Test-retest reproducibility analysis of lung CT image features

Machine learning-based quantitative texture analysis of conventional MRI combined with ADC maps for assessment of IDH1 mutation in high-grade gliomas

PURPOSE

To assess the performance of texture analysis of conventional magnetic resonance imaging (MRI) and apparent diffusion coefficient (ADC) maps in predicting IDH1 status in high-grade gliomas (HGG).

MATERIALS AND METHODS

A total of 142 patients with HGG were included in the study. IDH1 mutation was present in 48 of 142 HGG (33.8%). Patients were randomly divided into the training cohort (n = 96) and the validation cohort (n = 46). Texture features were extracted via regions of interest on axial T2WI FLAIR, post-contrast T1WI, and ADC maps covering the whole volume of the tumors. The training cohort was used to train the random forest classifier, and the diagnostic performance of the pre-trained model was tested on the validation cohort.

RESULTS

The random forest model of conventional MRI sequences and ADC images achieved diagnostic accuracy of 82.2% and 80.4% in predicting IDH1 status in the validation cohorts, respectively. The combined model of T2WI FLAIR, post-contrast T1WI, and ADC images exhibited the highest diagnostic accuracy equating 86.94% in the validation cohort.

CONCLUSION

Texture analysis of conventional MRI sequences enhanced by ML analysis can accurately predict the IDH1 status of HGG. Adding textural analysis of ADC maps to conventional MRI results in incremental diagnostic performance.

Stability and reproducibility of computed tomography radiomic features extracted from peritumoral regions of lung cancer lesions

PURPOSE

Recent efforts have demonstrated that radiomic features extracted from the peritumoral region, the area surrounding the tumor parenchyma, have clinical utility in various cancer types. However, as like any radiomic features, peritumoral features could also be unstable and/or nonreproducible. Hence, the purpose of this study was to assess the stability and reproducibility of computed tomography (CT) radiomic features extracted from the peritumoral regions of lung lesions where stability was defined as the consistency of a feature by different segmentations, and reproducibility was defined as the consistency of a feature to different image acquisitions.

METHODS

Stability was measured utilizing the "moist run" dataset and reproducibility was measured utilizing the Reference Image Database to Evaluate Therapy Response test-retest dataset. Peritumoral radiomic features were extracted from incremental distances of 3-12 mm outside the tumor segmentation. A total of 264 statistical, histogram, and texture radiomic features were assessed from the selected peritumoral region-of-interests (ROIs). All features (except wavelet texture features) were extracted using standardized algorithms defined by the Image Biomarker Standardisation Initiative. Stability and reproducibility of features were assessed using the concordance correlation coefficient. The clinical utility of stable and reproducible peritumoral features was tested in three previously published lung cancer datasets using overall survival as the endpoint.

RESULTS

Features found to be stable and reproducible, regardless of the peritumoral distances, included statistical, histogram, and a subset of texture features suggesting that these features are less affected by changes (e.g., size or shape) of the peritumoral region due to different segmentations and image acquisitions. The stability and reproducibility of Laws and wavelet texture features were inconsistent across all peritumoral distances. The analyses also revealed that a subset of features were consistently stable irrespective of the initial parameters (e.g., seed point) for a given segmentation algorithm. No significant differences were found in stability for features that were extracted from ROIs bounded by a lung parenchyma mask versus ROIs that were not bounded by a lung parenchyma mask (i.e., peritumoral regions that extended outside of lung parenchyma). After testing the clinical utility of peritumoral features, stable and reproducible features were shown to be more likely to create repeatable models than unstable and nonreproducible features.

CONCLUSIONS

This study identified a subset of stable and reproducible CT radiomic features extracted from the peritumoral region of lung lesions. The stable and reproducible features identified in this study could be applied to a feature selection pipeline for CT radiomic analyses. According to our findings, top performing features in survival models were more likely to be stable and reproducible hence, it may be best practice to utilize them to achieve repeatable studies and reduce the chance of overfitting.

Integrating radiomics into clinical trial design

In radiomics, quantitative features that describe phenotypic tumor characteristics are derived from radiographic images. Because radiomics generates information from routine medical images, it is a powerful way to non-invasively examine the spatial and temporal heterogeneity of disease, and thus has potential to significantly impact clinical trial design, execution, and ultimately patient care. The aim of this review article is to discuss how radiomics may address some of the current challenges in clinical randomized control trials, and the difficulties of integrating robust and repeatable radiomics analysis into trial design. Each step of the radiomics process, including image acquisition and reconstruction, image segmentation, feature extraction, and computational analysis, requires extensive standardization in order to be successfully incorporated into clinical trials and inform clinical decision making. By addressing these challenges, the potential of radiomics may be realized.

Image-based Classification of Tumor Type and Growth Rate using Machine Learning: a preclinical study

Medical images such as magnetic resonance (MR) imaging provide valuable information for cancer detection, diagnosis, and prognosis. In addition to the anatomical information these images provide, machine learning can identify texture features from these images to further personalize treatment. This study aims to evaluate the use of texture features derived from T₁-weighted post contrast scans to classify different types of brain tumors and predict tumor growth rate in a preclinical mouse model. To optimize prediction models this study uses varying gray-level co-occurrence matrix (GLCM) sizes, tumor region selection and different machine learning models. Using a random forest classification model with a GLCM of size 512 resulted in 92%, 91%, and 92% specificity, and 89%, 85%, and 73% sensitivity for GL261 (mouse glioma), U87 (human glioma) and Daoy (human medulloblastoma), respectively. A tenfold cross-validation of the classifier resulted in 84% accuracy when using the entire tumor volume for feature extraction and 74% accuracy for the central tumor region. A two-layer feedforward neural network using the same features is able to predict tumor growth with 16% mean squared error. Broadly applicable, these predictive models can use standard medical images to classify tumor type and predict tumor growth, with model performance, varying as a function of GLCM size, tumor region, and tumor type.

Prediction of Immunohistochemistry of Suspected Thyroid Nodules by Use of Machine Learning-Based Radiomics

OBJECTIVE. The purpose of this study was to develop and validate a radiomics model for evaluating immunohistochemical characteristics in patients with suspected thyroid nodules. MATERIALS AND METHODS. A total of 103 patients (training cohort-to-validation cohort ratio, ≈ 3:1) with suspected thyroid nodules who had undergone thyroidectomy and immunohistochemical analysis were enrolled. The immunohistochemical markers were cytokeratin 19, galectin 3, thyroperoxidase, and high-molecular-weight cytokeratin. All patients underwent CT before surgery, and a 3D slicer was used to analyze images of the surgical specimen. Test-retest and Spearman correlation coefficient (ρ) were used to select reproducible and nonredundant features. The Kruskal-Wallis test (p < 0.05) was used for feature selection, and a feature-based model was built by support vector machine methods. The performance of the radiomic models was assessed with respect to accuracy, sensitivity, specificity, corresponding AUC, and independent validation. RESULTS. Eighty-six reproducible and nonredundant features selected from the 828 features were used to build the model. The best performance of the cytokeratin 19 model yielded accuracy of 84.4% in the training cohort and 80.0% in the validation cohort. The thyroperoxidase and galectin 3 predictive models yielded accuracies of 81.4% and 82.5% in the training cohort and 84.2% and 85.0% in the validation cohort. The performance of the high-molecular-weight cytokeratin predictive model was not good (accuracy, 65.7%) and could not be validated. CONCLUSION. A radiomics model with excellent performance was developed for individualized noninvasive prediction of the presence of cytokeratin 19, galectin 3, and thyroperoxidase based on CT images. This model may be used to identify benign and malignant thyroid nodules.

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.

Radiomic feature reproducibility in contrast-enhanced CT of the pancreas is affected by variabilities in scan parameters and manual segmentation

OBJECTIVES

This study aims to measure the reproducibility of radiomic features in pancreatic parenchyma and ductal adenocarcinomas (PDAC) in patients who underwent consecutive contrast-enhanced computed tomography (CECT) scans.

METHODS

In this IRB-approved and HIPAA-compliant retrospective study, 37 pairs of scans from 37 unique patients who underwent CECTs within a 2-week interval were included in the analysis of the reproducibility of features derived from pancreatic parenchyma, and a subset of 18 pairs of scans were further analyzed for the reproducibility of features derived from PDAC. In each patient, pancreatic parenchyma and pancreatic tumor (when present) were manually segmented by two radiologists independently. A total of 266 radiomic features were extracted from the pancreatic parenchyma and tumor region and also the volume and diameter of the tumor. The concordance correlation coefficient (CCC) was calculated to assess feature reproducibility for each patient in three scenarios: (1) different radiologists, same CECT; (2) same radiologist, different CECTs; and (3) different radiologists, different CECTs.

RESULTS

Among pancreatic parenchyma-derived features, using a threshold of CCC > 0.90, 58/266 (21.8%) and 48/266 (18.1%) features met the threshold for scenario 1, 14/266 (5.3%) and 15/266 (5.6%) for scenario 2, and 14/266 (5.3%) and 10/266 (3.8%) for scenario 3. Among pancreatic tumor-derived features, 11/268 (4.1%) and 17/268 (6.3%) features met the threshold for scenario 1, 1/268 (0.4%) and 5/268 (1.9%) features met the threshold for scenario 2, and no features for scenario 3 met the threshold, respectively.

CONCLUSIONS

Variations between CECT scans affected radiomic feature reproducibility to a greater extent than variation in segmentation. A smaller number of pancreatic tumor-derived radiomic features were reproducible compared with pancreatic parenchyma-derived radiomic features under the same conditions.

KEY POINTS

• For pancreatic-derived radiomic features from contrast-enhanced CT (CECT), fewer than 25% are reproducible (with a threshold of CCC < 0.9) in a clinical heterogeneous dataset. • Variations between CECT scans affected the number of reproducible radiomic features to a greater extent than variations in radiologist segmentation. • A smaller number of pancreatic tumor-derived radiomic features were reproducible compared with pancreatic parenchyma-derived radiomic features under the same conditions.

MRI-based radiomics signature is a quantitative prognostic biomarker for nasopharyngeal carcinoma

This study aimed to develop prognosis signatures through a radiomics analysis for patients with nasopharyngeal carcinoma (NPC) by their pretreatment diagnosis magnetic resonance imaging (MRI). A total of 208 radiomics features were extracted for each patient from a database of 303 patients. The patients were split into the training and validation cohorts according to their pretreatment diagnosis date. The radiomics feature analysis consisted of cluster analysis and prognosis model analysis for disease free-survival (DFS), overall survival (OS), distant metastasis-free survival (DMFS) and locoregional recurrence-free survival (LRFS). Additionally, two prognosis models using clinical features only and combined radiomics and clinical features were generated to estimate the incremental prognostic value of radiomics features. Patients were clustered by non-negative matrix factorization (NMF) into two groups. It showed high correspondence with patients' T stage (p < 0.00001) and overall stage information (p < 0.00001) by chi-squared tests. There were significant differences in DFS (p = 0.0052), OS (p = 0.033), and LRFS (p = 0.037) between the two clustered groups but not in DMFS (p = 0.11) by log-rank tests. Radiomics nomograms that incorporated radiomics and clinical features could estimate DFS with the C-index of 0.751 [0.639, 0.863] and OS with the C-index of 0.845 [0.752, 0.939] in the validation cohort. The nomograms improved the prediction accuracy with the C-index value of 0.029 for DFS and 0.107 for OS compared with clinical features only. The DFS and OS radiomics nomograms developed in our study demonstrated the excellent prognostic estimation for NPC patients with a noninvasive way of MRI. The combination of clinical and radiomics features can provide more information for precise treatment decision.

Reproducibility and Generalizability in Radiomics Modeling: Possible Strategies in Radiologic and Statistical Perspectives

Radiomics, which involves the use of high-dimensional quantitative imaging features for predictive purposes, is a powerful tool for developing and testing medical hypotheses. Radiologic and statistical challenges in radiomics include those related to the reproducibility of imaging data, control of overfitting due to high dimensionality, and the generalizability of modeling. The aims of this review article are to clarify the distinctions between radiomics features and other omics and imaging data, to describe the challenges and potential strategies in reproducibility and feature selection, and to reveal the epidemiological background of modeling, thereby facilitating and promoting more reproducible and generalizable radiomics research.

Repeatability of Multiparametric Prostate MRI Radiomics Features

In this study we assessed the repeatability of radiomics features on small prostate tumors using test-retest Multiparametric Magnetic Resonance Imaging (mpMRI). The premise of radiomics is that quantitative image-based features can serve as biomarkers for detecting and characterizing disease. For such biomarkers to be useful, repeatability is a basic requirement, meaning its value must remain stable between two scans, if the conditions remain stable. We investigated repeatability of radiomics features under various preprocessing and extraction configurations including various image normalization schemes, different image pre-filtering, and different bin widths for image discretization. Although we found many radiomics features and preprocessing combinations with high repeatability (Intraclass Correlation Coefficient > 0.85), our results indicate that overall the repeatability is highly sensitive to the processing parameters. Neither image normalization, using a variety of approaches, nor the use of pre-filtering options resulted in consistent improvements in repeatability. We urge caution when interpreting radiomics features and advise paying close attention to the processing configuration details of reported results. Furthermore, we advocate reporting all processing details in radiomics studies and strongly recommend the use of open source implementations.

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.

Reliability of CT-based texture features: Phantom study

Objective

To determine the intra‐, inter‐ and test‐retest variability of CT‐based texture analysis (CTTA) metrics.

Materials and methods

In this study, we conducted a series of CT imaging experiments using a texture phantom to evaluate the performance of a CTTA panel on routine abdominal imaging protocols. The phantom comprises of three different regions with various textures found in tumors. The phantom was scanned on two CT scanners viz. the Philips Brilliance 64 CT and Toshiba Aquilion Prime 160 CT scanners. The intra‐scanner variability of the CTTA metrics was evaluated across imaging parameters such as slice thickness, field of view, post‐reconstruction filtering, tube voltage, and tube current. For each scanner and scanning parameter combination, we evaluated the performance of eight different types of texture quantification techniques on a predetermined region of interest (ROI) within the phantom image using 235 different texture metrics. We conducted the repeatability (test‐retest) and robustness (intra‐scanner) test on both the scanners and the reproducibility test was conducted by comparing the inter‐scanner differences in the repeatability and robustness to identify reliable CTTA metrics. Reliable metrics are those metrics that are repeatable, reproducible and robust.

Results

As expected, the robustness, repeatability and reproducibility of CTTA metrics are variably sensitive to various scanner and scanning parameters. Entropy of Fast Fourier Transform‐based texture metrics was overall most reliable across the two scanners and scanning conditions. Post‐processing techniques that reduce image noise while preserving the underlying edges associated with true anatomy or pathology bring about significant differences in radiomic reliability compared to when they were not used.

Conclusion

Following large‐scale validation, identification of reliable CTTA metrics can aid in conducting large‐scale multicenter CTTA analysis using sample sets acquired using different imaging protocols, scanners etc.

Quantitative Imaging features Improve Discrimination of Malignancy in Pulmonary nodules

Pulmonary nodules are frequently detected radiological abnormalities in lung cancer screening. Nodules of the highest- and lowest-risk for cancer are often easily diagnosed by a trained radiologist there is still a high rate of indeterminate pulmonary nodules (IPN) of unknown risk. Here, we test the hypothesis that computer extracted quantitative features (“radiomics”) can provide improved risk-assessment in the diagnostic setting. Nodules were segmented in 3D and 219 quantitative features are extracted from these volumes. Using these features novel malignancy risk predictors are formed with various stratifications based on size, shape and texture feature categories. We used images and data from the National Lung Screening Trial (NLST), curated a subset of 479 participants (244 for training and 235 for testing) that included incident lung cancers and nodule-positive controls. After removing redundant and non-reproducible features, optimal linear classifiers with area under the receiver operator characteristics (AUROC) curves were used with an exhaustive search approach to find a discriminant set of image features, which were validated in an independent test dataset. We identified several strong predictive models, using size and shape features the highest AUROC was 0.80. Using non-size based features the highest AUROC was 0.85. Combining features from all the categories, the highest AUROC were 0.83.

Radiomic feature stability across 4D respiratory phases and its impact on lung tumor prognosis prediction

Radiomic analysis has recently demonstrated versatile uses in improving diagnostic and prognostic prediction accuracy for lung cancer. However, since lung tumors are subject to substantial motion due to respiration, the stability of radiomic features over the respiratory cycle of the patient needs to be investigated to better evaluate the robustness of the inter-patient feature variability for clinical applications, and its impact in such applications needs to be assessed. A full panel of 841 radiomic features, including tumor intensity, shape, texture, and wavelet features, were extracted from individual phases of a four-dimensional (4D) computed tomography on 20 early-stage non-small-cell lung cancer (NSCLC) patients. The stability of each radiomic feature was assessed across different phase images of the same patient using the coefficient of variation (COV). The relationship between individual COVs and tumor motion magnitude was inspected. Population COVs, the mean COVs of all 20 patients, were used to evaluate feature motion stability and categorize the radiomic features into 4 different groups. The two extremes, the Very Small group (COV≤5%) and the Large group (COV>20%), each accounted for about a quarter of the features. Shape features were the most stable, with COV≤10% for all features. A clinical study was subsequently conducted using 140 early-stage NSCLC patients. Radiomic features were employed to predict the overall survival with a 500-round bootstrapping. Identical multiple regression model development process was applied, and the model performance was compared between models with and without a feature pre-selection step based on 4D COV to pre-exclude unstable features. Among the systematically tested cutoff values, feature pre-selection with 4D COV≤5% achieved the optimal model performance. The resulting 3-feature radiomic model significantly outperformed its counterpart with no 4D COV pre-selection, with P = 2.16x10^-27 in the one-tailed t-test comparing the prediction performances of the two models.

Multisite evaluation of radiomic feature reproducibility and discriminability for identifying peripheral zone prostate tumors on MRI

Recent advances in the field of radiomics have enabled the development of a number of prognostic and predictive imaging-based tools for a variety of diseases. However, wider clinical adoption of these tools is contingent on their generalizability across multiple sites and scanners. This may be particularly relevant in the context of radiomic features derived from T1- or T2-weighted magnetic resonance images (MRIs), where signal intensity values are known to lack tissue-specific meaning and vary based on differing acquisition protocols between institutions. We present the first empirical study of benchmarking five different radiomic feature families in terms of both reproducibility and discriminability in a multisite setting, specifically, for identifying prostate tumors in the peripheral zone on MRI. Our cohort comprised 147 patient T2-weighted MRI datasets from four different sites, all of which are first preprocessed to correct for acquisition-related artifacts such as bias field, differing voxel resolutions, and intensity drift (nonstandardness). About 406 three-dimensional voxel-wise radiomic features from five different families (gray, Haralick, gradient, Laws, and Gabor) were evaluated in a cross-site setting to determine (a) how reproducible they are within a relatively homogeneous nontumor tissue region and (b) how well they could discriminate tumor regions from nontumor regions. Our results demonstrate that a majority of the popular Haralick features are reproducible in over 99% of all cross-site comparisons, as well as achieve excellent cross-site discriminability (classification accuracy of ≈ 0.8 ). By contrast, a majority of Laws features are highly variable across sites (reproducible in < 75 % of all cross-site comparisons) as well as resulting in low cross-site classifier accuracies ( < 0.6 ), likely due to a large number of noisy filter responses that can be extracted. These trends suggest that only a subset of radiomic features and associated parameters may be both reproducible and discriminable enough for use within machine learning classifier schemes.

Radiomics: Principles and radiotherapy applications

Radiomics is defined as the extraction of a large quantity of quantitative image features. The different radiomic indexes that have been proposed in the literature are described as well as the various factors that have an impact on the robustness of these indexes. We will see that several hundred quantitative features can be extracted per lesion and imaging modality. The ever-growing number of features studied raises the question of the statistical method of analysis used. This review addresses the research supporting the clinical use of radiomics in oncology in the staging of disease, discrimination between healthy and pathological tissues, the identification of genetic features, the prediction of patient survival, the response to treatment, the recurrence after radiotherapy and chemoradiotherapy and the side effects. Based on the existing literature, it remains difficult to identify features that should be used for current clinical practice.

Revealing Tumor Habitats from Texture Heterogeneity Analysis for Classification of Lung Cancer Malignancy and Aggressiveness

We propose an approach for characterizing structural heterogeneity of lung cancer nodules using Computed Tomography Texture Analysis (CTTA). Measures of heterogeneity were used to test the hypothesis that heterogeneity can be used as predictor of nodule malignancy and patient survival. To do this, we use the National Lung Screening Trial (NLST) dataset to determine if heterogeneity can represent differences between nodules in lung cancer and nodules in non-lung cancer patients. 253 participants are in the training set and 207 participants in the test set. To discriminate cancerous from non-cancerous nodules at the time of diagnosis, a combination of heterogeneity and radiomic features were evaluated to produce the best area under receiver operating characteristic curve (AUROC) of 0.85 and accuracy 81.64%. Second, we tested the hypothesis that heterogeneity can predict patient survival. We analyzed 40 patients diagnosed with lung adenocarcinoma (20 short-term and 20 long-term survival patients) using a leave-one-out cross validation approach for performance evaluation. A combination of heterogeneity features and radiomic features produce an AUROC of 0.9 and an accuracy of 85% to discriminate long- and short-term survivors.

Artificial intelligence in cancer imaging: Clinical challenges and applications

Judgement, as one of the core tenets of medicine, relies upon the integration of multilayered data with nuanced decision making. Cancer offers a unique context for medical decisions given not only its variegated forms with evolution of disease but also the need to take into account the individual condition of patients, their ability to receive treatment, and their responses to treatment. Challenges remain in the accurate detection, characterization, and monitoring of cancers despite improved technologies. Radiographic assessment of disease most commonly relies upon visual evaluations, the interpretations of which may be augmented by advanced computational analyses. In particular, artificial intelligence (AI) promises to make great strides in the qualitative interpretation of cancer imaging by expert clinicians, including volumetric delineation of tumors over time, extrapolation of the tumor genotype and biological course from its radiographic phenotype, prediction of clinical outcome, and assessment of the impact of disease and treatment on adjacent organs. AI may automate processes in the initial interpretation of images and shift the clinical workflow of radiographic detection, management decisions on whether or not to administer an intervention, and subsequent observation to a yet to be envisioned paradigm. Here, the authors review the current state of AI as applied to medical imaging of cancer and describe advances in 4 tumor types (lung, brain, breast, and prostate) to illustrate how common clinical problems are being addressed. Although most studies evaluating AI applications in oncology to date have not been vigorously validated for reproducibility and generalizability, the results do highlight increasingly concerted efforts in pushing AI technology to clinical use and to impact future directions in cancer care.

Explaining Deep Features Using Radiologist-Defined Semantic Features and Traditional Quantitative Features

Quantitative features are generated from a tumor phenotype by various data characterization, feature-extraction approaches and have been used successfully as a biomarker. These features give us information about a nodule, for example, nodule size, pixel intensity, histogram-based information, and texture information from wavelets or a convolution kernel. Semantic features, on the other hand, can be generated by an experienced radiologist and consist of the common characteristics of a tumor, for example, location of a tumor, fissure, or pleural wall attachment, presence of fibrosis or emphysema, concave cut on nodule surface. These features have been derived for lung nodules by our group. Semantic features have also shown promise in predicting malignancy. Deep features from images are generally extracted from the last layers before the classification layer of a convolutional neural network (CNN). By training with the use of different types of images, the CNN learns to recognize various patterns and textures. But when we extract deep features, there is no specific naming approach for them, other than denoting them by the feature column number (position of a neuron in a hidden layer). In this study, we tried to relate and explain deep features with respect to traditional quantitative features and semantic features. We discovered that 26 deep features from the Vgg-S neural network and 12 deep features from our trained CNN could be explained by semantic or traditional quantitative features. From this, we concluded that those deep features can have a recognizable definition via semantic or quantitative features.

Assessment of Remote Myocardium Heterogeneity in Patients with Ventricular Tachycardia Using Texture Analysis of Late Iodine Enhancement (LIE) Cardiac Computed Tomography (cCT) Images

Purpose

Diffuse remodeling of myocardial extra-cellular matrix is largely responsible for left ventricle (LV) dysfunction and arrhythmias. Our hypothesis is that the texture analysis of late iodine enhancement (LIE) cardiac computed tomography (cCT) images may improve characterization of the diffuse extra-cellular matrix changes. Our aim was to extract volumetric extracellular volume (ECV) and LIE texture features of non-scarred (remote) myocardium from cCT of patients with recurrent ventricular tachycardia (rVT), and to compare these radiomic features with LV-function, LV-remodeling, and underlying cardiac disease.

Procedures

Forty-eight patients suffering from rVT were prospectively enrolled: 5/48 with idiopathic VT (IVT), 23/48 with post-ischemic dilated cardiomyopathy (ICM), 9/48 with idiopathic dilated cardiomyopathy (IDCM), and 11/48 with scars from a previous healed myocarditis (MYO). All patients underwent echocardiography to assess LV systolic and diastolic function and cCT with pre-contrast, angiographic, and LIE scan to obtain end-diastolic volume (EDV), ECV, and first-order texture parameters of Hounsfield Unit (HU) of remote myocardium in LIE [energy, entropy, HU-mean, HU-median, standard deviation (SD), and mean absolute deviation (MAD)].

Results

Energy, HU mean, and HU median by cCT texture analysis correlated with ECV (rho = 0.5650, rho = 0.5741, rho = 0.5068; p < 0.0005). cCT-derived ECV, HU-mean, HU-median, SD, and MAD correlated directly to EDV by cCT and inversely to ejection fraction by echocardiography (p < 0.05). SD and MAD correlated with diastolic function by echocardiography (rho = 0.3837, p = 0.0071; rho = 0.3330, p = 0.0208). MYO and IVT patients were characterized by significantly lower values of SD and MAD when compared with ICM and IDCM patients, independently of LV-volume systolic and diastolic function.

Conclusions

Texture analysis of LIE may expand cCT capability of myocardial characterization. Myocardial heterogeneity (SD and MAD) was associated with LV dilatation, systolic and diastolic function, and is able to potentially identify the different patterns of structural remodeling characterizing patients with rVT of different etiology.

Texture Analysis of Imaging: What Radiologists Need to Know

OBJECTIVE

Radiologic texture is the variation in image intensities within an image and is an important part of radiomics. The objective of this article is to discuss some parameters that affect the performance of texture metrics and propose recommendations that can guide both the design and evaluation of future radiomics studies.

CONCLUSION

A variety of texture-extraction techniques are used to assess clinical imaging data. Currently, no consensus exists regarding workflow, including acquisition, extraction, or reporting of variable settings leading to poor reproducibility.

Quantitative imaging of cancer in the postgenomic era: Radio(geno)mics, deep learning, and habitats

Although cancer often is referred to as "a disease of the genes," it is indisputable that the (epi)genetic properties of individual cancer cells are highly variable, even within the same tumor. Hence, preexisting resistant clones will emerge and proliferate after therapeutic selection that targets sensitive clones. Herein, the authors propose that quantitative image analytics, known as "radiomics," can be used to quantify and characterize this heterogeneity. Virtually every patient with cancer is imaged radiologically. Radiomics is predicated on the beliefs that these images reflect underlying pathophysiologies, and that they can be converted into mineable data for improved diagnosis, prognosis, prediction, and therapy monitoring. In the last decade, the radiomics of cancer has grown from a few laboratories to a worldwide enterprise. During this growth, radiomics has established a convention, wherein a large set of annotated image features (1-2000 features) are extracted from segmented regions of interest and used to build classifier models to separate individual patients into their appropriate class (eg, indolent vs aggressive disease). An extension of this conventional radiomics is the application of "deep learning," wherein convolutional neural networks can be used to detect the most informative regions and features without human intervention. A further extension of radiomics involves automatically segmenting informative subregions ("habitats") within tumors, which can be linked to underlying tumor pathophysiology. The goal of the radiomics enterprise is to provide informed decision support for the practice of precision oncology.

Delta radiomic features improve prediction for lung cancer incidence: A nested case-control analysis of the National Lung Screening Trial

Background

Current guidelines for lung cancer screening increased a positive scan threshold to a 6 mm longest diameter. We extracted radiomic features from baseline and follow‐up screens and performed size‐specific analyses to predict lung cancer incidence using three nodule size classes (<6 mm [small], 6‐16 mm [intermediate], and ≥16 mm [large]).

Methods

We extracted 219 features from baseline (T0) nodules and 219 delta features which are the change from T0 to first follow‐up (T1). Nodules were identified for 160 incidence cases diagnosed with lung cancer at T1 or second follow‐up screen (T2) and for 307 nodule‐positive controls that had three consecutive positive screens not diagnosed as lung cancer. The cases and controls were split into training and test cohorts; classifier models were used to identify the most predictive features.

Results

The final models revealed modest improvements for baseline and delta features when compared to only baseline features. The AUROCs for small‐ and intermediate‐sized nodules were 0.83 (95% CI 0.76‐0.90) and 0.76 (95% CI 0.71‐0.81) for baseline‐only radiomic features, respectively, and 0.84 (95% CI 0.77‐0.90) and 0.84 (95% CI 0.80‐0.88) for baseline and delta features, respectively. When intermediate and large nodules were combined, the AUROC for baseline‐only features was 0.80 (95% CI 0.76‐0.84) compared with 0.86 (95% CI 0.83‐0.89) for baseline and delta features.

Conclusions

We found modest improvements in predicting lung cancer incidence by combining baseline and delta radiomics. Radiomics could be used to improve current size‐based screening guidelines.

Short-term reproducibility of radiomic features in liver parenchyma and liver malignancies on contrast-enhanced CT imaging

PURPOSE

To evaluate the short-term reproducibility of radiomic features in liver parenchyma and liver cancers in patients who underwent consecutive contrast-enhanced CT (CECT) with intravenous iodinated contrast within 2 weeks by chance.

METHODS

The Institutional Review Board approved this HIPAA-compliant retrospective study and waived the requirement for patients' informed consent. Patients were included if they had a liver malignancy (liver metastasis, n = 22, intrahepatic cholangiocarcinoma, n = 10, and hepatocellular carcinoma, n = 6), had two consecutive CECT within 14 days, and had no prior or intervening therapy. Liver tumors and liver parenchyma were segmented and radiomic features (n = 254) were extracted. The number of reproducible features (with concordance correlation coefficients > 0.9) was calculated for patient subgroups with different variations in contrast injection rate and pixel resolution.

RESULTS

The number of reproducible radiomic features decreased with increasing variations in contrast injection rate and pixel resolution. When including all CECTs with injection rates differences of less than 15% vs. up to 50%, 63/254 vs. 0/254 features were reproducible for liver parenchyma and 68/254 vs. 50/254 features were reproducible for malignancies. When including all CT with pixel resolution differences of 0-5% or 0-15%, 20/254 vs. 0/254 features were reproducible for liver parenchyma; 34/254 liver malignancy features were reproducible with pixel differences up to 15%.

CONCLUSION

A greater number of liver malignancy radiomic features were reproducible compared to liver parenchyma features, but the proportion of reproducible features decreased with increasing variations in contrast injection rates and pixel resolution.

Detection of epithelial growth factor receptor (EGFR) mutations on CT images of patients with lung adenocarcinoma using radiomics and/or multi-level residual convolutionary neural networks

Background

We aim to analyze the ability to detect epithelial growth factor receptor (EGFR) mutations on chest CT images of patients with lung adenocarcinoma using radiomics and/or multi-level residual convolutionary neural networks (MCNNs).

Methods

We retrospectively collected 1,010 consecutive patients in Shanghai Chest Hospital from 2013 to 2017, among which 510 patients were EGFR-mutated and 500 patients were wild-type. The patients were randomly divided into a training set (810 patients) and a validation set (200 patients) according to a balanced distribution of clinical features. The CT images and the corresponding EGFR status measured by Amplification Refractory Mutation System (ARMS) method of the patients in the training set were utilized to construct both a radiomics-based model (M_Radiomics) and MCNNs-based model (M_MCNNs). The M_Radiomics and M_MCNNs were combined to build the Model_{Radiomics+MCNNs} (M_{Radiomics+MCNNs}). Clinical data of gender and smoking history constructed the clinical features-based model (M_Clinical). M_Clinical was then added into M_Radiomics, M_MCNNs, and M_{Radiomics+MCNNs} to establish the Model_{Radiomics+Clinical} (M_{Radiomics+Clinical}), the Model_{MCNNs+Clinical} (M_{MCNNs+Clinical}) and the Model_{Radiomics+MCNNs+Clinical} (M_{Radiomics+MCNNs+Clinical}). All the seven models were tested in the validation set to ascertain whether they were competent to detect EGFR mutations. The detection efficiency of each model was also compared in terms of area under the curve (AUC), sensitivity and specificity.

Results

The AUC of the M_Radiomics, M_MCNNs and M_{Radiomics+MCNNs} to predict EGFR mutations was 0.740, 0.810 and 0.811 respectively. The performance of M_MCNNs was better than that of M_Radiomics (P=0.0225). The addition of clinical features did not improve the AUC of the M_Radiomics (P=0.623), the M_MCNNs (P=0.114) and the M_{Radiomics+MCNNs} (P=0.058). The M_{Radiomics+MCNNs+Clinical} demonstrated the highest AUC value of 0.834. The M_MCNNs did not demonstrate any inferiority when compared with the M_{Radiomics+MCNNs} (P=0.742) and the M_{Radiomics+MCNNs+Clinical} (P=0.056).

Conclusions

Both of the M_Radiomics and the M_CNNs could predict EGFR mutations on CT images of patients with lung adenocarcinoma. The M_MCNNs outperformed the M_Radiomics in the detection of EGFR mutations. The combination of these two models, even added with clinical features, is not significantly more efficient than M_MCNNs alone.

Delta Radiomics Improves Pulmonary Nodule Malignancy Prediction in Lung Cancer Screening

Low-dose computed tomography (LDCT) plays a critical role in the early detection of lung cancer. Despite the life-saving benefit of early detection by LDCT, there are many limitations of this imaging modality including high rates of detection of indeterminate pulmonary nodules. Radiomics is the process of extracting and analyzing image-based, quantitative features from a region-of-interest which then can be analyzed to develop decision support tools that can improve lung cancer screening. Although prior published research has shown that delta radiomics (i.e., changes in features over time) have utility in predicting treatment response, limited work has been conducted using delta radiomics in lung cancer screening. As such, we conducted analyses to assess the performance of incorporating delta with conventional (non delta) features using machine learning to predict lung nodule malignancy. We found the best improved area under the receiver operating characteristic curve (AUC) was 0.822 when delta features were combined with conventional features versus an AUC 0.773 for conventional features only. Overall, this study demonstrated the important utility of combining delta radiomics features with conventional radiomics features to improve performance of models in the lung cancer screening setting.

Radiomics: the facts and the challenges of image analysis

Radiomics is an emerging translational field of research aiming to extract mineable high-dimensional data from clinical images. The radiomic process can be divided into distinct steps with definable inputs and outputs, such as image acquisition and reconstruction, image segmentation, features extraction and qualification, analysis, and model building. Each step needs careful evaluation for the construction of robust and reliable models to be transferred into clinical practice for the purposes of prognosis, non-invasive disease tracking, and evaluation of disease response to treatment. After the definition of texture parameters (shape features; first-, second-, and higher-order features), we briefly discuss the origin of the term radiomics and the methods for selecting the parameters useful for a radiomic approach, including cluster analysis, principal component analysis, random forest, neural network, linear/logistic regression, and other. Reproducibility and clinical value of parameters should be firstly tested with internal cross-validation and then validated on independent external cohorts. This article summarises the major issues regarding this multi-step process, focussing in particular on challenges of the extraction of radiomic features from data sets provided by computed tomography, positron emission tomography, and magnetic resonance imaging.

Radiomics: the facts and the challenges of image analysis

Radiomics is an emerging translational field of research aiming to extract mineable high-dimensional data from clinical images. The radiomic process can be divided into distinct steps with definable inputs and outputs, such as image acquisition and reconstruction, image segmentation, features extraction and qualification, analysis, and model building. Each step needs careful evaluation for the construction of robust and reliable models to be transferred into clinical practice for the purposes of prognosis, non-invasive disease tracking, and evaluation of disease response to treatment. After the definition of texture parameters (shape features; first-, second-, and higher-order features), we briefly discuss the origin of the term radiomics and the methods for selecting the parameters useful for a radiomic approach, including cluster analysis, principal component analysis, random forest, neural network, linear/logistic regression, and other. Reproducibility and clinical value of parameters should be firstly tested with internal cross-validation and then validated on independent external cohorts. This article summarises the major issues regarding this multi-step process, focussing in particular on challenges of the extraction of radiomic features from data sets provided by computed tomography, positron emission tomography, and magnetic resonance imaging.

Potentials of radiomics for cancer diagnosis and treatment in comparison with computer-aided diagnosis

Computer-aided diagnosis (CAD) is a field that is essentially based on pattern recognition that improves the accuracy of a diagnosis made by a physician who takes into account the computer's "opinion" derived from the quantitative analysis of radiological images. Radiomics is a field based on data science that massively and comprehensively analyzes a large number of medical images to extract a large number of phenotypic features reflecting disease traits, and explores the associations between the features and patients' prognoses for precision medicine. According to the definitions for both, you may think that radiomics is not a paraphrase of CAD, but you may also think that these definitions are "image manipulation". However, there are common and different features between the two fields. This review paper elaborates on these common and different features and introduces the potential of radiomics for cancer diagnosis and treatment by comparing it with CAD.

Identification of optimal mother wavelets in survival prediction of lung cancer patients using wavelet decomposition-based radiomic features

PURPOSE

To identify the optimal mother wavelets in survival prediction of lung cancer patients using wavelet decomposition-based (WDB) radiomic features in CT images.

MATERIALS AND METHODS

The CT images of patients with histologically confirmed nonsmall cell lung carcinomas (NSCLCs) in training (Dataset T; n = 162) and validation (Dataset V; n = 143) datasets were analyzed for this study. The optimal mother wavelets were identified based on the impacts of the WDB radiomic features on the patient survival times. Four hundred and thirty-two three-dimensional WDB radiomic features were calculated from regions of interest (ROI) of 162 tumor contours. A Coxnet algorithm was used to select a subset of radiomic features (signature) based on the prediction of survival times with a fivefold cross validation. The impacts of the radiomic features on the patients' survival times were assessed by using a multivariate Cox proportional hazard regression (MCPHR) model. The major contribution of this study was to identify optimal mother wavelets based on a maximization of a novel ranking index (RI) incorporating the Coxnet cross-validated partial log-likelihood and the summation of the P-values of the radiomic features in the MCPHR model on Dataset T. The prognostic performance of the optimal mother wavelets was validated based on the concordance index (CI) of the MCPHR models when applied to Dataset V. The proposed approach was tested by using 31 mother wavelets from 6 wavelet families that were available in a commercially available software (Matlab^® 2016b).

RESULTS

The optimal mother wavelets were Symlet 5 and Biorthogonal 2.6 at 128 requantization levels, which yielded RIs of 4.27 ± 0.29 (3 features) and 6.50 ± 0.50 (5 features), respectively. The CIs of the MCPHR models of Symlet 5 were 0.66 ± 0.03 (Dataset T) and 0.64 ± 0.00 (Dataset V), whereas those of Biorthogonal 2.6 were 0.68 ± 0.03 (Dataset T) and 0.62 ± 0.02 (Dataset V). The radiomic signatures included the GLRLM-based LHL gray level nonuniformity feature that demonstrated statistically significant differences in stratifying patients with better and worse prognoses in Datasets T and V.

CONCLUSION

This study has revealed the potential of Symlet and Biorthogonal mother wavelets in  the survival prediction of lung cancer patients by using WDB radiomic features in CT images.

Quantitative vessel tortuosity: A potential CT imaging biomarker for distinguishing lung granulomas from adenocarcinomas

Adenocarcinomas and active granulomas can both have a spiculated appearance on computed tomography (CT) and both are often fluorodeoxyglucose (FDG) avid on positron emission tomography (PET) scan, making them difficult to distinguish. Consequently, patients with benign granulomas are often subjected to invasive surgical biopsies or resections. In this study, quantitative vessel tortuosity (QVT), a novel CT imaging biomarker to distinguish between benign granulomas and adenocarcinomas on routine non-contrast lung CT scans is introduced. Our study comprised of CT scans of 290 patients from two different institutions, one cohort for training (N = 145) and the other (N = 145) for independent validation. In conjunction with a machine learning classifier, the top informative and stable QVT features yielded an area under receiver operating characteristic curve (ROC AUC) of 0.85 in the independent validation set. On the same cohort, the corresponding AUCs for two human experts including a radiologist and a pulmonologist were found to be 0.61 and 0.60, respectively. QVT features also outperformed well known shape and textural radiomic features which had a maximum AUC of 0.73 (p-value = 0.002), as well as features learned using a convolutional neural network AUC = 0.76 (p-value = 0.028). Our results suggest that QVT features could potentially serve as a non-invasive imaging biomarker to distinguish granulomas from adenocarcinomas on non-contrast CT scans.

Lung tumor segmentation methods: Impact on the uncertainty of radiomics features for non-small cell lung cancer

Purpose

To evaluate the uncertainty of radiomics features from contrast-enhanced breath-hold helical CT scans of non-small cell lung cancer for both manual and semi-automatic segmentation due to intra-observer, inter-observer, and inter-software reliability.

Methods

Three radiation oncologists manually delineated lung tumors twice from 10 CT scans using two software tools (3D-Slicer and MIM Maestro). Additionally, three observers without formal clinical training were instructed to use two semi-automatic segmentation tools, Lesion Sizing Toolkit (LSTK) and GrowCut, to delineate the same tumor volumes. The accuracy of the semi-automatic contours was assessed by comparison with physician manual contours using Dice similarity coefficients and Hausdorff distances. Eighty-three radiomics features were calculated for each delineated tumor contour. Informative features were identified based on their dynamic range and correlation to other features. Feature reliability was then evaluated using intra-class correlation coefficients (ICC). Feature range was used to evaluate the uncertainty of the segmentation methods.

Results

From the initial set of 83 features, 40 radiomics features were found to be informative, and these 40 features were used in the subsequent analyses. For both intra-observer and inter-observer reliability, LSTK had higher reliability than GrowCut and the two manual segmentation tools. All observers achieved consistently high ICC values when using LSTK, but the ICC value varied greatly for each observer when using GrowCut and the manual segmentation tools. For inter-software reliability, features were not reproducible across the software tools for either manual or semi-automatic segmentation methods. Additionally, no feature category was found to be more reproducible than another feature category. Feature ranges of LSTK contours were smaller than those of manual contours for all features.

Conclusion

Radiomics features extracted from LSTK contours were highly reliable across and among observers. With semi-automatic segmentation tools, observers without formal clinical training were comparable to physicians in evaluating tumor segmentation.

Parameters Influencing PET Imaging Features: A Phantom Study with Irregular and Heterogeneous Synthetic Lesions

Aim

To evaluate reproducibility and stability of radiomic features as effects of the use of different volume segmentation methods and reconstruction settings. The potential of radiomics in really capturing the presence of heterogeneous tumor uptake and irregular shape was also investigated.

Materials and Methods

An anthropomorphic phantom miming real clinical situations including synthetic lesions with irregular shape and nonuniform radiotracer uptake was used. ¹⁸F-FDG PET/CT measurements of the phantom were performed including 38 lesions of different shape, size, lesion-to-background ratio, and radiotracer uptake distribution. Different reconstruction parameters and segmentation methods were considered. COVs were calculated to quantify feature variations over the different reconstruction settings. Friedman test was applied to the values of the radiomic features obtained for the considered segmentation approaches. Two sets of test-retest measurement were acquired and the pairwise intraclass correlation coefficient was calculated. Fifty-eight morphological and statistical features were extracted from the segmented lesion volumes. A Mann–Whitney test was used to evaluate significant differences among each feature when calculated from heterogeneous versus homogeneous uptake. The significance of each radiomic feature in terms of capturing heterogeneity was evaluated also by testing correlation with gold standard indexes of heterogeneity and sphericity.

Results

The choice of the segmentation method has a strong impact on the stability of radiomic features (less than 20% can be considered stable features). Reconstruction affects the estimate of radiomic features (only 26% are stable). Thirty-one radiomic features (53%) resulted to be reproducible, 11 of them are able to discriminate heterogeneity. Among these, we found a subset of 3 radiomic features strongly correlated with GS heterogeneity index that can be suggested as good features for retrospective evaluations.

Radiomics Nomogram Building From Multiparametric MRI to Predict Grade in Patients With Glioma: A Cohort Study

BACKGROUND

Accurate classification of gliomas is crucial for prescribing therapy and assessing the prognosis of patients.

PURPOSE

To develop a radiomics nomogram using multiparametric MRI for predicting glioma grading.

STUDY TYPE

Retrospective.

POPULATION

This study involved 85 patients (training cohort: n = 56; validation cohort: n = 29) with pathologically confirmed gliomas.

FIELD STRENGTH/SEQUENCE

1.5T MR, containing contrast-enhanced T₁ -weighted (CET₁ WI), axial T₂ -weighted (T₂ WI), and apparent diffusion coefficient (ADC) sequences.

ASSESSMENT

A region of interest of the tumor was delineated. A total of 652 radiomics features were extracted and were reduced using least absolute shrinkage and selection operator regression.

STATISTICAL TESTING

Radiomic signature, participant's age, and gender were analyzed as potential predictors to perform logistic regression analysis and develop a prediction model of glioma grading, and a radiomics nomogram was used to represent this model. The performance of the nomogram was assessed in terms of discrimination, calibration, and clinical value in glioma grading.

RESULTS

The radiomic signature was significantly associated with glioma grade (P < 0.001) in both the training and validation cohorts. The performance of the radiomics nomogram derived from three MRI sequences (with C-index of 0.971 and 0.961 in the training and validation cohorts, respectively) was improved compared to those based on either CET₁ WI, T₂ WI, or ADC alone in glioma grading (with C-index of 0.914, 0.714, 0.842 in the training cohort, and 0.941, 0.500, 0.730 in the validation cohort). The nomogram derived from three sequences showed good calibration: the calibration curve showed good agreement between the estimated and the actual probability. The decision curve demonstrated that combining three sequences had more favorable clinical predictive value than single sequence imaging.

DATA CONCLUSION

We created and assessed a multiparametric MRI-based radiomics nomogram that may help clinicians classify gliomas more accurately.

LEVEL OF EVIDENCE

4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:825-833.

Radiomic analysis of contrast-enhanced ultrasound data

Radiomics describes the use radiological data in a quantitative manner to establish correlations in between imaging biomarkers and clinical outcomes to improve disease diagnosis, treatment monitoring and prediction of therapy responses. In this study, we evaluated whether a radiomic analysis on contrast-enhanced ultrasound (CEUS) data allows to automatically differentiate three xenograft mouse tumour models. Next to conventional imaging biomarker classes, i.e. intensity-based, textural, and wavelet-based features, we included biomarkers describing morphological and functional characteristics of the tumour vasculature. In total, 235 imaging biomarkers were extracted and evaluated. Dedicated feature selection allowed us to identify user-independent and stable imaging biomarkers for each imaging biomarker class. The selected radiomic signature, composed of median image intensity, energy of grey-level co-occurrence matrix, vessel network length, and run length nonuniformity of the grey-level run length matrix from the diagonal details, was used to train a linear support vector machine (SVM) to classify tumour phenotypes. The model was trained by using a four-fold cross-validation scheme and achieved 82.1% (95% CI [0.64 0.92]) correct classifications. In conclusion, our results show that a radiomic analysis can be successfully performed on CEUS data and may help to render ultrasound-based tumour imaging more accurate, reproducible and reliable.

Applicability of a prognostic CT-based radiomic signature model trained on stage I-III non-small cell lung cancer in stage IV non-small cell lung cancer

OBJECTIVES

Recently it has been shown that radiomic features of computed tomography (CT) have prognostic information in stage I-III non-small cell lung cancer (NSCLC) patients. We aim to validate this prognostic radiomic signature in stage IV adenocarcinoma patients undergoing chemotherapy.

MATERIALS AND METHODS

Two datasets of chemo-naive stage IV adenocarcinoma patients were investigated, dataset 1: 285 patients with CTs performed in a single center; dataset 2: 223 patients included in a multicenter clinical trial. The main exclusion criteria were EGFR mutation or unknown mutation status and non-delineated primary tumor. Radiomic features were calculated for the primary tumor. The c-index of cox regression was calculated and compared to the signature performance for overall survival (OS).

RESULTS

In total CT scans from 195 patients were eligible for analysis. Patients having a prognostic index (PI) lower than the signature median (n = 92) had a significantly better OS than patients with a PI higher than the median (n = 103, HR 1.445, 95% CI 1.07-1.95, p = 0.02, c-index 0.576, 95% CI 0.527-0.624).

CONCLUSION

The radiomic signature, derived from daily practice CT scans, has prognostic value for stage IV NSCLC, however the signature performs less than previously described for stage I-III NSCLC stages. In the future, machine learning techniques can potentially lead to a better prognostic imaging based model for stage IV NSCLC.

Comprehensive analysis of lung cancer pathology images to discover tumor shape and boundary features that predict survival outcome

Pathology images capture tumor histomorphological details in high resolution. However, manual detection and characterization of tumor regions in pathology images is labor intensive and subjective. Using a deep convolutional neural network (CNN), we developed an automated tumor region recognition system for lung cancer pathology images. From the identified tumor regions, we extracted 22 well-defined shape and boundary features and found that 15 of them were significantly associated with patient survival outcome in lung adenocarcinoma patients from the National Lung Screening Trial. A tumor region shape-based prognostic model was developed and validated in an independent patient cohort (n = 389). The predicted high-risk group had significantly worse survival than the low-risk group (p value = 0.0029). Predicted risk group serves as an independent prognostic factor (high-risk vs. low-risk, hazard ratio = 2.25, 95% CI 1.34–3.77, p value = 0.0022) after adjusting for age, gender, smoking status, and stage. This study provides new insights into the relationship between tumor shape and patient prognosis.

Radiomics in Nuclear Medicine Applied to Radiation Therapy: Methods, Pitfalls, and Challenges

Radiomics is a recent area of research in precision medicine and is based on the extraction of a large variety of features from medical images. In the field of radiation oncology, comprehensive image analysis is crucial to personalization of treatments. A better characterization of local heterogeneity and the shape of the tumor, depicting individual cancer aggressiveness, could guide dose planning and suggest volumes in which a higher dose is needed for better tumor control. In addition, noninvasive imaging features that could predict treatment outcome from baseline scans could help the radiation oncologist to determine the best treatment strategies and to stratify patients as at low risk or high risk of recurrence. Nuclear medicine molecular imaging reflects information regarding biological processes in the tumor thanks to a wide range of radiotracers. Many studies involving ¹⁸F-fluorodeoxyglucose positron emission tomography suggest an added value of radiomics compared with the use of conventional PET metrics such as standardized uptake value for both tumor diagnosis and prediction of recurrence or treatment outcome. However, these promising results should not hide technical difficulties that still currently prevent the approach from being widely studied or clinically used. These difficulties mostly pertain to the variability of the imaging features as a function of the acquisition device and protocol, the robustness of the models with respect to that variability, and the interpretation of the radiomic models. Addressing the impact of the variability in acquisition and reconstruction protocols is needed, as is harmonizing the radiomic feature calculation methods, to ensure the reproducibility of studies in a multicenter context and their implementation in a clinical workflow. In this review, we explain the potential impact of positron emission tomography radiomics for radiation therapy and underline the various aspects that need to be carefully addressed to make the most of this promising approach.

Prediction of pathological nodal involvement by CT-based Radiomic features of the primary tumor in patients with clinically node-negative peripheral lung adenocarcinomas

PURPOSE

The purpose of this study was to investigate the potential of computed tomography (CT) based radiomic features of primary tumors to predict pathological nodal involvement in clinically node-negative (N0) peripheral lung adenocarcinomas.

METHODS

A total of 187 patients with clinical N0 peripheral lung adenocarcinomas who underwent preoperative CT scan and subsequently received systematic lymph node dissection were retrospectively reviewed. 219 quantitative 3D radiomic features of primary lung tumor were extracted; meanwhile, nine radiological semantic features were evaluated. Univariate and multivariate logistic regression analysis were used to explore the role of these features in predicting pathological nodal involvement. The areas under the ROC curves (AUCs) were compared between multivariate logistic regression models.

RESULTS

A total of 153 patients had pathological N0 status and 34 had pathological lymph node metastasis. On univariate analysis, fissure attachment and 17 radiomic features were significantly associated with pathological nodal involvement. Multivariate analysis revealed that semantic features of pleural retraction (P = 0.048) and fissure attachment (P = 0.023) were significant predictors of pathological nodal involvement (AUC = 0.659); and the radiomic feature F185 (Histogram SD Layer 1) (P = 0.0001) was an independent prognostic factor of pathological nodal involvement (AUC = 0.73). A logistic regression model produced from combining radiomic feature and semantic feature showed the highest AUC of 0.758 (95% CI: 0.685-0.831), and the AUC value computed by fivefold cross-validation method was 0.737 (95% CI: 0.73-0.744).

CONCLUSIONS

Features derived on primary lung tumor described by semantic and radiomic could provide information of pathological nodal involvement in clinical N0 peripheral lung adenocarcinomas.

Radiomics of CT Features May Be Nonreproducible and Redundant: Influence of CT Acquisition Parameters

Purpose To identify the reproducible and nonredundant radiomics features (RFs) for computed tomography (CT). Materials and Methods Two phantoms were used to test RF reproducibility by using test-retest analysis, by changing the CT acquisition parameters (hereafter, intra-CT analysis), and by comparing five different scanners with the same CT parameters (hereafter, inter-CT analysis). Reproducible RFs were selected by using the concordance correlation coefficient (as a measure of the agreement between variables) and the coefficient of variation (defined as the ratio of the standard deviation to the mean). Redundant features were grouped by using hierarchical cluster analysis. Results A total of 177 RFs including intensity, shape, and texture features were evaluated. The test-retest analysis showed that 91% (161 of 177) of the RFs were reproducible according to concordance correlation coefficient. Reproducibility of intra-CT RFs, based on coefficient of variation, ranged from 89.3% (151 of 177) to 43.1% (76 of 177) where the pitch factor and the reconstruction kernel were modified, respectively. Reproducibility of inter-CT RFs, based on coefficient of variation, also showed large material differences, from 85.3% (151 of 177; wood) to only 15.8% (28 of 177; polyurethane). Ten clusters were identified after the hierarchical cluster analysis and one RF per cluster was chosen as representative. Conclusion Many RFs were redundant and nonreproducible. If all the CT parameters are fixed except field of view, tube voltage, and milliamperage, then the information provided by the analyzed RFs can be summarized in only 10 RFs (each representing a cluster) because of redundancy.

Sparse Representation-Based Radiomics for the Diagnosis of Brain Tumors

Brain tumors are the most common malignant neurologic tumors with the highest mortality and disability rate. Because of the delicate structure of the brain, the clinical use of several commonly used biopsy diagnosis is limited for brain tumors. Radiomics is an emerging technique for noninvasive diagnosis based on quantitative medical image analyses. However, current radiomics techniques are not standardized regarding feature extraction, feature selection, and decision making. In this paper, we propose a sparse representation-based radiomics (SRR) system for the diagnosis of brain tumors. First, we developed a dictionary learning- and sparse representation-based feature extraction method that exploits the statistical characteristics of the lesion area, leading to fine and more effective feature extraction compared with the traditional explicitly calculation-based methods. Then, we set up an iterative sparse representation method to solve the redundancy problem of the extracted features. Finally, we proposed a novel multi-feature collaborative sparse representation classification framework that introduces a new coefficient of regularization term to combine features from multi-modal images at the sparse representation coefficient level. Two clinical problems were used to validate the performance and usefulness of the proposed SRR system. One was the differential diagnosis between primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM), and the other was isocitrate dehydrogenase 1 estimation for gliomas. The SRR system had superior PCNSL and GBM differentiation performance compared with some advanced imaging techniques and yielded 11% better performance for estimating IDH1 compared with the traditional radiomics methods.

Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer

PURPOSE

To develop a radiomics prediction model to improve pulmonary nodule (PN) classification in low-dose CT. To compare the model with the American College of Radiology (ACR) Lung CT Screening Reporting and Data System (Lung-RADS) for early detection of lung cancer.

METHODS

We examined a set of 72 PNs (31 benign and 41 malignant) from the Lung Image Database Consortium image collection (LIDC-IDRI). One hundred three CT radiomic features were extracted from each PN. Before the model building process, distinctive features were identified using a hierarchical clustering method. We then constructed a prediction model by using a support vector machine (SVM) classifier coupled with a least absolute shrinkage and selection operator (LASSO). A tenfold cross-validation (CV) was repeated ten times (10 × 10-fold CV) to evaluate the accuracy of the SVM-LASSO model. Finally, the best model from the 10 × 10-fold CV was further evaluated using 20 × 5- and 50 × 2-fold CVs.

RESULTS

The best SVM-LASSO model consisted of only two features: the bounding box anterior-posterior dimension (BB_AP) and the standard deviation of inverse difference moment (SD_IDM). The BB_AP measured the extension of a PN in the anterior-posterior direction and was highly correlated (r = 0.94) with the PN size. The SD_IDM was a texture feature that measured the directional variation of the local homogeneity feature IDM. Univariate analysis showed that both features were statistically significant and discriminative (P = 0.00013 and 0.000038, respectively). PNs with larger BB_AP or smaller SD_IDM were more likely malignant. The 10 × 10-fold CV of the best SVM model using the two features achieved an accuracy of 84.6% and 0.89 AUC. By comparison, Lung-RADS achieved an accuracy of 72.2% and 0.77 AUC using four features (size, type, calcification, and spiculation). The prediction improvement of SVM-LASSO comparing to Lung-RADS was statistically significant (McNemar's test P = 0.026). Lung-RADS misclassified 19 cases because it was mainly based on PN size, whereas the SVM-LASSO model correctly classified 10 of these cases by combining a size (BB_AP) feature and a texture (SD_IDM) feature. The performance of the SVM-LASSO model was stable when leaving more patients out with five- and twofold CVs (accuracy 84.1% and 81.6%, respectively).

CONCLUSION

We developed an SVM-LASSO model to predict malignancy of PNs with two CT radiomic features. We demonstrated that the model achieved an accuracy of 84.6%, which was 12.4% higher than Lung-RADS.

Emergence of Radiomics: Novel Methodology Identifying Imaging Biomarkers of Disease in Diagnosis, Response, and Progression

Radiomics is an emerging area within clinical radiology research. It seeks to take full advantage of all the information contained in multiple medical imaging modalities. With a radiomics approach, medical images are not limited to providing only a qualitative assessment but can also provide quantitative data by parameterizing image features. These parameters can be used to identify regions and volumes of interest and discriminate normal healthy tissue from abnormal or diseased tissue. Radiomics is an interlinked sequence of processes of vital importance that begins with the acquisition and selection of medical images that involve standardization of acquisition protocols and inter-equipment normalization. This is followed by the identification and segmentation of regions or volumes of interest by expert radiologists through the use of computational tools that offer speed while reducing variability and bias. The segmentation process is the most critical stage in radiomics. This sometimes requires the incorporation of a pre-processing stage consisting of advanced techniques (reconstruction processes, filtering, etc.). Thereafter, representative characteristics of the region or volume of interest are extracted by approaches based on statistics, morphological features, and transform-based variables. Next, a statistical selection of the parameters that provide a high association and correlation with the clinical condition of interest is performed. Finally, processes such as data integration, standardization, classification, and mining processes can be applied as needed for particular applications. Ongoing research in radiomics aims to reduce the time and costs involved in interpreting medical images while simultaneously increasing the quality of diagnoses and monitoring of as well as the selection of treatment strategies. The results of many studies combining radiomics with standard medical techniques are highly encouraging, and these new approaches are increasingly used. This review article details the components of radiomics and discusses its applications, challenges, and future directions for this exciting new field of study.

Combining radiomic features with a miRNA classifier may improve prediction of malignant pathology for pancreatic intraductal papillary mucinous neoplasms

Intraductal papillary mucinous neoplasms (IPMNs) are pancreatic cancer precursors incidentally discovered by cross-sectional imaging. Consensus guidelines for IPMN management rely on standard radiologic features to predict pathology, but they lack accuracy. Using a retrospective cohort of 38 surgically-resected, pathologically-confirmed IPMNs (20 benign; 18 malignant) with preoperative computed tomography (CT) images and matched plasma-based ‘miRNA genomic classifier (MGC)’ data, we determined whether quantitative ‘radiomic’ CT features (+/- the MGC) can more accurately predict IPMN pathology than standard radiologic features ‘high-risk’ or ‘worrisome’ for malignancy. Logistic regression, principal component analyses, and cross-validation were used to examine associations. Sensitivity, specificity, positive and negative predictive value (PPV, NPV) were estimated. The MGC, ‘high-risk,’ and ‘worrisome’ radiologic features had area under the receiver operating characteristic curve (AUC) values of 0.83, 0.84, and 0.54, respectively. Fourteen radiomic features differentiated malignant from benign IPMNs (p<0.05) and collectively had an AUC=0.77. Combining radiomic features with the MGC revealed an AUC=0.92 and superior sensitivity (83%), specificity (89%), PPV (88%), and NPV (85%) than other models. Evaluation of uncertainty by 10-fold cross-validation retained an AUC>0.80 (0.87 (95% CI:0.84-0.89)). This proof-of-concept study suggests a noninvasive radiogenomic approach may more accurately predict IPMN pathology than ‘worrisome’ radiologic features considered in consensus guidelines.