Please use this identifier to cite or link to this item:
http://hdl.handle.net/2445/188851
Title: | Medical image segmentation with limited data |
Author: | Canales Martín, Iván |
Director/Tutor: | Balocco, Simone |
Keywords: | Ultrasons en medicina Malalties coronàries Programari Treballs de fi de grau Xarxes neuronals convolucionals Processament digital d'imatges Diagnòstic per la imatge Ultrasonics in medicine Coronary diseases Computer software Convolutional neural networks Digital image processing Bachelor's theses Diagnostic imaging |
Issue Date: | 13-Jun-2022 |
Abstract: | [en] Ischemic Heart Disease (IHD) is one of the leading causes of mortality in Spain; early diagnosis is key. Intravenous ultrasound imaging (IVUS) can help identify symptoms of IHD, at the cost of segmenting a large volume of frames by medical professionals. While promising, automated image segmentation using Convolutional Neural Networks (CNN) suffer from sample scarcity: a large amount of parameters is often used, and medical imaging datasets are typically small and costly to acquire and label. In this report we study and compare state of the art methods used to deal with sample scarcity. In particular we introduce data augmentation methodologies, specialized training losses and transfer learning methods, and compare their performance on IVUS segmentation of the media and lumen or the artery. Additionally we introduce a promising paradigm, few-shot segmentation, and provide an initial implementation using PFENet. This implementation can avoid significant overfitting, even when trained with a single example, outperforming traditional CNNs on the same segmentation problem. |
Note: | Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2022, Director: Simone Balocco |
URI: | http://hdl.handle.net/2445/188851 |
Appears in Collections: | Programari - Treballs de l'alumnat Treballs Finals de Grau (TFG) - Matemàtiques Treballs Finals de Grau (TFG) - Enginyeria Informàtica |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
codi.zip | Codi font | 17.47 MB | zip | View/Open |
tfg_canales_martin_ivan.pdf | Memòria | 3.8 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License