Two-Year Event-Free Survival Prediction in DLBCL Patients Based on In Vivo Radiomics and Clinical Parameters

Clinical application of 18F-fluorodeoxyglucose positron emission tomography/computed tomography radiomics-based machine learning analyses in the field of oncology

Machine learning (ML) analyses using 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomics features have been applied in the field of oncology. The current review aimed to summarize the current clinical articles about 18F-FDG PET/CT radiomics-based ML analyses to solve issues in classifying or constructing prediction models for several types of tumors. In these studies, lung and mediastinal tumors were the most commonly evaluated lesions, followed by lymphatic, abdominal, head and neck, breast, gynecological, and other types of tumors. Previous studies have commonly shown that 18F-FDG PET radiomics-based ML analysis has good performance in differentiating benign from malignant tumors, predicting tumor characteristics and stage, therapeutic response, and prognosis by examining significant differences in the area under the receiver operating characteristic curves, accuracies, or concordance indices (> 0.70). However, these studies have reported several ML algorithms. Moreover, different ML models have been applied for the same purpose. Thus, various procedures were used in 18F-FDG PET/CT radiomics-based ML analysis in oncology, and 18F-FDG PET/CT radiomics-based ML models, which are easy and universally applied in clinical practice, would be expected to be established.

Stacking Ensemble Learning-Based [18F]FDG PET Radiomics for Outcome Prediction in Diffuse Large B-Cell Lymphoma

This study aimed to develop an analytic approach based on [18F]FDG PET radiomics using stacking ensemble learning to improve the outcome prediction in diffuse large B-cell lymphoma (DLBCL). Methods: In total, 240 DLBCL patients from 2 medical centers were divided into the training set (n = 141), internal testing set (n = 61), and external testing set (n = 38). Radiomics features were extracted from pretreatment [18F]FDG PET scans at the patient level using 4 semiautomatic segmentation methods (SUV threshold of 2.5, SUV threshold of 4.0 [SUV4.0], 41% of SUVmax, and SUV threshold of mean liver uptake [PERCIST]). All extracted features were harmonized with the ComBat method. The intraclass correlation coefficient was used to evaluate the reliability of radiomics features extracted by different segmentation methods. Features from the most reliable segmentation method were selected by Pearson correlation coefficient analysis and the LASSO (least absolute shrinkage and selection operator) algorithm. A stacking ensemble learning approach was applied to build radiomics-only and combined clinical-radiomics models for prediction of 2-y progression-free survival and overall survival based on 4 machine learning classifiers (support vector machine, random forests, gradient boosting decision tree, and adaptive boosting). Confusion matrix, receiver-operating-characteristic curve analysis, and survival analysis were used to evaluate the model performance. Results: Among 4 semiautomatic segmentation methods, SUV4.0 segmentation yielded the highest interobserver reliability, with 830 (66.7%) selected radiomics features. The combined model constructed by the stacking method achieved the best discrimination performance. For progression-free survival prediction in the external testing set, the areas under the receiver-operating-characteristic curve and accuracy of the stacking-based combined model were 0.771 and 0.789, respectively. For overall survival prediction, the stacking-based combined model achieved an area under the curve of 0.725 and an accuracy of 0.763 in the external testing set. The combined model also demonstrated a more distinct risk stratification than the International Prognostic Index in all sets (log-rank test, all P < 0.05). Conclusion: The combined model that incorporates [18F]FDG PET radiomics and clinical characteristics based on stacking ensemble learning could enable improved risk stratification in DLBCL.

Clinicopathological analysis of diffuse large B-cell lymphoma using molecular biomarkers: a retrospective analysis from 7 Hungarian centers

Background

The clinical and genetic heterogeneity of diffuse large B-cell lymphoma (DLBCL) presents distinct challenges in predicting response to therapy and overall prognosis. The main objective of this study was to assess the application of the immunohistochemistry- and interphase fluorescence in situ hybridization (FISH)-based molecular markers in the diagnosis of DLBCL and its prognostic value in patients treated with rituximab-based immunochemotherapy.

Methods

This is a multicenter, retrospective study, which analyzed data from 7 Hungarian hematology centers. Eligible patients were adults, had a histologically confirmed diagnosis of DLBCL, were treated with rituximab-based immunochemotherapy in the first line, and had available clinicopathological data including International Prognostic Index (IPI). On the specimens, immunohistochemistry and FISH methods were performed. Germinal center B-cell like (GCB) and non-GCB subtypes were classified by the Hans algorithm. Outcomes included overall survival (OS), event-free survival (EFS), and EFS at 2 years (EFS24). For survival analysis, we used Kaplan-Meier curves with the log-rank test and multivariate Cox regression.

Results

A total of 247 DLBCL cases were included. Cases were positive for MYC, BCL2, BCL6, and MUM1 expression in 52.1%, 66.2%, 72.6%, and 77.8%, respectively. BCL6 translocation, BCL2 gene copy number (GCN) gain, IGH::MYC translocation, MYC GCN gain, IGH::BCL2 translocation, and BCL6 GCN gain were detected in 21.4%, 14.1%, 7.3%, 1.8%, 7.3%, and 0.9%, respectively. At a median follow-up of 52 months, 140 patients (56.7%) had disease progression or relapse. The Kaplan-Meier estimate for EFS24 was 56.2% (CI: 50.4-62.8%). In univariate analysis, only IPI and BCL6 expression were significant predictors of both OS and EFS, whereas MUM1 predicted EFS only. In multivariate analysis, the IPI score was a significant independent negative, whereas MIB-1 and BCL6 protein expressions were significant independent positive predictors of both OS and EFS.

Conclusion

In our study, we found that only IPI, BCL6 protein expression and MIB-1 protein expression are independent predictors of survival outcomes in DLBCL. We did not find any difference in survival by GCB vs. non-GCB subtypes. These findings may improve prognostication in DLBCL and can contribute to designing further research in the area.

Role of Artificial Intelligence in PET/CT Imaging for Management of Lymphoma

Our review shows that AI-based analysis of lymphoma whole-body FDG-PET/CT can inform all phases of clinical management including staging, prognostication, treatment planning, and treatment response evaluation. We highlight advancements in the role of neural networks for performing automated image segmentation to calculate PET-based imaging biomarkers such as the total metabolic tumor volume (TMTV). AI-based image segmentation methods are at levels where they can be semi-automatically implemented with minimal human inputs and nearing the level of a second-opinion radiologist. Advances in automated segmentation methods are particularly apparent in the discrimination of lymphomatous vs non-lymphomatous FDG-avid regions, which carries through to automated staging. Automated TMTV calculators, in addition to automated calculation of measures such as Dmax are informing robust models of progression-free survival which can then feed into improved treatment planning.

Automated data preparation for in vivo tumor characterization with machine learning

Background

This study proposes machine learning-driven data preparation (MLDP) for optimal data preparation (DP) prior to building prediction models for cancer cohorts.

Methods

A collection of well-established DP methods were incorporated for building the DP pipelines for various clinical cohorts prior to machine learning. Evolutionary algorithm principles combined with hyperparameter optimization were employed to iteratively select the best fitting subset of data preparation algorithms for the given dataset. The proposed method was validated for glioma and prostate single center cohorts by 100-fold Monte Carlo (MC) cross-validation scheme with 80-20% training-validation split ratio. In addition, a dual-center diffuse large B-cell lymphoma (DLBCL) cohort was utilized with Center 1 as training and Center 2 as independent validation datasets to predict cohort-specific clinical endpoints. Five machine learning (ML) classifiers were employed for building prediction models across all analyzed cohorts. Predictive performance was estimated by confusion matrix analytics over the validation sets of each cohort. The performance of each model with and without MLDP, as well as with manually-defined DP were compared in each of the four cohorts.

Results

Sixteen of twenty established predictive models demonstrated area under the receiver operator characteristics curve (AUC) performance increase utilizing the MLDP. The MLDP resulted in the highest performance increase for random forest (RF) (+0.16 AUC) and support vector machine (SVM) (+0.13 AUC) model schemes for predicting 36-months survival in the glioma cohort. Single center cohorts resulted in complex (6-7 DP steps) DP pipelines, with a high occurrence of outlier detection, feature selection and synthetic majority oversampling technique (SMOTE). In contrast, the optimal DP pipeline for the dual-center DLBCL cohort only included outlier detection and SMOTE DP steps.

Conclusions

This study demonstrates that data preparation prior to ML prediction model building in cancer cohorts shall be ML-driven itself, yielding optimal prediction models in both single and multi-centric settings.