Applications and limitations of radiomics

Promoting Collaborations Between Radiologists and Scientists

Radiology as a discipline thrives on the dynamic interplay between technological and clinical advances. Progress in almost all facets of the imaging sciences is highly dependent on complex tools sourced from physics, engineering, biology, and the clinical sciences to obtain, process, and view imaging studies. The application of these tools, however, requires broad and deep medical knowledge about disease pathophysiology and its relationship with medical imaging. This relationship between clinical medicine and imaging technology, nurtured and fostered over the past 75 years, has cultivated extraordinarily rich collaborative opportunities between basic scientists, engineers, and physicians. In this review, we attempt to provide a framework to identify both currently successful collaborative ventures and future opportunities for scientific partnership. This invited review is a product of a special working group within the Association of University Radiologists-Radiology Research Alliance.

Tree-based Methods for Characterizing Tumor Density Heterogeneity

Solid lesions emerge within diverse tissue environments making their characterization and diagnosis a challenge. With the advent of cancer radiomics, a variety of techniques have been developed to transform images into quantifiable feature sets producing summary statistics that describe the morphology and texture of solid masses. Relying on empirical distribution summaries as well as grey-level co-occurrence statistics, several approaches have been devised to characterize tissue density heterogeneity. This article proposes a novel decision-tree based approach which quantifies the tissue density heterogeneity of a given lesion through its resultant distribution of tree-structured dissimilarity metrics computed with least common ancestor trees under repeated pixel re-sampling. The methodology, based on statistics derived from Galton-Watson trees, produces metrics that are minimally correlated with existing features, adding new information to the feature space and improving quantitative characterization of the extent to which a CT image conveys heterogeneous density distribution. We demonstrate its practical application through a diagnostic study of adrenal lesions. Integrating the proposed with existing features identifies classifiers of three important lesion types; malignant from benign (AUC = 0.78), functioning from non-functioning (AUC = 0.93) and calcified from non-calcified (AUC of 1).

Towards precision medicine: from quantitative imaging to radiomics

Radiology (imaging) and imaging-guided interventions, which provide multi-parametric morphologic and functional information, are playing an increasingly significant role in precision medicine. Radiologists are trained to understand the imaging phenotypes, transcribe those observations (phenotypes) to correlate with underlying diseases and to characterize the images. However, in order to understand and characterize the molecular phenotype (to obtain genomic information) of solid heterogeneous tumours, the advanced sequencing of those tissues using biopsy is required. Thus, radiologists image the tissues from various views and angles in order to have the complete image phenotypes, thereby acquiring a huge amount of data. Deriving meaningful details from all these radiological data becomes challenging and raises the big data issues. Therefore, interest in the application of radiomics has been growing in recent years as it has the potential to provide significant interpretive and predictive information for decision support. Radiomics is a combination of conventional computer-aided diagnosis, deep learning methods, and human skills, and thus can be used for quantitative characterization of tumour phenotypes. This paper discusses the overview of radiomics workflow, the results of various radiomics-based studies conducted using various radiological images such as computed tomography (CT), magnetic resonance imaging (MRI), and positron-emission tomography (PET), the challenges we are facing, and the potential contribution of radiomics towards precision medicine.

Computed tomography-based radiomics for prediction of neoadjuvant chemotherapy outcomes in locally advanced gastric cancer: A pilot study

Objective

The standard treatment for patients with locally advanced gastric cancer has relied on perioperative radio-chemotherapy or chemotherapy and surgery. The aim of this study was to investigate the wealth of radiomics for pre-treatment computed tomography (CT) in the prediction of the pathological response of locally advanced gastric cancer with preoperative chemotherapy.

Methods

Thirty consecutive patients with CT-staged II/III gastric cancer receiving neoadjuvant chemotherapy were enrolled in this study between December 2014 and March 2017. All patients underwent upper abdominal CT during the unenhanced, late arterial phase (AP) and portal venous phase (PP) before the administration of neoadjuvant chemotherapy. In total, 19,985 radiomics features were extracted in the AP and PP for each patient. Four methods were adopted during feature selection and eight methods were used in the process of building the classifier model. Thirty-two combinations of feature selection and classification methods were examined. Receiver operating characteristic (ROC) curves were used to evaluate the capability of each combination of feature selection and classification method to predict a non-good response (non-GR) based on tumor regression grade (TRG).

Results

The mean area under the curve (AUC) ranged from 0.194 to 0.621 in the AP, and from 0.455 to 0.722 in the PP, according to different combinations of feature selection and the classification methods. There was only one cross-combination machine-learning method indicating a relatively higher AUC (>0.600) in the AP, while 12 cross-combination machine-learning methods presented relatively higher AUCs (all >0.600) in the PP. The feature selection method adopted by a filter based on linear discriminant analysis + classifier of random forest achieved a significantly prognostic performance in the PP (AUC, 0.722±0.108; accuracy, 0.793; sensitivity, 0.636; specificity, 0.889; Z=2.039; P=0.041).

Conclusions

It is possible to predict non-GR after neoadjuvant chemotherapy in locally advanced gastric cancers based on the radiomics of CT.

Radiomics for Response and Outcome Assessment for Non-Small Cell Lung Cancer

Routine follow-up visits and radiographic imaging are required for outcome evaluation and tumor recurrence monitoring. Yet more personalized surveillance is required in order to sufficiently address the nature of heterogeneity in nonsmall cell lung cancer and possible recurrences upon completion of treatment. Radiomics, an emerging noninvasive technology using medical imaging analysis and data mining methodology, has been adopted to the area of cancer diagnostics in recent years. Its potential application in response assessment for cancer treatment has also drawn considerable attention. Radiomics seeks to extract a large amount of valuable information from patients' medical images (both pretreatment and follow-up images) and quantitatively correlate image features with diagnostic and therapeutic outcomes. Radiomics relies on computers to identify and analyze vast amounts of quantitative image features that were previously overlooked, unmanageable, or failed to be identified (and recorded) by human eyes. The research area has been focusing on the predictive accuracy of pretreatment features for outcome and response and the early discovery of signs of tumor response, recurrence, distant metastasis, radiation-induced lung injury, death, and other outcomes, respectively. This review summarized the application of radiomics in response assessments in radiotherapy and chemotherapy for non-small cell lung cancer, including image acquisition/reconstruction, region of interest definition/segmentation, feature extraction, and feature selection and classification. The literature search for references of this article includes PubMed peer-reviewed publications over the last 10 years on the topics of radiomics, textural features, radiotherapy, chemotherapy, lung cancer, and response assessment. Summary tables of radiomics in response assessment and treatment outcome prediction in radiation oncology have been developed based on the comprehensive review of the literature.

High-dimensional regression analysis links magnetic resonance imaging features and protein expression and signaling pathway alterations in breast invasive carcinoma

BACKGROUND

Imaging features derived from MRI scans can be used for not only breast cancer detection and measuring disease extent, but can also determine gene expression and patient outcomes. The relationships between imaging features, gene/protein expression, and response to therapy hold potential to guide personalized medicine. We aim to characterize the relationship between radiologist-annotated tumor phenotypic features (based on MRI) and the underlying biological processes (based on proteomic profiling) in the tumor.

METHODS

Multiple-response regression of the image-derived, radiologist-scored features with reverse-phase protein array expression levels generated association coefficients for each combination of image-feature and protein in the RPPA dataset. Significantly-associated proteins for features were analyzed with Ingenuity Pathway Analysis software. Hierarchical clustering of the results of the pathway analysis determined which features were most strongly correlated with pathway activity and cellular functions.

RESULTS

Each of the twenty-nine imaging features was found to have a set of significantly correlated molecules, associated biological functions, and pathways.

CONCLUSIONS

We interrogated the pathway alterations represented by the protein expression associated with each imaging feature. Our study demonstrates the relationships between biological processes (via proteomic measurements) and MRI features within breast tumors.

Prediction of outcome using pretreatment 18F-FDG PET/CT and MRI radiomics in locally advanced cervical cancer treated with chemoradiotherapy

PURPOSE

The aim of this study is to determine if radiomics features from ¹⁸fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) and magnetic resonance imaging (MRI) images could contribute to prognoses in cervical cancer.

METHODS

One hundred and two patients (69 for training and 33 for testing) with locally advanced cervical cancer (LACC) receiving chemoradiotherapy (CRT) from 08/2010 to 12/2016 were enrolled in this study. ¹⁸F-FDG PET/CT and MRI examination [T1, T2, T1C, diffusion-weighted imaging (DWI)] were performed for each patient before CRT. Primary tumor volumes were delineated with the fuzzy locally adaptive Bayesian algorithm in the PET images and with 3D Slicer™ in the MRI images. Radiomics features (intensity, shape, and texture) were extracted and their prognostic value was compared with clinical parameters for recurrence-free and locoregional control.

RESULTS

In the training cohort, median follow-up was 3.0 years (range, 0.43-6.56 years) and relapse occurred in 36% of patients. In univariate analysis, FIGO stage (I-II vs. III-IV) and metabolic response (complete vs. non-complete) were probably associated with outcome without reaching statistical significance, contrary to several radiomics features from both PET and MRI sequences. Multivariate analysis in training test identified Grey Level Non Uniformity_GLRLM in PET and Entropy_GLCM in ADC maps from DWI MRI as independent prognostic factors. These had significantly higher prognostic power than clinical parameters, as evaluated in the testing cohort with accuracy of 94% for predicting recurrence and 100% for predicting lack of loco-regional control (versus ~50-60% for clinical parameters).

CONCLUSIONS

In LACC treated with CRT, radiomics features such as EntropyGLCM and GLNUGLRLM from functional imaging DWI-MRI and PET, respectively, are independent predictors of recurrence and loco-regional control with significantly higher prognostic power than usual clinical parameters. Further research is warranted for their validation, which may justify more aggressive treatment in patients identified with high probability of recurrence.

Classification of early stage non-small cell lung cancers on computed tomographic images into histological types using radiomic features: interobserver delineation variability analysis

Radiomics, which involves the extraction of large numbers of quantitative features from medical images, has attracted attention in cancer research. In radiomics analysis, tumor segmentation is a crucial step. In this study, we evaluated the potential application of radiomics for predicting the histology of early stage non-small cell lung cancer (NSCLC) by analyzing interobserver variability in tumor delineation. Forty patient datasets were included in this study, 21 involving adenocarcinomas and 19 involving squamous cell carcinomas. All patients underwent stereotactic body radiotherapy treatment. In total, 476 features were extracted from each dataset, representing treatment planning, computed tomography images, and gross tumor volume (GTV). The definition of GTV can significantly affect the histology prediction. Therefore, in the present study, the effect of interobserver tumor delineation variability on radiomic features was evaluated by preparing 4 volumes of interest (VOIs) for each patient, as follows: the original GTV (which was delineated at treatment planning); two GTVs delineated retrospectively by radiation oncologists; and a semi-automatic GTV contoured by a medical physicist. Radiomic features extracted from each VOI were then analyzed using a naïve Bayesian model. Area-under-the-curve (AUC) analysis showed that interobserver variability in delineation is a significant factor in radiomics performance. Nevertheless, with 8 selected features, AUC values averaged over the VOIs were high (0.725 ± 0.070). The present study indicated that radiomics has potential for predicting early stage NSCLC histology despite variability in delineation. The high prediction accuracy implies that noninvasive histology evaluation by radiomics is a promising clinical application.

Current status and future challenges for molecular imaging

Molecular imaging (MI), used in its wider sense of biology at the molecular level, is a field that lies at the intersection of molecular biology and traditional medical imaging. As advances in medicine have exponentially expanded over the last few decades, so has our need to better understand the fundamental behaviour of living organisms in a non-invasive and timely manner. This commentary draws from topics the authors addressed in their presentations at the 2017 Royal Society Meeting 'Challenges for chemistry in molecular imaging', as well as a discussion of where MI is today and where it is heading in the future.This article is part of the themed issue 'Challenges for chemistry in molecular imaging'.

Computational Radiomics System to Decode the Radiographic Phenotype

Radiomics aims to quantify phenotypic characteristics on medical imaging through the use of automated algorithms. Radiomic artificial intelligence (AI) technology, either based on engineered hard-coded algorithms or deep learning methods, can be used to develop noninvasive imaging-based biomarkers. However, lack of standardized algorithm definitions and image processing severely hampers reproducibility and comparability of results. To address this issue, we developed PyRadiomics, a flexible open-source platform capable of extracting a large panel of engineered features from medical images. PyRadiomics is implemented in Python and can be used standalone or using 3D Slicer. Here, we discuss the workflow and architecture of PyRadiomics and demonstrate its application in characterizing lung lesions. Source code, documentation, and examples are publicly available at www.radiomics.io With this platform, we aim to establish a reference standard for radiomic analyses, provide a tested and maintained resource, and to grow the community of radiomic developers addressing critical needs in cancer research. Cancer Res; 77(21); e104-7. ©2017 AACR.

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.

Radiographic prediction of meningioma grade by semantic and radiomic features

OBJECTIVES

The clinical management of meningioma is guided by tumor grade and biological behavior. Currently, the assessment of tumor grade follows surgical resection and histopathologic review. Reliable techniques for pre-operative determination of tumor grade may enhance clinical decision-making.

METHODS

A total of 175 meningioma patients (103 low-grade and 72 high-grade) with pre-operative contrast-enhanced T1-MRI were included. Fifteen radiomic (quantitative) and 10 semantic (qualitative) features were applied to quantify the imaging phenotype. Area under the curve (AUC) and odd ratios (OR) were computed with multiple-hypothesis correction. Random-forest classifiers were developed and validated on an independent dataset (n = 44).

RESULTS

Twelve radiographic features (eight radiomic and four semantic) were significantly associated with meningioma grade. High-grade tumors exhibited necrosis/hemorrhage (ORsem = 6.6, AUCrad = 0.62-0.68), intratumoral heterogeneity (ORsem = 7.9, AUCrad = 0.65), non-spherical shape (AUCrad = 0.61), and larger volumes (AUCrad = 0.69) compared to low-grade tumors. Radiomic and sematic classifiers could significantly predict meningioma grade (AUCsem = 0.76 and AUCrad = 0.78). Furthermore, combining them increased the classification power (AUCradio = 0.86). Clinical variables alone did not effectively predict tumor grade (AUCclin = 0.65) or show complementary value with imaging data (AUCcomb = 0.84).

CONCLUSIONS

We found a strong association between imaging features of meningioma and histopathologic grade, with ready application to clinical management. Combining qualitative and quantitative radiographic features significantly improved classification power.

Post-radiochemotherapy PET radiomics in head and neck cancer - The influence of radiomics implementation on the reproducibility of local control tumor models

PURPOSE

This study investigated an association of post-radiochemotherapy (RCT) PET radiomics with local tumor control in head and neck squamous cell carcinoma (HNSCC) and evaluated the models against two radiomics software implementations.

MATERIALS AND METHODS

649 features, available in two radiomics implementations and based on the same definitions, were extracted from HNSCC primary tumor region in 18F-FDG PET scans 3 months post definitive RCT (training cohort n = 128, validation cohort n = 50) and compared using the intraclass correlation coefficient (ICC). Local recurrence models were trained, separately for both implementations, using principal component analysis (PCA) and the least absolute shrinkage and selection operator. The reproducibility of the concordance indexes (CI) in univariable Cox regression for features preselected in PCA and the final multivariable models was investigated using respective features from the other implementation.

RESULTS

Only 80 PET radiomic features yielded ICC > 0.8 in the comparison between the implementations. The change of implementation caused high variability of CI in the univariable analysis. However, both final multivariable models performed equally well in the training and validation cohorts (CI > 0.7) independent of radiomics implementation.

CONCLUSION

The two post-RCT PET radiomic models, based on two different software implementations, were prognostic for local tumor control in HNSCC. However, 88% of the features was not reproducible between the implementations.

Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma

PURPOSE

An association between radiomic features extracted from CT and local tumor control in the head and neck squamous cell carcinoma (HNSCC) has been shown. This study investigated the value of pretreatment functional imaging (18F-FDG PET) radiomics for modeling of local tumor control.

MATERIAL AND METHODS

Data from HNSCC patients (n = 121) treated with definitive radiochemotherapy were used for model training. In total, 569 radiomic features were extracted from both contrast-enhanced CT and 18F-FDG PET images in the primary tumor region. CT, PET and combined PET/CT radiomic models to assess local tumor control were trained separately. Five feature selection and three classification methods were implemented. The performance of the models was quantified using concordance index (CI) in 5-fold cross validation in the training cohort. The best models, per image modality, were compared and verified in the independent validation cohort (n = 51). The difference in CI was investigated using bootstrapping. Additionally, the observed and radiomics-based estimated probabilities of local tumor control were compared between two risk groups.

RESULTS

The feature selection using principal component analysis and the classification based on the multivariabale Cox regression with backward selection of the variables resulted in the best models for all image modalities (CI_CT = 0.72, CI_PET = 0.74, CI_PET/CT = 0.77). Tumors more homogenous in CT density (decreased GLSZM_{size_zone_entropy}) and with a focused region of high FDG uptake (higher GLSZM_SZLGE) indicated better prognosis. No significant difference in the performance of the models in the validation cohort was observed (CI_CT = 0.73, CI_PET = 0.71, CI_PET/CT = 0.73). However, the CT radiomics-based model overestimated the probability of tumor control in the poor prognostic group (predicted  = 68%, observed  = 56%).

CONCLUSIONS

Both CT and PET radiomics showed equally good discriminative power for local tumor control modeling in HNSCC. However, CT-based predictions overestimated the local control rate in the poor prognostic validation cohort, and thus, we recommend to base the local control modeling on the 18F-FDG PET.

A comparative study of machine learning methods for time-to-event survival data for radiomics risk modelling

Radiomics applies machine learning algorithms to quantitative imaging data to characterise the tumour phenotype and predict clinical outcome. For the development of radiomics risk models, a variety of different algorithms is available and it is not clear which one gives optimal results. Therefore, we assessed the performance of 11 machine learning algorithms combined with 12 feature selection methods by the concordance index (C-Index), to predict loco-regional tumour control (LRC) and overall survival for patients with head and neck squamous cell carcinoma. The considered algorithms are able to deal with continuous time-to-event survival data. Feature selection and model building were performed on a multicentre cohort (213 patients) and validated using an independent cohort (80 patients). We found several combinations of machine learning algorithms and feature selection methods which achieve similar results, e.g.

, MSR-RF

C-Index = 0.71 and BT-COX: C-Index = 0.70 in combination with Spearman feature selection. Using the best performing models, patients were stratified into groups of low and high risk of recurrence. Significant differences in LRC were obtained between both groups on the validation cohort. Based on the presented analysis, we identified a subset of algorithms which should be considered in future radiomics studies to develop stable and clinically relevant predictive models for time-to-event endpoints.

Radiomics: the bridge between medical imaging and personalized medicine

Radiomics, the high-throughput mining of quantitative image features from standard-of-care medical imaging that enables data to be extracted and applied within clinical-decision support systems to improve diagnostic, prognostic, and predictive accuracy, is gaining importance in cancer research. Radiomic analysis exploits sophisticated image analysis tools and the rapid development and validation of medical imaging data that uses image-based signatures for precision diagnosis and treatment, providing a powerful tool in modern medicine. Herein, we describe the process of radiomics, its pitfalls, challenges, opportunities, and its capacity to improve clinical decision making, emphasizing the utility for patients with cancer. Currently, the field of radiomics lacks standardized evaluation of both the scientific integrity and the clinical relevance of the numerous published radiomics investigations resulting from the rapid growth of this area. Rigorous evaluation criteria and reporting guidelines need to be established in order for radiomics to mature as a discipline. Herein, we provide guidance for investigations to meet this urgent need in the field of radiomics.

Can CT and MR Shape and Textural Features Differentiate Benign Versus Malignant Pleural Lesions?

RATIONALE AND OBJECTIVES

The study aimed to identify a radiomic approach based on CT and or magnetic resonance (MR) features (shape and texture) that may help differentiate benign versus malignant pleural lesions, and to assess if the radiomic model may improve confidence and accuracy of radiologists with different subspecialty backgrounds.

MATERIALS AND METHODS

Twenty-nine patients with pleural lesions studied on both contrast-enhanced CT and MR imaging were reviewed retrospectively. Three texture and three shape features were extracted. Combinations of features were used to generate logistic regression models using histopathology as outcome. Two thoracic and two abdominal radiologists evaluated their degree of confidence in malignancy. Diagnostic accuracy of radiologists was determined using contingency tables. Cohen's kappa coefficient was used to assess inter-reader agreement. Using optimal threshold criteria, sensitivity, specificity, and accuracy of each feature and combination of features were obtained and compared to the accuracy and confidence of radiologists.

RESULTS

The CT model that best discriminated malignant from benign lesions revealed an AUC_CT = 0.92 ± 0.05 (P < 0.0001). The most discriminative MR model showed an AUC_MR = 0.87 ± 0.09 (P < 0.0001). The CT model was compared to the diagnostic confidence of all radiologists and the model outperformed both abdominal radiologists (P < 0.002), whereas the top discriminative MR model outperformed one of the abdominal radiologists (P = 0.02). The most discriminative MR model was more accurate than one abdominal (P = 0.04) and one thoracic radiologist (P = 0.02).

CONCLUSION

Quantitative textural and shape analysis may help distinguish malignant from benign lesions. A radiomics-based approach may increase diagnostic confidence of abdominal radiologists on CT and MR and may potentially improve radiologists' accuracy in the assessment of pleural lesions characterized by MR.

A review of GPU-based medical image reconstruction

Tomographic image reconstruction is a computationally demanding task, even more so when advanced models are used to describe a more complete and accurate picture of the image formation process. Such advanced modeling and reconstruction algorithms can lead to better images, often with less dose, but at the price of long calculation times that are hardly compatible with clinical workflows. Fortunately, reconstruction tasks can often be executed advantageously on Graphics Processing Units (GPUs), which are exploited as massively parallel computational engines. This review paper focuses on recent developments made in GPU-based medical image reconstruction, from a CT, PET, SPECT, MRI and US perspective. Strategies and approaches to get the most out of GPUs in image reconstruction are presented as well as innovative applications arising from an increased computing capacity. The future of GPU-based image reconstruction is also envisioned, based on current trends in high-performance computing.

Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer

Quantitative extraction of high-dimensional mineable data from medical images is a process known as radiomics. Radiomics is foreseen as an essential prognostic tool for cancer risk assessment and the quantification of intratumoural heterogeneity. In this work, 1615 radiomic features (quantifying tumour image intensity, shape, texture) extracted from pre-treatment FDG-PET and CT images of 300 patients from four different cohorts were analyzed for the risk assessment of locoregional recurrences (LR) and distant metastases (DM) in head-and-neck cancer. Prediction models combining radiomic and clinical variables were constructed via random forests and imbalance-adjustment strategies using two of the four cohorts. Independent validation of the prediction and prognostic performance of the models was carried out on the other two cohorts (LR: AUC = 0.69 and CI = 0.67; DM: AUC = 0.86 and CI = 0.88). Furthermore, the results obtained via Kaplan-Meier analysis demonstrated the potential of radiomics for assessing the risk of specific tumour outcomes using multiple stratification groups. This could have important clinical impact, notably by allowing for a better personalization of chemo-radiation treatments for head-and-neck cancer patients from different risk groups.

Radiomics Analysis on Ultrasound for Prediction of Biologic Behavior in Breast Invasive Ductal Carcinoma

INTRODUCTION

In current clinical practice, invasive ductal carcinoma is always screened using medical imaging techniques and diagnosed using immunohistochemistry. Recent studies have illustrated that radiomics approaches provide a comprehensive characterization of entire tumors and can reveal predictive or prognostic associations between the images and medical outcomes. To better reveal the underlying biology, an improved understanding between objective image features and biologic characteristics is urgently required.

PATIENTS AND METHODS

A total of 215 patients with definite histologic results were enrolled in our study. The tumors were automatically segmented using our phase-based active contour model. The high-throughput radiomics features were designed and extracted using a breast imaging reporting and data system and further selected using Student's t test, interfeature coefficients and a lasso regression model. The support vector machine classifier with threefold cross-validation was used to evaluate the relationship.

RESULTS

The radiomics approach demonstrated a strong correlation between receptor status and subtypes (P < .05; area under the curve, 0.760). The appearance of hormone receptor-positive cancer and human epidermal growth factor receptor 2-negative cancer on ultrasound scans differs from that of triple-negative cancer.

CONCLUSION

Our approach could assist clinicians with the accurate prediction of prognosis using ultrasound findings, allowing for early medical management and treatment.

"Radio-oncomics" : The potential of radiomics in radiation oncology

INTRODUCTION

Radiomics, a recently introduced concept, describes quantitative computerized algorithm-based feature extraction from imaging data including computer tomography (CT), magnetic resonance imaging (MRT), or positron-emission tomography (PET) images. For radiation oncology it offers the potential to significantly influence clinical decision-making and thus therapy planning and follow-up workflow.

METHODS

After image acquisition, image preprocessing, and defining regions of interest by structure segmentation, algorithms are applied to calculate shape, intensity, texture, and multiscale filter features. By combining multiple features and correlating them with clinical outcome, prognostic models can be created.

RESULTS

Retrospective studies have proposed radiomics classifiers predicting, e. g., overall survival, radiation treatment response, distant metastases, or radiation-related toxicity. Besides, radiomics features can be correlated with genomic information ("radiogenomics") and could be used for tumor characterization.

DISCUSSION

Distinct patterns based on data-based as well as genomics-based features will influence radiation oncology in the future. Individualized treatments in terms of dose level adaption and target volume definition, as well as other outcome-related parameters will depend on radiomics and radiogenomics. By integration of various datasets, the prognostic power can be increased making radiomics a valuable part of future precision medicine approaches.

CONCLUSION

This perspective demonstrates the evidence for the radiomics concept in radiation oncology. The necessity of further studies to integrate radiomics classifiers into clinical decision-making and the radiation therapy workflow is emphasized.

Associations between radiologist-defined semantic and automatically computed radiomic features in non-small cell lung cancer

Tumor phenotypes captured in computed tomography (CT) images can be described qualitatively and quantitatively using radiologist-defined "semantic" and computer-derived "radiomic" features, respectively. While both types of features have shown to be promising predictors of prognosis, the association between these groups of features remains unclear. We investigated the associations between semantic and radiomic features in CT images of 258 non-small cell lung adenocarcinomas. The tumor imaging phenotypes were described using 9 qualitative semantic features that were scored by radiologists, and 57 quantitative radiomic features that were automatically calculated using mathematical algorithms. Of the 9 semantic features, 3 were rated on a binary scale (cavitation, air bronchogram, and calcification) and 6 were rated on a categorical scale (texture, border definition, contour, lobulation, spiculation, and concavity). 32-41 radiomic features were associated with the binary semantic features (AUC = 0.56-0.76). The relationship between all radiomic features and the categorical semantic features ranged from weak to moderate (|Spearmen's correlation| = 0.002-0.65). There are associations between semantic and radiomic features, however the associations were not strong despite being significant. Our results indicate that radiomic features may capture distinct tumor phenotypes that fail to be perceived by naked eye that semantic features do not describe and vice versa.

Application of the 3D slicer chest imaging platform segmentation algorithm for large lung nodule delineation

PURPOSE

Accurate segmentation of lung nodules is crucial in the development of imaging biomarkers for predicting malignancy of the nodules. Manual segmentation is time consuming and affected by inter-observer variability. We evaluated the robustness and accuracy of a publically available semiautomatic segmentation algorithm that is implemented in the 3D Slicer Chest Imaging Platform (CIP) and compared it with the performance of manual segmentation.

METHODS

CT images of 354 manually segmented nodules were downloaded from the LIDC database. Four radiologists performed the manual segmentation and assessed various nodule characteristics. The semiautomatic CIP segmentation was initialized using the centroid of the manual segmentations, thereby generating four contours for each nodule. The robustness of both segmentation methods was assessed using the region of uncertainty (δ) and Dice similarity index (DSI). The robustness of the segmentation methods was compared using the Wilcoxon-signed rank test (pWilcoxon<0.05). The Dice similarity index (DSIAgree) between the manual and CIP segmentations was computed to estimate the accuracy of the semiautomatic contours.

RESULTS

The median computational time of the CIP segmentation was 10 s. The median CIP and manually segmented volumes were 477 ml and 309 ml, respectively. CIP segmentations were significantly more robust than manual segmentations (median δCIP = 14ml, median dsiCIP = 99% vs. median δmanual = 222ml, median dsimanual = 82%) with pWilcoxon~10-16. The agreement between CIP and manual segmentations had a median DSIAgree of 60%. While 13% (47/354) of the nodules did not require any manual adjustment, minor to substantial manual adjustments were needed for 87% (305/354) of the nodules. CIP segmentations were observed to perform poorly (median DSIAgree≈50%) for non-/sub-solid nodules with subtle appearances and poorly defined boundaries.

CONCLUSION

Semi-automatic CIP segmentation can potentially reduce the physician workload for 13% of nodules owing to its computational efficiency and superior stability compared to manual segmentation. Although manual adjustment is needed for many cases, CIP segmentation provides a preliminary contour for physicians as a starting point.

Beyond imaging: The promise of radiomics

The domain of investigation of radiomics consists of large-scale radiological image analysis and association with biological or clinical endpoints. The purpose of the present study is to provide a recent update on the status of this rapidly emerging field by performing a systematic review of the literature on radiomics, with a primary focus on oncologic applications. The systematic literature search, performed in Pubmed using the keywords: "radiomics OR radiomic" provided 97 research papers. Based on the results of this search, we describe the methods used for building a model of prognostic value from quantitative analysis of patient images. Then, we provide an up-to-date overview of the results achieved in this field, and discuss the current challenges and future developments of radiomics for oncology.

Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardization

Purpose

Textural measures have been widely explored as imaging biomarkers in cancer. However, their robustness under dynamic range and spatial resolution changes in brain 3D magnetic resonance images (MRI) has not been assessed. The aim of this work was to study potential variations of textural measures due to changes in MRI protocols.

Materials and methods

Twenty patients harboring glioblastoma with pretreatment 3D T1-weighted MRIs were included in the study. Four different spatial resolution combinations and three dynamic ranges were studied for each patient. Sixteen three-dimensional textural heterogeneity measures were computed for each patient and configuration including co-occurrence matrices (CM) features and run-length matrices (RLM) features. The coefficient of variation was used to assess the robustness of the measures in two series of experiments corresponding to (i) changing the dynamic range and (ii) changing the matrix size.

Results

No textural measures were robust under dynamic range changes. Entropy was the only textural feature robust under spatial resolution changes (coefficient of variation under 10% in all cases).

Conclusion

Textural measures of three-dimensional brain tumor images are not robust neither under dynamic range nor under matrix size changes. Standards should be harmonized to use textural features as imaging biomarkers in radiomic-based studies. The implications of this work go beyond the specific tumor type studied here and pose the need for standardization in textural feature calculation of oncological images.

Somatic Mutations Drive Distinct Imaging Phenotypes in Lung Cancer

Tumors are characterized by somatic mutations that drive biological processes ultimately reflected in tumor phenotype. With regard to radiographic phenotypes, generally unconnected through present understanding to the presence of specific mutations, artificial intelligence methods can automatically quantify phenotypic characters by using predefined, engineered algorithms or automatic deep-learning methods, a process also known as radiomics. Here we demonstrate how imaging phenotypes can be connected to somatic mutations through an integrated analysis of independent datasets of 763 lung adenocarcinoma patients with somatic mutation testing and engineered CT image analytics. We developed radiomic signatures capable of distinguishing between tumor genotypes in a discovery cohort (n = 353) and verified them in an independent validation cohort (n = 352). All radiomic signatures significantly outperformed conventional radiographic predictors (tumor volume and maximum diameter). We found a radiomic signature related to radiographic heterogeneity that successfully discriminated between EGFR⁺ and EGFR^- cases (AUC = 0.69). Combining this signature with a clinical model of EGFR status (AUC = 0.70) significantly improved prediction accuracy (AUC = 0.75). The highest performing signature was capable of distinguishing between EGFR⁺ and KRAS⁺ tumors (AUC = 0.80) and, when combined with a clinical model (AUC = 0.81), substantially improved its performance (AUC = 0.86). A KRAS⁺/KRAS^- radiomic signature also showed significant albeit lower performance (AUC = 0.63) and did not improve the accuracy of a clinical predictor of KRAS status. Our results argue that somatic mutations drive distinct radiographic phenotypes that can be predicted by radiomics. This work has implications for the use of imaging-based biomarkers in the clinic, as applied noninvasively, repeatedly, and at low cost. Cancer Res; 77(14); 3922-30. ©2017 AACR.

18F-FDG PET/CT in lung cancer. The added value of quantification

OBJECTIVE

To test a software application for the quantification of metabolic heterogeneity and to evaluate its superiority in relation to visual interpretation. To investigate if a quantitative analysis adds information to the interpretation of ¹⁸F-FDG-PET/CT.

MATERIAL AND METHODS

The study analyzed 215 patients with a ¹⁸F-FDG-PET/CT done for the initial staging of lung cancer between March 2011 and December 2015. The study included 57 (26.5%) women and 158 (73.5%) men, with ages ranging from 34 to 88 years (mean±SD: 67.23±10.04). There were 82 surgical stages (I, II, IIIA), and 133 non-surgical stages (IIIB, IV). The primary tumour was analyzed quantitatively by obtaining the following parameters: SUVmax, metabolic active tumour volume (MATV), total lesion glycolysis (TLG), and the entropy heterogeneity index (ET). Heterogeneity was assessed visually. Death dates and/or the follow-up time were registered, ranging from 0.70 to 67.60 months (mean±SD: 23.20±17.68).

RESULTS

In multivariate analysis, ET emerged as a better predictor of survival than visual analysis of heterogeneity that was not statistically significant. The C-index determination demonstrated that all quantitative parameters were statistically-significant predictors of survival. Cut-offs were obtained in order to compare survival times. A multivariate analysis was performed. In the total population, the best predictor was the TNM stage, but MATV, ET, and male gender were statistically significant and independent predictors of survival. In stages without surgical indication, the best predictor was the TNM stage, but the MATV and male gender were statistically significant and independent predictors of survival. In the surgical stages, ET was the only statistically significant and independent predictor of survival.

CONCLUSIONS

Quantification adds prognostic information to the visual analysis of ¹⁸F-FDG-PET/CT.

Radiomics-based Assessment of Radiation-induced Lung Injury After Stereotactic Body Radiotherapy

BACKGROUND

Over 50% of patients who receive stereotactic body radiotherapy (SBRT) develop radiographic evidence of radiation-induced lung injury. Radiomics is an emerging approach that extracts quantitative features from image data, which may provide greater value and a better understanding of pulmonary toxicity than conventional approaches. We aimed to investigate the potential of computed tomography-based radiomics in characterizing post-SBRT lung injury.

METHODS

A total of 48 diagnostic thoracic computed tomography scans (acquired prior to SBRT and at 3, 6, and 9 months post-SBRT) from 14 patients were analyzed. Nine radiomic features (ie, 7 gray level co-occurrence matrix [GLCM] texture features and 2 first-order features) were investigated. The ability of radiomic features to distinguish radiation oncologist-defined moderate/severe lung injury from none/mild lung injury was assessed using logistic regression and area under the receiver operating characteristic curve (AUC). Moreover, dose-response curves (DRCs) for radiomic feature changes were determined as a function of time to investigate whether there was a significant dose-response relationship.

RESULTS

The GLCM features (logistic regression P-value range, 0.012-0.262; AUC range, 0.643-0.750) outperformed the first-order features (P-value range, 0.100-0.990; AUC range, 0.543-0.661) in distinguishing lung injury severity levels. Eight of 9 radiomic features demonstrated a significant dose-response relationship at 3, 6, and 9 months post-SBRT. Although not statistically significant, the GLCM features showed clear separations between the 3- or 6-month DRC and the 9-month DRC.

CONCLUSION

Radiomic features significantly correlated with radiation oncologist-scored post-SBRT lung injury and showed a significant dose-response relationship, suggesting the potential for radiomics to provide a quantitative, objective measurement of post-SBRT lung injury.

Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI

Background

In this study, we evaluated the ability of radiomic textural analysis of intratumoral and peritumoral regions on pretreatment breast cancer dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to predict pathological complete response (pCR) to neoadjuvant chemotherapy (NAC).

Methods

A total of 117 patients who had received NAC were retrospectively analyzed. Within the intratumoral and peritumoral regions of T1-weighted contrast-enhanced MRI scans, a total of 99 radiomic textural features were computed at multiple phases. Feature selection was used to identify a set of top pCR-associated features from within a training set (n = 78), which were then used to train multiple machine learning classifiers to predict the likelihood of pCR for a given patient. Classifiers were then independently tested on 39 patients. Experiments were repeated separately among hormone receptor-positive and human epidermal growth factor receptor 2-negative (HR⁺, HER2⁻) and triple-negative or HER2⁺ (TN/HER2⁺) tumors via threefold cross-validation to determine whether receptor status-specific analysis could improve classification performance.

Results

Among all patients, a combined intratumoral and peritumoral radiomic feature set yielded a maximum AUC of 0.78 ± 0.030 within the training set and 0.74 within the independent testing set using a diagonal linear discriminant analysis (DLDA) classifier. Receptor status-specific feature discovery and classification enabled improved prediction of pCR, yielding maximum AUCs of 0.83 ± 0.025 within the HR⁺, HER2⁻ group using DLDA and 0.93 ± 0.018 within the TN/HER2⁺ group using a naive Bayes classifier. In HR⁺, HER2⁻ breast cancers, non-pCR was characterized by elevated peritumoral heterogeneity during initial contrast enhancement. However, TN/HER2⁺ tumors were best characterized by a speckled enhancement pattern within the peritumoral region of nonresponders. Radiomic features were found to strongly predict pCR independent of choice of classifier, suggesting their robustness as response predictors.

Conclusions

Through a combined intratumoral and peritumoral radiomics approach, we could successfully predict pCR to NAC from pretreatment breast DCE-MRI, both with and without a priori knowledge of receptor status. Further, our findings suggest that the radiomic features most predictive of response vary across different receptor subtypes.

Electronic supplementary material

The online version of this article (doi:10.1186/s13058-017-0846-1) contains supplementary material, which is available to authorized users.

On the impact of smoothing and noise on robustness of CT and CBCT radiomics features for patients with head and neck cancers

PURPOSE

We investigated the characteristics of radiomics features extracted from planning CT (pCT) and cone beam CT (CBCT) image datasets acquired for 18 oropharyngeal cancer patients treated with fractionated radiation therapy. Images were subjected to smoothing, sharpening, and noise to evaluate changes in features relative to baseline datasets.

METHODS

Textural features were extracted from tumor volumes, contoured on pCT and CBCT images, according to the following eight different classes: intensity based histogram features (IBHF), gray level run length (GLRL), law's textural information (LAWS), discrete orthonormal stockwell transform (DOST), local binary pattern (LBP), two-dimensional wavelet transform (2DWT), Two dimensional Gabor filter (2DGF), and gray level co-occurrence matrix (GLCM). A total of 165 radiomics features were extracted. Images were post-processed prior to feature extraction using a Gaussian noise model with different signal-to-noise-ratios (SNR = 5, 10, 15, 20, 25, 35, 50, 75, 100, and 150). Gaussian filters with different cut off frequencies (varied discreetly from 0.0458 to 0.7321 cycles-mm^-1 ) were applied to image datasets. Effect of noise and smoothing on each extracted feature was quantified using mean absolute percent change (MAPC) between the respective values on post-processed and baseline images. The Fisher method for combining Welch P-values was used for tests of significance. Three comparisons were investigated: (a) Baseline pCT versus modified pCT (with given filter applied); (b) Baseline CBCT versus modified CBCT, and (c) Baseline and modified pCT versus baseline and modified CBCT.

RESULTS

Features extracted from CT and CBCT image datasets were robust to low-pass filtering (MAPC = 17.5%, pvalFisher¯ = 0.93 for CBCT and MAPC = 7.5%, pvalFisher¯ = 0.98 for pCT) and noise (MAPC = 27.1%, pvalFisher¯ =  0.89 for CBCT, and MAPC = 34.6%, pvalFisher¯ = 0.61 for pCT). Extracted features were significantly impacted (MAPC=187.7%, pvalFisher¯ < 0.0001 for CBCT, and MAPC = 180.6%, pvalFisher¯ < 0.01 for pCT) by LOG which is classified as a high-pass filter. Features most impacted by low pass filtering were LAWS (MAPC = 11.2%, pvalFisher¯ = 0.44), GLRL (MAPC = 9.7%, pvalFisher¯ = 0.70) and IBHF (MAPC = 21.7%, pvalFisher¯ = 0.83), for the pCT datasets, and LAWS (MAPC = 20.2%, pvalFisher¯ = 0.24), GLRL (MAPC = 14.5%, pvalFisher¯ = 0.44), and 2DGF (MAPC=16.3%, pvalFisher¯ = 0.52), for CBCT image datasets. For pCT datasets, features most impacted by noise were GLRL (MAPC = 29.7%, pvalFisher¯ = 0.06), LAWS (MAPC = 96.6%, pvalFisher¯ = 0.42), and GLCM (MAPC = 36.2%, pvalFisher¯ = 0.48), while the LBPF (MAPC = 5.2%, pvalFisher¯ = 0.99) was found to be relatively insensitive to noise. For CBCT datasets, GLRL (MAPC = 8.9%, pvalFisher¯ = 0.80) and LAWS (MAPC = 89.3%, pvalFisher¯ = 0.81) features were impacted by noise, while the LBPF (MAPC = 2.2%, pvalFisher¯ = 0.99) and DOST (MAPC = 13.7%, pvalFisher¯ = 0.98) features were noise insensitive. Apart from 15 features, no significant differences were observed for the remaining 150 textural features extracted from baseline pCT and CBCT image datasets (MAPC = 90.1%, pvalFisher¯ = 0.26).

CONCLUSIONS

Radiomics features extracted from planning CT and daily CBCT image datasets for head/neck cancer patients were robust to low-power Gaussian noise and low-pass filtering, but were impacted by high-pass filtering. Textural features extracted from CBCT and pCT image datasets were similar, suggesting interchangeability of pCT and CBCT for investigating radiomics features as possible biomarkers for outcome.

Intrinsic dependencies of CT radiomic features on voxel size and number of gray levels

PURPOSE

Many radiomics features were originally developed for non-medical imaging applications and therefore original assumptions may need to be reexamined. In this study, we investigated the impact of slice thickness and pixel spacing (or pixel size) on radiomics features extracted from Computed Tomography (CT) phantom images acquired with different scanners as well as different acquisition and reconstruction parameters. The dependence of CT texture features on gray-level discretization was also evaluated.

METHODS AND MATERIALS

A texture phantom composed of 10 different cartridges of different materials was scanned on eight different CT scanners from three different manufacturers. The images were reconstructed for various slice thicknesses. For each slice thickness, the reconstruction Field Of View (FOV) was varied to render pixel sizes ranging from 0.39 to 0.98 mm. A fixed spherical region of interest (ROI) was contoured on the images of the shredded rubber cartridge and the 3D printed, 20% fill, acrylonitrile butadiene styrene plastic cartridge (ABS20) for all phantom imaging sets. Radiomic features were extracted from the ROIs using an in-house program. Features categories were: shape (10), intensity (16), GLCM (24), GLZSM (11), GLRLM (11), and NGTDM (5), fractal dimensions (8) and first-order wavelets (128), for a total of 213 features. Voxel-size resampling was performed to investigate the usefulness of extracting features using a suitably chosen voxel size. Acquired phantom image sets were resampled to a voxel size of 1 × 1 × 2 mm³ using linear interpolation. Image features were therefore extracted from resampled and original datasets and the absolute value of the percent coefficient of variation (%COV) for each feature was calculated. Based on the %COV values, features were classified in 3 groups: (1) features with large variations before and after resampling (%COV >50); (2) features with diminished variation (%COV <30) after resampling; and (3) features that had originally moderate variation (%COV <50%) and were negligibly affected by resampling. Group 2 features were further studied by modifying feature definitions to include voxel size. Original and voxel-size normalized features were used for interscanner comparisons. A subsequent analysis investigated feature dependency on gray-level discretization by extracting 51 texture features from ROIs from each of the 10 different phantom cartridges using 16, 32, 64, 128, and 256 gray levels.

RESULTS

Out of the 213 features extracted, 150 were reproducible across voxel sizes, 42 improved significantly (%COV <30, Group 2) after resampling, and 21 had large variations before and after resampling (Group 1). Ten features improved significantly after definition modification effectively removed their voxel-size dependency. Interscanner comparison indicated that feature variability among scanners nearly vanished for 8 of these 10 features. Furthermore, 17 out of 51 texture features were found to be dependent on the number of gray levels. These features were redefined to include the number of gray levels which greatly reduced this dependency.

CONCLUSION

Voxel-size resampling is an appropriate pre-processing step for image datasets acquired with variable voxel sizes to obtain more reproducible CT features. We found that some of the radiomics features were voxel size and gray-level discretization-dependent. The introduction of normalizing factors in their definitions greatly reduced or removed these dependencies.

PET Radiomics in NSCLC: state of the art and a proposal for harmonization of methodology

Imaging with positron emission tomography (PET)/computed tomography (CT) is crucial in the management of cancer because of its value in tumor staging, response assessment, restaging, prognosis and treatment responsiveness prediction. In the last years, interest has grown in texture analysis which provides an "in-vivo" lesion characterization, and predictive information in several malignances including NSCLC; however several drawbacks and limitations affect these studies, especially because of lack of standardization in features calculation, definitions and methodology reporting. The present paper provides a comprehensive review of literature describing the state-of-the-art of FDG-PET/CT texture analysis in NSCLC, suggesting a proposal for harmonization of methodology.

Predictive value of initial FDG-PET features for treatment response and survival in esophageal cancer patients treated with chemo-radiation therapy using a random forest classifier

Purpose

In oncology, texture features extracted from positron emission tomography with 18-fluorodeoxyglucose images (FDG-PET) are of increasing interest for predictive and prognostic studies, leading to several tens of features per tumor. To select the best features, the use of a random forest (RF) classifier was investigated.

Methods

Sixty-five patients with an esophageal cancer treated with a combined chemo-radiation therapy were retrospectively included. All patients underwent a pretreatment whole-body FDG-PET. The patients were followed for 3 years after the end of the treatment. The response assessment was performed 1 month after the end of the therapy. Patients were classified as complete responders and non-complete responders. Sixty-one features were extracted from medical records and PET images. First, Spearman’s analysis was performed to eliminate correlated features. Then, the best predictive and prognostic subsets of features were selected using a RF algorithm. These results were compared to those obtained by a Mann-Whitney U test (predictive study) and a univariate Kaplan-Meier analysis (prognostic study).

Results

Among the 61 initial features, 28 were not correlated. From these 28 features, the best subset of complementary features found using the RF classifier to predict response was composed of 2 features: metabolic tumor volume (MTV) and homogeneity from the co-occurrence matrix. The corresponding predictive value (AUC = 0.836 ± 0.105, Se = 82 ± 9%, Sp = 91 ± 12%) was higher than the best predictive results found using the Mann-Whitney test: busyness from the gray level difference matrix (P < 0.0001, AUC = 0.810, Se = 66%, Sp = 88%). The best prognostic subset found using RF was composed of 3 features: MTV and 2 clinical features (WHO status and nutritional risk index) (AUC = 0.822 ± 0.059, Se = 79 ± 9%, Sp = 95 ± 6%), while no feature was significantly prognostic according to the Kaplan-Meier analysis.

Conclusions

The RF classifier can improve predictive and prognostic values compared to the Mann-Whitney U test and the univariate Kaplan-Meier survival analysis when applied to several tens of features in a limited patient database.

Prediction of malignancy by a radiomic signature from contrast agent-free diffusion MRI in suspicious breast lesions found on screening mammography

PURPOSE

To assess radiomics as a tool to determine how well lesions found suspicious on breast cancer screening X-ray mammography can be categorized into malignant and benign with unenhanced magnetic resonance (MR) mammography with diffusion-weighted imaging and T₂ -weighted sequences.

MATERIALS AND METHODS

From an asymptomatic screening cohort, 50 women with mammographically suspicious findings were examined with contrast-enhanced breast MRI (ceMRI) at 1.5T. Out of this protocol an unenhanced, abbreviated diffusion-weighted imaging protocol (ueMRI) including T₂ -weighted, (T₂ w), diffusion-weighted imaging (DWI), and DWI with background suppression (DWIBS) sequences and corresponding apparent diffusion coefficient (ADC) maps were extracted. From ueMRI-derived radiomic features, three Lasso-supervised machine-learning classifiers were constructed and compared with the clinical performance of a highly experienced radiologist: 1) univariate mean ADC model, 2) unconstrained radiomic model, 3) constrained radiomic model with mandatory inclusion of mean ADC.

RESULTS

The unconstrained and constrained radiomic classifiers consisted of 11 parameters each and achieved differentiation of malignant from benign lesions with a .632 + bootstrap receiver operating characteristics (ROC) area under the curve (AUC) of 84.2%/85.1%, compared to 77.4% for mean ADC and 95.9%/95.9% for the experienced radiologist using ceMRI/ueMRI.

CONCLUSION

In this pilot study we identified two ueMRI radiomics classifiers that performed well in the differentiation of malignant from benign lesions and achieved higher performance than the mean ADC parameter alone. Classification was lower than the almost perfect performance of a highly experienced breast radiologist. The potential of radiomics to provide a training-independent diagnostic decision tool is indicated. A performance reaching the human expert would be highly desirable and based on our results is considered possible when the concept is extended in larger cohorts with further development and validation of the technique.

LEVEL OF EVIDENCE

1 Technical Efficacy: Stage 2 J. MAGN. RESON. IMAGING 2017;46:604-616.

Texture analysis of medical images for radiotherapy applications

The high-throughput extraction of quantitative information from medical images, known as radiomics, has grown in interest due to the current necessity to quantitatively characterize tumour heterogeneity. In this context, texture analysis, consisting of a variety of mathematical techniques that can describe the grey-level patterns of an image, plays an important role in assessing the spatial organization of different tissues and organs. For these reasons, the potentiality of texture analysis in the context of radiotherapy has been widely investigated in several studies, especially for the prediction of the treatment response of tumour and normal tissues. Nonetheless, many different factors can affect the robustness, reproducibility and reliability of textural features, thus limiting the impact of this technique. In this review, an overview of the most recent works that have applied texture analysis in the context of radiotherapy is presented, with particular focus on the assessment of tumour and tissue response to radiations. Preliminary, the main factors that have an influence on features estimation are discussed, highlighting the need of more standardized image acquisition and reconstruction protocols and more accurate methods for region of interest identification. Despite all these limitations, texture analysis is increasingly demonstrating its ability to improve the characterization of intratumour heterogeneity and the prediction of clinical outcome, although prospective studies and clinical trials are required to draw a more complete picture of the full potential of this technique.

Subclinical Disease Burden as Assessed by Whole-Body MRI in Subjects With Prediabetes, Subjects With Diabetes, and Normal Control Subjects From the General Population: The KORA-MRI Study

Detailed pathophysiological manifestations of early disease in the context of prediabetes are poorly understood. This study aimed to evaluate the extent of early signs of metabolic and cardio-cerebrovascular complications affecting multiple organs in individuals with prediabetes. Subjects without a history of stroke, coronary artery disease, or peripheral artery disease were enrolled in a case-control study nested within the Cooperative Health Research in the Region of Augsburg (KORA) FF4 cohort and underwent comprehensive MRI assessment to characterize cerebral parameters (white matter lesions, microbleeds), cardiovascular parameters (carotid plaque, left ventricular function, and myocardial late gadolinium enhancement [LGE]), and metabolic parameters (hepatic proton-density fat fraction [PDFF] and subcutaneous and visceral abdominal fat). Among 400 subjects who underwent MRI, 103 subjects had prediabetes and 54 had established diabetes. Subjects with prediabetes had an increased risk for carotid plaque and adverse functional cardiac parameters, including reduced early diastolic filling rates as well as a higher prevalence of LGE compared with healthy control subjects. In addition, people with prediabetes had significantly elevated levels of PDFF and total and visceral fat. Thus, subjects with prediabetes show early signs of subclinical disease that include vascular, cardiac, and metabolic changes, as measured by whole-body MRI after adjusting for cardiometabolic risk factors.

Stability of radiomic features in CT perfusion maps

This study aimed to identify a set of stable radiomic parameters in CT perfusion (CTP) maps with respect to CTP calculation factors and image discretization, as an input for future prognostic models for local tumor response to chemo-radiotherapy. Pre-treatment CTP images of eleven patients with oropharyngeal carcinoma and eleven patients with non-small cell lung cancer (NSCLC) were analyzed. 315 radiomic parameters were studied per perfusion map (blood volume, blood flow and mean transit time). Radiomics robustness was investigated regarding the potentially standardizable (image discretization method, Hounsfield unit (HU) threshold, voxel size and temporal resolution) and non-standardizable (artery contouring and noise threshold) perfusion calculation factors using the intraclass correlation (ICC). To gain added value for our model radiomic parameters correlated with tumor volume, a well-known predictive factor for local tumor response to chemo-radiotherapy, were excluded from the analysis. The remaining stable radiomic parameters were grouped according to inter-parameter Spearman correlations and for each group the parameter with the highest ICC was included in the final set. The acceptance level was 0.9 and 0.7 for the ICC and correlation, respectively. The image discretization method using fixed number of bins or fixed intervals gave a similar number of stable radiomic parameters (around 40%). The potentially standardizable factors introduced more variability into radiomic parameters than the non-standardizable ones with 56-98% and 43-58% instability rates, respectively. The highest variability was observed for voxel size (instability rate  >97% for both patient cohorts). Without standardization of CTP calculation factors none of the studied radiomic parameters were stable. After standardization with respect to non-standardizable factors ten radiomic parameters were stable for both patient cohorts after correction for inter-parameter correlations. Voxel size, image discretization, HU threshold and temporal resolution have to be standardized to build a reliable predictive model based on CTP radiomics analysis.

Associations Between Somatic Mutations and Metabolic Imaging Phenotypes in Non-Small Cell Lung Cancer

PET-based radiomics have been used to noninvasively quantify the metabolic tumor phenotypes; however, little is known about the relationship between these phenotypes and underlying somatic mutations. This study assessed the association and predictive power of ¹⁸F-FDG PET-based radiomic features for somatic mutations in non-small cell lung cancer patients. Methods: Three hundred forty-eight non-small cell lung cancer patients underwent diagnostic ¹⁸F-FDG PET scans and were tested for genetic mutations. Thirteen percent (44/348) and 28% (96/348) of patients were found to harbor epidermal growth factor receptor (EGFR) or Kristen rat sarcoma viral (KRAS) mutations, respectively. We evaluated 21 imaging features: 19 independent radiomic features quantifying phenotypic traits and 2 conventional features (metabolic tumor volume and maximum SUV). The association between imaging features and mutation status (e.g., EGFR-positive [EGFR+] vs. EGFR-negative) was assessed using the Wilcoxon rank-sum test. The ability of each imaging feature to predict mutation status was evaluated by the area under the receiver operating curve (AUC) and its significance was compared with a random guess (AUC = 0.5) using the Noether test. All P values were corrected for multiple hypothesis testing by controlling the false-discovery rate (FDR_Wilcoxon, FDR_Noether) with a significance threshold of 10%. Results: Eight radiomic features and both conventional features were significantly associated with EGFR mutation status (FDR_Wilcoxon = 0.01-0.10). One radiomic feature (normalized inverse difference moment) outperformed all other features in predicting EGFR mutation status (EGFR+ vs. EGFR-negative, AUC = 0.67, FDR_Noether = 0.0032), as well as differentiating between KRAS-positive and EGFR+ (AUC = 0.65, FDR_Noether = 0.05). None of the features was associated with or predictive of KRAS mutation status (KRAS-positive vs. KRAS-negative, AUC = 0.50-0.54). Conclusion: Our results indicate that EGFR mutations may drive different metabolic tumor phenotypes that are captured in PET images, whereas KRAS-mutated tumors do not. This proof-of-concept study sheds light on genotype-phenotype interactions, using radiomics to capture and describe the phenotype, and may have potential for developing noninvasive imaging biomarkers for somatic mutations.

Characterization of cervical lymph-nodes using a multi-parametric and multi-modal approach for an early prediction of tumor response to chemo-radiotherapy

PURPOSE

In the treatment of Head-and-Neck Squamous Cell Carcinoma (HNSCC), the early prediction of residual malignant lymph nodes (LNs) is currently required. Here, we investigated the potential of a multi-modal characterization (combination of CT, T2w-MRI and DW-MRI) at baseline and at mid-treatment, based on texture analysis (TA), for the early prediction of LNs response to chemo-radiotherapy (CRT).

METHODS

30 patients with pathologically confirmed HNSCC treated with CRT were considered. All patients underwent a planning CT and two serial MR examinations (including T2w and DW images), one before and one at mid-CRT. For each patient the largest malignant LN was selected and within each LN, morphological and textural features were estimated from T2w-MRI and CT, besides a quantification of the apparent diffusion coefficient (ADC) from DW-MRI. After a median follow-up time of 26.6months, 19 LNs showed regional control, while 11 LNs showedregional failure at a median time of 4.6months. Linear discriminant analysis was used to test the accuracy of the image-based features in predicting the final response.

RESULTS

Pre-treatment features showed higher predictive power than mid-CRT features, the ADC having the highest accuracy (80%); CT-based indices were found not predictive. When ADC was combined with TA, the classification performance increased (accuracy=82.8%). If only T2w-MRI features were considered, the best combination of pre-CRT indices and their variation reached an equivalent accuracy (81.8%).

CONCLUSION

Our results may suggest that TA on T2w-MRI and ADC can be combined together to obtain a more accurate prediction of response to CRT.