{"doi":"10.1016/j.ejmp.2021.03.007","title":"Breast glandularity and mean glandular dose assessment using a deep learning framework: Virtual patients study","abstract":null,"journal":"Physica Medica","year":2021,"id":671214,"datarank":0.624310170723811,"base_score":2.5649493574615367,"endowment":2.5649493574615367,"self_citation_contribution":0.38474240361923057,"citation_network_contribution":0.2395677671045805,"self_endowment_contribution":0.38474240361923057,"citer_contribution":0.2395677671045805,"corpus_percentile":null,"corpus_rank":null,"citation_count":12,"citer_count":9,"citers_with_citation_signal":7,"citers_with_endowment":7,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1753487,"name":"Alessandra Tomal","orcid":null,"position":1,"is_corresponding":false},{"id":1753486,"name":"Rodrigo T. Massera","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Breast glandularity and mean glandular dose assessment using a deep learning framework: Virtual patients study","abstract":"<h4>Purpose</h4>Breast dosimetry in mammography is an important aspect of radioprotection since women are exposed periodically to ionizing radiation due to breast cancer screening programs. Mean glandular dose (MGD) is the standard quantity employed for the establishment of dose reference levels in retrospective population studies. However, MGD calculations requires breast glandularity estimation. This work proposes a deep learning framework for volume glandular fraction (VGF) estimations based on mammography images, which in turn are converted to glandularity values for MGD calculations.<h4>Methods</h4>208 virtual breast phantoms were generated and compressed computationally. The mammography images were obtained with Monte Carlo simulations (MC-GPU code) and a ray-tracing algorithm was employed for labeling the training data. The architectures of the neural networks are based on the XNet and multilayer perceptron, adapted for each task. The network predictions were compared with the ground truth using the coefficient of determination (r<sup>2</sup>).<h4>Results</h4>The results have shown a good agreement for inner breast segmentation (r<sup>2</sup> = 0.999), breast volume prediction (r<sup>2</sup> = 0.982) and VGF prediction (r<sup>2</sup> = 0.935). Moreover, the DgN coefficients using the predicted VGF for the virtual population differ on average 1.3% from the ground truth values. Afterwards with the obtained DgN coefficients, the MGD values were estimated from exposure factors extracted from the DICOM header of a clinical cohort, with median(75 percentile) values of 1.91(2.45) mGy.<h4>Conclusion</h4>We successfully implemented a deep learning framework for VGF and MGD calculations for virtual breast phantoms.","is_dataset_classified":null,"base_score":2.5649493574615367,"endowment":2.5649493574615367,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"33984580","pmcid":null,"openalex_id":"https://openalex.org/W3160877225","authors":[],"funders":[{"funder_name":"Fundação de Amparo à Pesquisa do Estado de São Paulo","grant_id":"2015/21873–8","title":null},{"funder_name":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","grant_id":"140155/2019–8","title":null},{"funder_name":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","grant_id":"","title":null}],"total_grants":3,"fwci":0.9132,"citation_percentile":0.74474312,"influential_citations":0,"citation_trend":[{"year":2021,"count":1},{"year":2022,"count":1},{"year":2023,"count":3},{"year":2024,"count":2},{"year":2025,"count":3},{"year":2026,"count":2}],"oa_status":"bronze","license":"https://www.elsevier.com/legal/tdmrep-license","oa_locations":[{"url":"http://www.physicamedica.com/article/S112017972100123X/pdf","host_type":"journal"},{"url":"http://www.physicamedica.com/article/S112017972100123X/pdf","host_type":"publisher"},{"url":"https://api.elsevier.com/content/article/PII:S112017972100123X?httpAccept=text/xml","host_type":"publisher"},{"url":"https://api.elsevier.com/content/article/PII:S112017972100123X?httpAccept=text/plain","host_type":"publisher"},{"url":"https://doi.org/10.1016/j.ejmp.2021.03.007","host_type":"journal"},{"url":"https://pubmed.ncbi.nlm.nih.gov/33984580","host_type":"repository"},{"url":"https://hdl.handle.net/20.500.12733/884","host_type":"repository"}],"fields_of_study":["Digital Radiography and Breast Imaging","Radiation Dose and Imaging","Advanced Radiotherapy Techniques","Breast","Deep Learning","Female","Humans","Mammography","Monte Carlo Method","Phantoms, Imaging","Radiation Dosage","Retrospective Studies"],"mesh_terms":["Deep Learning","Breast","Female","Humans","Mammography","Monte Carlo Method","Radiation Dosage","Retrospective Studies","Phantoms, Imaging"],"keywords":["Mammography","Population","Artificial intelligence","Ground truth","Nuclear medicine","Breast cancer","Computer science","DICOM","Medicine","Cancer","Deep Learning","Mean Glandular Dose","Breast Glandularity"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Good health and well-being"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-16T01:48:13.941654Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}