A Postreconstruction Harmonization Method for Multicenter Radiomic Studies in PET

Impact of Preprocessing and Harmonization Methods on the Removal of Scanner Effects in Brain MRI Radiomic Features

Simple Summary

As a rapid-development research field, radiomics-based analysis has been applied to many clinical problems. However, the reproducibility of the radiomics studies remain challenging especially when data suffers from scanner effects, a kind of non-biological variations introduced by different image acquiring settings. This study aims to investigate how the image preprocessing methods (N4 bias field correction and image resampling) and the harmonization methods (intensity normalization methods working on images and ComBat method working on radiomic features) help to remove the scanner effects and improve the radiomics reproducibility in brain MRI radiomics.

Abstract

In brain MRI radiomics studies, the non-biological variations introduced by different image acquisition settings, namely scanner effects, affect the reliability and reproducibility of the radiomics results. This paper assesses how the preprocessing methods (including N4 bias field correction and image resampling) and the harmonization methods (either the six intensity normalization methods working on brain MRI images or the ComBat method working on radiomic features) help to remove the scanner effects and improve the radiomic feature reproducibility in brain MRI radiomics. The analyses were based on in vitro datasets (homogeneous and heterogeneous phantom data) and in vivo datasets (brain MRI images collected from healthy volunteers and clinical patients with brain tumors). The results show that the ComBat method is essential and vital to remove scanner effects in brain MRI radiomic studies. Moreover, the intensity normalization methods, while not able to remove scanner effects at the radiomic feature level, still yield more comparable MRI images and improve the robustness of the harmonized features to the choice among ComBat implementations.

Radiomics of high-resolution computed tomography for the differentiation between cholesteatoma and middle ear inflammation: effects of post-reconstruction methods in a dual-center study

OBJECTIVES

To evaluate the performance of radiomic features extracted from high-resolution computed tomography (HRCT) for the differentiation between cholesteatoma and middle ear inflammation (MEI), and to investigate the impact of post-reconstruction harmonization and data resampling.

METHODS

One hundred patients were included in this retrospective dual-center study: 48 with histology-proven cholesteatoma (center A: 23; center B: 25) and 52 with MEI (A: 27; B: 25). Radiomic features (co-occurrence and run-length matrix, absolute gradient, autoregressive model, Haar wavelet transform) were extracted from manually defined 2D-ROIs. The ten best features for lesion differentiation were selected using probability of error and average correlation coefficients. A multi-layer perceptron feed-forward artificial neural network (MLP-ANN) was used for radiomics-based classification, with histopathology serving as the reference standard (70% of cases for training, 30% for validation). The analysis was performed five times each on (a) unmodified data and on data that were (b) resampled to the same matrix size, and (c) corrected for acquisition protocol differences using ComBat harmonization.

RESULTS

Using unmodified data, the MLP-ANN classification yielded an overall median area under the receiver operating characteristic curve (AUC) of 0.78 (0.72-0.84). Using original data from center A and resampled data from center B, an overall median AUC of 0.88 (0.82-0.99) was yielded, while using ComBat harmonized data, an overall median AUC of 0.89 (0.79-0.92) was revealed.

CONCLUSION

Radiomic features extracted from HRCT differentiate between cholesteatoma and MEI. When using multi-centric data obtained with differences in CT acquisition parameters, data resampling and ComBat post-reconstruction harmonization clearly improve radiomics-based lesion classification.

KEY POINTS

• Unenhanced high-resolution CT coupled with radiomics analysis may be useful for the differentiation between cholesteatoma and middle ear inflammation. • Pooling of data extracted from inhomogeneous CT datasets does not appear meaningful without further post-processing. • When using multi-centric CT data obtained with differences in acquisition parameters, post-reconstruction harmonization and data resampling clearly improve radiomics-based soft-tissue differentiation.

Treatment response prediction using MRI-based pre-, post-, and delta-radiomic features and machine learning algorithms in colorectal cancer

OBJECTIVES

We evaluate the feasibility of treatment response prediction using MRI-based pre-, post-, and delta-radiomic features for locally advanced rectal cancer (LARC) patients treated by neoadjuvant chemoradiation therapy (nCRT).

MATERIALS AND METHODS

This retrospective study included 53 LARC patients divided into a training set (Center#1, n = 36) and external validation set (Center#2, n = 17). T2-weighted (T2W) MRI was acquired for all patients, 2 weeks before and 4 weeks after nCRT. Ninety-six radiomic features, including intensity, morphological and second- and high-order texture features were extracted from segmented 3D volumes from T2W MRI. All features were harmonized using ComBat algorithm. Max-Relevance-Min-Redundancy (MRMR) algorithm was used as feature selector and k-nearest neighbors (KNN), Naïve Bayes (NB), Random forests (RF), and eXtreme Gradient Boosting (XGB) algorithms were used as classifiers. The evaluation was performed using the area under the receiver operator characteristic (ROC) curve (AUC), sensitivity, specificity and accuracy.

RESULTS

In univariate analysis, the highest AUC in pre-, post-, and delta-radiomic features were 0.78, 0.70, and 0.71, for GLCM_IMC1, shape (surface area and volume) and GLSZM_GLNU features, respectively. In multivariate analysis, RF and KNN achieved the highest AUC (0.85 ± 0.04 and 0.81 ± 0.14, respectively) among pre- and post-treatment features. The highest AUC was achieved for the delta-radiomic-based RF model (0.96 ± 0.01) followed by NB (0.96 ± 0.04). Overall. Delta-radiomics model, outperformed both pre- and post-treatment features (P-value <0.05).

CONCLUSION

Multivariate analysis of delta-radiomic T2W MRI features using machine learning algorithms could potentially be used for response prediction in LARC patients undergoing nCRT. We also observed that multivariate analysis of delta-radiomic features using RF classifiers can be used as powerful biomarkers for response prediction in LARC.

The application of a workflow integrating the variable reproducibility and harmonizability of radiomic features on a phantom dataset

Radiomics–the high throughput extraction of quantitative features from medical images and their correlation with clinical and biological endpoints- is the subject of active and extensive research. Although the field shows promise, the generalizability of radiomic signatures is affected significantly by differences in scan acquisition and reconstruction settings. Previous studies reported on the sensitivity of radiomic features (RFs) to test-retest variability, inter-observer segmentation variability, and intra-scanner variability. A framework involving robust radiomics analysis and the application of a post-reconstruction feature harmonization method using ComBat was recently proposed to address these challenges. In this study, we investigated the reproducibility of RFs across different scanners and scanning parameters using this framework. We analysed thirteen scans of a ten-layer phantom that were acquired differently. Each layer was subdivided into sixteen regions of interest (ROIs), and the scans were compared in a pairwise manner, resulting in seventy-eight different scenarios. Ninety-one RFs were extracted from each ROI. As hypothesized, we demonstrate that the reproducibility of a given RF is not a constant but is dependent on the heterogeneity found in the data under analysis. The number (%) of reproducible RFs varied across the pairwise scenarios investigated, having a wide range between 8 (8.8%) and 78 (85.7%) RFs. Furthermore, in contrast to what has been previously reported, and as hypothesized in the robust radiomics analysis framework, our results demonstrate that ComBat cannot be applied to all RFs but rather on a percentage of those–the “ComBatable” RFs–which differed depending on the data being harmonized. The number (%) of reproducible RFs following ComBat harmonization varied across the pairwise scenarios investigated, ranging from 14 (15.4%) to 80 (87.9%) RFs, and was found to depend on the heterogeneity in the data. We conclude that the standardization of image acquisition protocols remains the cornerstone for improving the reproducibility of RFs, and the generalizability of the signatures developed. Our proposed approach helps identify the reproducible RFs across different datasets.

The Role of Radiomics in Lung Cancer: From Screening to Treatment and Follow-Up

PURPOSE

Lung cancer represents the first cause of cancer-related death in the world. Radiomics studies arise rapidly in this late decade. The aim of this review is to identify important recent publications to be synthesized into a comprehensive review of the current status of radiomics in lung cancer at each step of the patients' care.

METHODS

A literature review was conducted using PubMed/Medline for search of relevant peer-reviewed publications from January 2012 to June 2020.

RESULTS

We identified several studies at each point of patient's care: detection and classification of lung nodules (n=16), determination of histology and genomic (n=10) and finally treatment outcomes predictions (=23). We reported the methodology of those studies and their results and discuss the limitations and the progress to be made for clinical routine applications.

CONCLUSION

Promising perspectives arise from machine learning applications and radiomics based models in lung cancers, yet further data are necessary for their implementation in daily care. Multicentric collaboration and attention to quality and reproductivity of radiomics studies should be further consider.

PET Molecular Imaging: A Holistic Review of Current Practice and Emerging Perspectives for Diagnosis, Therapeutic Evaluation and Prognosis in Clinical Oncology

PET/CT molecular imaging has been imposed in clinical oncological practice over the past 20 years, driven by its two well-grounded foundations: quantification and radiolabeled molecular probe vectorization. From basic visual interpretation to more sophisticated full kinetic modeling, PET technology provides a unique opportunity to characterize various biological processes with different levels of analysis. In clinical practice, many efforts have been made during the last two decades to standardize image analyses at the international level, but advanced metrics are still under use in practice. In parallel, the integration of PET imaging with radionuclide therapy, also known as radiolabeled theranostics, has paved the way towards highly sensitive radionuclide-based precision medicine, with major breakthroughs emerging in neuroendocrine tumors and prostate cancer. PET imaging of tumor immunity and beyond is also emerging, emphasizing the unique capabilities of PET molecular imaging to constantly adapt to emerging oncological challenges. However, these new horizons face the growing complexity of multidimensional data. In the era of precision medicine, statistical and computer sciences are currently revolutionizing image-based decision making, paving the way for more holistic cancer molecular imaging analyses at the whole-body level.

Uncertainty measurement of radiomics features against inherent quantum noise in computed tomography imaging

OBJECTIVES

Quantum noise is a random process in X-ray-based imaging systems. We addressed and measured the uncertainty of radiomics features against this quantum noise in computed tomography (CT) images.

METHODS

A clinical multi-detector CT scanner, two homogeneous phantom sets, and four heterogeneous samples were used. A solid tumor tissue removed from a male BALB/c mouse was included. We the placed phantom sets on the CT scanning table and repeated 20 acquisitions with identical imaging settings. Regions of interest were delineated for feature extraction. Statistical quantities-average, standard deviation, and percentage uncertainty-were calculated from these 20 repeated scans. Percentage uncertainty was used to measure and quantify feature stability against quantum noise. Twelve radiomics features were measured. Random noise was added to study the robustness of machine learning classifiers against feature uncertainty.

RESULTS

We found the ranges of percentage uncertainties from homogeneous soft tissue phantoms, homogeneous bone phantoms, and solid tumor tissue to be 0.01-2138%, 0.02-15%, and 0.18-16%, respectively. Overall, it was found that the CT features ShortRunHighGrayLevelEmpha (SRHGE) (0.01-0.18%), ShortRunLowGrayLevelEmpha (SRLGE) (0.01-0.41%), LowGrayLevelRunEmpha (LGRE) (0.01-0.39%), and LongRunLowGrayLevelEmpha (LRLGE) (0.02-0.66%) were the most stable features against the inherent quantum noise. The most unstable features were cluster shade (1-2138%) and max probability (1-16%). The impact of random noise to the prediction accuracy by different machine learning classifiers was found to be between 0 and 12%.

CONCLUSIONS

Twelve features were used for uncertainty measurements. The upper and lower bounds of percentage uncertainties were determined. The quantum noise effect on machine learning classifiers is model dependent.

KEY POINTS

• Quantum noise is a random process and is intrinsic to X-ray-based imaging systems. This inherent quantum noise creates unpredictable fluctuations in the gray-level intensities of image pixels. Extra cautions and further validations are strongly recommended when unstable radiomics features are selected by a predictive model for disease classification or treatment outcome prognosis. • We addressed and used the statistical quantity of percentage uncertainty to measure the uncertainty of radiomics features against the inherent quantum noise in computed tomography (CT) images. • A clinical multi-detector CT scanner, two homogeneous phantom sets, and four heterogeneous samples were used in the stability measurement. A solid tumor tissue removed from a male BALB/c mouse was included in the heterogeneous sample.

The Effects of In-Plane Spatial Resolution on CT-Based Radiomic Features' Stability with and without ComBat Harmonization

Simple Summary

Handcrafted radiomic features (HRFs) are quantitative features extracted from medical images, and they are mined for associations with different clinical endpoints. While many studies reported on the potential of HRFs to unravel clinical endpoints, the sensitivity of HRFs to variations in scanning parameters is affecting the inclusion of radiomic signatures in clinical decision-making. In this study, we investigated the effects of variations in the in-plane resolution of scans, while all other scanning parameters were fixed. Moreover, we investigated the effects of ten different image resampling methods and ComBat harmonization on the reproducibility of HRFs. Our results show that the majority of HRFs are significantly and variably affected by the differences in in-plane resolution. The majority of image resampling methods resulted in a higher number of reproducible HRFs compared to ComBat harmonization. Our developed framework guides identifying the reproducible and harmonizable HRFs in different scenarios.

Abstract

While handcrafted radiomic features (HRFs) have shown promise in the field of personalized medicine, many hurdles hinder its incorporation into clinical practice, including but not limited to their sensitivity to differences in acquisition and reconstruction parameters. In this study, we evaluated the effects of differences in in-plane spatial resolution (IPR) on HRFs, using a phantom dataset (n = 14) acquired on two scanner models. Furthermore, we assessed the effects of interpolation methods (IMs), the choice of a new unified in-plane resolution (NUIR), and ComBat harmonization on the reproducibility of HRFs. The reproducibility of HRFs was significantly affected by variations in IPR, with pairwise concordant HRFs, as measured by the concordance correlation coefficient (CCC), ranging from 42% to 95%. The number of concordant HRFs (CCC > 0.9) after resampling varied depending on (i) the scanner model, (ii) the IM, and (iii) the NUIR. The number of concordant HRFs after ComBat harmonization depended on the variations between the batches harmonized. The majority of IMs resulted in a higher number of concordant HRFs compared to ComBat harmonization, and the combination of IMs and ComBat harmonization did not yield a significant benefit. Our developed framework can be used to assess the reproducibility and harmonizability of RFs.

Differences in Radiomics Signatures Between Patients with Early and Advanced T-Stage Nasopharyngeal Carcinoma Facilitate Prognostication

BACKGROUND

Accurately predicting the risk of death, recurrence, and metastasis of patients with nasopharyngeal carcinoma (NPC) is potentially important for personalized diagnosis and treatment. Survival outcomes of patients vary greatly in distinct stages of NPC. Prognostic models of stratified patients may aid in prognostication.

PURPOSE

To explore the prognostic performance of MRI-based radiomics signatures in stratified patients with NPC.

STUDY TYPE

Retrospective.

POPULATION

Seven hundred and seventy-eight patients with NPC (T1-2 stage: 298, T3-4 stage: 480; training cohort: 525, validation cohort: 253).

FIELD STRENGTH/SEQUENCE

Fast-spin echo (FSE) axial T1-weighted images, FSE axial T2-weighted images, contrast-enhanced FSE axial T1-weighted images at 1.5 T or 3.0 T.

ASSESSMENT

Radiomics signatures, clinical nomograms, and radiomics nomograms combining the radiomic score (Radscore) and clinical factors for predicting progression-free survival (PFS) were constructed on T1-2 stage patient cohort (A), T3-4 stage patient cohort (B), and the entire dataset (C).

STATISTICAL TESTS

Least absolute shrinkage and selection operator (LASSO) method was applied for radiomics modeling. Harrell's concordance indices (C-index) were employed to evaluate the predictive power of each model.

RESULTS

Among 4,410 MRI-extracted features, we selected 16, 16, and 14 radiomics features most relevant to PFS for Models A, B, and C, respectively. Only 0, 1, and 4 features were found overlapped between models A/B, A/C, and B/C, respectively. Radiomics signatures constructed on T1-2 stage and T3-4 stage patients yielded C-indices of 0.820 (95% confidence interval [CI]: 0.763-0.877) and 0.726 (0.687-0.765), respectively, which were larger than those on the entire validation cohort (0.675 [0.637-0.713]). Radiomics nomograms combining Radscore and clinical factors achieved significantly better performance than clinical nomograms (P < 0.05 for all).

DATA CONCLUSION

The selected radiomics features and prognostic performance of radiomics signatures differed per the type of NPC patients incorporated into the models. Radiomics models based on pre-stratified tumor stages had better prognostic performance than those on unstratified dataset.

LEVEL OF EVIDENCE

4 Technical Efficacy Stage: 5.

Understanding Sources of Variation to Improve the Reproducibility of Radiomics

Radiomics is the method of choice for investigating the association between cancer imaging phenotype, cancer genotype and clinical outcome prediction in the era of precision medicine. The fast dispersal of this new methodology has benefited from the existing advances of the core technologies involved in radiomics workflow: image acquisition, tumor segmentation, feature extraction and machine learning. However, despite the rapidly increasing body of publications, there is no real clinical use of a developed radiomics signature so far. Reasons are multifaceted. One of the major challenges is the lack of reproducibility and generalizability of the reported radiomics signatures (features and models). Sources of variation exist in each step of the workflow; some are controllable or can be controlled to certain degrees, while others are uncontrollable or even unknown. Insufficient transparency in reporting radiomics studies further prevents translation of the developed radiomics signatures from the bench to the bedside. This review article first addresses sources of variation, which is illustrated using demonstrative examples. Then, it reviews a number of published studies and progresses made to date in the investigation and improvement of feature reproducibility and model performance. Lastly, it discusses potential strategies and practical considerations to reduce feature variability and improve the quality of radiomics study. This review focuses on CT image acquisition, tumor segmentation, quantitative feature extraction, and the disease of lung cancer.

Application of a Machine Learning Approach for the Analysis of Clinical and Radiomic Features of Pretreatment [18F]-FDG PET/CT to Predict Prognosis of Patients with Endometrial Cancer

PURPOSE

To examine the prognostic significance of pretreatment 2-deoxy-2-[¹⁸F]fluoro-D-glucose ([¹⁸F]-FDG) positron emission tomography (PET)-based radiomic features using a machine learning approach in patients with endometrial cancers.

PROCEDURES

Included in this retrospective study were 53 patients with endometrial cancers who underwent [¹⁸F]-FDG PET/X-ray computed tomography (CT) before treatment. Since two different PET scanners were used, post-reconstruction harmonization was performed for all PET parameters using the ComBat harmonization method. Four clinical (age, histological type, stage, and treatment method) and 40 [¹⁸F]-FDG PET-based radiomic features were ranked, and a subset of useful features was selected based on the decrease in the Gini impurity in terms of associations with disease progression. The machine learning algorithms (random forest, neural network, k-nearest neighbors (kNN), naive Bayes, logistic regression, and support vector machine) were compared using the areas under the receiver operating characteristic curve (AUC) and validated by the random sampling method. Progression-free survival (PFS) and overall survival (OS) were assessed by the Cox regression analysis.

RESULTS

The five best predictors of disease progression were coarseness, gray-level run length nonuniformity, stage, treatment method, and gray-level zone length nonuniformity. The kNN model obtained the best performance classifier for predicting the disease progression (AUC =0.890, accuracy =0.849, F1 score =0.848, precision =0.857, and recall =0.849). Coarseness which was the first ranked radiomic feature was selected for survival analyses, and only coarseness remained as a significant and independent factor for both PFS (hazard ratios (HR), 0.65; 95 % confidence interval [CI], 0.49-0.86; p=0.003) and OS (HR, 0.52; 95 % CI, 0.36-0.76; p<0.001) at multivariate Cox regression analysis.

CONCLUSIONS

[¹⁸F]-FDG PET-based radiomic analysis using a machine learning approach may be useful for predicting tumor progression and prognosis in patients with endometrial cancers.

Standardization of histogram- and GLCM-based radiomics in the presence of blur and noise

Radiomics have been extensively investigated as quantitative biomarkers that can enhance the utility of imaging studies and aid the clinical decision making process. A major challenge to the clinical translation of radiomics is their variability as a result of different imaging and reconstruction protocols. In this work, we present a novel radiomics standardization framework capable of modeling and recovering the underlying radiomic feature in images that have been corrupted by the effects of spatial resolution and noise. We focus on two classes of radiomics based on pixel value distributions - i.e., histograms and gray-level co-occurrence matrices. We developed a model that predicts these distributions in the presence of system blur and noise, and used that model to invert these physical effects and recover the underlying distributions. Specifically, the effect of blur on histogram and GLCM is highly image-dependent, while additive noise convolves the histogram/GLCM of the noiseless image with those of the noise. The recovery method therefore consists of two deconvolution operations: the first in the image domain to remove the effect of system blur, the second in the histogram/GLCM domain to remove the effect of noise. The performance of the proposed recovery strategy was investigated using a set of texture phantoms and an emulated CT imaging chain with a range of realistic blur and noise levels. The proposed method was able to obtain histogram and GLCM estimates that closely resemble the ground truth. The method performed well across imaging conditions and significantly lowered the variability associated with different imaging protocols. This improvement also translated to better classification accuracy, where recovered radiomic values results in greater separation of radiomic clusters for two different texture phantoms as compared to values derived from the original blurred and noisy images. In summary, the novel radiomics standardization framework demonstrates high potential for mitigating radiomic variability as a result of the imaging system and can potentially be integrated as a preprocessing step towards more robust and reproducible radiomic models.

Breast Tumor Characterization Using [18F]FDG-PET/CT Imaging Combined with Data Preprocessing and Radiomics

Simple Summary

Breast cancer is the second most common diagnosed malignancy in women worldwide. In this study, we examine the feasibility of breast tumor characterization based on [¹⁸F]FDG-PET/CT images using machine learning (ML) approaches in combination with data-preprocessing techniques. ML prediction models for breast cancer detection and the identification of breast cancer receptor status, proliferation rate, and molecular subtypes were established and evaluated. Furthermore, the importance of most repeatable features was investigated. Results displayed high performance of malignant/benign tumor differentiation and triple negative tumor subtype ML models. We observed high repeatability of radiomic features for both high performing predictive models.

Abstract

Background: This study investigated the performance of ensemble learning holomic models for the detection of breast cancer, receptor status, proliferation rate, and molecular subtypes from [¹⁸F]FDG-PET/CT images with and without incorporating data pre-processing algorithms. Additionally, machine learning (ML) models were compared with conventional data analysis using standard uptake value lesion classification. Methods: A cohort of 170 patients with 173 breast cancer tumors (132 malignant, 38 benign) was examined with [¹⁸F]FDG-PET/CT. Breast tumors were segmented and radiomic features were extracted following the imaging biomarker standardization initiative (IBSI) guidelines combined with optimized feature extraction. Ensemble learning including five supervised ML algorithms was utilized in a 100-fold Monte Carlo (MC) cross-validation scheme. Data pre-processing methods were incorporated prior to machine learning, including outlier and borderline noisy sample detection, feature selection, and class imbalance correction. Feature importance in each model was assessed by calculating feature occurrence by the R-squared method across MC folds. Results: Cross validation demonstrated high performance of the cancer detection model (80% sensitivity, 78% specificity, 80% accuracy, 0.81 area under the curve (AUC)), and of the triple negative tumor identification model (85% sensitivity, 78% specificity, 82% accuracy, 0.82 AUC). The individual receptor status and luminal A/B subtype models yielded low performance (0.46–0.68 AUC). SUV_max model yielded 0.76 AUC in cancer detection and 0.70 AUC in predicting triple negative subtype. Conclusions: Predictive models based on [¹⁸F]FDG-PET/CT images in combination with advanced data pre-processing steps aid in breast cancer diagnosis and in ML-based prediction of the aggressive triple negative breast cancer subtype.

AI applications to medical images: From machine learning to deep learning

PURPOSE

Artificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context.

METHODS

A narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections.

RESULTS

We first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way.

CONCLUSIONS

Biomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.

A Systematic Review of PET Textural Analysis and Radiomics in Cancer

Background: Although many works have supported the utility of PET radiomics, several authors have raised concerns over the robustness and replicability of the results. This study aimed to perform a systematic review on the topic of PET radiomics and the used methodologies. Methods: PubMed was searched up to 15 October 2020. Original research articles based on human data specifying at least one tumor type and PET image were included, excluding those that apply only first-order statistics and those including fewer than 20 patients. Each publication, cancer type, objective and several methodological parameters (number of patients and features, validation approach, among other things) were extracted. Results: A total of 290 studies were included. Lung (28%) and head and neck (24%) were the most studied cancers. The most common objective was prognosis/treatment response (46%), followed by diagnosis/staging (21%), tumor characterization (18%) and technical evaluations (15%). The average number of patients included was 114 (median = 71; range 20–1419), and the average number of high-order features calculated per study was 31 (median = 26, range 1–286). Conclusions: PET radiomics is a promising field, but the number of patients in most publications is insufficient, and very few papers perform in-depth validations. The role of standardization initiatives will be crucial in the upcoming years.

A Multi-Center, Multi-Vendor Study to Evaluate the Generalizability of a Radiomics Model for Classifying Prostate cancer: High Grade vs. Low Grade

Radiomics applied in MRI has shown promising results in classifying prostate cancer lesions. However, many papers describe single-center studies without external validation. The issues of using radiomics models on unseen data have not yet been sufficiently addressed. The aim of this study is to evaluate the generalizability of radiomics models for prostate cancer classification and to compare the performance of these models to the performance of radiologists. Multiparametric MRI, photographs and histology of radical prostatectomy specimens, and pathology reports of 107 patients were obtained from three healthcare centers in the Netherlands. By spatially correlating the MRI with histology, 204 lesions were identified. For each lesion, radiomics features were extracted from the MRI data. Radiomics models for discriminating high-grade (Gleason score ≥ 7) versus low-grade lesions were automatically generated using open-source machine learning software. The performance was tested both in a single-center setting through cross-validation and in a multi-center setting using the two unseen datasets as external validation. For comparison with clinical practice, a multi-center classifier was tested and compared with the Prostate Imaging Reporting and Data System version 2 (PIRADS v2) scoring performed by two expert radiologists. The three single-center models obtained a mean AUC of 0.75, which decreased to 0.54 when the model was applied to the external data, the radiologists obtained a mean AUC of 0.46. In the multi-center setting, the radiomics model obtained a mean AUC of 0.75 while the radiologists obtained a mean AUC of 0.47 on the same subset. While radiomics models have a decent performance when tested on data from the same center(s), they may show a significant drop in performance when applied to external data. On a multi-center dataset our radiomics model outperformed the radiologists, and thus, may represent a more accurate alternative for malignancy prediction.

Longitudinal acquisition repeatability of MRI radiomics features: An ACR MRI phantom study on two MRI scanners using a 3D T1W TSE sequence

PURPOSE

The purpose of this study was to quantitatively assess the longitudinal acquisition repeatability of MRI radiomics features in a three-dimensional (3D) T1-weighted (T1W) TSE sequence via a well-controlled prospective phantom study.

METHODS

Thirty consecutive daily datasets of an ACR-MRI phantom were acquired on two 1.5T MRI simulators using a 3D T1W TSE sequence. Images were blindly segmented by two observers. Post-acquisition processing was minimized but an intensity discretization (fixed bin size of 25). One hundred and one radiomics features (shape n = 12; first order n = 16; texture n = 73) were extracted. Longitudinal repeatability of each feature was evaluated by Pearson correlation and coefficient of variance (CV_68% ). Interobserver feature value agreement was also quantified using intraclass correlation coefficient (ICC) and Bland-Altman analysis. A most repeatable radiomics feature set on both scanners was determined by feature coefficient of variance (CV_68% <5%), ICC (>0.75), and the ratio of the interobserver difference to the interobserver mean δ<5%.

RESULTS

No trend of radiomics feature value changed with time. Longitudinal feature repeatability CV_68% ranged 0.01-38.60% (mean/median: 12.5%/9.9%), and 0.01-40.47%, (8.49%/7.34%) on the scanners A and B. Shape features exhibited significantly better repeatability than first-order and texture features (all P < 0.01). Significant longitudinal repeatability difference was observed in texture features (P < 0.001) between the two scanners, but not in shape and first-order features (P > 0.30). First-order and texture features had smaller interobserver-dependent variation than acquisition-dependent variation. They also showed good interobserver agreement on both scanners (A:ICC = 0.80 ± 0.23; B:ICC = 0.80 ± 0.22), independent of acquisition repeatability. The repeatable radiomics features in common on both scanners, including 12 shape features, 0 first-order features, and 3 texture features, were determined as the most repeatable MRI radiomics feature set.

CONCLUSIONS

Radiomics features exhibited heterogeneous longitudinal repeatability, while the shape features were the most repeatable, in this phantom study with a 3D T1W TSE acquisition. The most repeatable radiomics feature set derived in this study should be helpful for the selection of reliable radiomics features in the future clinical use.

Harmonized pretreatment quantitative volume-based FDG-PET/CT parameters for prognosis of stage I-III breast cancer: Multicenter study

OBJECTIVES

This study investigated harmonized pretreatment volume-based quantitative FDG-PET/CT parameters in breast cancer patients for prognostic value.

RESULTS

During a median overall follow-up period of 5.3 years, 91 patients had recurrence and 40 died. Multivariate analysis of ER-positive/HER2-negative patients showed high maximum standardized uptake value (SUVmax) (p = 0.018), high total lesion glycolysis (TLG) (p = 0.010), and clinical N-classification (p = 0.0027) as independent negative predictors of RFS, while high maximum SUVmax (p = 0.037), advanced clinical T-classification (p = 0.030), and advanced TNM stage (p = 0.0067) were independent negative predictors of OS. For recurrence and death in HER2-positive patients, high total TLG (p = 0.037, p = 0.0048, respectively) and advanced TNM stage (p = 0.048, p = 0.046, respectively) were independent prediction factors. In the triple-negative group, independent factors related to recurrence and death were high maximum SUVmax (p = 0.0014, p = 0.0003, respectively) and advanced TNM stage (p < 0.0001, p < 0.0001, respectively).

MATERIALS AND METHODS

Records of 546 stage I-III invasive breast cancer patients, including 344 estrogen receptor (ER)-positive/human epidermal growth factor receptor 2 (HER2)-negative, 110 HER2-positive, and 92 triple-negative cases, treated at four institutions were reviewed retrospectively. Harmonized primary tumor and nodal maximum SUVmax, metabolic tumor volume (MTV), and TLG indicated in pretreatment FDG-PET/CT results were analyzed. Evaluations of relationships of clinicopathological factors, volume-based quantitative parameters, recurrence-free survival (RFS), and overall survival (OS) for each subtype were performed with a Cox proportional hazards model and log-rank test.

CONCLUSIONS

The results indicated that potential surrogate markers for prognosis in patients with the three main subtypes of operable breast cancer include harmonized pretreatment quantitative volume-based FDG-PET/CT parameters, particularly whole-lesion SUVmax and TLG.

Efficacy of cell proliferation imaging with 4DST PET/CT for predicting the prognosis of patients with esophageal cancer: a comparison study with FDG PET/CT

PURPOSE

4'-[Methyl-11C] thiothymidine (4DST) incorporates into DNA directly and is a PET tracer used for cell proliferation imaging. The aim of this study was to evaluate the prediction of prognosis with pretreatment 4DST PET/CT compared to fluorodeoxyglucose (FDG) PET/CT in patients with esophageal cancer.

METHODS

In this prospective study, we analyzed 46 patients (68.2 ± 10.0 years old) with pathologically proven esophageal squamous cell cancer who underwent pretreatment 4DST and FDG PET/CT. The maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), total lesion glycolysis (TLG), and total lesion proliferation (TLP) were measured for FDG and 4DST PET. The study endpoints were progression-free survival (PFS) and overall survival (OS). Patients' clinical backgrounds, including age, histological type, clinical stage, and surgical treatment, were adjusted using the Cox proportional-hazards model.

RESULTS

In the follow-up period (median 18.8 (interquartile range: 10.1-29.0) months), 26 and 19 patients showed disease progression and cancer-related death, respectively. After adjusting for clinical variables, only the 4DST parameters (SUVmax (p = 0.001) and TLP (p = 0.022)) were statistically significant for predicting PFS. FDG MTV (p = 0.031), 4DST SUVmax (p = 0.022), and TLP (p = 0.023) were statistically significant for predicting OS. Of the PET parameters, 4DST SUVmax yielded the highest adjusted hazard ratio for both PFS (4.88, 95% confidence intervals (CI): 1.83-12.97) and OS (4.19, 95% CI: 1.23-14.20).

CONCLUSION

Higher accumulation of 4DST in the primary tumor may lead to shorter OS and PFS. 4DST PET/CT is useful for predicting prognosis and may outperform FDG PET/CT.

Prognostic Value of Baseline Radiomic Features of 18F-FDG PET in Patients with Diffuse Large B-Cell Lymphoma

This study investigates whether baseline ¹⁸F-FDG PET radiomic features can predict survival outcomes in patients with diffuse large B-cell lymphoma (DLBCL). We retrospectively enrolled 83 patients diagnosed with DLBCL who underwent ¹⁸F-FDG PET scans before treatment. The patients were divided into the training cohort (n = 58) and the validation cohort (n = 25). Eighty radiomic features were extracted from the PET images for each patient. Least absolute shrinkage and selection operator regression were used to reduce the dimensionality within radiomic features. Cox proportional hazards model was used to determine the prognostic factors for progression-free survival (PFS) and overall survival (OS). A prognostic stratification model was built in the training cohort and validated in the validation cohort using Kaplan-Meier survival analysis. In the training cohort, run length non-uniformity (RLN), extracted from a gray level run length matrix (GLRLM), was independently associated with PFS (hazard ratio (HR) = 15.7, p = 0.007) and OS (HR = 8.64, p = 0.040). The International Prognostic Index was an independent prognostic factor for OS (HR = 2.63, p = 0.049). A prognostic stratification model was devised based on both risk factors, which allowed identification of three risk groups for PFS and OS in the training (p < 0.001 and p < 0.001) and validation (p < 0.001 and p = 0.020) cohorts. Our results indicate that the baseline ¹⁸F-FDG PET radiomic feature, RLN_GLRLM, is an independent prognostic factor for survival outcomes. Furthermore, we propose a prognostic stratification model that may enable tailored therapeutic strategies for patients with DLBCL.

Harmonization strategies for multicenter radiomics investigations

Carrying out large multicenter studies is one of the key goals to be achieved towards a faster transfer of the radiomics approach in the clinical setting. This requires large-scale radiomics data analysis, hence the need for integrating radiomic features extracted from images acquired in different centers. This is challenging as radiomic features exhibit variable sensitivity to differences in scanner model, acquisition protocols and reconstruction settings, which is similar to the so-called 'batch-effects' in genomics studies. In this review we discuss existing methods to perform data integration with the aid of reducing the unwanted variation associated with batch effects. We also discuss the future potential role of deep learning methods in providing solutions for addressing radiomic multicentre studies.

Technical Note: ROdiomiX: A validated software for radiomics analysis of medical images in radiation oncology

PURPOSE

This study introduces an in-house-designed software platform (ROdiomiX) for the radiomics analysis of medical images in radiation oncology. ROdiomiX is a MATLAB-based framework for the computation of radiomic features and feature aggregation techniques in compliance with the Image-Biomarker-Standardization-Initiative (IBSI) guidelines, which includes preprocessing protocols and quantitative benchmark results for analysis of computational phantom images.

METHODS AND MATERIALS

The ROdiomiX software system consists of a series of computation cores implemented on the basis of the guidelines proposed by the IBSI. It is capable of quantitative computation of the following 11 different feature categories: Local-Intensity, Intensity-Histogram, Intensity-Based-Statistical, Intensity-Volume-Histogram, Gray-Level-Co-occurrence, Gray-Level-Run-Length, Gray-Level-Size-Zone, Gray-Level-Distance-Zone, Neighborhood-Grey-Tone-Difference, Neighboring-Grey-Level-Dependence, and Morphological feature. ROdiomiX was validated against benchmark values for the IBSI 3D digital phantom, as well as one designed in-house (HFH). The intraclass correlation coefficient (ICC) for estimating the degree of absolute agreement between ROdiomiX computation and benchmark values for different features at the 95% confidence level (CL) was used for comparison.

RESULTS

Among the 11 feature categories with 149 total features including 10 different feature aggregation methods (following the IBSI guidelines), the percent difference between absolute feature values computed by the ROdiomiX software and benchmark values reported for IBSI and HFH digital phantoms were 0.14% + 0.43% and 0.11% + 0.27%, respectively. The ICC values were >0.997 for all ten feature categories for both the IBSI and HFH digital phantoms.

CONCLUSION

The authors successfully developed a platform for computation of quantitative radiomic features. The image preprocessing and computational software cores were designed following the procedures specified by the IBSI. Benchmarking testing was in excellent agreement against the IBSI- and HFH-designed computational phantoms.

Artificial intelligence applications for oncological positron emission tomography imaging

Positron emission tomography (PET), a functional and dynamic molecular imaging technique, is generally used to reveal tumors' biological behavior. Radiomics allows a high-throughput extraction of multiple features from images with artificial intelligence (AI) approaches and develops rapidly worldwide. Quantitative and objective features of medical images have been explored to recognize reliable biomarkers, with the development of PET radiomics. This paper will review the current clinical exploration of PET-based classical machine learning and deep learning methods, including disease diagnosis, the prediction of histological subtype, gene mutation status, tumor metastasis, tumor relapse, therapeutic side effects, therapeutic intervention and evaluation of prognosis. The applications of AI in oncology will be mainly discussed. The image-guided biopsy or surgery assisted by PET-based AI will be introduced as well. This paper aims to present the applications and methods of AI for PET imaging, which may offer important details for further clinical studies. Relevant precautions are put forward and future research directions are suggested.

A radiomics pipeline dedicated to Breast MRI: validation on a multi-scanner phantom study

OBJECTIVE

Quantitative analysis in MRI is challenging due to variabilities in intensity distributions across patients, acquisitions and scanners and suffers from bias field inhomogeneity. Radiomic studies are impacted by these effects that affect radiomic feature values. This paper describes a dedicated pipeline to increase reproducibility in breast MRI radiomic studies.

MATERIALS AND METHODS

T1, T2, and T1-DCE MR images of two breast phantoms were acquired using two scanners and three dual breast coils. Images were retrospectively corrected for bias field inhomogeneity and further normalised using Z score or histogram matching. Extracted radiomic features were harmonised between coils by the ComBat method. The whole pipeline was assessed qualitatively and quantitatively using statistical comparisons on two series of radiomic feature values computed in the gel mimicking the normal breast tissue or in dense lesions.

RESULTS

Intra and inter-acquisition variabilities were strongly reduced by the standardisation pipeline. Harmonisation by ComBat lowered the percentage of radiomic features significantly different between the three coils from 87% after bias field correction and MR normalisation to 3% in the gel, while preserving or improving performance of lesion classification in the phantoms.

DISCUSSION

A dedicated standardisation pipeline was developed to reduce variabilities in breast MRI, which paves the way for robust multi-scanner radiomic studies but needs to be assessed on patient data.

Radiomics in PET/CT: Current Status and Future AI-Based Evolutions

This short review aims at providing the readers with an update on the current status, as well as future perspectives in the quickly evolving field of radiomics applied to the field of PET/CT imaging. Numerous pitfalls have been identified in study design, data acquisition, segmentation, features calculation and modeling by the radiomics community, and these are often the same issues across all image modalities and clinical applications, however some of these are specific to PET/CT (and SPECT/CT) imaging and therefore the present paper focuses on those. In most cases, recommendations and potential methodological solutions do exist and should therefore be followed to improve the overall quality and reproducibility of published studies. In terms of future evolutions, the techniques from the larger field of artificial intelligence (AI), including those relying on deep neural networks (also known as deep learning) have already shown impressive potential to provide solutions, especially in terms of automation, but also to maybe fully replace the tools the radiomics community has been using until now in order to build the usual radiomics workflow. Some important challenges remain to be addressed before the full impact of AI may be realized but overall the field has made striking advances over the last few years and it is expected advances will continue at a rapid pace.

A Role for FDG PET Radiomics in Personalized Medicine?

Radiomics describes the extraction of multiple features from medical images, including molecular imaging modalities, that with bioinformatic approaches, provide additional clinically relevant information that may be invisible to the human eye. This information may complement standard radiological interpretation with data that may better characterize a disease or that may provide predictive or prognostic information. Progressing from predefined image features, often describing heterogeneity of voxel intensities within a volume of interest, there is increasing use of machine learning to classify disease characteristics and deep learning methods based on artificial neural networks that can learn features without a priori definition and without the need for preprocessing of images. There have been advances in standardization and harmonization of methods to a level that should support multicenter studies. However, in this relatively early phase of research in the field, there are limited aspects that have been adopted into routine practice. Most of the reports in the molecular imaging field describe radiomic approaches in cancer using 18F-fluorodeoxyglucose positron emission tomography (18F-FDG-PET). In this review, we will describe radiomics in molecular imaging and summarize the pertinent literature in lung cancer where reports are most prevalent and mature.

Harmonization of radiomic feature variability resulting from differences in CT image acquisition and reconstruction: assessment in a cadaveric liver

Studies investigating the effects of computed tomography (CT) image acquisition and reconstruction parameters have mostly been limited to non-human phantoms to limit exposure to patients. This study investigates these variations using a cadaveric liver and determines harmonization methods to mitigate these variations. A reference CT scan of a cadaveric liver was acquired along with 16 modified scans. Modified scans were obtained with altered image acquisition and reconstruction parameters. In each slice, the liver was segmented and used to calculate 142 features. Student's t-tests assessed differences between reference and modified scans for each feature after correcting for multiple comparisons. Features were harmonized between reference and modified scans using histogram normalization, pixel resampling, Butterworth filtering, resampling and filtering combined, and ComBat harmonization. The number of features reflecting significant differences before and after harmonization were compared across imaging parameters. Reducing the field-of-view (FOV) and using coronal instead of axial scans resulted in the greatest number of features reflecting significant differences (67.6%, and 35.9%, respectively) and resulted in the greatest median relative change in feature values (25.4% and 18.2%, respectively). Changes in tube voltage, pitch, and slice interval resulted in the smallest number of features reflecting significance (0.7%) with median relative changes in feature <2%. Histogram normalization reduced or maintained the number of significantly different features for all scans, while ComBat reduced the number of significantly different features to zero for all scans. The remaining harmonization methods had mixed effects: resampling reduced the number of features reflecting significant differences for half of the imaging parameters, while filtering alone and filtering combined with resampling both reduced the number of features reflecting significance for 10 of the 16 parameters. The dependence of radiomic features on image acquisition and reconstruction parameters varies in a cadaveric liver; however, various harmonization methods have shown promise in mitigating these dependencies, particularly ComBat.

Correlations between baseline 18F-FDG PET tumour parameters and circulating DNA in diffuse large B cell lymphoma and Hodgkin lymphoma

Background

¹⁸F-FDG PET/CT is a standard for many B cell malignancies, while blood DNA measurements are emerging tools. Our objective was to evaluate the correlations between baseline PET parameters and circulating DNA in diffuse large B cell lymphoma (DLBCL) and classical Hodgkin lymphoma (cHL).

Methods

Twenty-seven DLBCL and forty-eight cHL were prospectively included. Twelve PET parameters were analysed. Spearman’s correlations were used to compare PET parameters each other and to circulating cell-free DNA ([cfDNA]) and circulating tumour DNA ([ctDNA]). p values were controlled by Benjamini–Hochberg correction.

Results

Among the PET parameters, three different clusters for tumour burden, fragmentation/massiveness and dispersion parameters were observed. Some PET parameters were significantly correlated with blood DNA parameters, including the total metabolic tumour surface (TMTS) describing the tumour–host interface (e.g. ρ = 0.81 p < 0.001 for [ctDNA] of DLBLC), the tumour median distance between the periphery and the centroid (medPCD) describing the tumour’s massiveness (e.g. ρ = 0.81 p < 0.001 for [ctDNA] of DLBLC) and the volume of the bounding box including tumours (TumBB) describing the disease’s dispersion (e.g. ρ = 0.83 p < 0.001 for [ctDNA] of DLBLC).

Conclusions

Some PET parameters describing tumour burden, fragmentation/massiveness and dispersion are significantly correlated with circulating DNA parameters of DLBCL and cHL patients. These results could help to understand the pathophysiology of B cell malignancies.

How can we combat multicenter variability in MR radiomics? Validation of a correction procedure

OBJECTIVE

Test a practical realignment approach to compensate the technical variability of MR radiomic features.

METHODS

T1 phantom images acquired on 2 scanners, FLAIR and contrast-enhanced T1-weighted (CE-T1w) images of 18 brain tumor patients scanned on both 1.5-T and 3-T scanners, and 36 T2-weighted (T2w) images of prostate cancer patients scanned in one of two centers were investigated. The ComBat procedure was used for harmonizing radiomic features. Differences in statistical distributions in feature values between 1.5- and 3-T images were tested before and after harmonization. The prostate studies were used to determine the impact of harmonization to distinguish between Gleason grades (GGs).

RESULTS

In the phantom data, 40 out of 42 radiomic feature values were significantly different between the 2 scanners before harmonization and none after. In white matter regions, the statistical distributions of features were significantly different (p < 0.05) between the 1.5- and 3-T images for 37 out of 42 features in both FLAIR and CE-T1w images. After harmonization, no statistically significant differences were observed. In brain tumors, 41 (FLAIR) or 36 (CE-T1w) out of 42 features were significantly different between the 1.5- and 3-T images without harmonization, against 1 (FLAIR) or none (CE-T1w) with harmonization. In prostate studies, 636 radiomic features were significantly different between GGs after harmonization against 461 before. The ability to distinguish between GGs using radiomic features was increased after harmonization.

CONCLUSION

ComBat harmonization efficiently removes inter-center technical inconsistencies in radiomic feature values and increases the sensitivity of studies using data from several scanners.

KEY POINTS

• Radiomic feature values obtained using different MR scanners or imaging protocols can be harmonized by combining off-the-shelf image standardization and feature realignment procedures. • Harmonized radiomic features enable one to pool data from different scanners and centers without a substantial loss of statistical power caused by intra- and inter-center variability. • The proposed realignment method is applicable to radiomic features from different MR sequences and tumor types and does not rely on any phantom acquisition.

Radiogenomics of lung cancer

Machine learning (ML) and artificial intelligence (AI) are aiding in improving sensitivity and specificity of diagnostic imaging. The rapid adoption of these advanced ML algorithms is transforming imaging analysis; taking us from noninvasive detection of pathology to noninvasive precise diagnosis of the pathology by identifying whether detected abnormality is a secondary to infection, inflammation and/or neoplasm. This is led to the emergence of “Radiobiogenomics”; referring to the concept of identifying biologic (genomic, proteomic) alterations in the detected lesion. Radiobiogenomic involves image segmentation, feature extraction, and ML model to predict underlying tumor genotype and clinical outcomes. Lung cancer is the most common cause of cancer related death worldwide. There are several histologic subtypes of lung cancer, e.g., small cell lung cancer (SCLC), non-small cell lung cancer (NSCLC) (adenocarcinoma, squamous cell carcinoma). These variable histologic subtypes not only appear different at microscopic level, but these also differ at genetic and transcription level. This intrinsic heterogeneity reveals itself as different morphologic appearances on diagnostic imaging, such as CT, PET/CT and MRI. Traditional evaluation of imaging findings of lung cancer is limited to morphologic characteristics, such as lesion size, margins, density. Radiomics takes image analysis a step further by looking at imaging phenotype with higher order statistics in efforts to quantify intralesional heterogeneity. This heterogeneity, in turn, can be potentially used to extract intralesional genomic and proteomic data. This review aims to highlight novel concepts in ML and AI and their potential applications in identifying radiobiogenomics of lung cancer.

Characterization of FDG PET Images Using Texture Analysis in Tumors of the Gastro-Intestinal Tract: A Review

Radiomics or textural feature extraction obtained from positron emission tomography (PET) images through complex mathematical models of the spatial relationship between multiple image voxels is currently emerging as a new tool for assessing intra-tumoral heterogeneity in medical imaging. In this paper, available literature on texture analysis using FDG PET imaging in patients suffering from tumors of the gastro-intestinal tract is reviewed. While texture analysis of FDG PET images appears clinically promising, due to the lack of technical specifications, a large variability in the implemented methodology used for texture analysis and lack of statistical robustness, at present, no firm conclusions can be drawn regarding the predictive or prognostic value of FDG PET texture analysis derived indices in patients suffering from gastro-enterologic tumors. In order to move forward in this field, a harmonized image acquisition and processing protocol as well as a harmonized protocol for texture analysis of tumor volumes, allowing multi-center studies excluding statistical biases should be considered. Furthermore, the complementary and additional value of CT-imaging, as part of the PET/CT imaging technique, warrants exploration.

Radiomics in medical imaging-"how-to" guide and critical reflection

Radiomics is a quantitative approach to medical imaging, which aims at enhancing the existing data available to clinicians by means of advanced mathematical analysis. Through mathematical extraction of the spatial distribution of signal intensities and pixel interrelationships, radiomics quantifies textural information by using analysis methods from the field of artificial intelligence. Various studies from different fields in imaging have been published so far, highlighting the potential of radiomics to enhance clinical decision-making. However, the field faces several important challenges, which are mainly caused by the various technical factors influencing the extracted radiomic features.The aim of the present review is twofold: first, we present the typical workflow of a radiomics analysis and deliver a practical "how-to" guide for a typical radiomics analysis. Second, we discuss the current limitations of radiomics, suggest potential improvements, and summarize relevant literature on the subject.

Metabolic radiogenomics in lung cancer: associations between FDG PET image features and oncogenic signaling pathway alterations

This study investigated the associations between image features extracted from tumor ¹⁸F-fluorodeoxyglucose (FDG) uptake and genetic alterations in patients with lung cancer. A total of 137 patients (age, 62.7 ± 10.2 years) who underwent FDG positron emission tomography/computed tomography (PET/CT) and targeted deep sequencing analysis for a tumor lesion, comprising 61 adenocarcinoma (ADC), 31 squamous cell carcinoma (SQCC), and 45 small cell lung cancer (SCLC) patients, were enrolled in this study. From the tumor lesions, 86 image features were extracted, and 381 genes were assessed. PET features were associated with genetic mutations: 41 genes with 24 features in ADC; 35 genes with 22 features in SQCC; and 43 genes with 25 features in SCLC (FDR < 0.05). Clusters based on PET features showed an association with alterations in oncogenic signaling pathways: Cell cycle and WNT signaling pathways in ADC (p = 0.023, p = 0.035, respectively); Cell cycle, p53, and WNT in SQCC (p = 0.045, 0.009, and 0.029, respectively); and TGFβ in SCLC (p = 0.030). In addition, SUV_peak and SUV_max were associated with a mutation of the TGFβ signaling pathway in ADC (FDR = 0.001, < 0.001). In this study, PET image features had significant associations with alterations in genes and oncogenic signaling pathways in patients with lung cancer.

Intratumor Heterogeneity Assessed by 18F-FDG PET/CT Predicts Treatment Response and Survival Outcomes in Patients with Hodgkin Lymphoma

RATIONALE AND OBJECTIVES

Radiomic analysis of ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) images enables the extraction of quantitative information of intratumour heterogeneity. This study investigated whether the baseline ¹⁸F-FDG PET/CT radiomics can predict treatment response and survival outcomes in patients with Hodgkin lymphoma (HL).

MATERIALS AND METHODS

Thirty-five patients diagnosed with HL who underwent ¹⁸F-FDG PET/CT scans before and during chemotherapy were retrospectively enrolled in this investigation. For each patient, we extracted 709 radiomic features from pretreatment PET/CT images. Clinical variables (age, gender, B symptoms, bulky tumor, and disease stage) and radiomic signatures (intensity, texture, and wavelet) were analyzed according to response to therapy, progression-free survival (PFS), and overall survival (OS). Receiver operating characteristic curve, logistic regression, and Cox proportional hazards model were used to examine potential predictive and prognostic factors.

RESULTS

High-intensity run emphasis (HIR) of PET and run-length nonuniformity (RLNU) of CT extracted from gray-level run-length matrix (GLRM) in high-frequency wavelets were independent predictive factors for the treatment response (odds ratio [OR] = 36.4, p = 0.014; OR = 30.4, p = 0.020). Intensity nonuniformity (INU) of PET and wavelet short run emphasis (SRE) of CT from GLRM and Ann Arbor stage were independently related to PFS (hazard ratio [HR] = 9.29, p = 0.023; HR = 18.40, p = 0.012; HR = 7.46, p = 0.049). Zone-size nonuniformity (ZSNU) of PET from gray-level size zone matrix (GLSZM) was independently associated with OS (HR = 41.02, p = 0.001). Based on these factors, a prognostic stratification model was devised for the risk stratification of patients. The proposed model allowed the identification of four risk groups for PFS and OS (p < 0.001 and p < 0.001).

CONCLUSION

HIR_{_}GLRM_PET and RLNU_{_}GLRM_CT in high-frequency wavelets serve as independent predictive factors for treatment response. ZSNU_{_}GLSZM_PET, INU_{_}GLRM_PET, and wavelet SRE_{_}GLRM_CT serve as independent prognostic factors for survival outcomes. The present study proposes a prognostic stratification model that may be clinically beneficial in guiding risk-adapted treatment strategies for patients with HL.

Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test-retest and image registration analyses

PURPOSE

To assess the repeatability of radiomic features in magnetic resonance (MR) imaging of glioblastoma (GBM) tumors with respect to test-retest, different image registration approaches and inhomogeneity bias field correction.

METHODS

We analyzed MR images of 17 GBM patients including T1- and T2-weighted images (performed within the same imaging unit on two consecutive days). For image segmentation, we used a comprehensive segmentation approach including entire tumor, active area of tumor, necrotic regions in T1-weighted images, and edema regions in T2-weighted images (test studies only; registration to retest studies is discussed next). Analysis included N3, N4 as well as no bias correction performed on raw MR images. We evaluated 20 image registration approaches, generated by cross-combination of four transformation and five cost function methods. In total, 714 images (17 patients × 2 images × ((4 transformations × 5 cost functions) + 1 test image) and 2856 segmentations (714 images × 4 segmentations) were prepared for feature extraction. Various radiomic features were extracted, including the use of preprocessing filters, specifically wavelet (WAV) and Laplacian of Gaussian (LOG), as well as discretization into fixed bin width and fixed bin count (16, 32, 64, 128, and 256), Exponential, Gradient, Logarithm, Square and Square Root scales. Intraclass correlation coefficients (ICC) were calculated to assess the repeatability of MRI radiomic features (high repeatability defined as ICC ≥ 95%).

RESULTS

In our ICC results, we observed high repeatability (ICC ≥ 95%) with respect to image preprocessing, different image registration algorithms, and test-retest analysis, for example: RLNU and GLNU from GLRLM, GLNU and DNU from GLDM, Coarseness and Busyness from NGTDM, GLNU and ZP from GLSZM, and Energy and RMS from first order. Highest fraction (percent) of repeatable features was observed, among registration techniques, for the method Full Affine transformation with 12 degrees of freedom using Mutual Information cost function (mean 32.4%), and among image processing methods, for the method Laplacian of Gaussian (LOG) with Sigma (2.5-4.5 mm) (mean 78.9%). The trends were relatively consistent for N4, N3, or no bias correction.

CONCLUSION

Our results showed varying performances in repeatability of MR radiomic features for GBM tumors due to test-retest and image registration. The findings have implications for appropriate usage in diagnostic and predictive models.

Standardization of brain MR images across machines and protocols: bridging the gap for MRI-based radiomics

Radiomics relies on the extraction of a wide variety of quantitative image-based features to provide decision support. Magnetic resonance imaging (MRI) contributes to the personalization of patient care but suffers from being highly dependent on acquisition and reconstruction parameters. Today, there are no guidelines regarding the optimal pre-processing of MR images in the context of radiomics, which is crucial for the generalization of published image-based signatures. This study aims to assess the impact of three different intensity normalization methods (Nyul, WhiteStripe, Z-Score) typically used in MRI together with two methods for intensity discretization (fixed bin size and fixed bin number). The impact of these methods was evaluated on first- and second-order radiomics features extracted from brain MRI, establishing a unified methodology for future radiomics studies. Two independent MRI datasets were used. The first one (DATASET1) included 20 institutional patients with WHO grade II and III gliomas who underwent post-contrast 3D axial T1-weighted (T1w-gd) and axial T2-weighted fluid attenuation inversion recovery (T2w-flair) sequences on two different MR devices (1.5 T and 3.0 T) with a 1-month delay. Jensen–Shannon divergence was used to compare pairs of intensity histograms before and after normalization. The stability of first-order and second-order features across the two acquisitions was analysed using the concordance correlation coefficient and the intra-class correlation coefficient. The second dataset (DATASET2) was extracted from the public TCIA database and included 108 patients with WHO grade II and III gliomas and 135 patients with WHO grade IV glioblastomas. The impact of normalization and discretization methods was evaluated based on a tumour grade classification task (balanced accuracy measurement) using five well-established machine learning algorithms. Intensity normalization highly improved the robustness of first-order features and the performances of subsequent classification models. For the T1w-gd sequence, the mean balanced accuracy for tumour grade classification was increased from 0.67 (95% CI 0.61–0.73) to 0.82 (95% CI 0.79–0.84, P = .006), 0.79 (95% CI 0.76–0.82, P = .021) and 0.82 (95% CI 0.80–0.85, P = .005), respectively, using the Nyul, WhiteStripe and Z-Score normalization methods compared to no normalization. The relative discretization makes unnecessary the use of intensity normalization for the second-order radiomics features. Even if the bin number for the discretization had a small impact on classification performances, a good compromise was obtained using the 32 bins considering both T1w-gd and T2w-flair sequences. No significant improvements in classification performances were observed using feature selection. A standardized pre-processing pipeline is proposed for the use of radiomics in MRI of brain tumours. For models based on first- and second-order features, we recommend normalizing images with the Z-Score method and adopting an absolute discretization approach. For second-order feature-based signatures, relative discretization can be used without prior normalization. In both cases, 32 bins for discretization are recommended. This study may pave the way for the multicentric development and validation of MR-based radiomics biomarkers.

Reinventing radiation therapy with machine learning and imaging bio-markers (radiomics): State-of-the-art, challenges and perspectives

Radiation therapy is a pivotal cancer treatment that has significantly progressed over the last decade due to numerous technological breakthroughs. Imaging is now playing a critical role on deployment of the clinical workflow, both for treatment planning and treatment delivery. Machine-learning analysis of predefined features extracted from medical images, i.e. radiomics, has emerged as a promising clinical tool for a wide range of clinical problems addressing drug development, clinical diagnosis, treatment selection and implementation as well as prognosis. Radiomics denotes a paradigm shift redefining medical images as a quantitative asset for data-driven precision medicine. The adoption of machine-learning in a clinical setting and in particular of radiomics features requires the selection of robust, representative and clinically interpretable biomarkers that are properly evaluated on a representative clinical data set. To be clinically relevant, radiomics must not only improve patients' management with great accuracy but also be reproducible and generalizable. Hence, this review explores the existing literature and exposes its potential technical caveats, such as the lack of quality control, standardization, sufficient sample size, type of data collection, and external validation. Based upon the analysis of 165 original research studies based on PET, CT-scan, and MRI, this review provides an overview of new concepts, and hypotheses generating findings that should be validated. In particular, it describes evolving research trends to enhance several clinical tasks such as prognostication, treatment planning, response assessment, prediction of recurrence/relapse, and prediction of toxicity. Perspectives regarding the implementation of an AI-based radiotherapy workflow are presented.

FDG PET versus CT radiomics to predict outcome in malignant pleural mesothelioma patients

BACKGROUND

Careful selection of malignant pleural mesothelioma (MPM) patients for curative treatment is of highest importance, as the multimodal treatment regimen is challenging for patients and harbors a high risk of substantial toxicity. Radiomics-a quantitative method for image analysis-has shown its prognostic ability in different tumor entities and could therefore play an important role in optimizing patient selection for radical cancer treatment. So far, radiomics as a prognostic tool in MPM was not investigated.

MATERIALS AND METHODS

This study is based on 72 MPM patients treated with surgery in a curative intent at our institution between 2009 and 2017. Pre-treatment Fluorine-18 fluorodeoxyglucose (FDG) PET and CT scans were used for radiomics outcome modeling. After extraction of 1404 CT and 1410 FDG PET features from each image, a preselection by principal component analysis was performed to include only robust, non-redundant features for the cox regression to predict the progression-free survival (PFS) and the overall survival (OS). Results were validated on a separate cohort. Additionally, SUVmax and SUVmean, and volume were tested for their prognostic ability for PFS and OS.

RESULTS

For the PFS a concordance index (c-index) of 0.67 (95% CI 0.52-0.82) and 0.66 (95% CI 0.57-0.78) for the training cohort (n = 36) and internal validation cohort (n = 36), respectively, were obtained for the PET radiomics model. The PFS advantage of the low-risk group translated also into an OS advantage. On CT images, no radiomics model could be trained. SUV max and SUV mean were also not prognostic in terms of PFS and OS.

CONCLUSION

We were able to build a successful FDG PET radiomics model for the prediction of PFS in MPM. Radiomics could serve as a tool to aid clinical decision support systems for treatment of MPM in future.

Longitudinal ComBat: A method for harmonizing longitudinal multi-scanner imaging data

While aggregation of neuroimaging datasets from multiple sites and scanners can yield increased statistical power, it also presents challenges due to systematic scanner effects. This unwanted technical variability can introduce noise and bias into estimation of biological variability of interest. We propose a method for harmonizing longitudinal multi-scanner imaging data based on ComBat, a method originally developed for genomics and later adapted to cross-sectional neuroimaging data. Using longitudinal cortical thickness measurements from 663 participants in the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, we demonstrate the presence of additive and multiplicative scanner effects in various brain regions. We compare estimates of the association between diagnosis and change in cortical thickness over time using three versions of the ADNI data: unharmonized data, data harmonized using cross-sectional ComBat, and data harmonized using longitudinal ComBat. In simulation studies, we show that longitudinal ComBat is more powerful for detecting longitudinal change than cross-sectional ComBat and controls the type I error rate better than unharmonized data with scanner included as a covariate. The proposed method would be useful for other types of longitudinal data requiring harmonization, such as genomic data, or neuroimaging studies of neurodevelopment, psychiatric disorders, or other neurological diseases.

Functional imaging using radiomic features in assessment of lymphoma

Lymphomas are typically large, well-defined, and relatively homogeneous tumors, and therefore represent ideal targets for the use of radiomics. Of the available functional imaging tests, [18F]FDG-PET for body lymphoma and diffusion-weighted MRI (DWI) for central nervous system (CNS) lymphoma are of particular interest. The current literature suggests that two main applications for radiomics in lymphoma show promise: differentiation of lymphomas from other tumors, and lymphoma treatment response and outcome prognostication. In particular, encouraging results reported in the limited number of presently available studies that utilize functional imaging suggest that (1) MRI-based radiomics enables differentiation of CNS lymphoma from glioblastoma, and (2) baseline [18F]FDG-PET radiomics could be useful for survival prognostication, adding to or even replacing commonly used metrics such as standardized uptake values and metabolic tumor volume. However, due to differences in biological and clinical characteristics of different lymphoma subtypes and an increasing number of treatment options, more data are required to support these findings. Furthermore, a consensus on several critical steps in the radiomics workflow -most importantly, image reconstruction and post processing, lesion segmentation, and choice of classification algorithm- is desirable to ensure comparability of results between research institutions.

Performance comparison of modified ComBat for harmonization of radiomic features for multicenter studies

Multicenter studies are needed to demonstrate the clinical potential value of radiomics as a prognostic tool. However, variability in scanner models, acquisition protocols and reconstruction settings are unavoidable and radiomic features are notoriously sensitive to these factors, which hinders pooling them in a statistical analysis. A statistical harmonization method called ComBat was developed to deal with the "batch effect" in gene expression microarray data and was used in radiomics studies to deal with the "center-effect". Our goal was to evaluate modifications in ComBat allowing for more flexibility in choosing a reference and improving robustness of the estimation. Two modified ComBat versions were evaluated: M-ComBat allows to transform all features distributions to a chosen reference, instead of the overall mean, providing more flexibility. B-ComBat adds bootstrap and Monte Carlo for improved robustness in the estimation. BM-ComBat combines both modifications. The four versions were compared regarding their ability to harmonize features in a multicenter context in two different clinical datasets. The first contains 119 locally advanced cervical cancer patients from 3 centers, with magnetic resonance imaging and positron emission tomography imaging. In that case ComBat was applied with 3 labels corresponding to each center. The second one contains 98 locally advanced laryngeal cancer patients from 5 centers with contrast-enhanced computed tomography. In that specific case, because imaging settings were highly heterogeneous even within each of the five centers, unsupervised clustering was used to determine two labels for applying ComBat. The impact of each harmonization was evaluated through three different machine learning pipelines for the modelling step in predicting the clinical outcomes, across two performance metrics (balanced accuracy and Matthews correlation coefficient). Before harmonization, almost all radiomic features had significantly different distributions between labels. These differences were successfully removed with all ComBat versions. The predictive ability of the radiomic models was always improved with harmonization and the improved ComBat provided the best results. This was observed consistently in both datasets, through all machine learning pipelines and performance metrics. The proposed modifications allow for more flexibility and robustness in the estimation. They also slightly but consistently improve the predictive power of resulting radiomic models.

External validation of radiomics-based predictive models in low-dose CT screening for early lung cancer diagnosis

PURPOSE

Low-dose CT screening allows early lung cancer detection, but is affected by frequent false positive results, inter/intra observer variation and uncertain diagnoses of lung nodules. Radiomics-based models have recently been introduced to overcome these issues, but limitations in demonstrating their generalizability on independent datasets are slowing their introduction to clinic. The aim of this study is to evaluate two radiomics-based models to classify malignant pulmonary nodules in low-dose CT screening, and to externally validate them on an independent cohort. The effect of a radiomics features harmonization technique is also investigated to evaluate its impact on the classification of lung nodules from a multicenter data.

METHODS

Pulmonary nodules from two independent cohorts were considered in this study; the first cohort (110 subjects, 113 nodules) was used to train prediction models, and the second cohort (72 nodules) to externally validate them. Literature-based radiomics features were extracted and, after feature selection, used as predictive variables in models for malignancy identification. An in-house prediction model based on artificial neural network (ANN) was implemented and evaluated, along with an alternative model from the literature, based on a support vector machine (SVM) classifier coupled with a least absolute shrinkage and selection operator (LASSO). External validation was performed on the second cohort to evaluate models' generalization ability. Additionally, the impact of the Combat harmonization method was investigated to compensate for multicenter datasets variabilities. A new training of the models based on harmonized features was performed on the first cohort, then tested separately on the harmonized and non-harmonized features of the second cohort.

RESULTS

Preliminary results showed a good accuracy of the investigated models in distinguishing benign from malignant pulmonary nodules with both sets of radiomics features (i.e., non-harmonized and harmonized). The performance of the models, quantified in terms of Area Under the Curve (AUC), was > 0.89 in the training set and > 0.82 in the external validation set for all the investigated scenarios, outperforming the clinical standard (AUC of 0.76). Slightly higher performance was observed for the SVM-LASSO model than the ANN in the external dataset, although they did not result significantly different. For both harmonized and non-harmonized features, no statistical difference was found between Receiver operating characteristic (ROC) curves related to training and test set for both models.

CONCLUSIONS

Although no significant improvements were observed when applying the Combat harmonization method, both in-house and literature-based models were able to classify lung nodules with good generalization to an independent dataset, thus showing their potential as tools for clinical decision-making in lung cancer screening.

Radiomics for precision medicine: Current challenges, future prospects, and the proposal of a new framework

The advancement of artificial intelligence concurrent with the development of medical imaging techniques provided a unique opportunity to turn medical imaging from mostly qualitative, to further quantitative and mineable data that can be explored for the development of clinical decision support systems (cDSS). Radiomics, a method for the high throughput extraction of hand-crafted features from medical images, and deep learning -the data driven modeling techniques based on the principles of simplified brain neuron interactions, are the most researched quantitative imaging techniques. Many studies reported on the potential of such techniques in the context of cDSS. Such techniques could be highly appealing due to the reuse of existing data, automation of clinical workflows, minimal invasiveness, three-dimensional volumetric characterization, and the promise of high accuracy and reproducibility of results and cost-effectiveness. Nevertheless, there are several challenges that quantitative imaging techniques face, and need to be addressed before the translation to clinical use. These challenges include, but are not limited to, the explainability of the models, the reproducibility of the quantitative imaging features, and their sensitivity to variations in image acquisition and reconstruction parameters. In this narrative review, we report on the status of quantitative medical image analysis using radiomics and deep learning, the challenges the field is facing, propose a framework for robust radiomics analysis, and discuss future prospects.

Methodological framework for radiomics applications in Hodgkin's lymphoma

BACKGROUND

According to published data, radiomics features differ between lesions of refractory/relapsing HL patients from those of long-term responders. However, several methodological aspects have not been elucidated yet.

PURPOSE

The study aimed at setting up a methodological framework in radiomics applications in Hodgkin's lymphoma (HL), especially at (a) developing a novel feature selection approach, (b) evaluating radiomic intra-patient lesions' similarity, and (c) classifying relapsing refractory (R/R) vs non-(R/R) patients.

METHODS

We retrospectively included 85 patients (male:female = 52:33; median age 35 years, range 19-74). LIFEx (www.lifexsoft.org) was used for [18F]FDG-PET/CT segmentation and feature extraction. Features were a-priori selected if they were highly correlated or uncorrelated to the volume. Principal component analysis-transformed features were used to build the fingerprints that were tested to assess lesions' similarity, using the silhouette. For intra-patient similarity analysis, we used patients having multiple lesions only. To classify patients as non-R/R and R/R, the fingerprint considering one single lesion (fingerprint_One) and all lesions (fingerprint_All) was tested using Random Undersampling Boosting of Tree Ensemble (RUBTE).

RESULTS

HL fingerprints included up to 15 features. Intra-patient lesion similarity analysis resulted in mean/median silhouette values below 0.5 (low similarity especially in the non-R/R group). In the test set, the fingerprint_One classification accuracy was 62% (78% sensitivity and 53% specificity); the classification by RUBTE using fingerprint_All resulted in 82% accuracy (70% sensitivity and 88% specificity).

CONCLUSIONS

Lesion similarity analysis was developed, and it allowed to demonstrate that HL lesions were not homogeneous within patients in terms of radiomics signature. Therefore, a random target lesion selection should not be adopted for radiomics applications. Moreover, the classifier to predict R/R vs non-R/R performed the best when all the lesions were used.

Generative Adversarial Networks Improve the Reproducibility and Discriminative Power of Radiomic Features

Purpose

To assess the contribution of a generative adversarial network (GAN) to improve intermanufacturer reproducibility of radiomic features (RFs).

Materials and Methods

The authors retrospectively developed a cycle-GAN to translate texture information from chest radiographs acquired using one manufacturer (Siemens) to chest radiographs acquired using another (Philips), producing fake chest radiographs with different textures. The authors prospectively evaluated the ability of this texture-translation cycle-GAN to reduce the intermanufacturer variability of RFs extracted from the lung parenchyma. This study assessed the cycle-GAN's ability to fool several machine learning (ML) classifiers tasked with recognizing the manufacturer on the basis of chest radiography inputs. The authors also evaluated the cycle-GAN's ability to mislead radiologists who were asked to perform the same recognition task. Finally, the authors tested whether the cycle-GAN had an impact on radiomic diagnostic accuracy for chest radiography in patients with congestive heart failure (CHF).

Results

RFs, extracted from chest radiographs after the cycle-GAN's texture translation (fake chest radiographs), showed decreased intermanufacturer RF variability. Using cycle-GAN-generated chest radiographs as inputs, ML classifiers categorized the fake chest radiographs as belonging to the target manufacturer rather than to a native one. Moreover, cycle-GAN fooled two experienced radiologists who identified fake chest radiographs as belonging to a target manufacturer class. Finally, reducing intermanufacturer RF variability with cycle-GAN improved the discriminative power of RFs for patients without CHF versus patients with CHF (from 55% to 73.5%, P < .001).

Conclusion

Both ML classifiers and radiologists had difficulty recognizing the chest radiographs' manufacturer. The cycle-GAN improved RF intermanufacturer reproducibility and discriminative power for identifying patients with CHF. This deep learning approach may help counteract the sensitivity of RFs to differences in acquisition.Supplemental material is available for this article.© RSNA, 2020See also the commentary by Alderson in this issue.

Pre-Therapeutic Total Lesion Glycolysis on [18F]FDG-PET Enables Prognostication of 2-Year Progression-Free Survival in MALT Lymphoma Patients Treated with CD20-Antibody-Based Immunotherapy

PURPOSE

Standardized uptake values (SUV), total metabolic tumor volumes (TMTV), and total lesion glycolysis (TLG) based on positron emission tomography with 2-deoxy-2-[¹⁸F]fluoro-D-glucose ([¹⁸F]FDG/positron emission tomography (PET) are established outcome predictors in FDG-avid lymphomas. We therefore investigated whether these biomarkers also have prognostic value in extranodal marginal zone B cell lymphoma of the mucosa-associated lymphoid tissue (MALT lymphoma), with a focus on patients treated with anti-CD20 antibody-based immunotherapy.

PROCEDURES

Pre-therapeutic [¹⁸F]FDG/PET scans of 61 treatment-naïve MALT lymphoma patients, including 35 scheduled for anti-CD20 antibody-based immunotherapy, were included in this retrospective study. SUVmean, SUVmax, TMTV, and TLG were measured and tested for 2-year progression-free survival (PFS) prognostication, using Cox regression analyses. Receiver operating characteristic curves were used to determine optimal cutoffs for prognostic [¹⁸F]FDG/PET parameters, and Kaplan-Meier estimates with log rank tests were performed.

RESULTS

After 2 years, progression had occurred in 12/61 patients (CD20-anitbody group 6/35). TLG emerged as the only significant prognostic factor for 2-year PFS in the multivariate analyses with forward selection, both in entire cohort (hazard ratio HR, 1.001; 95 % CI, 1.001-1.002; P < 0.0001) and in the CD20-antibody group (HR, 1.001; 95 % CI, 1.001-1.002; P = 0.001). However, in the entire population, where 8/26 patients with a TLG > 90 (30.8 %) vs. 4/35 patients with a TLG ≤ 90 (11.4 %) showed progression within the 2-year observation period, TLG-based separation of risk groups failed (HR, 0.35; 95 % CI, 0.10-1.15; P = 0.069); whereas in the CD20-antibody group, where 6/16 patients with a TLG > 90 (37.5 %) vs. 0/19 patients with a TLG ≤ 90 (0.0 %) showed progression, risk group separation was successful (HR, 0.010; 95 % CI, 0.0001-8.068; P = 0.003).

CONCLUSIONS

TLG may improve early risk stratification of MALT lymphoma patients treated with CD20-antibody-based immunotherapy.

Nuclear medicine radiomics in precision medicine: why we can't do without artificial intelligence

In recent years, radiomics, defined as the extraction of large amounts of quantitative features from medical images, has gained emerging interest. Radiomics consists of the extraction of handcrafted features combined with sophisticated statistical methods or machine learning algorithms for modelling, or deep learning algorithms that both learn features from raw data and perform modelling. These features have the potential to serve as non-invasive biomarkers for tumor characterization, prognostic stratification and response prediction, thereby contributing to precision medicine. However, especially in nuclear medicine, variable results are obtained when using radiomics for these purposes. Individual studies show promising results, but due to small numbers of patients per study and little standardization, it is difficult to compare and validate results on other datasets. This review describes the radiomic pipeline, its applications and the increasing role of artificial intelligence within the field. Furthermore, the challenges that need to be overcome to achieve clinical translation are discussed, so that, eventually, radiomics, combined with clinical data and other biomarkers, can contribute to precision medicine, by providing the right treatment to the right patient, with the right dose, at the right time.

Radiogenomics Based on PET Imaging

Radiogenomics or imaging genomics is a novel omics strategy of associating imaging data with genetic information, which has the potential to advance personalized medicine. Imaging features extracted from PET or PET/CT enable assessment of in vivo functional and physiological activity and provide comprehensive tumor information non-invasively. However, PET features are considered secondary to features on conventional imaging, and there has not yet been a review of the radiogenomic approach using PET features. This review article summarizes the current state of PET-based radiogenomic research for cancer, which discusses some of its limitations and directions for future study.