Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction

Bibliographic Details
Main Author: Rodrigues, Nuno M.
Publication Date: 2024
Other Authors: Almeida, José Guilherme de, Rodrigues, Ana, Vanneschi, Leonardo, Matos, Celso, Lisitskaya, Maria, Uysal, Aycan, Silva, Sara, Papanikolaou, Nickolas
Format: Article
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/10362/177895
Summary: Rodrigues, N. M., Almeida, J. G. D., Rodrigues, A., Vanneschi, L., Matos, C., Lisitskaya, M., Uysal, A., Silva, S., & Papanikolaou, N. (2024). Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction. JCO Clinical Cancer Informatics, 8, Article e2300180. https://doi.org/10.1200/CCI.23.00180 --- Supported in part by FCT, Portugal, through funding of the LASIGE Research Unit (UIDB/00408/2020 [https://doi.org/10.54499/UIDB/00408/2020], UIDP/00408/2020 [https://doi.org/10.54499/UIDP/00408/2020]), and Nuno Rodrigues PhD Grant 10.54499/2021.05322.BD (https://doi.org/10.54499/2021.05322.BD). Ana Rodrigues and José Guilherme de Almeida were supported by the European Union H2020: ProCAncer-I project (EU grant 952159). This work was supported by national funds through FCT (Fundação para a Ciéncia e a Tecnologia), under the project—UIDB/04152/2020—Centro de Investigação em Gestão de Informação (MagIC)/NOVA IMS.
id RCAP_feba27e42a72a8db4074db3b44daa06c
oai_identifier_str oai:run.unl.pt:10362/177895
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness PredictionMedicine(all)SDG 3 - Good Health and Well-beingRodrigues, N. M., Almeida, J. G. D., Rodrigues, A., Vanneschi, L., Matos, C., Lisitskaya, M., Uysal, A., Silva, S., & Papanikolaou, N. (2024). Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction. JCO Clinical Cancer Informatics, 8, Article e2300180. https://doi.org/10.1200/CCI.23.00180 --- Supported in part by FCT, Portugal, through funding of the LASIGE Research Unit (UIDB/00408/2020 [https://doi.org/10.54499/UIDB/00408/2020], UIDP/00408/2020 [https://doi.org/10.54499/UIDP/00408/2020]), and Nuno Rodrigues PhD Grant 10.54499/2021.05322.BD (https://doi.org/10.54499/2021.05322.BD). Ana Rodrigues and José Guilherme de Almeida were supported by the European Union H2020: ProCAncer-I project (EU grant 952159). This work was supported by national funds through FCT (Fundação para a Ciéncia e a Tecnologia), under the project—UIDB/04152/2020—Centro de Investigação em Gestão de Informação (MagIC)/NOVA IMS.Purpose Emerging evidence suggests that the use of artificial intelligence can assist in the timely detection and optimization of therapeutic approach in patients with prostate cancer. The conventional perspective on radiomics encompassing segmentation and the extraction of radiomic features considers it as an independent and sequential process. However, it is not necessary to adhere to this viewpoint. In this study, we show that besides generating masks from which radiomic features can be extracted, prostate segmentation and reconstruction models provide valuable information in their feature space, which can improve the quality of radiomic signatures models for disease aggressiveness classification. Materials and Methods We perform 2,244 experiments with deep learning features extracted from 13 different models trained using different anatomic zones and characterize how modeling decisions, such as deep feature aggregation and dimensionality reduction, affect performance. Results While models using deep features from full gland and radiomic features consistently lead to improved disease aggressiveness prediction performance, others are detrimental. Our results suggest that the use of deep features can be beneficial, but an appropriate and comprehensive assessment is necessary to ensure that their inclusion does not harm predictive performance. Conclusion The study findings reveal that incorporating deep features derived from autoencoder models trained to reconstruct the full prostate gland (both zonal models show worse performance than radiomics only models), combined with radiomic features, often lead to a statistically significant increase in model performance for disease aggressiveness classification. Additionally, the results also demonstrate that the choice of feature selection is key to achieving good performance, with principal component analysis (PCA) and PCA + relief being the best approaches and that there is no clear difference between the three proposed latent representation extraction techniques.Information Management Research Center (MagIC) - NOVA Information Management SchoolNOVA Information Management School (NOVA IMS)RUNRodrigues, Nuno M.Almeida, José Guilherme deRodrigues, AnaVanneschi, LeonardoMatos, CelsoLisitskaya, MariaUysal, AycanSilva, SaraPapanikolaou, Nickolas2024-09-182025-09-18T00:00:00Z2024-09-18T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10362/177895eng2473-4276PURE: 93641020https://doi.org/10.1200/CCI.23.00180info:eu-repo/semantics/embargoedAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2025-02-03T01:37:19Zoai:run.unl.pt:10362/177895Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T19:41:42.391489Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction
title Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction
spellingShingle Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction
Rodrigues, Nuno M.
Medicine(all)
SDG 3 - Good Health and Well-being
title_short Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction
title_full Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction
title_fullStr Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction
title_full_unstemmed Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction
title_sort Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction
author Rodrigues, Nuno M.
author_facet Rodrigues, Nuno M.
Almeida, José Guilherme de
Rodrigues, Ana
Vanneschi, Leonardo
Matos, Celso
Lisitskaya, Maria
Uysal, Aycan
Silva, Sara
Papanikolaou, Nickolas
author_role author
author2 Almeida, José Guilherme de
Rodrigues, Ana
Vanneschi, Leonardo
Matos, Celso
Lisitskaya, Maria
Uysal, Aycan
Silva, Sara
Papanikolaou, Nickolas
author2_role author
author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Information Management Research Center (MagIC) - NOVA Information Management School
NOVA Information Management School (NOVA IMS)
RUN
dc.contributor.author.fl_str_mv Rodrigues, Nuno M.
Almeida, José Guilherme de
Rodrigues, Ana
Vanneschi, Leonardo
Matos, Celso
Lisitskaya, Maria
Uysal, Aycan
Silva, Sara
Papanikolaou, Nickolas
dc.subject.por.fl_str_mv Medicine(all)
SDG 3 - Good Health and Well-being
topic Medicine(all)
SDG 3 - Good Health and Well-being
description Rodrigues, N. M., Almeida, J. G. D., Rodrigues, A., Vanneschi, L., Matos, C., Lisitskaya, M., Uysal, A., Silva, S., & Papanikolaou, N. (2024). Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction. JCO Clinical Cancer Informatics, 8, Article e2300180. https://doi.org/10.1200/CCI.23.00180 --- Supported in part by FCT, Portugal, through funding of the LASIGE Research Unit (UIDB/00408/2020 [https://doi.org/10.54499/UIDB/00408/2020], UIDP/00408/2020 [https://doi.org/10.54499/UIDP/00408/2020]), and Nuno Rodrigues PhD Grant 10.54499/2021.05322.BD (https://doi.org/10.54499/2021.05322.BD). Ana Rodrigues and José Guilherme de Almeida were supported by the European Union H2020: ProCAncer-I project (EU grant 952159). This work was supported by national funds through FCT (Fundação para a Ciéncia e a Tecnologia), under the project—UIDB/04152/2020—Centro de Investigação em Gestão de Informação (MagIC)/NOVA IMS.
publishDate 2024
dc.date.none.fl_str_mv 2024-09-18
2024-09-18T00:00:00Z
2025-09-18T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/177895
url http://hdl.handle.net/10362/177895
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2473-4276
PURE: 93641020
https://doi.org/10.1200/CCI.23.00180
dc.rights.driver.fl_str_mv info:eu-repo/semantics/embargoedAccess
eu_rights_str_mv embargoedAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833598262021455872

Similar Items