Breast cancer is the second leading cause of cancer related mortality among American women. Mammography screening has emerged as a reliable non-invasive technique for early detection of breast cancer. The radiographic appearance of the female breast consists of radiolucent (dark) regions and radiodense (light) regions due to connective and epithelial tissue. It has been established that the percentage of radiodense tissue in a patient's breast can be used as a marker for predicting breast cancer risk. This thesis presents the design, development and validation of a novel automated algorithm for estimating the percentage of radiodense tissue in a digitized mammogram. The technique involves determining a dynamic threshold for segmenting radiodense indications in mammograms. Both the mammographic image and the threshold are modeled as Gaussian random variables and a constrained Neyman-Pearson criteria has been developed for segmenting radiodense tissue. Promising results have been obtained using the proposed technique. Mammograms have been obtained from an existing cohort of women enrolled in the Family Risk Analysis Program at Fox Chase Cancer Center (FCCC). The proposed technique has been validated using a set of ten images with percentages of radiodense tissue, estimated by a trained radiologist using previously established methods. This work is intended to support a concurrent study at the FCCC exploring the association between dietary patterns and breast cancer risk.
","abstract_html":"<p>Breast cancer is the second leading cause of cancer related mortality among American women. Mammography screening has emerged as a reliable non-invasive technique for early detection of breast cancer. The radiographic appearance of the female breast consists of radiolucent (dark) regions and radiodense (light) regions due to connective and epithelial tissue. It has been established that the percentage of radiodense tissue in a patient's breast can be used as a marker for predicting breast cancer risk. This thesis presents the design, development and validation of a novel automated algorithm for estimating the percentage of radiodense tissue in a digitized mammogram. The technique involves determining a dynamic threshold for segmenting radiodense indications in mammograms. Both the mammographic image and the threshold are modeled as Gaussian random variables and a constrained Neyman-Pearson criteria has been developed for segmenting radiodense tissue. Promising results have been obtained using the proposed technique. Mammograms have been obtained from an existing cohort of women enrolled in the Family Risk Analysis Program at Fox Chase Cancer Center (FCCC). The proposed technique has been validated using a set of ten images with percentages of radiodense tissue, estimated by a trained radiologist using previously established methods. This work is intended to support a concurrent study at the FCCC exploring the association between dietary patterns and breast cancer risk.</p>","abstract_has_math":false,"creators":["Neyhart, Jeremy Thomas"],"institution":null,"degree_name":"M.S. in Engineering","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engineering","degree_department":null,"school":null,"contributors":["Mandayam, Shreekanth"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2002,"date_issued":"2002-12-31T08:00:00Z","date_published":"2002-12-31T08:00:00Z","updated_at":"2026-07-24T04:14:32Z","subjects":["Breast--Radiography","Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://rdw.rowan.edu/etd/1492","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Mandayam, Shreekanth"]},{"key":"dc:creator","label":"Author","values":["Neyhart, Jeremy Thomas"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2016-05-18T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S. in Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Breast--Radiography","Electrical and Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://rdw.rowan.edu/etd/1492"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Breast cancer is the second leading cause of cancer related mortality among American women. Mammography screening has emerged as a reliable non-invasive technique for early detection of breast cancer. The radiographic appearance of the female breast consists of radiolucent (dark) regions and radiodense (light) regions due to connective and epithelial tissue. It has been established that the percentage of radiodense tissue in a patient's breast can be used as a marker for predicting breast cancer risk. This thesis presents the design, development and validation of a novel automated algorithm for estimating the percentage of radiodense tissue in a digitized mammogram. The technique involves determining a dynamic threshold for segmenting radiodense indications in mammograms. Both the mammographic image and the threshold are modeled as Gaussian random variables and a constrained Neyman-Pearson criteria has been developed for segmenting radiodense tissue. Promising results have been obtained using the proposed technique. Mammograms have been obtained from an existing cohort of women enrolled in the Family Risk Analysis Program at Fox Chase Cancer Center (FCCC). The proposed technique has been validated using a set of ten images with percentages of radiodense tissue, estimated by a trained radiologist using previously established methods. This work is intended to support a concurrent study at the FCCC exploring the association between dietary patterns and breast cancer risk.
"]},{"key":"dc:title","label":"Title","values":["Automated segmentation of radiodense tissue in digitized mammograms using a constrained Neyman-Pearson classifier"]}]}],"canonical_facts":{"dc:contributor":["Mandayam, Shreekanth"],"dc:creator":["Neyhart, Jeremy Thomas"],"dc:date.available":["2016-05-18T07:00:00Z"],"dc:description.abstract":["Breast cancer is the second leading cause of cancer related mortality among American women. Mammography screening has emerged as a reliable non-invasive technique for early detection of breast cancer. The radiographic appearance of the female breast consists of radiolucent (dark) regions and radiodense (light) regions due to connective and epithelial tissue. It has been established that the percentage of radiodense tissue in a patient's breast can be used as a marker for predicting breast cancer risk. This thesis presents the design, development and validation of a novel automated algorithm for estimating the percentage of radiodense tissue in a digitized mammogram. The technique involves determining a dynamic threshold for segmenting radiodense indications in mammograms. Both the mammographic image and the threshold are modeled as Gaussian random variables and a constrained Neyman-Pearson criteria has been developed for segmenting radiodense tissue. Promising results have been obtained using the proposed technique. Mammograms have been obtained from an existing cohort of women enrolled in the Family Risk Analysis Program at Fox Chase Cancer Center (FCCC). The proposed technique has been validated using a set of ten images with percentages of radiodense tissue, estimated by a trained radiologist using previously established methods. This work is intended to support a concurrent study at the FCCC exploring the association between dietary patterns and breast cancer risk.
"],"dc:identifier":["https://rdw.rowan.edu/etd/1492"],"dc:subject":["Breast--Radiography","Electrical and Computer Engineering"],"dc:title":["Automated segmentation of radiodense tissue in digitized mammograms using a constrained Neyman-Pearson classifier"],"thesis:degree_discipline":["Electrical & Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S. in Engineering"]},"updated_at":"2026-07-24T04:14:32Z"}