Leveraging RSF and PET images for prognosis of multiple myeloma at diagnosis

Radiomics and Artificial Intelligence Landscape for [18F]FDG PET/CT in Multiple Myeloma

[18F]FDG PET/CT is a powerful imaging modality of high performance in multiple myeloma (MM) and is considered the appropriate method for assessing treatment response in this disease. On the other hand, due to the heterogeneous and sometimes complex patterns of bone marrow infiltration in MM, the interpretation of PET/CT can be particularly challenging, hampering interobserver reproducibility and limiting the diagnostic and prognostic ability of the modality. Although many approaches have been developed to address the issue of standardization, none can yet be considered a standard method for interpretation or objective quantification of PET/CT. Therefore, advanced diagnostic quantification approaches are needed to support and potentially guide the management of MM. In recent years, radiomics has emerged as an innovative method for high-throughput mining of image-derived features for clinical decision making, which may be particularly helpful in oncology. In addition, machine learning and deep learning, both subfields of artificial intelligence (AI) closely related to the radiomics process, have been increasingly applied to automated image analysis, offering new possibilities for a standardized evaluation of imaging modalities such as CT, PET/CT and MRI in oncology. In line with this, the initial but steadily growing literature on the application of radiomics and AI-based methods in the field of [18F]FDG PET/CT in MM has already yielded encouraging results, offering a potentially reliable tool towards optimization and standardization of interpretation in this disease. The main results of these studies are presented in this review.

A systematic epidemiological trends analysis study in global burden of multiple myeloma and 29 years forecast

Multiple myeloma is a prevalent hematologic cancer. This investigation analyzes the latest global, regional, and national data from the Global Burden of Diseases, Injuries, and Risk Factors Study 2021. Data on the incidence, prevalence, disability-adjusted life years, and mortality rates of multiple myeloma, including estimates and 95% uncertainty intervals, were sourced from the 2021 Global Burden of Diseases Study. Furthermore, we explored the trends affecting the multiple myeloma burden from 1990 to 2021, breaking it down by demographic, age, and epidemiological factors. By 2021, the global incidence of multiple myeloma involved 148,754.63 reported cases, with confidence intervals ranging from 131,780.43 to 162,049.23. Worldwide, the number of mortality attributed to multiple myeloma reached 116,359.63, with the confidence interval lying between 103,078.62 and 128,470.57, and an age-standardized mortality rate of 1.37 per 100,000 individuals, the confidence interval for which was 1.22 to 1.52. There was a consistent increase in the incidence, prevalence, and disability-adjusted life years associated with multiple myeloma. Most of the disease burdens were seen in high income countries though its incidence is on the rise in low-income countries. Forecast for the years 2022-2050 showed the further increase in the incidence, prevalence, disability-adjusted life years, and age-standardized death rates of multiple myeloma.

EANM guidelines on the use of [18F]FDG PET/CT in diagnosis, staging, prognostication, therapy assessment, and restaging of plasma cell disorders

We provide updated guidance and standards for the indication, acquisition, and interpretation of [18F]FDG PET/CT for plasma cell disorders. Procedures and characteristics are reported and different scenarios for the clinical use of [18F]FDG PET/CT are discussed. This document provides clinicians and technicians with the best available evidence to support the implementation of [18F]FDG PET/CT imaging in routine practice and future research.

Coefficient of variation and texture analysis of 18F-FDG PET/CT images for the prediction of outcome in patients with multiple myeloma

In multiple myeloma (MM) bone marrow infiltration by monoclonal plasma cells can occur in both focal and diffuse manner, making staging and prognosis rather difficult. The aim of our study was to test whether texture analysis of 18 F-2-deoxy-d-glucose positron emission tomography/computed tomography (18F-FDG PET/CT) images can predict survival in MM patients. Forty-six patients underwent 18 F-FDG-PET/CT before treatment. We used an automated contouring program for segmenting the hottest focal lesion (FL) and a lumbar vertebra for assessing diffuse bone marrow involvement (DI). Maximum standardized uptake value (SUVmax), mean standardized uptake value (SUVmean) and texture features such as Coefficient of variation (CoV), were obtained from 46 FL and 46 DI. After a mean follow-up of 51 months, 24 patients died of myeloma and were compared to the 22 survivors. At univariate analysis, FL SUVmax (p = 0.0453), FL SUVmean (p = 0.0463), FL CoV (p = 0.0211) and DI SUVmax (p = 0.0538) predicted overall survival (OS). At multivariate analysis only FL CoV and DI SUVmax were retained in the model (p = 0.0154). By Kaplan-Meier method and log-rank testing, patients with FL CoV below the cut-off had significantly better OS than those with FL CoV above the cut-off (p = 0.0003), as well as patients with DI SUVmax below the threshold versus those with DI SUVmax above the threshold (p = 0.0006). Combining FL CoV and DI SUVmax by using their respective cut-off values, a statistically significant difference was found between the resulting four survival curves (p = 0.0001). Indeed, patients with both FL CoV and DI SUVmax below their respective cut-off values showed the best prognosis. Conventional and texture parameters derived from 18F-FDG PET/CT analysis can predict survival in MM patients by assessing the heterogeneity and aggressiveness of both focal and diffuse infiltration.

Recent advances in imaging and artificial intelligence (AI) for quantitative assessment of multiple myeloma

Multiple myeloma (MM) is a malignant blood disease, but there have been significant improvements in the prognosis due to advancements in quantitative assessment and targeted therapy in recent years. The quantitative assessment of MM bone marrow infiltration and prognosis prediction is influenced by imaging and artificial intelligence (AI) quantitative parameters. At present, the primary imaging methods include computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). These methods are now crucial for diagnosing MM and evaluating myeloma cell infiltration, extramedullary disease, treatment effectiveness, and prognosis. Furthermore, the utilization of AI, specifically incorporating machine learning and radiomics, shows great potential in the field of diagnosing MM and distinguishing between MM and lytic metastases. This review discusses the advancements in imaging methods, including CT, MRI, and PET/CT, as well as AI for quantitatively assessing MM. We have summarized the key concepts, advantages, limitations, and diagnostic performance of each technology. Finally, we discussed the challenges related to clinical implementation and presented our views on advancing this field, with the aim of providing guidance for future research.

Mortality prediction and influencing factors for intensive care unit patients with acute tubular necrosis: random survival forest and cox regression analysis

Background: Patients with acute tubular necrosis (ATN) not only have severe renal failure, but also have many comorbidities, which can be life-threatening and require timely treatment. Identifying the influencing factors of ATN and taking appropriate interventions can effectively shorten the duration of the disease to reduce mortality and improve patient prognosis. Methods: Mortality prediction models were constructed by using the random survival forest (RSF) algorithm and the Cox regression. Next, the performance of both models was assessed by the out-of-bag (OOB) error rate, the integrated brier score, the prediction error curve, and area under the curve (AUC) at 30, 60 and 90 days. Finally, the optimal prediction model was selected and the decision curve analysis and nomogram were established. Results: RSF model was constructed under the optimal combination of parameters (mtry = 10, nodesize = 88). Vasopressors, international normalized ratio (INR)_min, chloride_max, base excess_min, bicarbonate_max, anion gap_min, and metastatic solid tumor were identified as risk factors that had strong influence on mortality in ATN patients. Uni-variate and multivariate regression analyses were used to establish the Cox regression model. Nor-epinephrine, vasopressors, INR_min, severe liver disease, and metastatic solid tumor were identified as important risk factors. The discrimination and calibration ability of both predictive models were demonstrated by the OOB error rate and the integrated brier score. However, the prediction error curve of Cox regression model was consistently lower than that of RSF model, indicating that Cox regression model was more stable and reliable. Then, Cox regression model was also more accurate in predicting mortality of ATN patients based on the AUC at different time points (30, 60 and 90 days). The analysis of decision curve analysis shows that the net benefit range of Cox regression model at different time points is large, indicating that the model has good clinical effectiveness. Finally, a nomogram predicting the risk of death was created based on Cox model. Conclusion: The Cox regression model is superior to the RSF algorithm model in predicting mortality of patients with ATN. Moreover, the model has certain clinical utility, which can provide clinicians with some reference basis in the treatment of ATN and contribute to improve patient prognosis.

The Ratio of Serum Urea Nitrogen to Albumin Is a Better Predictor of Overall Survival in Multiple Myeloma Patients than Urea Nitrogen Alone

INTRODUCTION

Multiple myeloma (MM) is a malignant proliferative disease of plasma cells. Abnormally cloned plasma cells secrete large amounts of monoclonal immunoglobulins in the bone marrow of MM patients. Serum urea nitrogen (sUN) is a byproduct of protein metabolism, and its effect on MM patients' prognoses remains unknown. Therefore, we analyzed MM patients' clinical data to explore the role of sUN and sUN/serum albumin (sUAR) in the baseline tumor load and MM prognosis of MM patients.

METHODS

We downloaded the clinical data of 762 MM patients from the MMRF database. After excluding those without baseline sUN, 452 patients were finally included in the study. Smoothed curve fitting, threshold analysis, Tamhane's T2 test, multivariate-adjusted Cox regression analysis, Kaplan-Meier (K-M) curves, and receiver operating characteristic (ROC) analysis were applied in the study.

RESULTS

There were 452 newly diagnosed MM patients included in this study. In most patient groups, sUN and sUAR were positively linked with β2-microglobulin (β2-MG) and lactic dehydrogenase (LDH) according to smoothing curve fitting and threshold analysis. The higher the ISS stage, the greater the values of sUN and sUAR. Furthermore, smoothed curve fitting and threshold analysis showed that sUN was correlated with overall survival (OS), although sUAR had a stronger correlation with OS and could be applied to a broader group. The results of a multivariate-adjusted Cox regression analysis demonstrated that sUN and sUAR were independent prognostic factors for OS. The K-M curve confirmed the correlation between higher sUN and sUAR levels and worse OS. β2-MG and LDH are generally recognized prognostic factors of OS. ROC analysis revealed that sUN might boost β2-MG and LDH's predictive value and sUAR had a higher predictive value.

CONCLUSION

This retrospective study based on the MMRF database showed that high sUN and sUAR levels were positively associated with β2-MG, LDH, and ISS staging, and sUAR exhibited a stronger correlation with OS than sUN alone.

INTRODUCTION

Multiple myeloma (MM) is a malignant proliferative disease of plasma cells. Abnormally cloned plasma cells secrete large amounts of monoclonal immunoglobulins in the bone marrow of MM patients. Serum urea nitrogen (sUN) is a byproduct of protein metabolism, and its effect on MM patients' prognoses remains unknown. Therefore, we analyzed MM patients' clinical data to explore the role of sUN and sUN/serum albumin (sUAR) in the baseline tumor load and MM prognosis of MM patients.

METHODS

We downloaded the clinical data of 762 MM patients from the MMRF database. After excluding those without baseline sUN, 452 patients were finally included in the study. Smoothed curve fitting, threshold analysis, Tamhane's T2 test, multivariate-adjusted Cox regression analysis, Kaplan-Meier (K-M) curves, and receiver operating characteristic (ROC) analysis were applied in the study.

RESULTS

There were 452 newly diagnosed MM patients included in this study. In most patient groups, sUN and sUAR were positively linked with β2-microglobulin (β2-MG) and lactic dehydrogenase (LDH) according to smoothing curve fitting and threshold analysis. The higher the ISS stage, the greater the values of sUN and sUAR. Furthermore, smoothed curve fitting and threshold analysis showed that sUN was correlated with overall survival (OS), although sUAR had a stronger correlation with OS and could be applied to a broader group. The results of a multivariate-adjusted Cox regression analysis demonstrated that sUN and sUAR were independent prognostic factors for OS. The K-M curve confirmed the correlation between higher sUN and sUAR levels and worse OS. β2-MG and LDH are generally recognized prognostic factors of OS. ROC analysis revealed that sUN might boost β2-MG and LDH's predictive value and sUAR had a higher predictive value.

CONCLUSION

This retrospective study based on the MMRF database showed that high sUN and sUAR levels were positively associated with β2-MG, LDH, and ISS staging, and sUAR exhibited a stronger correlation with OS than sUN alone.

Applications of machine learning and deep learning in SPECT and PET imaging: General overview, challenges and future prospects

The integration of positron emission tomography (PET) and single-photon emission computed tomography (SPECT) imaging techniques with machine learning (ML) algorithms, including deep learning (DL) models, is a promising approach. This integration enhances the precision and efficiency of current diagnostic and treatment strategies while offering invaluable insights into disease mechanisms. In this comprehensive review, we delve into the transformative impact of ML and DL in this domain. Firstly, a brief analysis is provided of how these algorithms have evolved and which are the most widely applied in this domain. Their different potential applications in nuclear imaging are then discussed, such as optimization of image adquisition or reconstruction, biomarkers identification, multimodal fusion and the development of diagnostic, prognostic, and disease progression evaluation systems. This is because they are able to analyse complex patterns and relationships within imaging data, as well as extracting quantitative and objective measures. Furthermore, we discuss the challenges in implementation, such as data standardization and limited sample sizes, and explore the clinical opportunities and future horizons, including data augmentation and explainable AI. Together, these factors are propelling the continuous advancement of more robust, transparent, and reliable systems.

New Developments in Myeloma Treatment and Response Assessment

Recent innovative strategies have dramatically redefined the therapeutic landscape for treating multiple myeloma patients. In particular, the development and application of immunotherapy and high-dose therapy have demonstrated high response rates and have prolonged remission duration. Over the past decade, new morphologic or hybrid imaging techniques have gradually replaced conventional skeletal surveys. PET/CT using 18F-FDG is a powerful imaging tool for the workup at diagnosis and for therapeutic evaluation allowing medullary and extramedullary assessment. The independent negative prognostic value for progression-free and overall survival derived from baseline PET-derived parameters such as the presence of extramedullary disease or paramedullary disease, as well as the number of focal bone lesions and SUVmax, has been reported in several large prospective studies. During therapeutic evaluation, 18F-FDG PET/CT is considered the reference imaging technique because it can be performed much earlier than MRI, which lacks specificity. Persistence of significant abnormal 18F-FDG uptake after therapy is an independent negative prognostic factor, and 18F-FDG PET/CT and medullary flow cytometry are complementary tools for detecting minimal residual disease before maintenance therapy. The definition of a PET metabolic complete response has recently been standardized and the interpretation criteria harmonized. The development of advanced PET analysis and radiomics using machine learning, as well as hybrid imaging with PET/MRI, offers new perspectives for multiple myeloma imaging. Most recently, innovative radiopharmaceuticals such as C-X-C chemokine receptor type 4-targeted small molecules and anti-CD38 radiolabeled antibodies have shown promising results for tumor phenotype imaging and as potential theranostics.

18F‑FDG PET/CT based radiomics features improve prediction of prognosis: multiple machine learning algorithms and multimodality applications for multiple myeloma

PURPOSE

Multiple myeloma (MM), the second most hematological malignancy, have been studied extensively in the prognosis of the clinical parameters, however there are only a few studies have discussed the role of dual modalities and multiple algorithms of ¹⁸F-FDG (¹⁸F-fluorodeoxyglucose) PET/CT based radiomics signatures for prognosis in MM patients. We hope to deeply mine the utility of raiomics data in the prognosis of MM.

METHODS

We extensively explored the predictive ability and clinical decision-making ability of different combination image data of PET, CT, clinical parameters and six machine learning algorithms, Cox proportional hazards model (Cox), linear gradient boosting models based on Cox's partial likelihood (GB-Cox), Cox model by likelihood based boosting (CoxBoost), generalized boosted regression modelling (GBM), random forests for survival model (RFS) and support vector regression for censored data model (SVCR). And the model evaluation methods include Harrell concordance index, time dependent receiver operating characteristic (ROC) curve, and decision curve analysis (DCA).

RESULTS

We finally confirmed 5 PET based features, and 4 CT based features, as well as 6 clinical derived features significantly related to progression free survival (PFS) and we included them in the model construction. In various modalities combinations, RSF and GBM algorithms significantly improved the accuracy and clinical net benefit of predicting prognosis compared with other algorithms. For all combinations of various modalities based models, single-modality PET based prognostic models' performance was outperformed baseline clinical parameters based models, while the performance of models of PET and CT combined with clinical parameters was significantly improved in various algorithms.

CONCLUSION

¹⁸F‑FDG PET/CT based radiomics models implemented with machine learning algorithms can significantly improve the clinical prediction of progress and increased clinical benefits providing prospects for clinical prognostic stratification for precision treatment as well as new research areas.

Study on the prediction model of atherosclerotic cardiovascular disease in the rural Xinjiang population based on survival analysis

PURPOSE

With the increase in aging and cardiovascular risk factors, the morbidity and mortality of atherosclerotic cardiovascular disease (ASCVD), represented by ischemic heart disease and stroke, continue to rise in China. For better prevention and intervention, relevant guidelines recommend using predictive models for early detection of ASCVD high-risk groups. Therefore, this study aims to establish a population ASCVD prediction model in rural areas of Xinjiang using survival analysis.

METHODS

Baseline cohort data were collected from September to December 2016 and followed up till June 2022. A total of 7975 residents (4054 males and 3920 females) aged 30-74 years were included in the analysis. The data set was divided according to different genders, and the training and test sets ratio was 7:3 for different genders. A Cox regression, Lasso-Cox regression, and random survival forest (RSF) model were established in the training set. The model parameters were determined by cross-validation and parameter tuning and then verified in the training set. Traditional ASCVD prediction models (Framingham and China-PAR models) were constructed in the test set. Different models' discrimination and calibration degrees were compared to find the optimal prediction model for this population according to different genders and further analyze the risk factors of ASCVD.

RESULTS

After 5.79 years of follow-up, 873 ASCVD events with a cumulative incidence of 10.19% were found (7.57% in men and 14.44% in women). By comparing the discrimination and calibration degrees of each model, the RSF showed the best prediction performance in males and females (male: Area Under Curve (AUC) 0.791 (95%CI 0.767,0.813), C statistic 0.780 (95%CI 0.730,0.829), Brier Score (BS):0.060, female: AUC 0.759 (95%CI 0.734,0.783) C statistic was 0.737 (95%CI 0.702,0.771), BS:0.110). Age, systolic blood pressure (SBP), apolipoprotein B (APOB), Visceral Adiposity Index (VAI), hip circumference (HC), and plasma arteriosclerosis index (AIP) are important predictors of ASCVD in the rural population of Xinjiang.

CONCLUSION

The performance of the ASCVD prediction model based on the RSF algorithm is better than that based on Cox regression, Lasso-Cox, and the traditional ASCVD prediction model in the rural population of Xinjiang.

Radiomics analysis of bone marrow biopsy locations in [18F]FDG PET/CT images for measurable residual disease assessment in multiple myeloma

The combination of visual assessment of whole body [¹⁸F]FDG PET images and evaluation of bone marrow samples by Multiparameter Flow Cytometry (MFC) or Next-Generation Sequencing (NGS) is currently the most common clinical practice for the detection of Measurable Residual Disease (MRD) in Multiple Myeloma (MM) patients. In this study, radiomic features extracted from the bone marrow biopsy locations are analyzed and compared to those extracted from the whole bone marrow in order to study the representativeness of these biopsy locations in the image-based MRD assessment. Whole body [¹⁸F]FDG PET of 39 patients with newly diagnosed MM were included in the database, and visually evaluated by experts in nuclear medicine. A methodology for the segmentation of biopsy sites from PET images, including sternum and posterior iliac crest, and their subsequent quantification is proposed. First, starting from the bone marrow segmentation, a segmentation of the biopsy sites is performed. Then, segmentations are quantified extracting SUV metrics and radiomic features from the [¹⁸F]FDG PET images and are evaluated by Mann-Whitney U-tests as valuable features differentiating PET+/PET- and MFC+ /MFC- groups. Moreover, correlation between whole bone marrow and biopsy sites is studied by Spearman ρ rank. Classification performance of the radiomics features is evaluated applying seven machine learning algorithms. Statistical analyses reveal that some images features are significant in PET+/PET- differentiation, such as SUV_max, Gray Level Non-Uniformity or Entropy, especially with a balanced database where 16 of the features show a p value < 0.001. Correlation analyses between whole bone marrow and biopsy sites results in significant and acceptable coefficients, with 11 of the variables reaching a correlation coefficient greater than 0.7, with a maximum of 0.853. Machine learning algorithms demonstrate high performances in PET+/PET- classification reaching a maximum AUC of 0.974, but not for MFC+/MFC- classification. The results demonstrate the representativeness of sample sites as well as the effectiveness of extracted features (SUV metrics and radiomic features) from the [¹⁸F]FDG PET images in MRD assessment in MM patients.

The application of machine learning to imaging in hematological oncology: A scoping review

Background

Here, we conducted a scoping review to (i) establish which machine learning (ML) methods have been applied to hematological malignancy imaging; (ii) establish how ML is being applied to hematological cancer radiology; and (iii) identify addressable research gaps.

Methods

The review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews guidelines. The inclusion criteria were (i) pediatric and adult patients with suspected or confirmed hematological malignancy undergoing imaging (population); (ii) any study using ML techniques to derive models using radiological images to apply to the clinical management of these patients (concept); and (iii) original research articles conducted in any setting globally (context). Quality Assessment of Diagnostic Accuracy Studies 2 criteria were used to assess diagnostic and segmentation studies, while the Newcastle-Ottawa scale was used to assess the quality of observational studies.

Results

Of 53 eligible studies, 33 applied diverse ML techniques to diagnose hematological malignancies or to differentiate them from other diseases, especially discriminating gliomas from primary central nervous system lymphomas (n=18); 11 applied ML to segmentation tasks, while 9 applied ML to prognostication or predicting therapeutic responses, especially for diffuse large B-cell lymphoma. All studies reported discrimination statistics, but no study calculated calibration statistics. Every diagnostic/segmentation study had a high risk of bias due to their case-control design; many studies failed to provide adequate details of the reference standard; and only a few studies used independent validation.

Conclusion

To deliver validated ML-based models to radiologists managing hematological malignancies, future studies should (i) adhere to standardized, high-quality reporting guidelines such as the Checklist for Artificial Intelligence in Medical Imaging; (ii) validate models in independent cohorts; (ii) standardize volume segmentation methods for segmentation tasks; (iv) establish comprehensive prospective studies that include different tumor grades, comparisons with radiologists, optimal imaging modalities, sequences, and planes; (v) include side-by-side comparisons of different methods; and (vi) include low- and middle-income countries in multicentric studies to enhance generalizability and reduce inequity.

Radiomic Analysis of Positron-Emission Tomography and Computed Tomography Images to Differentiate between Multiple Myeloma and Skeletal Metastases

Context

Multiple myeloma and extensive lytic skeletal metastases may appear similar on positron-emission tomography and computed tomography (PET-CT) in the absence of an obvious primary site or occult malignancy. Radiomic analysis extracts a large number of quantitative features from medical images with the potential to uncover disease characteristics below the human visual threshold.

Aim

This study aimed to evaluate the diagnostic capability of PET and CT radiomic features to differentiate skeletal metastases from multiple myeloma.

Settings and Design

Forty patients (20 histopathologically proven cases of multiple myeloma and 20 cases of a variety of bone metastases) underwent staging 18F-fluorodeoxyglucose PET-CT at our institute.

Methodology

A total of 138 PET and 138 CT radiomic features were extracted by manual semi-automatic segmentation and standardized. The original dataset was subject separately to receiver operating curve analysis and correlation matrix filtering. The former showed 16 CT and 19 PET parameters to be significantly related to the outcome at 5%, whereas the latter resulted in 16 CT and 14 PET features. Feature selection was done with 7 evaluators with stratified 10-fold cross-validation. The selected features of each evaluator were subject to 14 machine-learning algorithms. In view of small sample size, two approaches for model performance were adopted: The first using 10-fold stratified cross-validation and the second using independent random training and test samples (26:14). In both approaches, the highest area under the curve (AUC) values were selected for 5 CT and 5 PET features. These 10 features were combined and the same process was repeated.

Statistical Analysis Used

The quality of the performance of the models was assessed by MSE, RMSE, kappa statistic, AUC, area under the precision-recall curve, F-measure, and Matthews correlation coefficient.

Results

In the first approach, the highest AUC = 0.945 was seen with 5 CT parameters. In the second approach, the highest AUC = 0.9538 was seen with 4 CT and one PET parameter. CT neighborhood gray-level different matrix coarseness and CT gray-level run-length matrix LGRE were common parameters in both approaches. Comparison of AUC of the above models showed no significant difference (P = 0.9845). Feature selection by principal components analysis and feature classification by the multilayer perceptron machine-learning model using independent training and test samples yielded the overall highest AUC.

Conclusions

Machine-learning models using CT parameters were found to differentiate bone metastases from multiple myeloma better than models using PET parameters. Combined models using PET and CECT data showed better overall performance than models using only either PET or CECT data. Machine-learning models using independent training and test sets were performed on par with those using 10-fold stratified cross-validation with the former incorporating slightly more PET features. Certain first- and second-order CT and PET texture features contributed in differentiating these two conditions. Our findings suggested that, in general, metastases were finer in CT and PET texture and myelomas were more compact.

Spinal MRI-Based Radiomics Analysis to Predict Treatment Response in Multiple Myeloma

OBJECTIVE

The aim of this study was to explore the clinical utility of spinal magnetic resonance imaging-based radiomics to predict treatment response (TR) in patients with multiple myeloma (MM).

METHODS

A total of 123 MM patients (85 in the training cohort and 38 in the test cohort) with complete response (CR) (n = 40) or non-CR (n = 83) were retrospectively enrolled in the study. Key feature selection and data dimension reduction were performed using the least absolute shrinkage and selection operator regression. A nomogram was built by combining radiomic signatures and independent clinical risk factors. The prediction performance of the nomogram was assessed using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis. Treatment response was assessed by determining the serum and urinary levels of M-proteins, serum-free light chain ratio, and the percentage of bone marrow plasma cells.

RESULTS

Thirteen features were selected to build a radiomic signature. The International Staging System (ISS) stage was selected as an independent clinical factor. The radiomic signature and nomogram showed better calibration and higher discriminatory capacity (AUC of 0.929 and 0.917 for the radiomics and nomogram in the training cohort, respectively, and 0.862 and 0.874 for the radiomics and nomogram in the test cohort, respectively) than the clinical model (AUC of 0.661 and 0.674 in the training and test cohort, respectively). Decision curve analysis confirmed the clinical utility of the radiomics model.

CONCLUSIONS

Nomograms incorporating a magnetic resonance imaging-based radiomic signature and ISS stage help predict the response to chemotherapy for MM and can be useful in clinical decision-making.

Radiomics model of 18F-FDG PET/CT imaging for predicting disease-free survival of early-stage uterine cervical squamous cancer

BACKGROUND

To explore an effective predictive model based on PET/CT radiomics for the prognosis of early-stage uterine cervical squamous cancer.

METHODS

Preoperative PET/CT data were collected from 201 uterine cervical squamous cancer patients with stage IB-IIA disease (FIGO 2009) who underwent radical surgery between 2010 and 2015. The tumor regions were manually segmented, and 1318 radiomic features were extracted. First, model-based univariate analysis was performed to exclude features with small correlations. Then, the redundant features were further removed by feature collinearity. Finally, the random survival forest (RSF) was used to assess feature importance for multivariate analysis. The prognostic models were established based on RSF, and their predictive performances were measured by the C-index and the time-dependent cumulative/dynamics AUC (C/D AUC).

RESULTS

In total, 6 radiomic features (5 for CT and 1 for PET) and 6 clinicopathologic features were selected. The radiomic, clinicopathologic and combination prognostic models yielded C-indexes of 0.9338, 0.9019 and 0.9527, and the mean values of the C/D AUC (mC/D AUC) were 0.9146, 0.8645 and 0.9199, respectively.

CONCLUSIONS

PET/CT radiomics could achieve approval power in predicting DFS in early-stage uterine cervical squamous cancer.

A preliminary study using spinal MRI-based radiomics to predict high-risk cytogenetic abnormalities in multiple myeloma

OBJECTIVES

We aimed to investigate the feasibility of predicting high-risk cytogenetic abnormalities (HRCAs) in patients with multiple myeloma (MM) using a spinal MRI-based radiomics method.

MATERIALS AND METHODS

In this retrospective study, we analyzed the radiomic features of 248 lesions (HRCA [n = 111] and non-HRCA [n = 137]) using T1WI, T2WI, and fat suppression T2WI. To construct the radiomics model, the top nine most frequent radiomic features were selected using logistic regression (LR) machine-learning processes. A combined LR model incorporating radiomic features and basic clinical characteristics (age and sex) was also built. Fivefold external cross-validation was performed, and a comparative analysis of 10 random fivefold cross-validation sets was used to verify result stability. Model performance was compared by plotting receiver operating characteristic curves and the area under the curve (AUC).

RESULTS

Comparable AUC values were observed between the radiomics model and the combined model in validation cohorts (AUC: 0.863 vs. 0.870, respectively, p = 0.206). The radiomics model had an AUC of 0.863, with a sensitivity of 0.789, a specificity of 0.787, a positive predictive value of 0.753, a negative predictive value of 0.824, and an accuracy of 0.788 in the validation cohort, which were comparable with the performance in the training cohorts.

CONCLUSIONS

Radiomic features of routine spinal MRI reflect differences between HRCAs and non-HRCAs in patients with MM. This MRI-based radiomics model might be a useful and independent tool to predict HRCAs in patients MM.

Prediction of High-Risk Cytogenetic Status in Multiple Myeloma Based on Magnetic Resonance Imaging: Utility of Radiomics and Comparison of Machine Learning Methods

BACKGROUND

Radiomics has shown promising results in the diagnosis, efficacy, and prognostic assessments of multiple myeloma (MM). However, little evidence exists on the utility of radiomics in predicting a high-risk cytogenetic (HRC) status in MM.

PURPOSE

To develop and test a magnetic resonance imaging (MRI)-based radiomics model for predicting an HRC status in MM patients.

STUDY TYPE

Retrospective.

POPULATION

Eighty-nine MM patients (HRC [n: 37] and non-HRC [n: 52]).

FIELD STRENGTH/SEQUENCE

A 3.0 T; fast spin-echo (FSE): T1-weighted image (T1WI) and fat-suppression T2WI (FS-T2WI).

ASSESSMENT

Overall, 1409 radiomics features were extracted from each volume of interest drawn by radiologists. Three sequential feature selection steps-variance threshold, SelectKBest, and least absolute shrinkage selection operator-were repeated 10 times with 5-fold cross-validation. Radiomics models were constructed with the top three frequency features of T₁ WI/T₂ WI/two-sequence MRI (T₁ WI and FS-T₂ WI). Radiomics models, clinical data (age and visually assessed MRI pattern), or radiomics combined with clinical data were used with six classifiers to distinguish between HRC and non-HRC statuses. Six classifiers used were support vector machine, random forest, logistic regression (LR), decision tree, k-nearest neighbor, and XGBoost. Model performance was evaluated with area under the curve (AUC) values.

STATISTICAL TESTS

Mann-Whitney U-test, Chi-squared test, Z test, and DeLong method.

RESULTS

The LR classifier performed better than the other classifiers based on different data (AUC: 0.65-0.82; P < 0.05). The two-sequence MRI models performed better than the other data models using different classifiers (AUC: 0.68-0.82; P < 0.05). Thus, the LR two-sequence model yielded the best performance (AUC: 0.82 ± 0.02; sensitivity: 84.1%; specificity: 68.1%; accuracy: 74.7%; P < 0.05).

CONCLUSION

The LR-based machine learning method appears superior to other classifier methods for assessing HRC in MM. Radiomics features based on two-sequence MRI showed good performance in differentiating HRC and non-HRC statuses in MM.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Progression to Symptomatic Multiple Myeloma Predicted by Texture Analysis-Derived Parameters in Patients Without Focal Disease at 18F-FDG PET/CT

This retrospective study is focused on the possible clinical implications of texture analysis-derived PET parameters in patients with smoldering multiple myeloma. Several texture features are significantly associated with progression to symptomatic multiple myeloma and with a shorter time to progression. The results of this study may lead to early identification of patients who could benefit from specific therapies.

BACKGROUND

The aim of the study was to determine whether positron emission tomography parameters derived from texture analysis of axial and peripheral skeleton predict progression to symptomatic multiple myeloma (MM) in patients undergoing 18F-​fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) without evidence of focal sites of ¹⁸F-FDG uptake.

PATIENTS AND METHODS

Patients with smoldering MM who underwent ¹⁸F-FDG PET/CT from May 2014 to June 2018 were retrospectively reviewed. Volumes of interest (VOIs) were placed on T5-T7 and L2-L4, iliac crests, and femoral diaphyses. Dedicated software (LIFEx) allowed us to obtain PET-derived first-, second-, and higher order texture features. Possible associations between PET parameters and progression to symptomatic MM were determined. Kaplan-Meier curves allowed to assess time to progression (TTP) based on the PET parameters.

RESULTS

Forty-five patients were included: 26 patients (58%) did not meet the criteria for symptomatic MM, but 19 patients (42%) progressed to symptomatic MM. Several texture features extracted from VOIs placed on iliac crests and femoral diaphyses were significantly associated with progression to symptomatic MM and with a shorter TTP (P < .05); conversely, the above-mentioned parameters extracted from VOIs placed on T5-T7 and L2-L4 did not significantly differ among the patients with regard to their progression to symptomatic MM and length of TTP, except for the gray-level zone length matrix-short-zone low-gray-level emphasis and gray-level zone length matrix-low gray-level zone emphasis. Particularly, second- and higher order texture features showed a significant association with the above-mentioned outcomes.

CONCLUSION

Texture features derived from PET may be an expression of subtle disease distribution in the axial and peripheral bone marrow.

Random survival forest to predict transplant-eligible newly diagnosed multiple myeloma outcome including FDG-PET radiomics: a combined analysis of two independent prospective European trials

PURPOSE

Fluorodeoxyglucose-positron emission tomography/computed tomography (FDG-PET/CT) is included in the International Myeloma Working Group (IMWG) imaging guidelines for the work-up at diagnosis and the follow-up of multiple myeloma (MM) notably because it is a reliable tool as a predictor of prognosis. Nevertheless, none of the published studies focusing on the prognostic value of PET-derived features at baseline consider tumor heterogeneity, which could be of high importance in MM. The aim of this study was to evaluate the prognostic value of baseline PET-derived features in transplant-eligible newly diagnosed (TEND) MM patients enrolled in two prospective independent European randomized phase III trials using an innovative statistical random survival forest (RSF) approach.

METHODS

Imaging ancillary studies of IFM/DFCI2009 and EMN02/HO95 trials formed part of the present analysis (IMAJEM and EMN02/HO95, respectively). Among all patients initially enrolled in these studies, those with a positive baseline FDG-PET/CT imaging and focal bone lesions (FLs) and/or extramedullary disease (EMD) were included in the present analysis. A total of 17 image features (visual and quantitative, reflecting whole imaging characteristics) and 5 clinical/histopathological parameters were collected. The statistical analysis was conducted using two RSF approaches (train/validation + test and additional nested cross-validation) to predict progression-free survival (PFS).

RESULTS

One hundred thirty-nine patients were considered for this study. The final model based on the first RSF (train/validation + test) approach selected 3 features (treatment arm, hemoglobin, and SUV_maxBone Marrow (BM)) among the 22 involved initially, and two risk groups of patients (good and poor prognosis) could be defined with a mean hazard ratio of 4.3 ± 1.5 and a mean log-rank p value of 0.01 ± 0.01. The additional RSF (nested cross-validation) analysis highlighted the robustness of the proposed model across different splits of the dataset. Indeed, the first features selected using the train/validation + test approach remained the first ones over the folds with the nested approach.

CONCLUSION

We proposed a new prognosis model for TEND MM patients at diagnosis based on two RSF approaches.

TRIAL REGISTRATION

IMAJEM: NCT01309334 and EMN02/HO95: NCT01134484.

Glucose Metabolism Quantified by SUVmax on Baseline FDG-PET/CT Predicts Survival in Newly Diagnosed Multiple Myeloma Patients: Combined Harmonized Analysis of Two Prospective Phase III Trials

Simple Summary

Multiple myeloma (MM) is associated with high morbidity and mortality and variable survival that requires early identification of high-risk patients in order to quickly adapt treatment. FDG-PET/CT is a promising technique for initial staging of symptomatic MM. The aim of our retrospective study was to asses the prognostic value of this technique at baseline in symptomatic MM patients included in two large European prospective studies. After harmonization of data by and ad-hoc approach called M-Combat, we confirmed the prognostic value of FDG-PET/CT in a population of 227 MM patients, by integrating a new prognostic biomarker named “bone SUVmax” (including the maximum intensity of fixation of focal lesions and bone marrow) which is strongly correlated with a poorer prognosis of MM patients. Prognostic patient stratification is currently based on laboratory tests and genomic abnormalities, but FDG-PET/CT is likely to be an important method of defining high-risk patients, and thus, to potentially better adapt future therapeutic management.

Abstract

Background: Multiple myeloma is a hematological neoplasm characterized by a clonal proliferation of malignant plasma cells in the bone marrow, and is associated with high morbidity and mortality and variable survival. Positron emission tomography combined with computed tomography using 18F-deoxyfluoroglucose (FDG-PET/CT) is a promising technique for initial staging of symptomatic multiple myeloma patients. The objective of this study was to assess the prognostic value of this technique at baseline in symptomatic multiple myeloma patients included in two large European prospective studies (French and Italian). Methods: We retrospectively performed a combined harmonized analysis of 227 newly diagnosed transplant eligible multiple myeloma patients from two separate phase III trials. All images were centrally reviewed and analyzed using visual criteria and maximal standardized uptake value. An ad-hoc approach (called modified Combat) was applied to harmonize the data and then remove the “country effect” in order to strengthen the reliability of the final conclusions. Results: Using a multivariate analysis including treatment arm, R-ISS score, presence of extra-medullary disease and bone SUVmax, only bone SUVmax (p = 0.016) was an independent prognosis factor with an OS threshold of 7.1. For PFS, treatment arm and presence of extra-medullary disease were both independent prognosis biomarkers (p = 0.022 and 0.006 respectively). Conclusions: Our results show that bone SUVmax is a simple and reliable biomarker to analyze FDG-PET/CT at baseline that strongly correlates with a poorer prognosis for MM patients.

FDG-PET/CT, a Promising Exam for Detecting High-Risk Myeloma Patients?

Multiple myeloma (MM) is a haematological neoplasm characterized by a clonal proliferation of malignant plasma cells in the bone marrow. MM is associated with high morbidity and mortality and variable survival, which can be very short for some patients but over 10 years for others. These differences in survival are explained by intra- and inter-tumoral heterogeneity and demonstrate the potential benefits of adapting the treatment course for high-risk patients with a poorer prognosis. Indeed, identification of these high-risk patients is necessary and is based on the identification of high-risk biomarkers including clinical variables, genomics and imaging results. Positron emission tomography combined with computed tomography using 18F-deoxyfluoroglucose (FDG-PET/CT) is a reliable technique for the initial staging of patients with symptomatic multiple myeloma (MM), and has been included in the IMWG (International Myeloma Working Group) recommendations in 2019. According to clinical studies, FDG-PET/CT characteristics could be used to define high-risk patients at initial diagnosis of symptomatic MM. The goal of this review is to demonstrate the prognostic value of FDG-PET in symptomatic MM patients, particularly in identifying high-risk patients, and thus, to best adapt therapeutic management in the future.

Extended Texture Analysis of Non-Enhanced Whole-Body MRI Image Data for Response Assessment in Multiple Myeloma Patients Undergoing Systemic Therapy

Identifying MRI-based radiomics features capable to assess response to systemic treatment in multiple myeloma (MM) patients. Retrospective analysis of whole-body MR-image data in 67 consecutive stage III MM patients (40 men; mean age, 60.4 years). Bone marrow involvement was evaluated using a standardized MR-imaging protocol consisting of T1w-, short-tau inversion recovery- (STIR-) and diffusion-weighted-imaging (DWI) sequences. Ninety-two radiomics features were evaluated, both in focally and diffusely involved bone marrow. Volumes of interest (VOI) were used. Response to treatment was classified according to International Myeloma Working Group (IMWG) criteria in complete response (CR), very-good and/or partial response (VGPR + PR), and non-response (stable disease (SD) and progressive disease (PD)). According to the IMWG-criteria, response categories were CR (n = 35), VGPR + PR (n = 19), and non-responders (n = 13). On apparent diffusion coefficient (ADC)-maps, gray-level small size matrix small area emphasis (Gray Level Size Zone (GLSZM) small area emphasis (SAE)) significantly correlated with CR (p < 0.001), whereas GLSZM non-uniformity normalized (NUN) significantly (p < 0.008) with VGPR/PR in focal medullary lesions (FL), whereas in diffuse involvement, 1st order root mean squared significantly (p < 0.001) correlated with CR, whereas for VGPR/PR Log (gray-level run-length matrix (GLRLM) Short Run High Gray Level Emphasis) proved significant (p < 0.003). On T1w, GLRLM NUN significantly (p < 0.002) correlated with CR in FL, whereas gray-level co-occurrence matric (GLCM) informational measure of correlation (Imc1) significantly (p < 0.04) correlated with VGPR/PR. For diffuse myeloma involvement, neighboring gray-tone difference matrix (NGTDM) contrast and 1st order skewness were significantly associated with CR and VGPR/PR (p < 0.001 for both). On STIR-images, CR correlated with gray-level co-occurrence matrix (GLCM) Informational Measure of Correlation (IMC) 1 (p < 0.001) in FL and 1st order mean absolute deviation in diffusely involved bone marrow (p < 0.001). VGPR/PR correlated at best in FL with GSZLM size zone NUN (p < 0.019) and in all other involved medullary areas with GLSZM large area low gray level emphasis (p < 0.001). GLSZM large area low gray level emphasis also significantly correlated with the degree of bone marrow infiltration assessed histologically (p = 0.006). GLCM IMC 1 proved significant throughout T1w/STIR sequences, whereas GLSZM NUN in STIR and ADC. MRI-based texture features proved significant to assess clinical and hematological response (CR, VPGR, and PR) in multiple myeloma patients undergoing systemic treatment.