{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-4838"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-4838","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"A Convolutional Neural Network Approach to Breast Cancer Tumor Boundary Detection","abstract":"Breast cancer is the second most common form of cancer and often goes undetected in its initial stages due to its subtle symptoms. As the tumors grow, they become more difficult to surgically remove with clean borders. To minimize the chance of recurrence, a 2D convolutional neural network is developed in this work for delineating tumor boundaries. Specifically, the U-shaped network model is trained, validated, and tested with longitudinal MRI scans of patients diagnosed with breast cancer and undergoing neoadjuvant therapy. For training, image masks were generated as ground truths using signal enhancement ratio segmentation, thresholding, and contour detection. The effectiveness of two lightweight models, with and without batch normalization and dropout layers, were compared for accuracy, loss, and processing times. The model including batch normalization and dropout layers outperformed the network without these functions; the enhanced model was additionally compared to several other more intricate machine learning algorithms for tumor-feature detection. The convolutional neural network designed for this work performed with higher accuracy and lower loss rates than the majority of the complex models, demonstrating that algorithm simplicity does not mean reduced functionality of the machine learning system.","abstract_html":"Breast cancer is the second most common form of cancer and often goes undetected in its initial stages due to its subtle symptoms. As the tumors grow, they become more difficult to surgically remove with clean borders. To minimize the chance of recurrence, a 2D convolutional neural network is developed in this work for delineating tumor boundaries. Specifically, the U-shaped network model is trained, validated, and tested with longitudinal MRI scans of patients diagnosed with breast cancer and undergoing neoadjuvant therapy. For training, image masks were generated as ground truths using signal enhancement ratio segmentation, thresholding, and contour detection. The effectiveness of two lightweight models, with and without batch normalization and dropout layers, were compared for accuracy, loss, and processing times. The model including batch normalization and dropout layers outperformed the network without these functions; the enhanced model was additionally compared to several other more intricate machine learning algorithms for tumor-feature detection. The convolutional neural network designed for this work performed with higher accuracy and lower loss rates than the majority of the complex models, demonstrating that algorithm simplicity does not mean reduced functionality of the machine learning system.","abstract_has_math":false,"creators":["Matlosz, James Leah"],"institution":null,"degree_name":"MS in Engineering - Bioengineering","degree_level":null,"degree_discipline":"Biomedical Engineering","degree_department":null,"school":null,"contributors":["Robert Szlavik","Biomedical Engineering","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:41Z","subjects":["Breast cancer","tumor boundaries","magnetic resonance imaging","convolutional neural network","edge detection","Bioimaging and Biomedical Optics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/3182","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/3182","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-4838","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Robert Szlavik","Biomedical Engineering","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Matlosz, James Leah"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-11-23T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-11-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Biomedical Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Engineering - Bioengineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Breast cancer","tumor boundaries","magnetic resonance imaging","convolutional neural network","edge detection","Bioimaging and Biomedical Optics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/3182"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Breast cancer is the second most common form of cancer and often goes undetected in its initial stages due to its subtle symptoms. As the tumors grow, they become more difficult to surgically remove with clean borders. To minimize the chance of recurrence, a 2D convolutional neural network is developed in this work for delineating tumor boundaries. Specifically, the U-shaped network model is trained, validated, and tested with longitudinal MRI scans of patients diagnosed with breast cancer and undergoing neoadjuvant therapy. For training, image masks were generated as ground truths using signal enhancement ratio segmentation, thresholding, and contour detection. The effectiveness of two lightweight models, with and without batch normalization and dropout layers, were compared for accuracy, loss, and processing times. The model including batch normalization and dropout layers outperformed the network without these functions; the enhanced model was additionally compared to several other more intricate machine learning algorithms for tumor-feature detection. The convolutional neural network designed for this work performed with higher accuracy and lower loss rates than the majority of the complex models, demonstrating that algorithm simplicity does not mean reduced functionality of the machine learning system."]},{"key":"dc:title","label":"Title","values":["A Convolutional Neural Network Approach to Breast Cancer Tumor Boundary Detection"]}]}],"canonical_facts":{"dc:contributor":["Robert Szlavik","Biomedical Engineering","College of Engineering"],"dc:creator":["Matlosz, James Leah"],"dc:date.available":["2025-11-23T08:00:00Z"],"dc:date.created":["2025-11-01T07:00:00Z"],"dc:description.abstract":["Breast cancer is the second most common form of cancer and often goes undetected in its initial stages due to its subtle symptoms. As the tumors grow, they become more difficult to surgically remove with clean borders. To minimize the chance of recurrence, a 2D convolutional neural network is developed in this work for delineating tumor boundaries. Specifically, the U-shaped network model is trained, validated, and tested with longitudinal MRI scans of patients diagnosed with breast cancer and undergoing neoadjuvant therapy. For training, image masks were generated as ground truths using signal enhancement ratio segmentation, thresholding, and contour detection. The effectiveness of two lightweight models, with and without batch normalization and dropout layers, were compared for accuracy, loss, and processing times. The model including batch normalization and dropout layers outperformed the network without these functions; the enhanced model was additionally compared to several other more intricate machine learning algorithms for tumor-feature detection. The convolutional neural network designed for this work performed with higher accuracy and lower loss rates than the majority of the complex models, demonstrating that algorithm simplicity does not mean reduced functionality of the machine learning system."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/3182"],"dc:subject":["Breast cancer","tumor boundaries","magnetic resonance imaging","convolutional neural network","edge detection","Bioimaging and Biomedical Optics"],"dc:title":["A Convolutional Neural Network Approach to Breast Cancer Tumor Boundary Detection"],"thesis:degree_discipline":["Biomedical Engineering"],"thesis:degree_name":["MS in Engineering - Bioengineering"]},"updated_at":"2026-11-19T07:12:41Z"}