{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/25780"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/25780","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"Deep Convolutional Neural Networks for Multiclassification of Imbalanced Liver MRI Sequence Dataset","abstract":"Application of deep learning in radiology has the potential to automate workflows, support radiologists with decision support, and provide patients a logic-based algorithmic assessment. Unfortunately, medical datasets are often not uniformly distributed due to a naturally occurring imbalance. For this research, a multi-classification of liver MRI sequences for imaging of hepatocellular carcinoma (HCC) was conducted on a highly imbalanced clinical dataset using deep convolutional neural network. We have compared four multi classification classifiers which were Model A and Model B (both trained using imbalanced training data), Model C (trained using augmented training images) and Model D (trained using under sampled training images). Data augmentation such as 45-degree rotation, horizontal and vertical flip and random under sampling were performed to tackle class imbalance. HCC, the third most common cause of cancer-related mortality [1], can be diagnosed with high specificity using Magnetic Resonance Imaging (MRI) with the Liver Imaging Reporting and Data System (LI-RADS). Each individual MRI sequence reveals different characteristics that are useful to determine likelihood of HCC. We developed a deep convolutional neural network for the multi-classification of imbalanced MRI sequences that will aid when building a model to apply LI-RADS to diagnose HCC. Radiologists use these MRI sequences to help them identify specific LI-RADS features, it helps automate some of the LIRADS process, and further applications of machine learning to LI-RADS will likely depend on automatic sequence classification as a first step. Our study included an imbalanced dataset of 193,868 images containing 10 MRI sequences: in- phase (IP) chemical shift imaging, out-phase (OOP) chemical shift imaging, T1-weighted post contrast imaging (C+, C-, C-C+), fat suppressed T2 weighted imaging (T2FS), T2 weighted imaging, Diffusion Weighted Imaging (DWI), Apparent Diffusion Coefficient map (ADC) and In phase/Out of phase (IPOOP) imaging. Model performance for Models A, B, C and D provided a macro average F1 score of 0.97, 0.96, 0.95 and 0.93 respectively. Model A showed higher classification scores than models trained using data augmentation and under sampling.","abstract_html":"Application of deep learning in radiology has the potential to automate workflows, support radiologists with decision support, and provide patients a logic-based algorithmic assessment. Unfortunately, medical datasets are often not uniformly distributed due to a naturally occurring imbalance. For this research, a multi-classification of liver MRI sequences for imaging of hepatocellular carcinoma (HCC) was conducted on a highly imbalanced clinical dataset using deep convolutional neural network. We have compared four multi classification classifiers which were Model A and Model B (both trained using imbalanced training data), Model C (trained using augmented training images) and Model D (trained using under sampled training images). Data augmentation such as 45-degree rotation, horizontal and vertical flip and random under sampling were performed to tackle class imbalance. HCC, the third most common cause of cancer-related mortality [1], can be diagnosed with high specificity using Magnetic Resonance Imaging (MRI) with the Liver Imaging Reporting and Data System (LI-RADS). Each individual MRI sequence reveals different characteristics that are useful to determine likelihood of HCC. We developed a deep convolutional neural network for the multi-classification of imbalanced MRI sequences that will aid when building a model to apply LI-RADS to diagnose HCC. Radiologists use these MRI sequences to help them identify specific LI-RADS features, it helps automate some of the LIRADS process, and further applications of machine learning to LI-RADS will likely depend on automatic sequence classification as a first step. Our study included an imbalanced dataset of 193,868 images containing 10 MRI sequences: in- phase (IP) chemical shift imaging, out-phase (OOP) chemical shift imaging, T1-weighted post contrast imaging (C+, C-, C-C+), fat suppressed T2 weighted imaging (T2FS), T2 weighted imaging, Diffusion Weighted Imaging (DWI), Apparent Diffusion Coefficient map (ADC) and In phase/Out of phase (IPOOP) imaging. Model performance for Models A, B, C and D provided a macro average F1 score of 0.97, 0.96, 0.95 and 0.93 respectively. Model A showed higher classification scores than models trained using data augmentation and under sampling.","abstract_has_math":false,"creators":["Trivedi, Aditya"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"eHealth","school":null,"contributors":[],"advisors":["Doyle, Thomas"],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020","date_published":"2020","updated_at":"2026-11-18T19:30:48Z","subjects":["Imbalanced","Medical Imaging","Deep Learning","Convolutional Neural Networks","Clinical Decision Support","Radiology"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/8520"],"render_values":[{"text":"https://doi.org/10.71548/8520","href":"https://doi.org/10.71548/8520","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11375/25780","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"http://hdl.handle.net/11375/25780","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://macsphere.mcmaster.ca/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Amacsphere.mcmaster.ca%3A11375%2F25780","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Doyle, Thomas"]},{"key":"dc:contributor.department","label":"Department","values":["eHealth"]},{"key":"dc:creator","label":"Author","values":["Trivedi, Aditya"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-09-09T15:54:39Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-09-09T15:54:39Z"]},{"key":"dc:date.issued","label":"Date","values":["2020"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Imbalanced","Medical Imaging","Deep Learning","Convolutional Neural Networks","Clinical Decision Support","Radiology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11375/25780","https://doi.org/10.71548/8520"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Application of deep learning in radiology has the potential to automate workflows, support radiologists with decision support, and provide patients a logic-based algorithmic assessment. Unfortunately, medical datasets are often not uniformly distributed due to a naturally occurring imbalance. For this research, a multi-classification of liver MRI sequences for imaging of hepatocellular carcinoma (HCC) was conducted on a highly imbalanced clinical dataset using deep convolutional neural network. We have compared four multi classification classifiers which were Model A and Model B (both trained using imbalanced training data), Model C (trained using augmented training images) and Model D (trained using under sampled training images). Data augmentation such as 45-degree rotation, horizontal and vertical flip and random under sampling were performed to tackle class imbalance. HCC, the third most common cause of cancer-related mortality [1], can be diagnosed with high specificity using Magnetic Resonance Imaging (MRI) with the Liver Imaging Reporting and Data System (LI-RADS). Each individual MRI sequence reveals different characteristics that are useful to determine likelihood of HCC. We developed a deep convolutional neural network for the multi-classification of imbalanced MRI sequences that will aid when building a model to apply LI-RADS to diagnose HCC. Radiologists use these MRI sequences to help them identify specific LI-RADS features, it helps automate some of the LIRADS process, and further applications of machine learning to LI-RADS will likely depend on automatic sequence classification as a first step. Our study included an imbalanced dataset of 193,868 images containing 10 MRI sequences: in- phase (IP) chemical shift imaging, out-phase (OOP) chemical shift imaging, T1-weighted post contrast imaging (C+, C-, C-C+), fat suppressed T2 weighted imaging (T2FS), T2 weighted imaging, Diffusion Weighted Imaging (DWI), Apparent Diffusion Coefficient map (ADC) and In phase/Out of phase (IPOOP) imaging. Model performance for Models A, B, C and D provided a macro average F1 score of 0.97, 0.96, 0.95 and 0.93 respectively. Model A showed higher classification scores than models trained using data augmentation and under sampling."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science (MSc)"]},{"key":"dc:title","label":"Title","values":["Deep Convolutional Neural Networks for Multiclassification of Imbalanced Liver MRI Sequence Dataset"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"dc:contributor.advisor":["Doyle, Thomas"],"dc:contributor.department":["eHealth"],"dc:creator":["Trivedi, Aditya"],"dc:date.accessioned":["2020-09-09T15:54:39Z"],"dc:date.available":["2020-09-09T15:54:39Z"],"dc:date.issued":["2020"],"dc:description.abstract":["Application of deep learning in radiology has the potential to automate workflows, support radiologists with decision support, and provide patients a logic-based algorithmic assessment. Unfortunately, medical datasets are often not uniformly distributed due to a naturally occurring imbalance. For this research, a multi-classification of liver MRI sequences for imaging of hepatocellular carcinoma (HCC) was conducted on a highly imbalanced clinical dataset using deep convolutional neural network. We have compared four multi classification classifiers which were Model A and Model B (both trained using imbalanced training data), Model C (trained using augmented training images) and Model D (trained using under sampled training images). Data augmentation such as 45-degree rotation, horizontal and vertical flip and random under sampling were performed to tackle class imbalance. HCC, the third most common cause of cancer-related mortality [1], can be diagnosed with high specificity using Magnetic Resonance Imaging (MRI) with the Liver Imaging Reporting and Data System (LI-RADS). Each individual MRI sequence reveals different characteristics that are useful to determine likelihood of HCC. We developed a deep convolutional neural network for the multi-classification of imbalanced MRI sequences that will aid when building a model to apply LI-RADS to diagnose HCC. Radiologists use these MRI sequences to help them identify specific LI-RADS features, it helps automate some of the LIRADS process, and further applications of machine learning to LI-RADS will likely depend on automatic sequence classification as a first step. Our study included an imbalanced dataset of 193,868 images containing 10 MRI sequences: in- phase (IP) chemical shift imaging, out-phase (OOP) chemical shift imaging, T1-weighted post contrast imaging (C+, C-, C-C+), fat suppressed T2 weighted imaging (T2FS), T2 weighted imaging, Diffusion Weighted Imaging (DWI), Apparent Diffusion Coefficient map (ADC) and In phase/Out of phase (IPOOP) imaging. Model performance for Models A, B, C and D provided a macro average F1 score of 0.97, 0.96, 0.95 and 0.93 respectively. Model A showed higher classification scores than models trained using data augmentation and under sampling."],"dc:description.degree":["Master of Science (MSc)"],"dc:identifier.uri":["http://hdl.handle.net/11375/25780","https://doi.org/10.71548/8520"],"dc:language.iso":["en"],"dc:subject":["Imbalanced","Medical Imaging","Deep Learning","Convolutional Neural Networks","Clinical Decision Support","Radiology"],"dc:title":["Deep Convolutional Neural Networks for Multiclassification of Imbalanced Liver MRI Sequence Dataset"],"dc:type":["Thesis"],"others:access_status":["open.access"]},"updated_at":"2026-11-18T19:30:48Z"}