{"id":{"repo_id":"rowan","oai_identifier":"oai:rdw.rowan.edu:etd-3684"},"canonical_url":"https://search.ndltd.org/etd/rowan/oai:rdw.rowan.edu:etd-3684","repository":{"repo_id":"rowan","name":"Rowan University","base_url":"https://rdw.rowan.edu/do/oai/"},"display":{"title":"Inverted cone convolutional neural network for deboning MRIs","abstract":"Data plenitude is the power but also the bottleneck for data-driven approaches, including neural networks. In particular, Convolutional Neural Networks (CNNs) require an abundant database of training images to achieve a desired high accuracy. Current techniques employed for boosting small datasets are data augmentation and synthetic data generation, which suffer from computational complexity and imprecision compared to original datasets. In this thesis, we intercalate prior knowledge based on the temporal relation between the images in the third dimension. Specifically, we compute the gradient of subsequent images in the dataset to remove extraneous information and highlight subtle variations between the images. The approach is coined \"Inverted Cone\" because the volume of brain images below the level of the eyes is ordered to form an inverted cone geometry. The application explored in this work is deboning, or brain extraction, in brain magnetic resonance imaging (MRI) scans. We considered a limited dataset of 23 patients with and without malignant glioblastoma provided by the University of Alabama at Birmingham School of Medicine. Automatic deboning was performed by employing an optimized CNN architecture with and without the Inverted Cone processing. The classic CNN achieved a validation accuracy of 77%, while the Inverted Cone CNN model achieved a validation accuracy of 86% in a dataset of 451 brain MRI slices.","abstract_html":"Data plenitude is the power but also the bottleneck for data-driven approaches, including neural networks. In particular, Convolutional Neural Networks (CNNs) require an abundant database of training images to achieve a desired high accuracy. Current techniques employed for boosting small datasets are data augmentation and synthetic data generation, which suffer from computational complexity and imprecision compared to original datasets. In this thesis, we intercalate prior knowledge based on the temporal relation between the images in the third dimension. Specifically, we compute the gradient of subsequent images in the dataset to remove extraneous information and highlight subtle variations between the images. The approach is coined &quot;Inverted Cone&quot; because the volume of brain images below the level of the eyes is ordered to form an inverted cone geometry. The application explored in this work is deboning, or brain extraction, in brain magnetic resonance imaging (MRI) scans. We considered a limited dataset of 23 patients with and without malignant glioblastoma provided by the University of Alabama at Birmingham School of Medicine. Automatic deboning was performed by employing an optimized CNN architecture with and without the Inverted Cone processing. The classic CNN achieved a validation accuracy of 77%, while the Inverted Cone CNN model achieved a validation accuracy of 86% in a dataset of 451 brain MRI slices.","abstract_has_math":false,"creators":["Palumbo, Oliver John"],"institution":null,"degree_name":"M.S. Electrical and Computer Engineering","degree_level":"Thesis","degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Bouaynaya, Nidhal C.","Fathallah-Shaykh, Hassan","Rasool, Ghulam"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:59:05Z","subjects":["artificial intelligence","deep learning","human brain","object recognition","object classification","Magnetic resonance imaging","Neural networks (Computer science)","Biomedical Engineering and Bioengineering","Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://rdw.rowan.edu/etd/2682","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://rdw.rowan.edu/etd/2682","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://rdw.rowan.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Ardw.rowan.edu%3Aetd-3684","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Bouaynaya, Nidhal C.","Fathallah-Shaykh, Hassan","Rasool, Ghulam"]},{"key":"dc:creator","label":"Author","values":["Palumbo, Oliver John"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2019-07-30T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2019-06-25T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S. Electrical and Computer Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["artificial intelligence","deep learning","human brain","object recognition","object classification","Magnetic resonance imaging","Neural networks (Computer science)","Biomedical Engineering and Bioengineering","Electrical and Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://rdw.rowan.edu/etd/2682"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Data plenitude is the power but also the bottleneck for data-driven approaches, including neural networks. In particular, Convolutional Neural Networks (CNNs) require an abundant database of training images to achieve a desired high accuracy. Current techniques employed for boosting small datasets are data augmentation and synthetic data generation, which suffer from computational complexity and imprecision compared to original datasets. In this thesis, we intercalate prior knowledge based on the temporal relation between the images in the third dimension. Specifically, we compute the gradient of subsequent images in the dataset to remove extraneous information and highlight subtle variations between the images. The approach is coined \"Inverted Cone\" because the volume of brain images below the level of the eyes is ordered to form an inverted cone geometry. The application explored in this work is deboning, or brain extraction, in brain magnetic resonance imaging (MRI) scans. We considered a limited dataset of 23 patients with and without malignant glioblastoma provided by the University of Alabama at Birmingham School of Medicine. Automatic deboning was performed by employing an optimized CNN architecture with and without the Inverted Cone processing. The classic CNN achieved a validation accuracy of 77%, while the Inverted Cone CNN model achieved a validation accuracy of 86% in a dataset of 451 brain MRI slices."]},{"key":"dc:title","label":"Title","values":["Inverted cone convolutional neural network for deboning MRIs"]}]}],"canonical_facts":{"dc:contributor":["Bouaynaya, Nidhal C.","Fathallah-Shaykh, Hassan","Rasool, Ghulam"],"dc:creator":["Palumbo, Oliver John"],"dc:date.available":["2019-07-30T07:00:00Z"],"dc:date.created":["2019-06-25T07:00:00Z"],"dc:description.abstract":["Data plenitude is the power but also the bottleneck for data-driven approaches, including neural networks. In particular, Convolutional Neural Networks (CNNs) require an abundant database of training images to achieve a desired high accuracy. Current techniques employed for boosting small datasets are data augmentation and synthetic data generation, which suffer from computational complexity and imprecision compared to original datasets. In this thesis, we intercalate prior knowledge based on the temporal relation between the images in the third dimension. Specifically, we compute the gradient of subsequent images in the dataset to remove extraneous information and highlight subtle variations between the images. The approach is coined \"Inverted Cone\" because the volume of brain images below the level of the eyes is ordered to form an inverted cone geometry. The application explored in this work is deboning, or brain extraction, in brain magnetic resonance imaging (MRI) scans. We considered a limited dataset of 23 patients with and without malignant glioblastoma provided by the University of Alabama at Birmingham School of Medicine. Automatic deboning was performed by employing an optimized CNN architecture with and without the Inverted Cone processing. The classic CNN achieved a validation accuracy of 77%, while the Inverted Cone CNN model achieved a validation accuracy of 86% in a dataset of 451 brain MRI slices."],"dc:identifier":["https://rdw.rowan.edu/etd/2682"],"dc:subject":["artificial intelligence","deep learning","human brain","object recognition","object classification","Magnetic resonance imaging","Neural networks (Computer science)","Biomedical Engineering and Bioengineering","Electrical and Computer Engineering"],"dc:title":["Inverted cone convolutional neural network for deboning MRIs"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S. Electrical and Computer Engineering"]},"updated_at":"2026-11-19T08:59:05Z"}