A combined postoperative nomogram for survival prediction in clear cell renal carcinoma

Prediction study of surrounding tissue invasion in clear cell renal cell carcinoma based on multi-phase enhanced CT radiomics

OBJECTIVE

To examine the effectiveness of a nomogram model that combines clinical-image features and CT radiomics in predicting surrounding tissue invasion (STI) in clear cell renal cell carcinoma (ccRCC) patients before surgery.

METHODS

Postoperative pathological data of 248 ccRCC patients from two centers were retrospectively collected. Univariate and multivariate regression analyses were used to identify clinical and image features of ccRCC patients to construct a clinical model. Radiomics features were extracted from three CT scans, including tumoral, intratumor, and peritumoral regions. A nomogram was developed by integrating clinical model with optimal radiomics signature. The Shapley Additive Explanations (SHAP) method was used for interpretation.

RESULTS

This study included 65 ccRCC patients with STI and 183 patients without STI. The AUC of the clinical model was 0.766, 0.765, and 0.698 in the training cohort, internal validation cohort, and external validation cohort, respectively. The AUCs were higher in the radiomics signature based on ROI4 in NP than other radiomics (training cohort: 0.837 vs. 0.775-0.847; internal validation cohort: 0.831 vs. 0.695-0.811; external validation cohort: 0.762 vs. 0.623-0.731). Integrating the optimal radiomics signature with the clinical model to construct a combined model resulted in an AUC of 0.890, 0.886, and 0.826 in the training cohort, internal validation cohort, external validation cohort, respectively. SHAP values analysis revealed the top three radiomics features to be Small Dependence Low Gray Level Emphasis, Maximum 3D Diameter, and Maximum Probability.

CONCLUSION

A nomogram based on preoperative CT and clinical image features is a reliable tool for predicting STI in ccRCC patients. The use of SHAP values can help popularize this tool.

Development of a CT radiomics prognostic model for post renal tumor resection overall survival based on transformer enhanced K-means clustering

BACKGROUND

Kidney tumors, common in the urinary system, have widely varying survival rates post-surgery. Current prognostic methods rely on invasive biopsies, highlighting the need for non-invasive, accurate prediction models to assist in clinical decision-making.

PURPOSE

This study aimed to construct a K-means clustering algorithm enhanced by Transformer-based feature transformation to predict the overall survival rate of patients after kidney tumor resection and provide an interpretability analysis of the model to assist in clinical decision-making.

METHODS

This study was based on a publicly available C4KC-KiTS-2019 dataset from the TCIA database, including preoperative computed tomography (CT) images and survival time data of 210 patients. Initially, the radiomics features of the kidney tumor area were extracted using the 3D slicer software. Feature selection was then conducted using ICC, mRMR algorithms, and LASSO regression to calculate radiomics scores. Subsequently, the selected features were input into a pre-trained Transformer model for feature transformation to obtain a higher-dimensional feature set. Then, K-means clustering was performed using this feature set, and the model was evaluated using receiver operating characteristic (ROC) and Kaplan-Meier curves. Finally, the SHAP interpretability algorithm was used for the feature importance analysis of the K-means clustering results.

RESULTS

Eleven important features were selected from 851 radiomics features. The K-means clustering model after Transformer feature transformation showed AUCs of 0.889, 0.841, and 0.926 for predicting 1-, 3-, and 5-year overall survival rates, respectively, thereby outperforming both the K-means model with original feature inputs and the radiomics score method. A clustering analysis revealed survival prognosis differences among different patient groups, and a SHAP analysis provided insights into the features that had the most significant impacts on the model predictions.

CONCLUSIONS

The K-means clustering algorithm enhanced by the Transformer feature transformation proposed in this study demonstrates promising accuracy and interpretability in predicting the overall survival rate after kidney tumor resection. This method provides a valuable tool for clinical decision-making and contributes to improved management and treatment strategies for patients with kidney tumors.

Impact of Treatment Strategies on Survival and Within Multivariate Predictive Model for Renal Cell Carcinoma Based on the SEER Database: A Retrospective Cohort Study

BACKGROUND

This project aims to shed light on how various treatment approaches affect RCC patients' chances of survival and create a prediction model for them.

METHODS

Data from the Surveillance, Epidemiology, and End Results database were used in this investigation. OS and RCSS after radiation, chemotherapy, and surgery were investigated using the Kaplan-Meier approach. Fourteen factors, including gender, age, race, and others, were subjected to univariate and multivariate COX analyses. Predicting RCSS at three, five, or ten years is the main goal. Predicting OS at three, five, or ten years is the secondary endpoint. Cox analyses, both univariate and multivariate, were used to identify prognostic factors. Furthermore, a nomogram was developed to precisely forecast patient survival rates at 3-, 5-, and 10-year intervals. DCA, calibration curves, and ROC were used to assess the nomogram's efficacy.

RESULTS

Kaplan-Meier analysis revealed that PN was associated with better survival compared to RN for tumors ≤10 cm. Cox analysis identified 10 independent prognostic factors. These variables included gender, age, race, histological type, histological grade, AJCC stage, N stage, T stage, M stage, and surgical type. Based on these variables, a nomogram for OS and RCSS prediction was created.

CONCLUSION

PN is advised over RN for RCC patients whose tumors are less than 10 cm in diameter since it offers more advantages. The combined nomogram model, which is based on clinicopathological characteristics, therapy data, and demographic variables, may be used to predict the survival of RCC patients and perform prognostic and survival analysis with accuracy.

The Current Application and Future Potential of Artificial Intelligence in Renal Cancer

Artificial intelligence (AI) is the integration of human tasks into machine processes. The role of AI in kidney cancer evaluation, management, and outcome predictions are constantly evolving. We performed a narrative review utilizing PubMed electronic database to query AI as a method of analysis in kidney cancer research. Key search-words included: Artificial Intelligence, Supervised/Unsupervised Machine Learning, Deep Learning, Natural Language Processing, Neural Networks, radiomics, pathomics, and kidney or renal neoplasms or cancer. 72 clinically relevant and impactful studies related to imaging, histopathology, and outcomes were recognized. We anticipate the incorporation of AI tools into future clinical decision-making for kidney cancer.

Clinical application of radiomics for the prediction of treatment outcome and survival in patients with renal cell carcinoma: a systematic review

PURPOSE

The management of renal cell carcinoma (RCC) relies on clinical and histopathological features for treatment decisions. Recently, radiomics, which involves the extraction and analysis of quantitative imaging features, has shown promise in improving RCC management. This review evaluates the current application and limitations of radiomics for predicting treatment and oncological outcomes in RCC.

METHODS

A systematic search was conducted in Medline, EMBASE, and Web of Science databases or studies that used radiomics to predict response to treatment and survival outcomes in patients with RCC. The study quality was assessed using the Radiomics Quality Score (RQS) tools.

RESULTS

The systematic review identified a total of 27 studies, examining 6,119 patients. The most used imaging modality was contrast-enhanced abdominal CT. The reviewed studies extracted between 19 and 3376 radiomics features, including Histogram, Texture, Filter, or transformation method. Radiomics-based risk stratification models provided valuable insights into treatment response and oncological outcomes. All developed signatures demonstrated at least modest accuracy (AUC range: 0.55-0.99). The studies included in this analysis reported heterogeneous results regarding radiomics methods. The range of Radiomics Quality Score (RQS) was from - 5 to 20, with a mean RQS total of 9.15 ± 7.95.

CONCLUSION

Radiomics has emerged as a promising tool in the management of RCC. It offers the potential for improved risk stratification and response assessment. However, future trials must demonstrate the generalizability of findings to prospective cohorts before progressing towards clinical translation.

Predicting Survival of Metastatic Clear Cell Renal Cell Cancer Treated with VEGFR-TKI-Based Sequential Therapy

(1) Objective: To develop a clinically useful nomogram that may provide a more individualized and accurate estimation of cancer-specific survival (CSS) for patients with clear-cell (CC) metastatic renal cell carcinoma (mRCC) treated with nephrectomy and vascular endothelial growth factor receptor-tyrosine kinase inhibitor (VEGFR-TKI)-based sequential therapy. (2) Methods: A prospectively maintained database of 145 patients with mRCC treated between 2008 and 2018 was analyzed to predict the CSS of patients receiving sunitinib and second- and third-line therapies according to current standards of practice. A nomogram based on four independent clinical predictors (Eastern Cooperative Oncology Group status, International Metastatic RCC Database Consortium score, the Morphology, Attenuation, Size and Structure criteria and Response Evaluation Criteria in Solid Tumors response criteria) was calculated. The corresponding 1- to 10-year CSS probabilities were then determined from the nomogram. (3) Results: The median age was 60 years (95% CI 57.9-61.4). The disease was metastatic at diagnosis in 59 (40.7%), and 86 (59.3%) developed metastasis during follow-up. Patients were followed for a median 48 (IQR 72; 95% CI 56-75.7) months after first-line VEGFR-TKI initiation. The concordance probability estimator value for the nomogram is 0.778 ± 0.02 (mean ± SE). (4) Conclusions: A nomogram to predict CSS in patients with CC mRCC that incorporates patient status, clinical risk classification and response criteria to first-line VEGFR-TKI at 3 months is presented. This new tool may be useful to clinicians assessing the risk and prognosis of patients with mRCC.

Development and validation of a nomogram for predicting the impact of tumor size on cancer-specific survival of locally advanced renal cell carcinoma: a SEER-based study

This study was aimed to integrate tumor size with other prognostic factors into a prognostic nomogram to predict cancer-specific survival (CSS) in locally advanced (≥pT3a Nany M0) renal cell carcinoma (RCC) patients. Based on the Surveillance, Epidemiology, and End Results (SEER) database, 10,800 patients diagnosed with locally advanced RCC were collected. They were randomly divided into a training cohort (n = 7,056) and a validation cohort (n = 3,024). X-tile program was used to identify the optimal cut-off value of tumor size and age. The cut-off of age at diagnosis was 65 years old and 75 years old. The cut-off of tumor size was 54 mm and 119 mm. Univariate and multivariate Cox regression analyses were performed in the training cohort to identify independent prognostic factors for construction of nomogram. Then, the nomogram was used to predict the 1-, 3- and 5-year CSS. The performance of nomogram was evaluated by using concordance index (C-index), area under the Subject operating curve (AUC) and decision curve analysis (DCA). Moreover, the nomogram and tumor node metastasis (TNM) staging system (AJCC 8th edition) were compared. 10 variables were screened to develop the nomogram. The area under the receiver operating characteristic (ROC) curve (AUC) indicated satisfactory ability of the nomogram. Compared with the AJCC 8th edition of TNM stage, DCA showed that the nomogram had improved performance. We developed and validated a nomogram for predicting the CSS of patients with locally advanced RCC, which was more precise than the AJCC 8th edition of TNM staging system.

Development of a combined radiomics and CT feature-based model for differentiating malignant from benign subcentimeter solid pulmonary nodules

BACKGROUND

We aimed to develop a combined model based on radiomics and computed tomography (CT) imaging features for use in differential diagnosis of benign and malignant subcentimeter (≤ 10 mm) solid pulmonary nodules (SSPNs).

METHODS

A total of 324 patients with SSPNs were analyzed retrospectively between May 2016 and June 2022. Malignant nodules (n = 158) were confirmed by pathology, and benign nodules (n = 166) were confirmed by follow-up or pathology. SSPNs were divided into training (n = 226) and testing (n = 98) cohorts. A total of 2107 radiomics features were extracted from contrast-enhanced CT. The clinical and CT characteristics retained after univariate and multivariable logistic regression analyses were used to develop the clinical model. The combined model was established by associating radiomics features with CT imaging features using logistic regression. The performance of each model was evaluated using the area under the receiver-operating characteristic curve (AUC).

RESULTS

Six CT imaging features were independent predictors of SSPNs, and four radiomics features were selected after a dimensionality reduction. The combined model constructed by the logistic regression method had the best performance in differentiating malignant from benign SSPNs, with an AUC of 0.942 (95% confidence interval 0.918-0.966) in the training group and an AUC of 0.930 (0.902-0.957) in the testing group. The decision curve analysis showed that the combined model had clinical application value.

CONCLUSIONS

The combined model incorporating radiomics and CT imaging features had excellent discriminative ability and can potentially aid radiologists in diagnosing malignant from benign SSPNs.

RELEVANCE STATEMENT

The model combined radiomics features and clinical features achieved good efficiency in predicting malignant from benign SSPNs, having the potential to assist in early diagnosis of lung cancer and improving follow-up strategies in clinical work.

KEY POINTS

• We developed a pulmonary nodule diagnostic model including radiomics and CT features. • The model yielded the best performance in differentiating malignant from benign nodules. • The combined model had clinical application value and excellent discriminative ability. • The model can assist radiologists in diagnosing malignant from benign pulmonary nodules.

MRI-based radiomics approach for the prediction of recurrence-free survival in triple-negative breast cancer after breast-conserving surgery or mastectomy

To explore the value of a radiomics signature and develop a nomogram combined with a radiomics signature and clinical factors for predicting recurrence-free survival in triple-negative breast cancer patients. We enrolled 151 patients from the cancer imaging archive who underwent preoperative contrast-enhanced magnetic resonance imaging. They were assigned to training, validation and external validation cohorts. Image features with coefficients not equal to zero in the 10-fold cross-validation were selected to generate a radiomics signature. Based on the optimal cutoff value of the radiomics signature determined by maximally selected log-rank statistics, patients were stratified into high- and low-risk groups in the training and validation cohorts. Kaplan-Meier survival analysis was performed for both groups. Kaplan-Meier survival distributions in these groups were compared using log-rank tests. Univariate and multivariate Cox regression analyses were used to construct clinical and combined models. Concordance index was used to assess the predictive performance of the 3 models. Calibration of the combined model was assessed using calibration curves. Four image features were selected to generate the radiomics signature. The Kaplan-Meier survival distributions of patients in the 2 groups were significantly different in the training (P < .001) and validation cohorts (P = .001). The C-indices of the radiomics model, clinical model, and combined model in the training and validation cohorts were 0.772, 0.700, 0.878, and 0.744, 0.574, 0.777, respectively. The C-indices of the radiomics model, clinical model, and combined model in the external validation cohort were 0.778, 0.733, 0.822, respectively. The calibration curves of the combined model showed good calibration. The radiomics signature can predict recurrence-free survival of patients with triple-negative breast cancer and improve the predictive performance of the clinical model.

Establishment and validation of the survival prediction risk model for appendiceal cancer

OBJECTIVE

Establishing a risk model of the survival situation of appendix cancer for accurately identifying high-risk patients and developing individualized treatment plans.

METHODS

A total of 4,691 patients who were diagnosed with primary appendix cancer from 2010 to 2016 were extracted using Surveillance, Epidemiology, and End Results (SEER) * Stat software. The total sample size was divided into 3,283 cases in the modeling set and 1,408 cases in the validation set at a ratio of 7:3. A nomogram model based on independent risk factors that affect the prognosis of appendix cancer was established. Single-factor Cox risk regression, Lasso regression, and multifactor Cox risk regression were used for analyzing the risk factors that affect overall survival (OS) in appendectomy patients. A nomogram model was established based on the independent risk factors that affect appendix cancer prognosis, and the receiver operating characteristic curve (ROC) curve and calibration curve were used for evaluating the model. Survival differences between the high- and low-risk groups were analyzed through Kaplan-Meier survival analysis and the log-rank test. Single-factor Cox risk regression analysis found age, ethnicity, pathological type, pathological stage, surgery, radiotherapy, chemotherapy, number of lymph nodes removed, T stage, N stage, M stage, tumor size, and CEA all to be risk factors for appendiceal OS. At the same time, multifactor Cox risk regression analysis found age, tumor stage, surgery, lymph node removal, T stage, N stage, M stage, and CEA to be independent risk factors for appendiceal OS. A nomogram model was established for the multifactor statistically significant indicators. Further stratified with corresponding probability values based on multifactorial Cox risk regression, Kaplan-Meier survival analysis found the low-risk group of the modeling and validation sets to have a significantly better prognosis than the high-risk group (p < 0.001).

CONCLUSION

The established appendix cancer survival model can be used for the prediction of 1-, 3-, and 5-year OS and for the development of personalized treatment options through the identification of high-risk patients.