<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T01:43:27Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/29447" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/29447</identifier><datestamp>2026-09-24T04:08:28Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Shirani, Shahram</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Keshavarz-Motamed, Zahra</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Rahmati, Behnam</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2024-01-25T20:39:46Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2024-01-25T20:39:46Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2024</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/29447</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/22415</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Medical image segmentation plays a critical role in assessing, diagnosing, and treating various medical conditions. State-of-the-art convolutional neural network architectures have demonstrated promising performance. However, these methods heavily&#xd;
rely on labeled images to achieve optimal performance, which is challenging, particularly in medical cases where obtaining pixel-level annotations is often difficult.&#xd;
This thesis explores six distinct methods for the few-shot segmentation of medical&#xd;
images, with a  specific focus on cardiac structures: 1- We propose a novel weakly-&#xd;
supervised learning method for the rapid annotation of the left ventricle and based on&#xd;
its circular shape. 2-We introduce a novel physics-informed label-propagation method&#xd;
based on the patient-specific  characteristics of the left ventricle to transform the labels from end-diastole and end-systole phases through the entire cardiac cycle. 3- We&#xd;
combine this label propagation method with a semi-supervised learning approach to&#xd;
provide a labeling framework for the segmentation of the left ventricle with severely&#xd;
limited labeled data. 4- We propose a left ventricle segmentation method inspired by&#xd;
the idea of consistency regularization and by creating redundant complementing labels. 5- We introduce a semi-supervised learning method for the segmentation of any&#xd;
medical image by designing a novel loss function. The loss function incorporates an&#xd;
adaptation of active contours and also considers reliable and unreliable pixels through masked cross-entropy and masked active contour terms. 6- We develop a framework&#xd;
for enhancing medical image segmentation by using different techniques, including&#xd;
total variation, deformable models, and uncertainty-based pixel-level and image-level&#xd;
pseudo-label pruning.&#xd;
We evaluated our proposed methods on various medical image datasets, including&#xd;
SCD, ACDC, and CCLISD. These datasets segment different structures from CT&#xd;
and MRI modalities. Our methods significantly enhance the segmentation accuracy&#xd;
in terms of Dice index and Jaccard index while also reducing the required resources,&#xd;
including the time for each annotation, expertise, and the number of annotations.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Doctor of Philosophy (PhD)</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="layabstract" lang="en_US">This research delves into the vital realm of medical image segmentation, crucial for&#xd;
diagnosing and treating diverse medical conditions. While cutting-edge convolutional&#xd;
neural networks show promise, their reliance on labeled images poses challenges, especially in medical scenarios where obtaining detailed annotations is arduous. Focusing&#xd;
on cardiac structures, this thesis presents six innovative methods for few-shot segmentation of medical images. A unique weakly-supervised learning approach accelerates&#xd;
left ventricle annotation, and a novel label-propagation method leverages the physical&#xd;
characteristics of the left ventricle to fill missing labels in a cardiac cycle. Combining&#xd;
label propagation with semi-supervised learning forms a robust framework for left&#xd;
ventricle segmentation with limited labeled data. Additionally, three adapted semi-&#xd;
supervised learning approaches are explored for enhanced medical image segmentation. This research addresses the complexities of medical image analysis, paving the&#xd;
way for improved diagnostic tools.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Few-Shot Medical Image Segmentation Using Semi-Supervised and Weakly-Supervised Learning</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>