Denoising digital breast tomosynthesis projections using deep learning with synthetic data as training set

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorDe Araújo, Darlan M. N.-
Autor(es): dc.creatorSalvadeo, Denis H. P.-
Autor(es): dc.creatorDe Paula, Davi D.-
Data de aceite: dc.date.accessioned2025-08-21T18:02:00Z-
Data de disponibilização: dc.date.available2025-08-21T18:02:00Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2023-05-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1117/1.JMI.10.3.034001-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/305208-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/305208-
Descrição: dc.descriptionPurpose: Image denoising based on deep neural networks (DNN) needs a big dataset containing digital breast tomosynthesis (DBT) projections acquired in different radiation doses to be trained, which is impracticable. Therefore, we propose extensively investigating the use of synthetic data generated by software for training DNNs to denoise DBT real data. Approach: The approach consists of generating a synthetic dataset representative of the DBT sample space by software, containing noisy and original images. Synthetic data were generated in two different ways: (a) virtual DBT projections generated by OpenVCT and (b) noisy images synthesized from photography regarding noise models used in DBT (e.g., Poisson-Gaussian noise). Then, DNN-based denoising techniques were trained using a synthetic dataset and tested for denoising physical DBT data. Results were evaluated in quantitative (PSNR and SSIM measures) and qualitative (visual analysis) terms. Furthermore, a dimensionality reduction technique (t-SNE) was used for visualization of sample spaces of synthetic and real datasets. Results: The experiments showed that training DNN models with synthetic data could denoise DBT real data, achieving competitive results to traditional methods in quantitative terms but showing a better balance between noise filtering and detail preservation in a visual analysis. T-SNE enables us to visualize if synthetic and real noises are in the same sample space. Conclusion: We propose a solution for the lack of suitable training data to train DNN models for denoising DBT projections, showing that we just need the synthesized noise to be in the same sample space as the target image.-
Descrição: dc.descriptionSão Paulo State University Institute of Geociences and Exact Sciences-
Descrição: dc.descriptionSão Paulo State University Institute of Geociences and Exact Sciences-
Idioma: dc.languageen-
Relação: dc.relationJournal of Medical Imaging-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectdeep learning-
Palavras-chave: dc.subjectdigital breast tomosynthesis-
Palavras-chave: dc.subjectimage denoising-
Palavras-chave: dc.subjectsynthetic data-
Palavras-chave: dc.subjectvirtual clinical trials-
Título: dc.titleDenoising digital breast tomosynthesis projections using deep learning with synthetic data as training set-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.