Enhanced Lung Cancer Survival Prediction Using Semi-Supervised Pseudo-Labeling and Learning from Diverse PET/CT Datasets.
Simple Summary: This study presents a novel semi-supervised learning (SSL) approach that improves lung cancer survival predictions by incorporating diverse datasets, including head and neck cancer (HNCa), alongside handcrafted and deep radiomic features (HRF/DRF) from PET/CT scans. By shifting from...
| Published in: | Cancers Vol. 17; no. 2; pp. 285 - 304 |
|---|---|
| Main Authors: | , , , , , , , , , |
| Format: | research tables/charts Journal Article |
| Published: |
MDPI
Jan2025
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=182451055&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 182451055 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 20726694 B74B jtl: Cancers issn: 20726694 maglogo: N pubinfo: dt: Jan2025 vid: 17 iid: 2 pid: 97109 pub: MDPI artinfo: ui: 182451055 182451055 182451055 10.3390/cancers17020285 182451055 ppf: 285 ppct: 19 formats: tig: atl: Enhanced Lung Cancer Survival Prediction Using Semi-Supervised Pseudo-Labeling and Learning from Diverse PET/CT Datasets. aug: au: Salmanpour, Mohammad R. Gorji, Arman Mousavi, Amin Fathi Jouzdani, Ali Sanati, Nima Maghsudi, Mehdi Leung, Bonnie Ho, Cheryl Yuan, Ren Rahmim, Arman affil: BC Cancer Research Institute, Vancouver, BC V5Z 1L3, Canada sug: subj: Lung Neoplasms Prognosis Survival Analysis Machine Learning Methods Prediction Models Positron Emission Tomography Computed Tomography Radiomics Human Funding Source Male Female Middle Age Aged Factor Analysis Algorithms Neural Networks (Computer) Middle Aged: 45-64 years Aged: 65+ years Male Female ab: Simple Summary: This study presents a novel semi-supervised learning (SSL) approach that improves lung cancer survival predictions by incorporating diverse datasets, including head and neck cancer (HNCa), alongside handcrafted and deep radiomic features (HRF/DRF) from PET/CT scans. By shifting from traditional supervised learning to SSL, our method addresses data limitations by using heterogeneous yet clinically relevant data, achieving an average accuracy of 0.85 ± 0.05 with PCA + Multi-Layer Perceptron (MLP) models. This approach not only enhances predictive performance but also introduces a new paradigm for leveraging diverse datasets in tasks with limited data. 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 408 pseudo-labeled HNCa cases (labeled by the Random Forest algorithm) to 199 LCa cases, using the same HMLS techniques. Furthermore, principal component analysis (PCA) linked with four survival prediction algorithms were utilized in the survival hazard ratio analysis. Results: The SSL strategy outperformed the SL method (p << 0.001), achieving an average accuracy of 0.85 ± 0.05 with DRFs from PET and PCA + Multi-Layer Perceptron (MLP), compared to 0.69 ± 0.06 for the SL strategy using DRFs from CT and PCA + Light Gradient Boosting (LGB). Additionally, PCA linked with Component-wise Gradient Boosting Survival Analysis on both HRFs and DRFs, as extracted from CT, had an average C-index of 0.80, with a log rank p-value << 0.001, confirmed by external testing. Conclusions: Shifting from HRFs and SL to DRFs and SSL strategies, particularly in contexts with limited data points, enabling CT or PET alone, can significantly achieve high predictive performance. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|