{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["17(2)"],"submitter":["Salmanpour MR"],"pubmed_abstract":["Objective
This study explores a semi-supervised learning (SSL), pseudo-labeled strategy using diverse datasets such as head and neck cancer (HNCa) to enhance lung cancer (LCa) survival outcome predictions, analyzing handcrafted and deep radiomic features (HRF/DRF) from PET/CT scans with hybrid machine learning systems (HMLSs).Methods
We collected 199 LCa patients with both PET and CT images, obtained from TCIA and our local database, alongside 408 HNCa PET/CT images from TCIA. We extracted 215 HRFs and 1024 DRFs by PySERA and a 3D autoencoder, respectively, within the ViSERA 1.0.0 software, from segmented primary tumors. The supervised strategy (SL) employed an HMLS-PCA connected with six classifiers on both HRFs and DRFs. The SSL strategy expanded the datasets by adding 40"],"journal":["Cancers"],"pagination":["285"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11763441"],"repository":["biostudies-literature"],"pubmed_title":["Enhanced Lung Cancer Survival Prediction Using Semi-Supervised Pseudo-Labeling and Learning from Diverse PET/CT Datasets."],"pmcid":["PMC11763441"],"pubmed_authors":["Leung B","Fathi Jouzdani A","Sanati N","Gorji A","Yuan R","Ho C","Mousavi A","Maghsudi M","Salmanpour MR","Rahmim A"],"additional_accession":[]},"is_claimable":false,"name":"Enhanced Lung Cancer Survival Prediction Using Semi-Supervised Pseudo-Labeling and Learning from Diverse PET/CT Datasets.","description":"Objective
This study explores a semi-supervised learning (SSL), pseudo-labeled strategy using diverse datasets such as head and neck cancer (HNCa) to enhance lung cancer (LCa) survival outcome predictions, analyzing handcrafted and deep radiomic features (HRF/DRF) from PET/CT scans with hybrid machine learning systems (HMLSs).Methods
We collected 199 LCa patients with both PET and CT images, obtained from TCIA and our local database, alongside 408 HNCa PET/CT images from TCIA. We extracted 215 HRFs and 1024 DRFs by PySERA and a 3D autoencoder, respectively, within the ViSERA 1.0.0 software, from segmented primary tumors. The supervised strategy (SL) employed an HMLS-PCA connected with six classifiers on both HRFs and DRFs. The SSL strategy expanded the datasets by adding 40","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Jan","modification":"2025-04-18T14:27:43.523Z","creation":"2025-04-07T00:37:32.461Z"},"accession":"S-EPMC11763441","cross_references":{"pubmed":["39858067"],"doi":["10.3390/cancers17020285"]}}