Development and validation of a novel radiomics nomogram for prediction of early recurrence in colorectal cancer

Analysis of cancer-specific survival in patients with metastatic colorectal cancer: A evidence-based medicine study

BACKGROUND

Metastatic colorectal cancer (mCRC) is a common malignancy whose treatment has been a clinical challenge. Cancer-specific survival (CSS) plays a crucial role in assessing patient prognosis and treatment outcomes. However, there is still limited research on the factors affecting CSS in mCRC patients and their correlation.

AIM

To predict CSS, we developed a new nomogram model and risk grading system to classify risk levels in patients with mCRC.

METHODS

Data were extracted from the United States Surveillance, Epidemiology, and End Results database from 2018 to 2023. All eligible patients were randomly divided into a training cohort and a validation cohort. The Cox proportional hazards model was used to investigate the independent risk factors for CSS. A new nomogram model was developed to predict CSS and was evaluated through internal and external validation.

RESULTS

A multivariate Cox proportional risk model was used to identify independent risk factors for CSS. Then, new CSS columns were developed based on these factors. The consistency index (C-index) of the histogram was 0.718 (95%CI: 0.712-0.725), and that of the validation cohort was 0.722 (95%CI: 0.711-0.732), indicating good discrimination ability and better performance than tumor-node-metastasis staging (C-index: 0.712-0.732). For the training set, 0.533, 95%CI: 0.525-0.540; for the verification set, 0.524, 95%CI: 0.513-0.535. The calibration map and clinical decision curve showed good agreement and good potential clinical validity. The risk grading system divided all patients into three groups, and the Kaplan-Meier curve showed good stratification and differentiation of CSS between different groups. The median CSS times in the low-risk, medium-risk, and high-risk groups were 36 months (95%CI: 34.987-37.013), 18 months (95%CI: 17.273-18.727), and 5 months (95%CI: 4.503-5.497), respectively.

CONCLUSION

Our study developed a new nomogram model to predict CSS in patients with synchronous mCRC. In addition, the risk-grading system helps to accurately assess patient prognosis and guide treatment.

Machine Learning and Radiomics Analysis for Tumor Budding Prediction in Colorectal Liver Metastases Magnetic Resonance Imaging Assessment

PURPOSE

We aimed to assess the efficacy of machine learning and radiomics analysis using magnetic resonance imaging (MRI) with a hepatospecific contrast agent, in a pre-surgical setting, to predict tumor budding in liver metastases.

METHODS

Patients with MRI in a pre-surgical setting were retrospectively enrolled. Manual segmentation was made by means 3D Slicer image computing, and 851 radiomics features were extracted as median values using the PyRadiomics Python package. Balancing was performed and inter- and intraclass correlation coefficients were calculated to assess the between observer and within observer reproducibility of all radiomics extracted features. A Wilcoxon-Mann-Whitney nonparametric test and receiver operating characteristics (ROC) analysis were carried out. Balancing and feature selection procedures were performed. Linear and non-logistic regression models (LRM and NLRM) and different machine learning-based classifiers including decision tree (DT), k-nearest neighbor (KNN) and support vector machine (SVM) were considered.

RESULTS

The internal training set included 49 patients and 119 liver metastases. The validation cohort consisted of a total of 28 single lesion patients. The best single predictor to classify tumor budding was original_glcm_Idn obtained in the T1-W VIBE sequence arterial phase with an accuracy of 84%; wavelet_LLH_firstorder_10Percentile was obtained in the T1-W VIBE sequence portal phase with an accuracy of 92%; wavelet_HHL_glcm_MaximumProbability was obtained in the T1-W VIBE sequence hepatobiliary excretion phase with an accuracy of 88%; and wavelet_LLH_glcm_Imc1 was obtained in T2-W SPACE sequences with an accuracy of 88%. Considering the linear regression analysis, a statistically significant increase in accuracy to 96% was obtained using a linear weighted combination of 13 radiomic features extracted from the T1-W VIBE sequence arterial phase. Moreover, the best classifier was a KNN trained with the 13 radiomic features extracted from the arterial phase of the T1-W VIBE sequence, obtaining an accuracy of 95% and an AUC of 0.96. The validation set reached an accuracy of 94%, a sensitivity of 86% and a specificity of 95%.

CONCLUSIONS

Machine learning and radiomics analysis are promising tools in predicting tumor budding. Considering the linear regression analysis, there was a statistically significant increase in accuracy to 96% using a weighted linear combination of 13 radiomics features extracted from the arterial phase compared to a single radiomics feature.