image Analysis https://arxiv.org/abs/1702.05747

Background

Url

Difficulty Level

Easy

Ethical Approval

None

Number Of Students

2

Supervisor

Medhdhar Salem Ali Muthanna Al- Gaashani

Keywords

Degrees

Bachelor of Science in Computational Sciences and Software Engineering