The promise and limits of PET texture analysis

Patch-Based Texture Feature Extraction Towards Improved Clinical Task Performance

Texture features can capture microstructural patterns and tissue heterogeneity, playing a pivotal role in medical image analysis. Compared to deep learning-based features, texture features offer superior interpretability in clinical applications. However, as conventional texture features focus strictly on voxel-level statistical information, they fail to account for critical spatial heterogeneity between small tissue volumes, which may hold significant importance. To overcome this limitation, we propose novel 3D patch-based texture features and develop a radiomics analysis framework to validate the efficacy of our proposed features. Specifically, multi-scale 3D patches were created to construct patch patterns via k-means clustering. The multi-resolution images were discretized based on labels of the patterns, and then texture features were extracted to quantify the spatial heterogeneity between patches. Twenty-five cross-combination models of five feature selection methods and five classifiers were constructed. Our methodology was evaluated using two independent MRI datasets. Specifically, 145 breast cancer patients were included for axillary lymph node metastasis prediction, and 63 cervical cancer patients were enrolled for histological subtype prediction. Experimental results demonstrated that the proposed 3D patch-based texture features achieved an AUC of 0.76 in the breast cancer lymph node metastasis prediction task and an AUC of 0.94 in cervical cancer histological subtype prediction, outperforming conventional texture features (0.74 and 0.83, respectively). Our proposed features have successfully captured multi-scale patch-level texture representations, which could enhance the application of imaging biomarkers in the precise prediction of cancers and personalized therapeutic interventions.

Standardized Radiomics Analysis of Clinical Myocardial Perfusion Stress SPECT Images to Identify Coronary Artery Calcification

PURPOSE

Myocardial perfusion (MP) stress single-photon emission computed tomography (SPECT) is an established diagnostic test for patients suspected of coronary artery disease (CAD). Meanwhile, coronary artery calcification (CAC) scoring obtained from diagnostic CT is a highly sensitive test, offering incremental diagnostic information in identifying patients with significant CAD yet normal MP stress SPECT (MPSS) scans. However, after decades of wide utilization of MPSS, CAC is not commonly reimbursed (e.g. by the CMS), nor widely deployed in community settings. We studied the potential of complementary information deduced from the radiomics analysis of normal MPSS scans in predicting the CAC score.

METHODS

We collected data from 428 patients with normal (non-ischemic) MPSS (99mTc-sestamibi; consensus reading). A nuclear medicine physician verified iteratively reconstructed images (attenuation-corrected) to be free from fixed perfusion defects and artifactual attenuation. Three-dimensional images were automatically segmented into four regions of interest (ROIs), including myocardium and three vascular segments (left anterior descending [LAD]-left circumference [LCX]-right coronary artery [RCA]). We used our software package, standardized environment for radiomics analysis (SERA), to extract 487 radiomic features in compliance with the image biomarker standardization initiative (IBSI). Isotropic cubic voxels were discretized using fixed bin-number discretization (eight schemes). We first performed blind-to-outcome feature selection focusing on a priori usefulness, dynamic range, and redundancy of features. Subsequently, we performed univariate and multivariate machine learning analyses to predict CAC scores from i) selected radiomic features, ii) 10 clinical features, and iii) combined radiomics + clinical features. Univariate analysis invoked Spearman correlation with Benjamini-Hotchberg false-discovery correction. The multivariate analysis incorporated stepwise linear regression, where we randomly selected a 15% test set and divided the other 85% of data into 70% training and 30% validation sets. Training started from a constant (intercept) model, iteratively adding/removing features (stepwise regression), invoking the Akaike information criterion (AIC) to discourage overfitting. Validation was run similarly, except that the training output model was used as the initial model. We randomized training/validation sets 20 times, selecting the best model using log-likelihood for evaluation in the test set. Assessment in the test set was performed thoroughly by running the entire operation 50 times, subsequently employing Fisher's method to verify the significance of independent tests.

RESULTS

Unsupervised feature selection significantly reduced 8×487 features to 56. In univariate analysis, no feature survived the false-discovery rate (FDR) to directly correlate with CAC scores. Applying Fisher's method to the multivariate regression results demonstrated combining radiomics with the clinical features to enhance the significance of the prediction model across all cardiac segments.  Conclusions: Our standardized and statistically robust multivariate analysis demonstrated significant prediction of the CAC score for all cardiac segments when combining MPSS radiomic features with clinical features, suggesting radiomics analysis can add diagnostic or prognostic value to standard MPSS for wide clinical usage.

Radiomics analysis of pre-treatment F-18 FDG PET/CT for predicting response to transarterial radioembolization in liver tumors

Aim: To investigate the relationship between the textural features extracted from pre-treatment fluorine-18 fluorodeoxyglucose positron emission with computed tomography (F-18 FDG PET/CT) and the response to treatment in patients undergoing transarterial radioembolization (TARE) due to primary or metastatic liver tumors. Material and Method: A total of 25 liver lesions from the pre-treatment F-18 PET/CT images of 14 patients were segmented manually. Standard uptake value (SUV) metrics and radiomics features were extracted for each lesion. Metabolic treatment response was determined according to PERCIST criteria in 18F-FDG PET/CT imaging performed 2 months after the treatment. Feature selection was done with recursive feature elimination (RFE). The association between selected features and treatment response was evaluated with logistic regression analysis. Results: Eventually, 13 lesions responded to TARE, while 12 lesions remain stable or progressed. All standard uptake values and 27 out of 30 textural heterogeneity indicators were significantly higher in lesions that responded to treatment. SUVmax, kurtosis and dissimilarity features were selected by the RFE algorithm for the prediction of response to TARE. Logistic regression analysis revealed that all three parameters were significantly associated with treatment outcome. Conclusion: Textural features extracted from pre-treatment F-18 FDG PET/CT in patients undergoing TARE due to liver tumors are promising biomarkers that can be potentially used to predict metabolic treatment response.

The Machine Learning Model for Distinguishing Pathological Subtypes of Non-Small Cell Lung Cancer

Purpose

Machine learning models were developed and validated to identify lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) using clinical factors, laboratory metrics, and 2-deoxy-2[¹⁸F]fluoro-D-glucose ([¹⁸F]F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomic features.

Methods

One hundred and twenty non-small cell lung cancer (NSCLC) patients (62 LUAD and 58 LUSC) were analyzed retrospectively and randomized into a training group (n = 85) and validation group (n = 35). A total of 99 feature parameters—four clinical factors, four laboratory indicators, and 91 [¹⁸F]F-FDG PET/CT radiomic features—were used for data analysis and model construction. The Boruta algorithm was used to screen the features. The retained minimum optimal feature subset was input into ten machine learning to construct a classifier for distinguishing between LUAD and LUSC. Univariate and multivariate analyses were used to identify the independent risk factors of the NSCLC subtype and constructed the Clinical model. Finally, the area under the receiver operating characteristic curve (AUC) values, sensitivity, specificity, and accuracy (ACC) was used to validate the machine learning model with the best performance effect and Clinical model in the validation group, and the DeLong test was used to compare the model performance.

Results

Boruta algorithm selected the optimal subset consisting of 13 features, including two clinical features, two laboratory indicators, and nine PEF/CT radiomic features. The Random Forest (RF) model and Support Vector Machine (SVM) model in the training group showed the best performance. Gender (P=0.018) and smoking status (P=0.011) construct the Clinical model. In the validation group, the SVM model (AUC: 0.876, ACC: 0.800) and RF model (AUC: 0.863, ACC: 0.800) performed well, while Clinical model (AUC:0.712, ACC: 0.686) performed moderately. There was no significant difference between the RF and Clinical models, but the SVM model was significantly better than the Clinical model. 

Conclusions

The proposed SVM and RF models successfully identified LUAD and LUSC. The results indicate that the proposed model is an accurate and noninvasive predictive tool that can assist clinical decision-making, especially for patients who cannot have biopsies or where a biopsy fails.

Imbalanced Data Correction Based PET/CT Radiomics Model for Predicting Lymph Node Metastasis in Clinical Stage T1 Lung Adenocarcinoma

OBJECTIVES

To develop and validate the imbalanced data correction based PET/CT radiomics model for predicting lymph node metastasis (LNM) in clinical stage T1 lung adenocarcinoma (LUAD).

METHODS

A total of 183 patients (148/35 non-metastasis/LNM) with pathologically confirmed LUAD were retrospectively included. The cohorts were divided into training vs. validation cohort in a ratio of 7:3. A total of 487 radiomics features were extracted from PET and CT components separately for radiomics model construction. Four clinical features and seven PET/CT radiological features were extracted for traditional model construction. To balance the distribution of majority (non-metastasis) class and minority (LNM) class, the imbalance-adjustment strategies using ten data re-sampling methods were adopted. Three multivariate models (denoted as Traditional, Radiomics, and Combined) were constructed using multivariable logistic regression analysis, where the combined model incorporated all of the significant clinical, radiological, and radiomics features. One hundred times repeated Monte Carlo cross-validation was used to assess the application order of feature selection and imbalance-adjustment strategies in the machine learning pipeline. Prediction performance of each model was evaluated using the area under the receiver operating characteristic curve (AUC) and Geometric mean score (G-mean).

RESULTS

A total of 2 clinical parameters, 2 radiological features, 3 PET, and 5 CT radiomics features were significantly associated with LNM. The combined model with Edited Nearest Neighbors (ENN) re-sampling methods showed strong prediction performance than traditional model or radiomics model with the AUC of 0.94 (95%CI = 0.86-0.97) vs. 0.89 (95%CI = 0.79-0.93), 0.92 (95%CI = 0.85-0.97), and G-mean of 0.88 vs. 0.82, 0.80 in the training cohort, and the AUC of 0.75 (95%CI = 0.57-0.91) vs. 0.68 (95%CI = 0.36-0.83), 0.71 (95%CI = 0.48-0.83) and G-mean of 0.76 vs. 0.64, 0.51 in the validation cohort. The combination of performing feature selection before data re-sampling obtains a better result than the reverse combination (AUC 0.76 ± 0.06 vs. 0.70 ± 0.07, p<0.001).

CONCLUSIONS

The combined model (consisting of age, histological type, C/T ratio, MATV, and radiomics signature) integrated with ENN re-sampling methods had strong lymph node metastasis prediction performance for imbalance cohorts in clinical stage T1 LUAD. Radiomics signatures extracted from PET/CT images could provide complementary prediction information compared with traditional model.

Baseline 18F-FDG PET textural features as predictors of response to chemotherapy in diffuse large B-cell lymphoma

PURPOSE

We sought to investigate the performance of radiomics analysis on baseline 18F-FDG PET/CT for predicting response to first-line chemotherapy in diffuse large B-cell lymphoma (DLBCL).

MATERIAL AND METHODS

Forty-five patients who received first-line rituximab, cyclophosphamide, doxorubicin, vincristine and prednisone (R-CHOP) chemotherapy for DLBCL were included in the study. Radiomics features and standard uptake value (SUV)-based measurements were extracted from baseline PET images for a total of 147 lesions. The selection of the most relevant features was made using the recursive feature elimination algorithm. A machine-learning model was trained using the logistic regression classifier with cross-validation to predict treatment response. The independent predictors of incomplete response were evaluated with multivariable regression analysis.

RESULTS

A total of 14 textural features were selected by the recursive elimination algorithm, achieving a feature-to-lesion ratio of 1:10. The accuracy and area under the receiver operating characteristic curve of the model for predicting incomplete response were 0.87 and 0.81, respectively. Multivariable analysis revealed that SUVmax and gray level co-occurrence matrix dissimilarity were independent predictors of lesions with incomplete response to first-line R-CHOP chemotherapy.

CONCLUSION

Increased textural heterogeneity in baseline PET images was found to be associated with incomplete response in DLBCL.

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.

Histologic subtype classification of non-small cell lung cancer using PET/CT images

PURPOSES

To evaluate the capability of PET/CT images for differentiating the histologic subtypes of non-small cell lung cancer (NSCLC) and to identify the optimal model from radiomics-based machine learning/deep learning algorithms.

METHODS

In this study, 867 patients with adenocarcinoma (ADC) and 552 patients with squamous cell carcinoma (SCC) were retrospectively analysed. A stratified random sample of 283 patients (20%) was used as the testing set (173 ADC and 110 SCC); the remaining data were used as the training set. A total of 688 features were extracted from each outlined tumour region. Ten feature selection techniques, ten machine learning (ML) models and the VGG16 deep learning (DL) algorithm were evaluated to construct an optimal classification model for the differential diagnosis of ADC and SCC. Tenfold cross-validation and grid search technique were employed to evaluate and optimize the model hyperparameters on the training dataset. The area under the receiver operating characteristic curve (AUROC), accuracy, precision, sensitivity and specificity was used to evaluate the performance of the models on the test dataset.

RESULTS

Fifty top-ranked subset features were selected by each feature selection technique for classification. The linear discriminant analysis (LDA) (AUROC, 0.863; accuracy, 0.794) and support vector machine (SVM) (AUROC, 0.863; accuracy, 0.792) classifiers, both of which coupled with the ℓ_2,1NR feature selection method, achieved optimal performance. The random forest (RF) classifier (AUROC, 0.824; accuracy, 0.775) and ℓ_2,1NR feature selection method (AUROC, 0.815; accuracy, 0.764) showed excellent average performance among the classifiers and feature selection methods employed in our study, respectively. Furthermore, the VGG16 DL algorithm (AUROC, 0.903; accuracy, 0.841) outperformed all conventional machine learning methods in combination with radiomics.

CONCLUSION

Employing radiomic machine learning/deep learning algorithms could help radiologists to differentiate the histologic subtypes of NSCLC via PET/CT images.

Effects of variability in radiomics software packages on classifying patients with radiation pneumonitis

Purpose: While radiomics feature values can differ when extracted using different radiomics software, the effects of these variations when applied to a particular clinical task are currently unknown. The goal of our study was to use various radiomics software packages to classify patients with radiation pneumonitis (RP) and to quantify the variation in classification ability among packages. Approach: A database of serial thoracic computed tomography scans was obtained from 105 patients with esophageal cancer. Patients were treated with radiation therapy (RT), resulting in 20 patients developing RP grade ≥ 2 . Regions of interest (ROIs) were randomly placed in the lung volume of the pre-RT scan within high-dose regions ( ≥ 30    Gy ), and corresponding ROIs were anatomically matched in the post-RT scan. Three radiomics packages were compared: A1 (in-house), IBEX v1.0 beta, and PyRadiomics v.2.0.0. Radiomics features robust to deformable registration and common among radiomics packages were calculated: four first-order and four gray-level co-occurrence matrix features. Differences in feature values between time points were calculated for each feature, and logistic regression was used in conjunction with analysis of variance to classify patients with and without RP ( p < 0.006 ). Classification ability for each package was assessed using receiver operating characteristic (ROC) analysis and compared using the area under the ROC curve (AUC). Results: Of the eight radiomics features, five were significantly correlated with RP status for all three packages, whereas one feature was not significantly correlated with RP for all three packages. The remaining two features differed in whether or not they were significantly associated with RP status among the packages. Seven of the eight features agreed among the packages in whether the AUC value was significantly > 0.5 . Conclusions: Radiomics features extracted using different software packages can result in differences in classification ability.

Can Laws Be a Potential PET Image Texture Analysis Approach for Evaluation of Tumor Heterogeneity and Histopathological Characteristics in NSCLC?

We investigated the association between the textural features obtained from ¹⁸F-FDG images, metabolic parameters (SUVmax_, SUVmean, MTV, TLG), and tumor histopathological characteristics (stage and Ki-67 proliferation index) in non-small cell lung cancer (NSCLC). The FDG-PET images of 67 patients with NSCLC were evaluated. MATLAB technical computing language was employed in the extraction of 137 features by using first order statistics (FOS), gray-level co-occurrence matrix (GLCM), gray-level run length matrix (GLRLM), and Laws' texture filters. Textural features and metabolic parameters were statistically analyzed in terms of good discrimination power between tumor stages, and selected features/parameters were used in the automatic classification by k-nearest neighbors (k-NN) and support vector machines (SVM). We showed that one textural feature (gray-level nonuniformity, GLN) obtained using GLRLM approach and nine textural features using Laws' approach were successful in discriminating all tumor stages, unlike metabolic parameters. There were significant correlations between Ki-67 index and some of the textural features computed using Laws' method (r = 0.6, p = 0.013). In terms of automatic classification of tumor stage, the accuracy was approximately 84% with k-NN classifier (k = 3) and SVM, using selected five features. Texture analysis of FDG-PET images has a potential to be an objective tool to assess tumor histopathological characteristics. The textural features obtained using Laws' approach could be useful in the discrimination of tumor stage.

Use of Precision Imaging in the Evaluation of Pancreas Cancer

Pancreas cancer is an aggressive and fatal disease that will become one of the leading causes of cancer mortality by 2030. An all-out effort is underway to better understand the basic biologic mechanisms of this disease ranging from early development to metastatic disease. In order to change the course of this disease, diagnostic radiology imaging may play a vital role in providing a precise, noninvasive method for early diagnosis and assessment of treatment response. Recent progress in combining medical imaging, advanced image analysis and artificial intelligence, termed radiomics, can offer an innovate approach in detecting the earliest changes of tumor development as well as a rapid method for the detection of response. In this chapter, we introduce the principles of radiomics and demonstrate how it can provide additional information into tumor biology, early detection, and response assessments advancing the goals of precision imaging to deliver the right treatment to the right person at the right time.

Voxel based comparison and texture analysis of 18F-FDG and 18F-FMISO PET of patients with head-and-neck cancer

Background

Hypoxia can induce radiation resistance and is an independent prognostic marker for outcome in head and neck cancer. As ¹⁸F-FMISO (FMISO), a hypoxia tracer for PET, is far less common than ¹⁸F-FDG (FDG) and two separate PET scans result in doubled cost and radiation exposure to the patient, we aimed to predict hypoxia from FDG PET with new techniques of voxel based analysis and texture analysis.

Methods

Thirty-eight patients with head-and-neck cancer underwent consecutive FDG and FMISO PET scans before any treatment. ROIs enclosing the primary cancer were compared in a voxel-by-voxel manner between FDG and FMISO PET. Tumour hypoxia was defined as the volume with a tumour-to-muscle ratio (TMR) > 1.25 in the FMISO PET and hypermetabolic volume was defined as >50% SUVmax in the FDG PET. The concordance rate was defined as percentage of voxels within the tumour which were both hypermetabolic and hypoxic. 38 different texture analysis (TA) parameters were computed based on the ROIs and correlated with presence of hypoxia.

Results

Within the hypoxic tumour regions, the FDG uptake was twice as high as in the non-hypoxic tumour regions (SUVmean 10.9 vs. 5.4; p<0.001). A moderate correlation between FDG and FMISO uptake was found by a voxel-by-voxel comparison (r = 0.664 p<0.001). The average concordance rate was 25% (± 22%). Entropy was the TA parameter showing the highest correlation with hypoxia (r = 0.524 p<0.001).

Conclusion

FDG uptake was higher in hypoxic tumour regions than in non-hypoxic regions as expected by tumour biology. A moderate correlation between FDG and FMISO PET was found by voxel-based analysis. TA yielded similar results in FDG and FMISO PET. However, it may not be possible to predict tumour hypoxia even with the help of texture analysis.

Variation in algorithm implementation across radiomics software

Given the increased need for consistent quantitative image analysis, variations in radiomics feature calculations due to differences in radiomics software were investigated. Two in-house radiomics packages and two freely available radiomics packages, MaZda and IBEX, were utilized. Forty 256 × 256 - pixel regions of interest (ROIs) from 40 digital mammograms were studied along with 39 manually delineated ROIs from the head and neck (HN) computed tomography (CT) scans of 39 patients. Each package was used to calculate first-order histogram and second-order gray-level co-occurrence matrix (GLCM) features. Friedman tests determined differences in feature values across packages, whereas intraclass-correlation coefficients (ICC) quantified agreement. All first-order features computed from both mammography and HN cases (except skewness in mammography) showed significant differences across all packages due to systematic biases introduced by each package; however, based on ICC values, all but one first-order feature calculated on mammography ROIs and all but two first-order features calculated on HN CT ROIs showed excellent agreement, indicating the observed differences were small relative to the feature values but the bias was systematic. All second-order features computed from the two databases both differed significantly and showed poor agreement among packages, due largely to discrepancies in package-specific default GLCM parameters. Additional differences in radiomics features were traced to variations in image preprocessing, algorithm implementation, and naming conventions. Large variations in features among software packages indicate that increased efforts to standardize radiomics processes must be conducted.

Quantifying the robustness of [ 18 F]FDG-PET/CT radiomic features with respect to tumor delineation in head and neck and pancreatic cancer patients

PURPOSE

To investigate the robustness of PET radiomic features (RF) against tumour delineation uncertainty in two clinically relevant situations.

METHODS

Twenty-five head-and-neck (HN) and 25 pancreatic cancer patients previously treated with ¹⁸F-Fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT)-based planning optimization were considered. Seven FDG-based contours were delineated for tumour (T) and positive lymph nodes (N, for HN patients only) following manual (2 observers), semi-automatic (based on SUV maximum gradient: PET_Edge) and automatic (40%, 50%, 60%, 70% SUV_max thresholds) methods. Seventy-three RF (14 of first order and 59 of higher order) were extracted using the CGITA software (v.1.4). The impact of delineation on volume agreement and RF was assessed by DICE and Intra-class Correlation Coefficients (ICC).

RESULTS

A large disagreement between manual and SUV_max method was found for thresholds  ≥50%. Inter-observer variability showed median DICE values between 0.81 (HN-T) and 0.73 (pancreas). Volumes defined by PET_Edge were better consistent with the manual ones compared to SUV40%. Regarding RF, 19%/19%/47% of the features showed ICC < 0.80 between observers for HN-N/HN-T/pancreas, mostly in the Voxel-alignment matrix and in the intensity-size zone matrix families. RFs with ICC < 0.80 against manual delineation (taking the worst value) increased to 44%/36%/61% for PET_Edge and to 69%/53%/75% for SUV40%.

CONCLUSIONS

About 80%/50% of 72 RF were consistent between observers for HN/pancreas patients. PET_edge was sufficiently robust against manual delineation while SUV40% showed a worse performance. This result suggests the possibility to replace manual with semi-automatic delineation of HN and pancreas tumours in studies including PET radiomic analyses.

Translational Radiomics: Defining the Strategy Pipeline and Considerations for Application-Part 2: From Clinical Implementation to Enterprise

Enterprise imaging has channeled various technological innovations to the field of clinical radiology, ranging from advanced imaging equipment and postacquisition iterative reconstruction tools to image analysis and computer-aided detection tools. More recently, the advancement in the field of quantitative image analysis coupled with machine learning-based data analytics, classification, and integration has ushered in the era of radiomics, a paradigm shift that holds tremendous potential in clinical decision support as well as drug discovery. However, there are important issues to consider to incorporate radiomics into a clinically applicable system and a commercially viable solution. In this two-part series, we offer insights into the development of the translational pipeline for radiomics from methodology to clinical implementation (Part 1) and from that point to enterprise development (Part 2). In Part 2 of this two-part series, we study the components of the strategy pipeline, from clinical implementation to building enterprise solutions.

Radiomics in precision medicine for lung cancer

With the improvement of external radiotherapy delivery accuracy, such as intensity-modulated and stereotactic body radiation therapy, radiation oncology has recently entered in the era of precision medicine. Despite these precise irradiation modalities, lung cancers remain one of the most aggressive human cancers worldwide, possibly because of diverse genotypic alterations that drive and maintain lung tumorigenesis. It has been long recognized that imaging could aid in the diagnosis, tumor delineation, and monitoring of lung cancer. Moreover, accumulating evidence suggests that imaging information could be further used to tailor treatment type and intensity, as well as predict treatment outcomes in radiotherapy. However, these imaging tasks have been carried out either qualitatively or using simplistic metrics that doesn't take advantage of the full scale of imaging knowledge. Radiomics, which is a recent field of research that aims to provide a more quantitative representation of imaging information relating tumor phenotypes to clinical and genotypic endpoints by embedding extracted image features into predictive mathematical models. These predictive models can be a key component in the clinician decision making and treatment personalization. This review provides an overview of the radiomics application and its methodology for radiation oncology studies in lung cancer.

Towards enhanced PET quantification in clinical oncology

Positron emission tomography (PET) has, since its inception, established itself as the imaging modality of choice for the in vivo quantitative assessment of molecular targets in a wide range of biochemical processes underlying tumour physiology. PET image quantification enables to ascertain a direct link between the time-varying activity concentration in organs/tissues and the fundamental parameters portraying the biological processes at the cellular level being assessed. However, the quantitative potential of PET may be affected by a number of factors related to physical effects, hardware and software system specifications, tracer kinetics, motion, scan protocol design and limitations in current image-derived PET metrics. Given the relatively large number of PET metrics reported in the literature, the selection of the best metric for fulfilling a specific task in a particular application is still a matter of debate. Quantitative PET has advanced elegantly during the last two decades and is now reaching the maturity required for clinical exploitation, particularly in oncology where it has the capability to open many avenues for clinical diagnosis, assessment of response to treatment and therapy planning. Therefore, the preservation and further enhancement of the quantitative features of PET imaging is crucial to ensure that the full clinical value of PET imaging modality is utilized in clinical oncology. Recent advancements in PET technology and methodology have paved the way for faster PET acquisitions of enhanced sensitivity to support the clinical translation of highly quantitative four-dimensional (4D) parametric imaging methods in clinical oncology. In this report, we provide an overview of recent advances and future trends in quantitative PET imaging in the context of clinical oncology. The pros/cons of the various image-derived PET metrics will be discussed and the promise of novel methodologies will be highlighted.

Characterization of PET/CT images using texture analysis: the past, the present… any future?

After seminal papers over the period 2009 - 2011, the use of texture analysis of PET/CT images for quantification of intratumour uptake heterogeneity has received increasing attention in the last 4 years. Results are difficult to compare due to the heterogeneity of studies and lack of standardization. There are also numerous challenges to address. In this review we provide critical insights into the recent development of texture analysis for quantifying the heterogeneity in PET/CT images, identify issues and challenges, and offer recommendations for the use of texture analysis in clinical research. Numerous potentially confounding issues have been identified, related to the complex workflow for the calculation of textural features, and the dependency of features on various factors such as acquisition, image reconstruction, preprocessing, functional volume segmentation, and methods of establishing and quantifying correspondences with genomic and clinical metrics of interest. A lack of understanding of what the features may represent in terms of the underlying pathophysiological processes and the variability of technical implementation practices makes comparing results in the literature challenging, if not impossible. Since progress as a field requires pooling results, there is an urgent need for standardization and recommendations/guidelines to enable the field to move forward. We provide a list of correct formulae for usual features and recommendations regarding implementation. Studies on larger cohorts with robust statistical analysis and machine learning approaches are promising directions to evaluate the potential of this approach.

Applications and limitations of radiomics

Radiomics is an emerging field in quantitative imaging that uses advanced imaging features to objectively and quantitatively describe tumour phenotypes. Radiomic features have recently drawn considerable interest due to its potential predictive power for treatment outcomes and cancer genetics, which may have important applications in personalized medicine. In this technical review, we describe applications and challenges of the radiomic field. We will review radiomic application areas and technical issues, as well as proper practices for the designs of radiomic studies.

Variability of Image Features Computed from Conventional and Respiratory-Gated PET/CT Images of Lung Cancer

Radiomics is being explored for potential applications in radiation therapy. How various imaging protocols affect quantitative image features is currently a highly active area of research. To assess the variability of image features derived from conventional [three-dimensional (3D)] and respiratory-gated (RG) positron emission tomography (PET)/computed tomography (CT) images of lung cancer patients, image features were computed from 23 lung cancer patients. Both protocols for each patient were acquired during the same imaging session. PET tumor volumes were segmented using an adaptive technique which accounted for background. CT tumor volumes were delineated with a commercial segmentation tool. Using RG PET images, the tumor center of mass motion, length, and rotation were calculated. Fifty-six image features were extracted from all images consisting of shape descriptors, first-order features, and second-order texture features. Overall, 26.6% and 26.2% of total features demonstrated less than 5% difference between 3D and RG protocols for CT and PET, respectively. Between 10 RG phases in PET, 53.4% of features demonstrated percent differences less than 5%. The features with least variability for PET were sphericity, spherical disproportion, entropy (first and second order), sum entropy, information measure of correlation 2, Short Run Emphasis (SRE), Long Run Emphasis (LRE), and Run Percentage (RPC); and those for CT were minimum intensity, mean intensity, Root Mean Square (RMS), Short Run Emphasis (SRE), and RPC. Quantitative analysis using a 3D acquisition versus RG acquisition (to reduce the effects of motion) provided notably different image feature values. This study suggests that the variability between 3D and RG features is mainly due to the impact of respiratory motion.

The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis

FDG-PET-derived textural features describing intra-tumor heterogeneity are increasingly investigated as imaging biomarkers. As part of the process of quantifying heterogeneity, image intensities (SUVs) are typically resampled into a reduced number of discrete bins. We focused on the implications of the manner in which this discretization is implemented. Two methods were evaluated: (1) R_D, dividing the SUV range into D equally spaced bins, where the intensity resolution (i.e. bin size) varies per image; and (2) R_B, maintaining a constant intensity resolution B. Clinical feasibility was assessed on 35 lung cancer patients, imaged before and in the second week of radiotherapy. Forty-four textural features were determined for different D and B for both imaging time points. Feature values depended on the intensity resolution and out of both assessed methods, R_B was shown to allow for a meaningful inter- and intra-patient comparison of feature values. Overall, patients ranked differently according to feature values–which was used as a surrogate for textural feature interpretation–between both discretization methods. Our study shows that the manner of SUV discretization has a crucial effect on the resulting textural features and the interpretation thereof, emphasizing the importance of standardized methodology in tumor texture analysis.

False Discovery Rates in PET and CT Studies with Texture Features: A Systematic Review

Purpose

A number of recent publications have proposed that a family of image-derived indices, called texture features, can predict clinical outcome in patients with cancer. However, the investigation of multiple indices on a single data set can lead to significant inflation of type-I errors. We report a systematic review of the type-I error inflation in such studies and review the evidence regarding associations between patient outcome and texture features derived from positron emission tomography (PET) or computed tomography (CT) images.

Methods

For study identification PubMed and Scopus were searched (1/2000–9/2013) using combinations of the keywords texture, prognostic, predictive and cancer. Studies were divided into three categories according to the sources of the type-I error inflation and the use or not of an independent validation dataset. For each study, the true type-I error probability and the adjusted level of significance were estimated using the optimum cut-off approach correction, and the Benjamini-Hochberg method. To demonstrate explicitly the variable selection bias in these studies, we re-analyzed data from one of the published studies, but using 100 random variables substituted for the original image-derived indices. The significance of the random variables as potential predictors of outcome was examined using the analysis methods used in the identified studies.

Results

Fifteen studies were identified. After applying appropriate statistical corrections, an average type-I error probability of 76% (range: 34–99%) was estimated with the majority of published results not reaching statistical significance. Only 3/15 studies used a validation dataset. For the 100 random variables examined, 10% proved to be significant predictors of survival when subjected to ROC and multiple hypothesis testing analysis.

Conclusions

We found insufficient evidence to support a relationship between PET or CT texture features and patient survival. Further fit for purpose validation of these image-derived biomarkers should be supported by appropriate biological and statistical evidence before their association with patient outcome is investigated in prospective studies.

State-Of-The-Art and Recent Advances in Quantification for Therapeutic Follow-Up in Oncology Using PET

¹⁸F-fluoro-2-deoxyglucose (¹⁸F-FDG) positron emission tomography (PET) is an important tool in oncology. Its use has greatly progressed from initial diagnosis to staging and patient monitoring. The information derived from ¹⁸F-FDG-PET allowed the development of a wide range of PET quantitative analysis techniques ranging from simple semi-quantitative methods like the standardized uptake value (SUV) to “high order metrics” that require a segmentation step and additional image processing. In this review, these methods are discussed, focusing particularly on the available methodologies that can be used in clinical trials as well as their current applications in international consensus for PET interpretation in lymphoma and solid tumors.

Comparison of texture features derived from static and respiratory-gated PET images in non-small cell lung cancer

BACKGROUND

PET-based texture features have been used to quantify tumor heterogeneity due to their predictive power in treatment outcome. We investigated the sensitivity of texture features to tumor motion by comparing static (3D) and respiratory-gated (4D) PET imaging.

METHODS

Twenty-six patients (34 lesions) received 3D and 4D [18F]FDG-PET scans before the chemo-radiotherapy. The acquired 4D data were retrospectively binned into five breathing phases to create the 4D image sequence. Texture features, including Maximal correlation coefficient (MCC), Long run low gray (LRLG), Coarseness, Contrast, and Busyness, were computed within the physician-defined tumor volume. The relative difference (δ3D-4D) in each texture between the 3D- and 4D-PET imaging was calculated. Coefficient of variation (CV) was used to determine the variability in the textures between all 4D-PET phases. Correlations between tumor volume, motion amplitude, and δ3D-4D were also assessed.

RESULTS

4D-PET increased LRLG ( = 1%-2%, p < 0.02), Busyness ( = 7%-19%, p < 0.01), and decreased MCC ( = 1%-2%, p < 7.5 × 10(-3)), Coarseness ( = 5%-10%, p < 0.05) and Contrast ( = 4%-6%, p > 0.08) compared to 3D-PET. Nearly negligible variability was found between the 4D phase bins with CV < 5% for MCC, LRLG, and Coarseness. For Contrast and Busyness, moderate variability was found with CV = 9% and 10%, respectively. No strong correlation was found between the tumor volume and δ3D-4D for the texture features. Motion amplitude had moderate impact on δ for MCC and Busyness and no impact for LRLG, Coarseness, and Contrast.

CONCLUSIONS

Significant differences were found in MCC, LRLG, Coarseness, and Busyness between 3D and 4D PET imaging. The variability between phase bins for MCC, LRLG, and Coarseness was negligible, suggesting that similar quantification can be obtained from all phases. Texture features, blurred out by respiratory motion during 3D-PET acquisition, can be better resolved by 4D-PET imaging. 4D-PET textures may have better prognostic value as they are less susceptible to tumor motion.

Autoclustering of Non-small Cell Lung Carcinoma Subtypes on (18)F-FDG PET Using Texture Analysis: A Preliminary Result

PURPOSE

Texture analysis on (18)F-fluorodeoxyglucose positron emission tomography ((18)F-FDG PET) scan is a relatively new imaging analysis tool to evaluate metabolic heterogeneity. We analyzed the difference in textural characteristics between non-small cell lung carcinoma (NSCLC) subtypes, namely adenocarcinoma (ADC) and squamous cell carcinoma (SqCC).

METHODS

Diagnostic (18)F-FDG PET/computed tomography (CT) scans of 30y patients (median age, 67; range, 42-88) with NSCLC (17 ADC and 13 SqCC) were retrospectively analyzed. Regions of interest were manually determined on selected transverse image containing the highest SUV value in tumors. Texture parameters were extracted by histogram-based algorithms, absolute gradient-based algorithms, run-length matrix-based algorithms, co-occurrence matrix-based algorithms, and autoregressive model-based algorithms. Twenty-four out of hundreds of texture features were selected by three algorithms: Fisher coefficient, minimization of both classification error probability and average correlation, and mutual information. Automated clustering of tumors was based on the most discriminating feature calculated by linear discriminant analysis (LDA). Each tumor subtype was determined by histopathologic examination after biopsy and surgery.

RESULTS

Fifteen texture features had significant different values between ADC and SqCC. LDA with 24 automate-selected texture features accurately clustered between ADC and SqCC with 0.90 linear separability. There was no high correlation between SUVmax and texture parameters (|r| ≤ 0.62).

CONCLUSION

Each subtype of NSCLC tumor has different metabolic heterogeneity. The results of this study support the potential of textural parameters on FDG PET as an imaging biomarker.