Multimodality radiomics prediction of radiotherapy-induced the early proctitis and cystitis in rectal cancer patients: a machine learning study

Abstract

Purpose. This study aims to predict radiotherapy-induced rectal and bladder toxicity using computed tomography (CT) and magnetic resonance imaging (MRI) radiomics features in combination with clinical and dosimetric features in rectal cancer patients. Methods. A total of sixty-three patients with locally advanced rectal cancer who underwent three-dimensional conformal radiation therapy (3D-CRT) were included in this study. Radiomics features were extracted from the rectum and bladder walls in pretreatment CT and MR-T2W-weighted images. Feature selection was performed using various methods, including Least Absolute Shrinkage and Selection Operator (Lasso), Minimum Redundancy Maximum Relevance (MRMR), Chi-square (Chi2), Analysis of Variance (ANOVA), Recursive Feature Elimination (RFE), and SelectPercentile. Predictive modeling was carried out using machine learning algorithms, such as K-nearest neighbor (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Gradient Boosting (XGB), and Linear Discriminant Analysis (LDA). The impact of the Laplacian of Gaussian (LoG) filter was investigated with sigma values ranging from 0.5 to 2. Model performance was evaluated in terms of the area under the receiver operating characteristic curve (AUC), accuracy, precision, sensitivity, and specificity. Results. A total of 479 radiomics features were extracted, and 59 features were selected. The pre-MRI T2W model exhibited the highest predictive performance with an AUC: 91.0/96.57%, accuracy: 90.38/96.92%, precision: 90.0/97.14%, sensitivity: 93.33/96.50%, and specificity: 88.09/97.14%. These results were achieved with both original image and LoG filter (sigma = 0.5–1.5) based on LDA/DT-RF classifiers for proctitis and cystitis, respectively. Furthermore, for the CT data, AUC: 90.71/96.0%, accuracy: 90.0/96.92%, precision: 88.14/97.14%, sensitivity: 93.0/96.0%, and specificity: 88.09/97.14% were acquired. The highest values were achieved using XGB/DT-XGB classifiers for proctitis and cystitis with LoG filter (sigma = 2)/LoG filter (sigma = 0.5–2), respectively. MRMR/RFE-Chi2 feature selection methods demonstrated the best performance for proctitis and cystitis in the pre-MRI T2W model. MRMR/MRMR-Lasso yielded the highest model performance for CT. Conclusion. Radiomics features extracted from pretreatment CT and MR images can effectively predict radiation-induced proctitis and cystitis. The study found that LDA, DT, RF, and XGB classifiers, combined with MRMR, RFE, Chi2, and Lasso feature selection algorithms, along with the LoG filter, offer strong predictive performance. With the inclusion of a larger training dataset, these models can be valuable tools for personalized radiotherapy decision-making.

Association of the CXCL12 rs1801157 Polymorphism with Breast Cancer Risk: A Meta-Analysis

“…Heterogeneity in meta-analysis refers to the variation in study outcomes between studies. Thus, assessing heterogeneity in meta-analysis is critical for model selection and decision making [60][61][62]. High heterogeneity was found in this meta-analysis under three genetic models in overall population [63].…”

Correlation between rs1800871, rs1800872 and rs1800896 Polymorphisms at IL-10 Gene and Lung Cancer Risk

“…Their pooled data showed that there was no significant association in distribution of IL-4 rs2070874, IL-6 rs1800795, IL-6 rs1800796, IL-8 rs4073, IL-10 rs1800871, and IL-10 rs1800896 polymorphisms among lung cancer patients and controls. However, their subgroup analysis showed that IL-4 rs2243250 might influence predisposition to lung cancer in Asians, whereas IL-10 rs1800872 polymorphism might influence predisposition The heterogeneity and publication bias are of importance which may affect the results of meta-analysis [44,70,42,71,72]. In the current meta-analysis, a significant heterogeneity existed for -819T>C and -1082A>G polymorphisms under almost genetic models in overall, but not for IL-10 -592A>C. After subgroup analyses by ethnicity, the heterogeneity was not decreased by ethnicity, suggesting that other factors such as geneenvironment factors or histological type cause the heterogeneity.…”

Association between XRCC2 Arg188His Polymorphism and Breast Cancer Susceptibility: A Systematic Review and Meta-Analysis

“…BRCA1 and BRCA2 mutations are inherited in an autosomal dominant fashion [14,15]. Germline mutations in BRCA1 have been identified in 15-20% of women with a family history of breast cancer and 60-80% of women with a family history of both breast and ovarian cancer [16][17][18]. Moreover, genomewide association studies (GWAS) have identified over 80 loci significantly associated with sporadic breast cancer, which these variants explain only 16 % of breast cancer heritability [19,10].…”