Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/151137
Title: Machine learning based x-ray / CT image analysis
Authors: Tang, Yuan
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2021
Publisher: Nanyang Technological University
Source: Tang, Y. (2021). Machine learning based x-ray / CT image analysis. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/151137
Abstract: Medical image analysis aims to extract clinically relevant information from medical images, such as X-ray, CT, or MRI images. The project focuses on two domains of medical image analysis, image segmentation and classification. Medical image segmentation is a process to determine regions or boundaries of objects of interest, which is the first step in many clinical decision systems. Medical image classification performs disease detection on medical images to assess the probability of certain diseases. In this project, two networks are proposed to improve the existing methods on multi-organ segmentation on x-ray and CT images and disease classification on chest X-ray images. Existing segmentation networks consist of an encoder to extract features from input images, while a decoder decodes the features and outputs pixel-wise segmentation masks. We proposed a generative adversarial segmentation network that improves the performance of traditional segmentation networks with the aid of unlabelled data. Inspired by segmentation networks, we have also proposed an attention-based classification network. The network utilises the location information, such as organ mask, region of interest (ROI) bounding box to improve the classification performance while generating disease localization heatmaps.
URI: https://hdl.handle.net/10356/151137
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
TangYuan_FYP_final_report.pdf
  Restricted Access
1.52 MBAdobe PDFView/Open

Page view(s)

94
Updated on Sep 26, 2021

Download(s)

21
Updated on Sep 26, 2021

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.