Dataset Information

A Machine Learning Approach Using FDG PET-Based Radiomics for Prediction of Tumor Mutational Burden and Prognosis in Stage IV Colorectal Cancer.

ABSTRACT:

Introduction

We assessed the performance of F-18 fluorodeoxyglucose positron emission tomography (FDG PET)-based radiomics for the prediction of tumor mutational burden (TMB) and prognosis using a machine learning (ML) approach in patients with stage IV colorectal cancer (CRC).

Methods

Ninety-one CRC patients who underwent pretreatment FDG PET/computed tomography (CT) and palliative chemotherapy were retrospectively included. PET-based radiomics were extracted from the primary tumor on PET imaging using the software LIFEx. For feature selection, PET-based radiomics associated with TMB were selected by logistic regression analysis. The performances of seven ML algorithms to predict high TMB were compared by the area under the receiver's operating characteristic curves (AUCs) and validated by five-fold cross-validation. A PET radiomic score was calculated by averaging the z-score of each radiomic feature. The prognostic power of the PET radiomic score was assessed using Cox proportional hazards regression analysis.

Results

Ten significant radiomic features associated with TMB were selected: surface-to-volume ratio, total lesion glycolysis, tumor volume, area, compacity, complexity, entropy, correlation, coarseness, and zone size non-uniformity. The k-nearest neighbors model obtained the good performance for prediction of high TMB (AUC: 0.791, accuracy: 0.814, sensitivity: 0.619, specificity: 0.871). On multivariable Cox regression analysis, the PET radiomic score (Hazard ratio = 4.498, 95% confidential interval = 1.024-19.759; p = 0.046) was a significant independent prognostic factor for OS.

Conclusions

This study demonstrates that PET-based radiomics are useful image biomarkers for the prediction of TMB status in stage IV CRC. PET radiomic score, which integrates significant radiomic features, has the potential to predict survival in stage IV CRC patients.

SUBMITTER: Lee H

PROVIDER: S-EPMC10416826 | biostudies-literature | 2023 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Machine Learning Approach Using FDG PET-Based Radiomics for Prediction of Tumor Mutational Burden and Prognosis in Stage IV Colorectal Cancer.

Lee Hyunjong H Moon Seung Hwan SH Hong Jung Yong JY Lee Jeeyun J Hyun Seung Hyup SH

Cancers 20230728 15

<h4>Introduction</h4>We assessed the performance of F-18 fluorodeoxyglucose positron emission tomography (FDG PET)-based radiomics for the prediction of tumor mutational burden (TMB) and prognosis using a machine learning (ML) approach in patients with stage IV colorectal cancer (CRC).<h4>Methods</h4>Ninety-one CRC patients who underwent pretreatment FDG PET/computed tomography (CT) and palliative chemotherapy were retrospectively included. PET-based radiomics were extracted from the primary tum ...[more]

PMID: 37568657

Similar Datasets

Project description:BackgroundColorectal cancer (CRC) is the third most frequent cause of cancer-related death, while tumor/node/metastasis (TNM) stage of American Joint Committee on Cancer is the guideline of making treatment strategy and predicting survival. The aim of this study is to investigate the association of preoperative 2-deoxy-2[18F]fluoro-D-glucose positron emission tomography/computed tomography (18F-FDG PET/CT), TNM stage, and prognosis of patients with CRC.MethodsFrom September 2016 to August 2022, a total of 132 patients were retrospectively and consecutively enrolled in this cross-sectional study, who were diagnosed as CRC by histopathology and received preoperative 18F-FDG PET/CT. Firstly, the correlation between the metabolic parameters and clinicopathological features of the primary tumors was investigated. Secondly, univariate and multivariate logistic regression analyses were used to estimate the odds ratio of the association between the clinical and metabolic parameters and the advanced TNM stage (stage III-IV). Thirdly, progression-free survival (PFS) was analyzed using Kaplan-Meier curves and Log-rank test.ResultsThe results revealed that the metabolic tumor volume (MTV) >6.6 cm3 and serum carcinoembryonic antigen (CEA) >5.84 ng/mL were independently associated with advanced TNM stage (P=0.0009, 0.0011, respectively). Larger tumor size, higher tumor-to-liver standardized uptake value ratio, MTV, and total lesion glycolysis (TLG) were significantly correlated with advanced pT stage (stage 4), and higher TLG and MTV were significantly correlated with advanced pN stage (stage 1-2) (P<0.05), while no metabolic parameters were significantly correlated with metastasis status (P>0.05). Higher serum CEA and carbohydrate antigen 19-9 levels were significantly correlated with advanced pT, pN stage, and metastasis status (P<0.05). Patients were followed up for at least 1 year. The MTV >6.6 cm3 was significantly associated with worse PFS (P=0.032).Conclusions18F-FDG PET-CT can serve as a noninvasive tool for preoperatively staging CRC. The MTV >6.6 cm3 might be associated with advanced TNM stage and worse PFS.

Project description:BackgroundDiffuse large B-cell lymphoma (DLBCL) is the most common subtype of non-Hodgkin lymphoma in adults. Standard treatment includes chemoimmunotherapy with R-CHOP or similar regimens. Despite treatment advancements, many patients with DLBCL experience refractory disease or relapse. While baseline 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) parameters have shown promise in predicting survival, they may not fully capture lesion heterogeneity. This study aimed to assess the prognostic value of baseline 18F-FDG PET radiomics features in comparison with clinical factors and metabolic parameters for assessing 2-year progression-free survival (PFS) and 5-year overall survival (OS) in patients with DLBCL.ResultsA total of 201 patients with DLBCL were enrolled in this study, and 1328 radiomics features were extracted. The radiomics signatures, clinical factors, and metabolic parameters showed significant prognostic value for individualized prognosis prediction in patients with DLBCL. Radiomics signatures showed the lowest Akaike information criterion (AIC) value and highest Harrell's concordance index (C-index) value in comparison with clinical factors and metabolic parameters for both PFS (AIC: 571.688 vs. 596.040 vs. 576.481; C-index: 0.732 vs. 0.658 vs. 0.702, respectively) and OS (AIC: 339.843 vs. 363.671 vs. 358.412; C-index: 0.759 vs. 0.667 vs. 0.659, respectively). Statistically significant differences were observed in the area under the curve (AUC) values between the radiomics signatures and clinical factors for both PFS (AUC: 0.768 vs. 0.681, P = 0.017) and OS (AUC: 0.767 vs. 0.667, P = 0.023). For OS, the AUC of the radiomics signatures were significantly higher than those of metabolic parameters (AUC: 0.767 vs. 0.688, P = 0.007). However, for PFS, no significant difference was observed between the radiomics signatures and metabolic parameters (AUC: 0.768 vs. 0.756, P = 0.654). The combined model and the best-performing individual model (radiomics signatures) alone showed no significant difference for both PFS (AUC: 0.784 vs. 0.768, P = 0.163) or OS (AUC: 0.772 vs. 0.767, P = 0.403).ConclusionsRadiomics signatures derived from PET images showed the high predictive power for progression in patients with DLBCL. The combination of radiomics signatures, clinical factors, and metabolic parameters may not significantly improve predictive value beyond that of radiomics signatures alone.

Project description:BackgroundStage IV colorectal cancer patients with liver metastasis represent a special group of CRC patients with poor prognosis. The prognostic factors have not been investigated for stage IV CRC patients undergoing primary cancer resection but not candidates for metastasis resection.MethodsNinety-nine stage IV CRC patients who underwent primary cancer resection without metastasis resection were retrospectively recruited. Both whole-exome sequencing (WES) and RNA-seq were performed with frozen primary cancer tissues, using para-cancerous normal tissues as the control. Valid data were obtained from 78 patients for WES and 84 patients for RNA-seq. Univariate, multivariate Cox analyses were performed and Nomogram model was established to predict patient prognosis.ResultsThe correlation between patient prognosis and clinicopathological factors, mutational status, or mRNA level changes was examined. Univariate (p = 0.0007) and subsequent multivariate analyses on clinicopathological factors showed that location (left or right) was the only independent risk factor for patient prognosis (HR = 3.63; 95% CI: 1.56-8.40, p = 0.003), while T, N, M staging, gender, race, location (rectum or colon), and pathological types were not stratifying factors. The mutational status of APC, TP53, KRAS, TTN, SYNE1, SMAD4, PIK3CA, RYR2, and BRAF did not show significant stratification in patient prognosis. RNA-seq showed that genes related to membrane function, ion channels, transporters, or receptors were among those with significant mRNA level alterations. Univariate analysis identified 97 genes with significantly altered mRNA levels, while NEUROD1, FGF18, SFTA2, PLAC1, SAA2, DSCAML1, and OTOP3 were significant in multivariate analysis. A risk model was established to stratify the prognosis of stage IV CRC patients. A Nomogram model was established with these genes to predict individual patient prognosis.ConclusionsA panel of eight genes with significant mRNA level alterations was capable of predicting the prognosis and risk of the specific patient group. Future prospective study is needed to validate the model.

Dataset Information

A Machine Learning Approach Using FDG PET-Based Radiomics for Prediction of Tumor Mutational Burden and Prognosis in Stage IV Colorectal Cancer.

Introduction

Methods

Results

Conclusions

Publications

A Machine Learning Approach Using FDG PET-Based Radiomics for Prediction of Tumor Mutational Burden and Prognosis in Stage IV Colorectal Cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets