Radiogenomics of lower-grade gliomas: machine learning-based MRI texture analysis for predicting 1p/19q codeletion status.

OBJECTIVE: To evaluate the potential value of the machine learning (ML)-based MRI texture analysis for predicting 1p/19q codeletion status of lower-grade gliomas (LGG), using various state-of-the-art ML algorithms. MATERIALS AND METHODS: For this retrospective study, 107 patients with LGG were included from a public database. Texture features were extracted from conventional T2-weighted and contrast-enhanced T1-weighted MRI images, using LIFEx software. Training and unseen validation splits were created using stratified 10-fold cross-validation technique along with minority over-sampling. Dimension reduction was done using collinearity analysis and feature selection (ReliefF). Classifications were done using adaptive boosting, k-nearest neighbours, naive Bayes, neural network, random forest, stochastic gradient descent, and support vector machine. Friedman test and pairwise post hoc analyses were used for comparison of classification performances based on the area under the curve (AUC). RESULTS: Overall, the predictive performance of the ML algorithms were statistically significantly different, χ2(6) = 26.7, p < 0.001. There was no statistically significant difference among the performance of the neural network, naive Bayes, support vector machine, random forest, and stochastic gradient descent, adjusted p > 0.05. The mean AUC and accuracy values of these five algorithms ranged from 0.769 to 0.869 and from 80.1 to 84%, respectively. The neural network had the highest mean rank with mean AUC and accuracy values of 0.869 and 83.8%, respectively. CONCLUSIONS: The ML-based MRI texture analysis might be a promising non-invasive technique for predicting the 1p/19q codeletion status of LGGs. Using this technique along with various ML algorithms, more than four-fifths of the LGGs can be correctly classified. KEY POINTS: • More than four-fifths of the lower-grade gliomas can be correctly classified with machine learning-based MRI texture analysis. Satisfying classification outcomes are not limited to a single algorithm. • A few-slice-based volumetric segmentation technique would be a valid approach, providing satisfactory predictive textural information and avoiding excessive segmentation duration in clinical practice. • Feature selection is sensitive to different patient data set samples so that each sampling leads to the selection of different feature subsets, which needs to be considered in future works.

Artificial Intelligence in Renal Mass Characterization: A Systematic Review of Methodologic Items Related to Modeling, Performance Evaluation, Clinical Utility, and Transparency.

OBJECTIVE. The objective of our study was to systematically review the literature about the application of artificial intelligence (AI) to renal mass characterization with a focus on the methodologic quality items. MATERIALS AND METHODS. A systematic literature search was conducted using PubMed to identify original research studies about the application of AI to renal mass characterization. Besides baseline study characteristics, a total of 15 methodologic quality items were extracted and evaluated on the basis of the following four main categories: modeling, performance evaluation, clinical utility, and transparency items. The qualitative synthesis was presented using descriptive statistics with an accompanying narrative. RESULTS. Thirty studies were included in this systematic review. Overall, the methodologic quality items were mostly favorable for modeling (63%) and performance evaluation (63%). Even so, the studies (57%) more frequently constructed their work on nonrobust features. Furthermore, only a few studies (10%) had a generalizability assessment with independent or external validation. The studies were mostly unsuccessful in terms of clinical utility evaluation (89%) and transparency (97%) items. For clinical utility, the interesting findings were lack of comparisons with both radiologists' evaluation (87%) and traditional models (70%) in most of the studies. For transparency, most studies (97%) did not share their data with the public. CONCLUSION. To bring AI-based renal mass characterization from research to practice, future studies need to improve modeling and performance evaluation strategies and pay attention to clinical utility and transparency issues.

Radiomics of Renal Masses: Systematic Review of Reproducibility and Validation Strategies.

OBJECTIVE. The purpose of this study was to systematically review the radiomics literature on renal mass characterization in terms of reproducibility and validation strategies. MATERIALS AND METHODS. With use of PubMed and Google Scholar, a systematic literature search was performed to identify original research papers assessing the value of radiomics in characterization of renal masses. The data items were extracted on the basis of three main categories: baseline study characteristics, radiomic feature reproducibility strategies, and statistical model validation strategies. RESULTS. After screening and application of the eligibility criteria, a total of 41 papers were included in the study. Almost one-half of the papers (19 [46%]) presented at least one reproducibility analysis. Segmentation variability (18 [44%]) was the main theme of the analyses, outnumbering image acquisition or processing (3 [7%]). No single paper considered slice selection bias. The most commonly used statistical tool for analysis was intraclass correlation coefficient (14 of 19 [74%]), with no consensus on the threshold or cutoff values. Approximately one-half of the papers (22 [54%]) used at least one validation method, with a predominance of internal validation techniques (20 [49%]). The most frequently used internal validation technique was k-fold cross-validation (12 [29%]). Independent or external validation was used in only three papers (7%). CONCLUSION. Workflow characteristics described in the radiomics literature about renal mass characterization are heterogeneous. To bring radiomics from a mere research area to clinical use, the field needs many more papers that consider the reproducibility of radiomic features and include independent or external validation in their workflow.

Machine learning-based unenhanced CT texture analysis for predicting BAP1 mutation status of clear cell renal cell carcinomas.

BACKGROUND: BRCA1-associated protein 1 (BAP1) mutation is an unfavorable factor for overall survival in patients with clear cell renal cell carcinoma (ccRCC). Radiomics literature about BAP1 mutation lacks papers that consider the reliability of texture features in their workflow. PURPOSE: Using texture features with a high inter-observer agreement, we aimed to develop and internally validate a machine learning-based radiomic model for predicting the BAP1 mutation status of ccRCCs. MATERIAL AND METHODS: For this retrospective study, 65 ccRCCs were included from a public database. Texture features were extracted from unenhanced computed tomography (CT) images, using two-dimensional manual segmentation. Dimension reduction was done in three steps: (i) inter-observer agreement analysis; (ii) collinearity analysis; and (iii) feature selection. The machine learning classifier was random forest. The model was validated using 10-fold nested cross-validation. The reference standard was the BAP1 mutation status. RESULTS: Out of 744 features, 468 had an excellent inter-observer agreement. After the collinearity analysis, the number of features decreased to 17. Finally, the wrapper-based algorithm selected six features. Using selected features, the random forest correctly classified 84.6% of the labelled slices regarding BAP1 mutation status with an area under the receiver operating characteristic curve of 0.897. For predicting ccRCCs with BAP1 mutation, the sensitivity, specificity, and precision were 90.4%, 78.8%, and 81%, respectively. For predicting ccRCCs without BAP1 mutation, the sensitivity, specificity, and precision were 78.8%, 90.4%, and 89.1%, respectively. CONCLUSION: Machine learning-based unenhanced CT texture analysis might be a potential method for predicting the BAP1 mutation status of ccRCCs.

Unenhanced CT Texture Analysis of Clear Cell Renal Cell Carcinomas: A Machine Learning-Based Study for Predicting Histopathologic Nuclear Grade.

OBJECTIVE. The purpose of this study is to investigate the predictive performance of machine learning (ML)-based unenhanced CT texture analysis in distinguishing low (grades I and II) and high (grades III and IV) nuclear grade clear cell renal cell carcinomas (RCCs). MATERIALS AND METHODS. For this retrospective study, 81 patients with clear cell RCC (56 high and 25 low nuclear grade) were included from a public database. Using 2D manual segmentation, 744 texture features were extracted from unenhanced CT images. Dimension reduction was done in three consecutive steps: reproducibility analysis by two radiologists, collinearity analysis, and feature selection. Models were created using artificial neural network (ANN) and binary logistic regression, with and without synthetic minority oversampling technique (SMOTE), and were validated using 10-fold cross-validation. The reference standard was histopathologic nuclear grade (low vs high). RESULTS. Dimension reduction steps yielded five texture features for the ANN and six for the logistic regression algorithm. None of clinical variables was selected. ANN alone and ANN with SMOTE correctly classified 81.5% and 70.5%, respectively, of clear cell RCCs, with AUC values of 0.714 and 0.702, respectively. The logistic regression algorithm alone and with SMOTE correctly classified 75.3% and 62.5%, respectively, of the tumors, with AUC values of 0.656 and 0.666, respectively. The ANN performed better than the logistic regression (p < 0.05). No statistically significant difference was present between the model performances created with and without SMOTE (p > 0.05). CONCLUSION. ML-based unenhanced CT texture analysis using ANN can be a promising noninvasive method in predicting the nuclear grade of clear cell RCCs.

Reliability of Single-Slice-Based 2D CT Texture Analysis of Renal Masses: Influence of Intra- and Interobserver Manual Segmentation Variability on Radiomic Feature Reproducibility.

OBJECTIVE. The objective of our study was to investigate the potential influence of intra- and interobserver manual segmentation variability on the reliability of single-slice-based 2D CT texture analysis of renal masses. MATERIALS AND METHODS. For this retrospective study, 30 patients with clear cell renal cell carcinoma were included from a public database. For intra- and interobserver analyses, three radiologists with varying degrees of experience segmented the tumors from unenhanced CT and corticomedullary phase contrast-enhanced CT (CECT) in different sessions. Each radiologist was blind to the image slices selected by other radiologists and him- or herself in the previous session. A total of 744 texture features were extracted from original, filtered, and transformed images. The intraclass correlation coefficient was used for reliability analysis. RESULTS. In the intraobserver analysis, the rates of features with good to excellent reliability were 84.4-92.2% for unenhanced CT and 85.5-93.1% for CECT. Considering the mean rates of unenhanced CT and CECT, having high experience resulted in better reliability rates in terms of the intraobserver analysis. In the interobserver analysis, the rates were 76.7% for unenhanced CT and 84.9% for CECT. The gray-level cooccurrence matrix and first-order feature groups yielded higher good to excellent reliability rates on both unenhanced CT and CECT. Filtered and transformed images resulted in more features with good to excellent reliability than the original images did on both unenhanced CT and CECT. CONCLUSION. Single-slice-based 2D CT texture analysis of renal masses is sensitive to intra- and interobserver manual segmentation variability. Therefore, it may lead to nonreproducible results in radiomic analysis unless a reliability analysis is considered in the workflow.