{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-9349"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-9349","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"Active Deep Learning Method to Automate Unbiased Stereology Cell Counting","abstract":"Cell quantification in histopathology images plays a significant role in understanding and diagnosing diseases such as cancer and Alzheimers. The gold-standard for quantifying cells in tissue sections is the unbiased stereology approach. Unfortunately, in unbiased stereology current practices rely on a well-trained human to manually count hundreds of cells in microscopy images. However, this human-based manual approach is time-consuming, labor-intensive, subject to human errors, recognition bias, fatigue, variable training, poor reproducibility, and inter-observer error. Thus, the lack of high-throughput technology for automating unbiased stereology analyses remains a major obstacle to further progress in a wide range of neuroscience and cancer sub-disciplines. This dissertation provides deep learning methods to automate unbiased stereology cell counting in microscopy images of mice stained brain sections. These methods are based on supervised deep learning, which requires large labeled data sets for training in order to learn to count cells effectively. However, labeling data is time-consuming, labor-intensive, and requires expert knowledge in many fields, such as neuroscience. Therefore obtaining labeled data remains a bottleneck for effective supervised leaning based models. Here, we propose multiple approaches to generate and leverage unlabeled data for training deep learning models. First initial microscopic image labels (cell masks) were created using a handcrafted algorithm called the Adaptive Segmentation Algorithm (ASA), followed by human verification, instead of creating pixel-level cell masks manually. Second, due to the limitations of the generalization ability of ASA and the growing amount of unlabeled data --- due to the advancements and automation of microscopy image acquisition technology such as the Stereologer system, an algorithm to leverage unlabeled data using an active learning approach is proposed. This technique uses a previously trained deep learning model to create masks and query an unlabeled pool of data for masks to be verified by a human and increase the training examples for the deep learning model to improve performance. Moreover, the dissertation presents an experimental study of the effect of the non-reproducibility of deep learning models using two different deep learning libraries. The study shows the various sources of non-reproducibility for deep learning results.","abstract_html":"Cell quantification in histopathology images plays a significant role in understanding and diagnosing diseases such as cancer and Alzheimers. The gold-standard for quantifying cells in tissue sections is the unbiased stereology approach. Unfortunately, in unbiased stereology current practices rely on a well-trained human to manually count hundreds of cells in microscopy images. However, this human-based manual approach is time-consuming, labor-intensive, subject to human errors, recognition bias, fatigue, variable training, poor reproducibility, and inter-observer error. Thus, the lack of high-throughput technology for automating unbiased stereology analyses remains a major obstacle to further progress in a wide range of neuroscience and cancer sub-disciplines. This dissertation provides deep learning methods to automate unbiased stereology cell counting in microscopy images of mice stained brain sections. These methods are based on supervised deep learning, which requires large labeled data sets for training in order to learn to count cells effectively. However, labeling data is time-consuming, labor-intensive, and requires expert knowledge in many fields, such as neuroscience. Therefore obtaining labeled data remains a bottleneck for effective supervised leaning based models. Here, we propose multiple approaches to generate and leverage unlabeled data for training deep learning models. First initial microscopic image labels (cell masks) were created using a handcrafted algorithm called the Adaptive Segmentation Algorithm (ASA), followed by human verification, instead of creating pixel-level cell masks manually. Second, due to the limitations of the generalization ability of ASA and the growing amount of unlabeled data --- due to the advancements and automation of microscopy image acquisition technology such as the Stereologer system, an algorithm to leverage unlabeled data using an active learning approach is proposed. This technique uses a previously trained deep learning model to create masks and query an unlabeled pool of data for masks to be verified by a human and increase the training examples for the deep learning model to improve performance. Moreover, the dissertation presents an experimental study of the effect of the non-reproducibility of deep learning models using two different deep learning libraries. The study shows the various sources of non-reproducibility for deep learning results.","abstract_has_math":false,"creators":["Alahmari, Saeed"],"institution":"University of South Florida","degree_name":"Doctor of Philosophy (Ph.D.)","degree_level":"Dissertation","degree_discipline":"Engineering Computer Science","degree_department":null,"school":null,"contributors":["Dmitry Goldgof, Ph.D.","Lawrence Hall, Ph.D.","Sudeep Sarkar, Ph.D.","Nasir Ghani, Ph.D.","Peter R. Mouton, Ph.D.","Robert Gillies, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-06-29T07:00:00Z","date_published":"2020-06-29T07:00:00Z","updated_at":"2026-11-19T08:51:23Z","subjects":["Active Learning","Unbiased Cell Quantification","Deep Neural Network","Cell Segmentation","Reproducibility of Deep Learning","Deterministic Deep Learning Models","Bioimaging and Biomedical Optics","Computer Sciences","Pathology"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/8152","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/8152","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.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-9349","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dmitry Goldgof, Ph.D.","Lawrence Hall, Ph.D.","Sudeep Sarkar, Ph.D.","Nasir Ghani, Ph.D.","Peter R. Mouton, Ph.D.","Robert Gillies, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Alahmari, Saeed"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-06-29T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Engineering Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation","Ph.D."]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (Ph.D.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Active Learning","Unbiased Cell Quantification","Deep Neural Network","Cell Segmentation","Reproducibility of Deep Learning","Deterministic Deep Learning Models","Bioimaging and Biomedical Optics","Computer Sciences","Pathology"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/8152"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Cell quantification in histopathology images plays a significant role in understanding and diagnosing diseases such as cancer and Alzheimers. The gold-standard for quantifying cells in tissue sections is the unbiased stereology approach. Unfortunately, in unbiased stereology current practices rely on a well-trained human to manually count hundreds of cells in microscopy images. However, this human-based manual approach is time-consuming, labor-intensive, subject to human errors, recognition bias, fatigue, variable training, poor reproducibility, and inter-observer error. Thus, the lack of high-throughput technology for automating unbiased stereology analyses remains a major obstacle to further progress in a wide range of neuroscience and cancer sub-disciplines. This dissertation provides deep learning methods to automate unbiased stereology cell counting in microscopy images of mice stained brain sections. These methods are based on supervised deep learning, which requires large labeled data sets for training in order to learn to count cells effectively. However, labeling data is time-consuming, labor-intensive, and requires expert knowledge in many fields, such as neuroscience. Therefore obtaining labeled data remains a bottleneck for effective supervised leaning based models. Here, we propose multiple approaches to generate and leverage unlabeled data for training deep learning models. First initial microscopic image labels (cell masks) were created using a handcrafted algorithm called the Adaptive Segmentation Algorithm (ASA), followed by human verification, instead of creating pixel-level cell masks manually. Second, due to the limitations of the generalization ability of ASA and the growing amount of unlabeled data --- due to the advancements and automation of microscopy image acquisition technology such as the Stereologer system, an algorithm to leverage unlabeled data using an active learning approach is proposed. This technique uses a previously trained deep learning model to create masks and query an unlabeled pool of data for masks to be verified by a human and increase the training examples for the deep learning model to improve performance. Moreover, the dissertation presents an experimental study of the effect of the non-reproducibility of deep learning models using two different deep learning libraries. The study shows the various sources of non-reproducibility for deep learning results."]},{"key":"dc:title","label":"Title","values":["Active Deep Learning Method to Automate Unbiased Stereology Cell Counting"]}]}],"canonical_facts":{"dc:contributor":["Dmitry Goldgof, Ph.D.","Lawrence Hall, Ph.D.","Sudeep Sarkar, Ph.D.","Nasir Ghani, Ph.D.","Peter R. Mouton, Ph.D.","Robert Gillies, Ph.D."],"dc:creator":["Alahmari, Saeed"],"dc:date":["2020-06-29T07:00:00Z"],"dc:description":["Cell quantification in histopathology images plays a significant role in understanding and diagnosing diseases such as cancer and Alzheimers. The gold-standard for quantifying cells in tissue sections is the unbiased stereology approach. Unfortunately, in unbiased stereology current practices rely on a well-trained human to manually count hundreds of cells in microscopy images. However, this human-based manual approach is time-consuming, labor-intensive, subject to human errors, recognition bias, fatigue, variable training, poor reproducibility, and inter-observer error. Thus, the lack of high-throughput technology for automating unbiased stereology analyses remains a major obstacle to further progress in a wide range of neuroscience and cancer sub-disciplines. This dissertation provides deep learning methods to automate unbiased stereology cell counting in microscopy images of mice stained brain sections. These methods are based on supervised deep learning, which requires large labeled data sets for training in order to learn to count cells effectively. However, labeling data is time-consuming, labor-intensive, and requires expert knowledge in many fields, such as neuroscience. Therefore obtaining labeled data remains a bottleneck for effective supervised leaning based models. Here, we propose multiple approaches to generate and leverage unlabeled data for training deep learning models. First initial microscopic image labels (cell masks) were created using a handcrafted algorithm called the Adaptive Segmentation Algorithm (ASA), followed by human verification, instead of creating pixel-level cell masks manually. Second, due to the limitations of the generalization ability of ASA and the growing amount of unlabeled data --- due to the advancements and automation of microscopy image acquisition technology such as the Stereologer system, an algorithm to leverage unlabeled data using an active learning approach is proposed. This technique uses a previously trained deep learning model to create masks and query an unlabeled pool of data for masks to be verified by a human and increase the training examples for the deep learning model to improve performance. Moreover, the dissertation presents an experimental study of the effect of the non-reproducibility of deep learning models using two different deep learning libraries. The study shows the various sources of non-reproducibility for deep learning results."],"dc:identifier":["https://digitalcommons.usf.edu/etd/8152"],"dc:subject":["Active Learning","Unbiased Cell Quantification","Deep Neural Network","Cell Segmentation","Reproducibility of Deep Learning","Deterministic Deep Learning Models","Bioimaging and Biomedical Optics","Computer Sciences","Pathology"],"dc:title":["Active Deep Learning Method to Automate Unbiased Stereology Cell Counting"],"thesis:degree_discipline":["Engineering Computer Science"],"thesis:degree_level":["Dissertation","Ph.D."],"thesis:degree_name":["Doctor of Philosophy (Ph.D.)"],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:51:23Z"}