Please use this identifier to cite or link to this item:
https://dspace.univ-ouargla.dz/jspui/handle/123456789/36824
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Oussama Aiadi | - |
dc.contributor.author | Rezzag Bedida, Tahar | - |
dc.contributor.author | Hammouya, Abdeldjalil | - |
dc.date.accessioned | 2024-09-24T08:32:40Z | - |
dc.date.available | 2024-09-24T08:32:40Z | - |
dc.date.issued | 2024 | - |
dc.identifier.citation | FACULTY OF N EW I NFORMATION AND C OMMUNICATION T ECHNOLOGIES | en_US |
dc.identifier.uri | https://dspace.univ-ouargla.dz/jspui/handle/123456789/36824 | - |
dc.description | Artificial Intelligence and Data Science | en_US |
dc.description.abstract | Early detection of polyps in the colon is crucial for preventing colorectal cancer, the second leading cause of cancer-related deaths globally. However, accurate identification of polyps can be challenging due to factors like subtle visual cues, variable lighting, and human fatigue. This work aims to adapt the Segment Anything Model (SAM) to segment colonoscopy polyp by replacing its encoder with a lightweight convolutional neural net- work. Additionally, we strive to enhance the model’s accuracy and automation through the implementation of zero-shot learning. This approach involves utilizing a pre-trained object detection model with K-means clustering algorithm to extract the bounding box prompt, which serves as auxiliary information for SAM, thereby improving its performance on un- seen polyp data without the need for fine-tuning or manual prompt design. The proposed method reduces the number of SAM encoder parameters from 91M to 3M. It demonstrates superior performance compared to some existing approaches that work to fine-tune SAM with large number of parameters.This work offers a contribution to computer-aided polyp detection. It paves the way for more efficient and accurate polyp segmentation systems, ultimately improving early cancer diagnosis and patient care. | en_US |
dc.description.sponsorship | Department of Computer Science and Information Technology | en_US |
dc.language.iso | en | en_US |
dc.publisher | KASDI MERBAH UNIVERSITY OUARGLA | en_US |
dc.subject | Medical Imaging | en_US |
dc.subject | Polyps Segmentation | en_US |
dc.subject | Segment Anything Model (SAM | en_US |
dc.subject | Vision Transformers (ViTs) | en_US |
dc.title | Improving SAM model for medical image segmentation | en_US |
dc.type | Thesis | en_US |
Appears in Collections: | Département d'informatique et technologie de l'information - Master |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
REZZAGBEDIDA_HAMMOUYA.pdf | Artificial Intelligence and Data Science | 12,72 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.