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

Differentiation of Pituitary Adenoma from Rathke Cleft Cyst: Combining MR Image Features with Texture Features

Objectives

To differentiate pituitary adenoma from Rathke cleft cyst in magnetic resonance (MR) scan by combing MR image features with texture features.

Methods

A total number of 133 patients were included in this study, 83 with pituitary adenoma and 50 with Rathke cleft cyst. Qualitative MR image features and quantitative texture features were evaluated by using the chi-square tests or Mann–Whitney U test. Binary logistic regression analysis was conducted to investigate their ability as independent predictors. ROC analysis was conducted subsequently on the independent predictors to assess their practical value in discrimination and was used to investigate the association between two types of features.

Results

Signal intensity on the contrast-enhanced image was found to be the only significantly different MR image feature between the two lesions. Two texture features from the contrast-enhanced images (Histo-Skewness and GLCM-Correlation) were found to be the independent predictors in discrimination, of which AUC values were 0.80 and 0.75, respectively. Besides, the above two texture features (Histo-Skewness and GLCM-Contrast) were suggested to be associated with signal intensity on the contrast-enhanced image.

Conclusion

Signal intensity on the contrast-enhanced image was the most significant MR image feature in differentiation between pituitary adenoma and Rathke cleft cyst, and texture features also showed promising and practical ability in discrimination. Moreover, two types of features could be coordinated with each other.

Usefulness of gradient tree boosting for predicting histological subtype and EGFR mutation status of non-small cell lung cancer on 18F FDG-PET/CT

OBJECTIVE

To develop and evaluate a radiomics approach for classifying histological subtypes and epidermal growth factor receptor (EGFR) mutation status in lung cancer on PET/CT images.

METHODS

PET/CT images of lung cancer patients were obtained from public databases and used to establish two datasets, respectively to classify histological subtypes (156 adenocarcinomas and 32 squamous cell carcinomas) and EGFR mutation status (38 mutant and 100 wild-type samples). Seven types of imaging features were obtained from PET/CT images of lung cancer. Two types of machine learning algorithms were used to predict histological subtypes and EGFR mutation status: random forest (RF) and gradient tree boosting (XGB). The classifiers used either a single type or multiple types of imaging features. In the latter case, the optimal combination of the seven types of imaging features was selected by Bayesian optimization. Receiver operating characteristic analysis, area under the curve (AUC), and tenfold cross validation were used to assess the performance of the approach.

RESULTS

In the classification of histological subtypes, the AUC values of the various classifiers were as follows: RF, single type: 0.759; XGB, single type: 0.760; RF, multiple types: 0.720; XGB, multiple types: 0.843. In the classification of EGFR mutation status, the AUC values were: RF, single type: 0.625; XGB, single type: 0.617; RF, multiple types: 0.577; XGB, multiple types: 0.659.

CONCLUSIONS

The radiomics approach to PET/CT images, together with XGB and Bayesian optimization, is useful for classifying histological subtypes and EGFR mutation status in lung cancer.

MRI-derived radiomics: methodology and clinical applications in the field of pelvic oncology

Personalized medicine aims at offering optimized treatment options and improved survival for cancer patients based on individual variability. The success of precision medicine depends on robust biomarkers. Recently, the requirement for improved non-biologic biomarkers that reflect tumor biology has emerged and there has been a growing interest in the automatic extraction of quantitative features from medical images, denoted as radiomics. Radiomics as a methodological approach can be applied to any image and most studies have focused on PET, CT, ultrasound, and MRI. Here, we aim to present an overview of the radiomics workflow as well as the major challenges with special emphasis on the use of multiparametric MRI datasets. We then reviewed recent studies on radiomics in the field of pelvic oncology including prostate, cervical, and colorectal cancer.

Metabolic Biomarker-Based BRAFV600 Mutation Association and Prediction in Melanoma

The aim of this study was to associate and predict B-rapidly accelerated fibrosarcoma valine 600 (BRAFV600) mutation status with both conventional and radiomics ¹⁸F-FDG PET/CT features, while exploring several methods of feature selection in melanoma radiomics. Methods: Seventy unresectable stage III-IV melanoma patients who underwent a baseline ¹⁸F-FDG PET/CT scan were identified. Patients were assigned to the BRAFV600 group or BRAF wild-type group according to mutational status. ¹⁸F-FDG uptake quantification was performed by semiautomatic lesion delineation. Four hundred eighty radiomics features and 4 conventional PET features (SUV_max, SUV_mean, SUV_peak, and total lesion glycolysis) were extracted per lesion. Six different methods of feature selection were implemented, and 10-fold cross-validated predictive models were built for each. Model performances were evaluated with areas under the curve (AUCs) for the receiver operating characteristic curves. Results: Thirty-five BRAFV600 mutated patients (100 lesions) and 35 BRAF wild-type patients (79 lesions) were analyzed. AUCs predicting the BRAFV600 mutation varied from 0.54 to 0.62 and were susceptible to feature selection method. The best AUCs were achieved by feature selection based on literature, a penalized binary logistic regression model, and random forest model. No significant difference was found between the BRAFV600 and BRAF wild-type group in conventional PET features or predictive value. Conclusion: BRAFV600 mutation status is not associated with, nor can it be predicted with, conventional PET features, whereas radiomics features were of low predictive value (AUC = 0.62). We showed feature selection methods to influence predictive model performance, describing and evaluating 6 unique methods. Detecting BRAFV600 status in melanoma based on ¹⁸F-FDG PET/CT alone does not yet provide clinically relevant knowledge.

Molecular Subtype Classification in Lower-Grade Glioma with Accelerated DTI

BACKGROUND AND PURPOSE

Image-based classification of lower-grade glioma molecular subtypes has substantial prognostic value. Diffusion tensor imaging has shown promise in lower-grade glioma subtyping but currently requires lengthy, nonstandard acquisitions. Our goal was to investigate lower-grade glioma classification using a machine learning technique that estimates fractional anisotropy from accelerated diffusion MR imaging scans containing only 3 diffusion-encoding directions.

MATERIALS AND METHODS

Patients with lower-grade gliomas (n = 41) (World Health Organization grades II and III) with known isocitrate dehydrogenase (IDH) mutation and 1p/19q codeletion status were imaged preoperatively with DTI. Whole-tumor volumes were autodelineated using conventional anatomic MR imaging sequences. In addition to conventional ADC and fractional anisotropy reconstructions, fractional anisotropy estimates were computed from 3-direction DTI subsets using DiffNet, a neural network that directly computes fractional anisotropy from raw DTI data. Differences in whole-tumor ADC, fractional anisotropy, and estimated fractional anisotropy were assessed between IDH-wild-type and IDH-mutant lower-grade gliomas with and without 1p/19q codeletion. Multivariate classification models were developed using whole-tumor histogram and texture features from ADC, ADC + fractional anisotropy, and ADC + estimated fractional anisotropy to identify the added value provided by fractional anisotropy and estimated fractional anisotropy.

RESULTS

ADC (P = .008), fractional anisotropy (P < .001), and estimated fractional anisotropy (P < .001) significantly differed between IDH-wild-type and IDH-mutant lower-grade gliomas. ADC (P < .001) significantly differed between IDH-mutant gliomas with and without codeletion. ADC-only multivariate classification predicted IDH mutation status with an area under the curve of 0.81 and codeletion status with an area under the curve of 0.83. Performance improved to area under the curve = 0.90/0.94 for the ADC + fractional anisotropy classification and to area under the curve = 0.89/0.89 for the ADC + estimated fractional anisotropy classification.

CONCLUSIONS

Fractional anisotropy estimates made from accelerated 3-direction DTI scans add value in classifying lower-grade glioma molecular status.

Exploring Tumor Heterogeneity Using PET Imaging: The Big Picture

Personalized medicine represents a major goal in oncology. It has its underpinning in the identification of biomarkers with diagnostic, prognostic, or predictive values. Nowadays, the concept of biomarker no longer necessarily corresponds to biological characteristics measured ex vivo but includes complex physiological characteristics acquired by different technologies. Positron-emission-tomography (PET) imaging is an integral part of this approach by enabling the fine characterization of tumor heterogeneity in vivo in a non-invasive way. It can effectively be assessed by exploring the heterogeneous distribution and uptake of a tracer such as 18F-fluoro-deoxyglucose (FDG) or by using multiple radiopharmaceuticals, each providing different information. These two approaches represent two avenues of development for the research of new biomarkers in oncology. In this article, we review the existing evidence that the measurement of tumor heterogeneity with PET imaging provide essential information in clinical practice for treatment decision-making strategy, to better select patients with poor prognosis for more intensive therapy or those eligible for targeted therapy.

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.

Radiomic analysis for preoperative prediction of cervical lymph node metastasis in patients with papillary thyroid carcinoma

PURPOSE

Cervical lymph node (LN) metastasis of papillary thyroid carcinoma (PTC) is critical for treatment and prognosis. We explored the feasibility of using radiomics to preoperatively predict cervical LN metastasis in PTC patients.

METHOD

Total 221 PTC patients (training cohort: n = 154; validation cohort: n = 67; divided randomly at the ratio of 7:3) were enrolled and divided into 2 groups based on LN pathologic diagnosis (N0: n = 118; N1a and N1b: n = 88 and 15, respectively). We extracted 546 radiomic features from non-contrast and venous contrast-enhanced computed tomography (CT) images. We selected 8 groups of candidate feature sets by minimum redundancy maximum relevance (mRMR), and obtained 8 radiomic sub-signatures by support vector machine (SVM) to construct the radiomic signature. Incorporating the radiomic signature, CT-reported cervical LN status and clinical risk factors, a nomogram was constructed using multivariable logistic regression. The nomogram's calibration, discrimination, and clinical utility were assessed.

RESULTS

The radiomic signature was associated significantly with cervical LN status (p < 0.01 for both training and validation cohorts). The radiomic signature showed better predictive performance than any radiomic sub-signatures devised by SVM. Addition of radiomic signature to the nomogram improved the predictive value (area under the curve (AUC), 0.807 to 0.867) in the training cohort; this was confirmed in an independent validation cohort (AUC, 0.795 to 0.822). Good agreement was observed using calibration curves in both cohorts. Decision curve analysis demonstrated the radiomic nomogram was worthy of clinical application.

CONCLUSIONS

Our radiomic nomogram improved the preoperative prediction of cervical LN metastasis in PTC patients.

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.

AI-based applications in hybrid imaging: how to build smart and truly multi-parametric decision models for radiomics

INTRODUCTION

The quantitative imaging features (radiomics) that can be obtained from the different modalities of current-generation hybrid imaging can give complementary information with regard to the tumour environment, as they measure different morphologic and functional imaging properties. These multi-parametric image descriptors can be combined with artificial intelligence applications into predictive models. It is now the time for hybrid PET/CT and PET/MRI to take the advantage offered by radiomics to assess the added clinical benefit of using multi-parametric models for the personalized diagnosis and prognosis of different disease phenotypes.

OBJECTIVE

The aim of the paper is to provide an overview of current challenges and available solutions to translate radiomics into hybrid PET-CT and PET-MRI imaging for a smart and truly multi-parametric decision model.

18F-FDG PET/CT Radiomic Analysis with Machine Learning for Identifying Bone Marrow Involvement in the Patients with Suspected Relapsed Acute Leukemia

¹⁸F-FDG PET / CT is used clinically for the detection of extramedullary lesions in patients with relapsed acute leukemia (AL). However, the visual analysis of ¹⁸F-FDG diffuse bone marrow uptake in detecting bone marrow involvement (BMI) in routine clinical practice is still challenging. This study aims to improve the diagnostic performance of ¹⁸F-FDG PET/CT in detecting BMI for patients with suspected relapsed AL.

Methods: Forty-one patients (35 in training group and 6 in independent validation group) with suspected relapsed AL were retrospectively included in this study. All patients underwent both bone marrow biopsy (BMB) and ¹⁸F-FDG PET/CT within one week. The BMB results were used as the gold standard or real “truth” for BMI. The bone marrow ¹⁸F-FDG uptake was visually diagnosed as positive and negative by three nuclear medicine physicians. The skeletal volumes of interest were manually drawn on PET/CT images. A total of 781 PET and 1045 CT radiomic features were automatically extracted to provide a more comprehensive understanding of the embedded pattern. To select the most important and predictive features, an unsupervised consensus clustering method was first performed to analyze the feature correlations and then used to guide a random forest supervised machine learning model for feature importance analysis. Cross-validation and independent validation were conducted to justify the performance of our model.

Results: The training group involved 16 BMB positive and 19 BMB negative patients. Based on the visual analysis of ¹⁸F-FDG PET, 3 patients had focal uptake, 8 patients had normal uptake, and 24 patients had diffuse uptake. The sensitivity, specificity, and accuracy of visual analysis for BMI diagnosis were 62.5%, 73.7%, and 68.6%, respectively. With the cross-validation on the training group, the machine learning model correctly predicted 31 patients in BMI. The sensitivity, specificity, and accuracy of the machine learning model in BMI detection were 87.5%, 89.5%, and 88.6%, respectively, significantly higher than the ones in visual analysis (P < 0.05). The evaluation on the independent validation group showed that the machine learning model could achieve 83.3% accuracy.

Conclusions:¹⁸F-FDG PET/CT radiomic analysis with machine learning model provided a quantitative, objective and efficient mechanism for identifying BMI in the patients with suspected relapsed AL. It is suggested in particular for the diagnosis of BMI in the patients with ¹⁸F-FDG diffuse uptake patterns.

Non-invasive classification of non-small cell lung cancer: a comparison between random forest models utilising radiomic and semantic features

OBJECTIVE

Non-invasive distinction between squamous cell carcinoma and adenocarcinoma subtypes of non-small-cell lung cancer (NSCLC) may be beneficial to patients unfit for invasive diagnostic procedures or when tissue is insufficient for diagnosis. The purpose of our study was to compare the performance of random forest algorithms utilizing CT radiomics and/or semantic features in classifying NSCLC.

METHODS

Two thoracic radiologists scored 11 semantic features on CT scans of 106 patients with NSCLC. A set of 115 radiomics features was extracted from the CT scans. Random forest models were developed from semantic (RM-sem), radiomics (RM-rad), and all features combined (RM-all). External validation of models was performed using an independent test data set (n = 100) of CT scans. Model performance was measured with out-of-bag error and area under curve (AUC), and compared using receiver-operating characteristics curve analysis on the test data set.

RESULTS

The median (interquartile-range) error rates of the models were: RF-sem 24.5 % (22.6 - 37.5 %), RF-rad 35.8 % (34.9 - 38.7 %), and RM-all 37.7 % (37.7 - 37.7). On training data, both RF-rad and RF-all gave perfect discrimination (AUC = 1), which was significantly higher than that achieved by RF-sem (AUC = 0.78; p < 0.0001). On test data, however, RM-sem model (AUC = 0.82) out-performed RM-rad and RM-all (AUC = 0.5 and AUC = 0.56; p < 0.0001), neither of which was significantly different from random guess ( p = 0.9 and 0.6 respectively).

CONCLUSION

Non-invasive classification of NSCLC can be done accurately using random forest classification models based on well-known CT-derived descriptive features. However, radiomics-based classification models performed poorly in this scenario when tested on independent data and should be used with caution, due to their possible lack of generalizability to new data.

ADVANCES IN KNOWLEDGE

Our study describes novel CT-derived random forest models based on radiologist-interpretation of CT scans (semantic features) that can assist NSCLC classification when histopathology is equivocal or when histopathological sampling is not possible. It also shows that random forest models based on semantic features may be more useful than those built from computational radiomic features.

A review of the principles of texture analysis and its role in imaging of genitourinary neoplasms

Advances in the management of genitourinary neoplasms have resulted in a trend towards providing patients with personalized care. Texture analysis of medical images, is one of the tools that is being explored to provide information such as detection and characterization of tumors, determining their aggressiveness including grade and metastatic potential and for prediction of survival rates and risk of recurrence. In this article we review the basic principles of texture analysis and then detail its current role in imaging of individual neoplasms of the genitourinary system.

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.

Radiomics in nuclear medicine: robustness, reproducibility, standardization, and how to avoid data analysis traps and replication crisis

Radiomics in nuclear medicine is rapidly expanding. Reproducibility of radiomics studies in multicentre settings is an important criterion for clinical translation. We therefore performed a meta-analysis to investigate reproducibility of radiomics biomarkers in PET imaging and to obtain quantitative information regarding their sensitivity to variations in various imaging and radiomics-related factors as well as their inherent sensitivity. Additionally, we identify and describe data analysis pitfalls that affect the reproducibility and generalizability of radiomics studies. After a systematic literature search, 42 studies were included in the qualitative synthesis, and data from 21 were used for the quantitative meta-analysis. Data concerning measurement agreement and reliability were collected for 21 of 38 different factors associated with image acquisition, reconstruction, segmentation and radiomics-specific processing steps. Variations in voxel size, segmentation and several reconstruction parameters strongly affected reproducibility, but the level of evidence remained weak. Based on the meta-analysis, we also assessed inherent sensitivity to variations of 110 PET image biomarkers. SUV_mean and SUV_max were found to be reliable, whereas image biomarkers based on the neighbourhood grey tone difference matrix and most biomarkers based on the size zone matrix were found to be highly sensitive to variations, and should be used with care in multicentre settings. Lastly, we identify 11 data analysis pitfalls. These pitfalls concern model validation and information leakage during model development, but also relate to reporting and the software used for data analysis. Avoiding such pitfalls is essential for minimizing bias in the results and to enable reproduction and validation of radiomics studies.

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.

Risk Prediction for Early Biliary Infection after Percutaneous Transhepatic Biliary Stent Placement in Malignant Biliary Obstruction

PURPOSE

To establish a nomogram for predicting the occurrence of early biliary infection (EBI) after percutaneous transhepatic biliary stent (PTBS) placement in malignant biliary obstruction (MBO).

MATERIALS AND METHODS

In this multicenter study, patients treated with PTBS for MBO were allocated to a training cohort or a validation cohort. The independent risk factors for EBI selected by multivariate analyses in the training cohort were used to develop a predictive nomogram. An artificial neural network was applied to assess the importance of these factors in predicting EBI. The predictive accuracy of this nomogram was determined by concordance index (c-index) and a calibration plot, both internally and externally.

RESULTS

A total of 243 patients (training cohort: n = 182; validation cohort: n = 61) were included in this study. The independent risk factors were length of obstruction (odds ratio [OR], 1.061; 95% confidence interval [CI], 1.013-1.111; P = .012), diabetes (OR, 5.070; 95% CI, 1.917-13.412; P = .001), location of obstruction (OR, 2.283; 95% CI, 1.012-5.149; P = .047), and previous surgical or endoscopic intervention (OR, 3.968; 95% CI, 1.709-9.217; P = .001), which were selected into the nomogram. The c-index values showed good predictive performance in the training and validation cohorts (0.792 and 0.802, respectively). The optimum cutoff value of risk was 0.25.

CONCLUSIONS

The nomogram can facilitate the early and accurate prediction of EBI in patients with MBO who underwent PTBS. Patients with high risk (> 0.25) should be administered more effective prophylactic antibiotics and undergo closer monitoring.

Artificial intelligence and radiomics in pulmonary nodule management: current status and future applications

Artificial intelligence (AI) has been present in some guise within the field of radiology for over 50 years. The first studies investigating computer-aided diagnosis in thoracic radiology date back to the 1960s, and in the subsequent years, the main application of these techniques has been the detection and classification of pulmonary nodules. In addition, there have been other less intensely researched applications, such as the diagnosis of interstitial lung disease, chronic obstructive pulmonary disease, and the detection of pulmonary emboli. Despite extensive literature on the use of convolutional neural networks in thoracic imaging over the last few decades, we are yet to see these systems in use in clinical practice. The article reviews current state-of-the-art applications of AI and in detection, classification, and follow-up of pulmonary nodules and how deep-learning techniques might influence these going forward. Finally, we postulate the impact of these advancements on the role of radiologists and the importance of radiologists in the development and evaluation of these techniques.

Challenges and caveats of a multi-center retrospective radiomics study: an example of early treatment response assessment for NSCLC patients using FDG-PET/CT radiomics

Background

Prognostic models based on individual patient characteristics can improve treatment decisions and outcome in the future. In many (radiomic) studies, small size and heterogeneity of datasets is a challenge that often limits performance and potential clinical applicability of these models. The current study is example of a retrospective multi-centric study with challenges and caveats. To highlight common issues and emphasize potential pitfalls, we aimed for an extensive analysis of these multi-center pre-treatment datasets, with an additional ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) scan acquired during treatment.

Methods

The dataset consisted of 138 stage II-IV non-small cell lung cancer (NSCLC) patients from four different cohorts acquired from three different institutes. The differences between the cohorts were compared in terms of clinical characteristics and using the so-called ‘cohort differences model’ approach. Moreover, the potential prognostic performances for overall survival of radiomic features extracted from CT or FDG-PET, or relative or absolute differences between the scans at the two time points, were assessed using the LASSO regression method. Furthermore, the performances of five different classifiers were evaluated for all image sets.

Results

The individual cohorts substantially differed in terms of patient characteristics. Moreover, the cohort differences model indicated statistically significant differences between the cohorts. Neither LASSO nor any of the tested classifiers resulted in a clinical relevant prognostic model that could be validated on the available datasets.

Conclusion

The results imply that the study might have been influenced by a limited sample size, heterogeneous patient characteristics, and inconsistent imaging parameters. No prognostic performance of FDG-PET or CT based radiomics models can be reported. This study highlights the necessity of extensive evaluations of cohorts and of validation datasets, especially in retrospective multi-centric datasets.

Pre-therapy Somatostatin Receptor-Based Heterogeneity Predicts Overall Survival in Pancreatic Neuroendocrine Tumor Patients Undergoing Peptide Receptor Radionuclide Therapy

PURPOSE

Early identification of aggressive disease could improve decision support in pancreatic neuroendocrine tumor (pNET) patients prior to peptide receptor radionuclide therapy (PRRT). The prognostic value of intratumoral textural features (TF) determined by baseline somatostatin receptor (SSTR)-positron emission tomography (PET) before PRRT was analyzed.

PROCEDURES

Thirty-one patients with G1/G2 pNET were enrolled (G2, n = 23/31). Prior to PRRT with [¹⁷⁷Lu]DOTATATE (mean, 3.6 cycles), baseline SSTR-PET computed tomography was performed. By segmentation of 162 (median per patient, 5) metastases, intratumoral TF were computed. The impact of conventional PET parameters (SUV_mean/max), imaging-based TF, and clinical parameters (Ki67, CgA) for prediction of both progression-free survival (PFS) and overall survival (OS) after PRRT were evaluated.

RESULTS

Within a median follow-up of 3.7 years, tumor progression was detected in 21 patients (median, 1.5 years) and 13/31 deceased (median, 1.9 years). In ROC analysis, the TF entropy, reflecting derangement on a voxel-by-voxel level, demonstrated predictive capability for OS (cutoff = 6.7, AUC = 0.71, p = 0.02). Of note, increasing entropy could predict a longer survival (> 6.7, OS = 2.5 years, 17/31), whereas less voxel-based derangement portended inferior outcome (< 6.7, OS = 1.9 years, 14/31). These findings were supported in a G2 subanalysis (> 6.9, OS = 2.8 years, 9/23 vs. < 6.9, OS = 1.9 years, 14/23). Kaplan-Meier analysis revealed a significant distinction between high- and low-risk groups using entropy (n = 31, p < 0.05). For those patients below the ROC-derived threshold, the relative risk of death after PRRT was 2.73 (n = 31, p = 0.04). Ki67 was negatively associated with PFS (p = 0.002); however, SUV_mean/max failed in prognostication (n.s.).

CONCLUSIONS

In contrast to conventional PET parameters, assessment of intratumoral heterogeneity demonstrated superior prognostic performance in pNET patients undergoing PRRT. This novel PET-based strategy of outcome prediction prior to PRRT might be useful for patient risk stratification.

Radiomics and radiogenomics of prostate cancer

Radiomics and radiogenomics are attractive research topics in prostate cancer. Radiomics mainly focuses on extraction of quantitative information from medical imaging, whereas radiogenomics aims to correlate these imaging features to genomic data. The purpose of this review is to provide a brief overview summarizing recent progress in the application of radiomics-based approaches in prostate cancer and to discuss the potential role of radiogenomics in prostate cancer.

A radiomics nomogram may improve the prediction of IDH genotype for astrocytoma before surgery

OBJECTIVES

To develop and validate a radiomics nomogram to preoperative prediction of isocitrate dehydrogenase (IDH) genotype for astrocytomas, which might contribute to the pretreatment decision-making and prognosis evaluating.

METHODS

One hundred five astrocytomas (Grades II-IV) with contrast-enhanced T1-weighted imaging (CE-T1WI), T2 fluid-attenuated inversion recovery (T2FLAIR), and apparent diffusion coefficient (ADC) map were enrolled in this study (training cohort: n = 74; validation cohort: n = 31). IDH1/2 genotypes were determined using Sanger sequencing. A total of 3882 radiomics features were extracted. Support vector machine algorithm was used to build the radiomics signature on the training cohort. Incorporating radiomics signature and clinico-radiological risk factors, the radiomics nomogram was developed. Receiver operating characteristic (ROC) curve and area under the curve (AUC) were used to assess these models. Kaplan-Meier survival analysis and log rank test were performed to assess the prognostic value of the radiomics nomogram.

RESULTS

The radiomics signature was built by six selected radiomics features and yielded AUC values of 0.901 and 0.888 in the training and validation cohorts. The radiomics nomogram based on the radiomics signature and age performed better than the clinico-radiological model (training cohort, AUC = 0.913 and 0.817; validation cohort, AUC = 0.900 and 0.804). Additionally, the survival analysis showed that prognostic values of the radiomics nomogram and IDH genotype were similar (log rank test, p < 0.001; C-index = 0.762 and 0.687; z-score test, p = 0.062).

CONCLUSIONS

The radiomics nomogram might be a useful supporting tool for the preoperative prediction of IDH genotype for astrocytoma, which could aid pretreatment decision-making.

KEY POINTS

• The radiomics signature based on multiparametric and multiregional MRI images could predict IDH genotype of Grades II-IV astrocytomas. • The radiomics nomogram performed better than the clinico-radiological model, and it might be an easy-to-use supporting tool for IDH genotype prediction. • The prognostic value of the radiomics nomogram was similar with that of the IDH genotype, which might contribute to prognosis evaluating.

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.

Pretreatment MRI radiomics analysis allows for reliable prediction of local recurrence in non-metastatic T4 nasopharyngeal carcinoma

BACKGROUND

To identify a radiomics signature to predict local recurrence in patients with non-metastatic T4 nasopharyngeal carcinoma (NPC).

METHODS

A total of 737 patients from Sun Yat-sen University Cancer Center (training cohort: n = 360; internal validation cohort: n = 120) and Wuzhou Red Cross Hospital (external validation cohort: n = 257) underwent feature extraction from the largest axial area of the tumor on pretreatment magnetic resonance imaging scans. Feature selection was based on the prognostic performance and feature stability in the training cohort. Radscores were generated using the Cox proportional hazards regression model with the selected features in the training cohort and then validated in the internal and external validation cohorts. We also constructed a nomogram for predicting local recurrence-free survival (LRFS).

FINDINGS

Eleven features were selected to construct the Radscore, which was significantly associated with LRFS. For the training, internal validation, and external validation cohorts, the Radscore (C-index: 0.741 vs. 0.753 vs. 0.730) outperformed clinical prognostic variables (C-index for primary gross tumor volume: 0.665 vs. 0.672 vs. 0.577; C-index for age: 0.571 vs. 0.629 vs. 0.605) in predicting LRFS. The generated radiomics nomogram, which integrated the Radscore and clinical variables, exhibited a satisfactory prediction performance (C-index: 0.810 vs. 0.807 vs. 0.753). The nomogram-defined high-risk group had a shorter LRFS than did the low-risk group (5-year LRFS: 73.6% vs. 95.3%, P < .001; 79.6% vs 95.8%, P = .006; 85.7% vs 96.7%, P = .005).

INTERPRETATION

The Radscore can reliably predict LRFS in patients with non-metastatic T4 NPC, which might guide individual treatment decisions. FUND: This study was funded by the Health & Medical Collaborative Innovation Project of Guangzhou City, China.

Reproducibility and non-redundancy of radiomic features extracted from arterial phase CT scans in hepatocellular carcinoma patients: impact of tumor segmentation variability

Background

The reproducibility and non-redundancy of radiomic features are challenges in accelerating the clinical translation of radiomics. In this study, we focused on the robustness and non-redundancy of radiomic features extracted from computed tomography (CT) scans in hepatocellular carcinoma (HCC) patients with respect to different tumor segmentation methods.

Methods

Arterial enhanced CT images were retrospectively randomly obtained from 106 patients. As a training data set, 26 HCC patients were used to calculate the features' reproducibility and redundancy. Another data set (55 HCC patients and 25 healthy volunteers) was used for classification. The GrowCut and GraphCut semiautomatic segmentation methods were implemented in 3D Slicer software by two independent observers, and manual delineation was performed by five abdominal radiation oncologists to acquire the gross tumor volume (GTV). Seventy-one radiomic features were extracted from GTVs using Imaging Biomarker Explorer (IBEX) software, including 17 tumor intensity statistical features, 16 shape features and 38 textural features. For each radiomic feature, intraclass correlation coefficient (ICC) and hierarchical clustering were used to quantify its reproducibility and redundancy. Features with ICC values greater than 0.75 were considered reproducible. To generate the number of non-redundancy feature subgroups, the R² statistic method was used. Then, a classification model was built using a support vector machine (SVM) algorithm with 10-fold cross validation, and area under ROC curve (AUC) was used to evaluate the utility of non-redundant feature extraction by hierarchical clustering.

Results

The percentages of excellent reproducible features in the manual delineation group, GraphCut and GrowCut segmentation group were 69% [49], 73% [52] and 79% [56], respectively. Sixty-five percent [46] of the features showed strong robustness for all segmentation methods. The optimal number of cluster subgroup were 9, 13 and 11 for manual delineation, GraphCut and GrowCut segmentation, respectively. The optimal cluster subgroup number was 6 for all groups when the collectively high reproducibility features were selected for clustering. The receiver operating characteristic (ROC) analysis of radiomics classification model with and without feature reduction for healthy liver and HCC had an AUC value of 0.857 and 0.721 respectively.

Conclusions

Our study demonstrates that variations exist in the reproducibility of quantitative imaging features extracted from tumor regions segmented using different methods. The reproducibility and non-redundancy of the radiomic features rely greatly on the tumor segmentation in HCC CT images. We recommend that the most reliable and uniform radiomic features should be selected in the clinical use of radiomics. Classification experiments with feature reduction showed that radiomic features were effective in identifying healthy liver and HCC.

Prognostic modeling for patients with colorectal liver metastases incorporating FDG PET radiomic features

OBJECTIVE

We aimed to improve prediction of outcome for patients with colorectal liver metastases, via prognostic models incorporating PET-derived measures, including radiomic features that move beyond conventional standard uptake value (SUV) measures.

PATIENTS AND METHODS

A range of parameters including volumetric and heterogeneity measures were derived from FDG PET images of 52 patients with colorectal intrahepatic-only metastases (29 males and 23 females; mean age 62.9 years [SD 9.8; range 32-82]). The patients underwent PET/CT imaging as part of the clinical workup prior to final decision on treatment. Univariate and multivariate models were implemented, which included statistical considerations (to discourage false discovery and overfitting), to predict overall survival (OS), progression-free survival (PFS) and event-free survival (EFS). Kaplan-Meier survival analyses were performed, where the subjects were divided into high-risk and low-risk groups, from which the hazard ratios (HR) were computed via Cox proportional hazards regression.

RESULTS

Commonly-invoked SUV metrics performed relatively poorly for different prediction tasks (SUVmax HR = 1.48, 0.83 and 1.16; SUVpeak HR = 2.05, 1.93, and 1.64, for OS, PFS and EFS, respectively). By contrast, the number of liver metastases and metabolic tumor volume (MTV) each performed well (with respective HR values of 2.71, 2.61 and 2.42, and 2.62, 1.96 and 2.29, for OS, PFS and EFS). Total lesion glycolysis (TLG) also resulted in similar performance as MTV. Multivariate prognostic modeling incorporating different features (including those quantifying intra-tumor heterogeneity) resulted in further enhanced prediction. Specifically, HR values of 4.29, 4.02 and 3.20 (p-values = 0.00004, 0.0019 and 0.0002) were obtained for OS, PFS and EFS, respectively.

CONCLUSIONS

PET-derived measures beyond commonly invoked SUV parameters hold significant potential towards improved prediction of clinical outcome in patients with liver metastases, especially when utilizing multivariate models.

CT texture analysis: a potential tool for predicting the Fuhrman grade of clear-cell renal carcinoma

BACKGROUND

The purpose of this study was to analyze the image heterogeneity of clear-cell renal-cell carcinoma (ccRCC) by computer tomography texture analysis and to provide new objective quantitative imaging parameters for the pre-operative prediction of Fuhrman-grade ccRCC.

METHODS

A retrospective analysis of 131 cases of ccRCCs was performed by manually depicting tumor areas. Then, histogram-based texture parameters were calculated. The texture-feature values between Fuhrman low- (Grade I-II) and high-grade (Grade III-IV) ccRCCs were compared by two independent sample t-tests (False Discovery Rate correction), and receiver operating characteristic curve (ROC) was used to evaluate the efficacy of using texture features to predict Fuhrman high- and low-grade ccRCCs.

RESULTS

There were no statistical differences for any texture parameters without filtering (p > 0.05). There was a statistically significant difference between the entropy (fine) of the corticomedullary phase and the entropy (fine and coarse) of the nephrographic phase after Laplace of Gaussian filtering. The area under the ROC of the entropy was between 0.74 and 0.83.

CONCLUSIONS

Computer tomography texture features can predict the Fuhrman grading of ccRCC pre-operatively, with entropy being the most important imaging marker for clinical application.

Discovery of pre-therapy 2-deoxy-2-18F-fluoro-D-glucose positron emission tomography-based radiomics classifiers of survival outcome in non-small-cell lung cancer patients

PURPOSE

The aim of this multi-center study was to discover and validate radiomics classifiers as image-derived biomarkers for risk stratification of non-small-cell lung cancer (NSCLC).

PATIENTS AND METHODS

Pre-therapy PET scans from a total of 358 Stage I-III NSCLC patients scheduled for radiotherapy/chemo-radiotherapy acquired between October 2008 and December 2013 were included in this seven-institution study. A semi-automatic threshold method was used to segment the primary tumors. Radiomics predictive classifiers were derived from a training set of 133 scans using TexLAB v2. Least absolute shrinkage and selection operator (LASSO) regression analysis was used for data dimension reduction and radiomics feature vector (FV) discovery. Multivariable analysis was performed to establish the relationship between FV, stage and overall survival (OS). Performance of the optimal FV was tested in an independent validation set of 204 patients, and a further independent set of 21 (TESTI) patients.

RESULTS

Of 358 patients, 249 died within the follow-up period [median 22 (range 0-85) months]. From each primary tumor, 665 three-dimensional radiomics features from each of seven gray levels were extracted. The most predictive feature vector discovered (FVX) was independent of known prognostic factors, such as stage and tumor volume, and of interest to multi-center studies, invariant to the type of PET/CT manufacturer. Using the median cut-off, FVX predicted a 14-month survival difference in the validation cohort (N = 204, p = 0.00465; HR = 1.61, 95% CI 1.16-2.24). In the TESTI cohort, a smaller cohort that presented with unusually poor survival of stage I cancers, FVX correctly indicated a lack of survival difference (N = 21, p = 0.501). In contrast to the radiomics classifier, clinically routine PET variables including SUVmax, SUVmean and SUVpeak lacked any prognostic information.

CONCLUSION

PET-based radiomics classifiers derived from routine pre-treatment imaging possess intrinsic prognostic information for risk stratification of NSCLC patients to radiotherapy/chemo-radiotherapy.

Can Texture Analysis Be Used to Distinguish Benign From Malignant Adrenal Nodules on Unenhanced CT, Contrast-Enhanced CT, or In-Phase and Opposed-Phase MRI?

OBJECTIVE

The purpose of this study is to determine whether second-order texture analysis can be used to distinguish lipid-poor adenomas from malignant adrenal nodules on unenhanced CT, contrast-enhanced CT (CECT), and chemical-shift MRI.

MATERIALS AND METHODS

In this retrospective study, 23 adrenal nodules (15 lipid-poor adenomas and eight adrenal malignancies) in 20 patients (nine female patients and 11 male patients; mean age, 59 years [range, 15-80 years]) were assessed. All patients underwent unenhanced CT, CECT, and chemical-shift MRI. Twenty-one second-order texture features from the gray-level cooccurrence matrix and gray-level run-length matrix were calculated in 3D. The mean values for 21 texture features and four imaging features (lesion size, unenhanced CT attenuation, CECT attenuation, and signal intensity index) were compared using a t test. The diagnostic performance of texture analysis versus imaging features was also compared using AUC values. Multivariate logistic regression models to predict malignancy were constructed for texture analysis and imaging features.

RESULTS

Lesion size, unenhanced CT attenuation, and the signal intensity index showed significant differences between benign and malignant adrenal nodules. No significant difference was seen for CECT attenuation. Eighteen of 21 CECT texture features and nine of 21 unenhanced CT texture features revealed significant differences between benign and malignant adrenal nodules. CECT texture features (mean AUC value, 0.80) performed better than CECT attenuation (mean AUC value, 0.60). Multivariate logistic regression models showed that CECT texture features, chemical-shift MRI texture features, and imaging features were predictive of malignancy.

CONCLUSION

Texture analysis has a potential role in distinguishing benign from malignant adrenal nodules on CECT and may decrease the need for additional imaging studies in the workup of incidentally discovered adrenal nodules.

MRI of pancreatic ductal adenocarcinoma: texture analysis of T2-weighted images for predicting long-term outcome

PURPOSE

To assess the association between T2-weighted imaging (T2WI) texture-analysis parameters and the pathological aggressiveness or long-term outcomes in pancreatic ductal adenocarcinoma (PDAC) patients.

METHODS

A total of 66 patients (mean age 65.3 ± 9.0 years) who underwent preoperative MRI followed by pancreatectomy for PDAC between 2013 and 2015 were included in this study. A radiologist performed a texture analysis twice on one axial image using commercial software. Differences in the tex parameters, according to pathological factors, were analyzed using a Student's t test or an ANOVA with Tukey's test. Univariate and multivariate Cox proportional hazards regression analyses were used to evaluate the association between tex parameters and recurrence-free survival (RFS) or overall survival (OS).

RESULTS

The mean follow-up time was 18.5 months, and there were 58 recurrences and 39 deaths. The mean of the positive pixel (MPP)-related factors was significantly lower in poorly differentiated tumors than in well-differentiated tumors as well as in cases with perineural invasion. The univariate Cox proportional hazards analysis showed a significant association between the tex parameters and RFS or OS. However, only tumor size was statistically significant after the multivariate analysis. Only tumor size and entropy with medium texture were significantly associated with OS after the multivariate analysis.

CONCLUSIONS

Tumor size was a significant predictive factor for RFS and OS in PDAC patients. Although entropy with medium texture analysis was significantly associated with OS, there were also limitations in the texture analysis; thus, further study is necessary.

Prognostic value of textural indices extracted from pretherapeutic 18-F FDG-PET/CT in head and neck squamous cell carcinoma

BACKGROUND

This study aimed at assessing the prognostic value of textural indices extracted from 18F-fluorodeoxyglucose positron-emission tomography (FDG-PET)/CT in a large cohort of patients with head and neck squamous cell carcinomas (HNSCC) of any anatomic subsite and staging.

METHODS

Consecutive patients with HNSCC referred for a pretreatment FDG-PET/CT were retrospectively included and followed up for a minimum of 2 years. Standardized uptake value, metabolic tumor volume (MTV), and textural indices were calculated using LIFEx software. Prognostic significance of parameters was assessed in univariate and multivariate analysis.

RESULTS

Textural indices were extracted in 284 patients (mean age = 63.7±9.6 years). In univariate analysis, MTV and 4 textural indices-Correlation, Entropy, Energy, and Coarseness-were significantly correlated with overall survival (OS). In multivariate analysis, MTV (P = .008) and Correlation (P = .028) remained independently correlated to OS.

CONCLUSION

This study showed that MTV and 1 textural index extracted from pretherapeutic FDG-PET/CT (Correlation) were independent prognostic factors of OS in patients with HNSCC.

Novel imaging techniques in staging oesophageal cancer

The survival of oesophageal cancer is poor as most patients present with advanced disease. Radiological staging of oesophageal cancer is complex but is fundamental to clinical management. Accurate staging investigations are vitally important to guide treatment decisions and optimise patient outcomes. A combination of baseline computed tomography (CT), endoscopic ultrasound (EUS) and positron emission tomography (PET) are currently used for initial treatment decisions. The potential value of these imaging modalities to re-stage disease, monitor response and alter treatment is currently being investigated. This review presents an essential update on the accuracy of oesophageal cancer staging investigations, their use in re-staging after neo-adjuvant therapy and introduces evolving imaging techniques, including novel biomarkers that have clinical potential in oesophageal cancer.

Deep learning in medical imaging and radiation therapy

The goals of this review paper on deep learning (DL) in medical imaging and radiation therapy are to (a) summarize what has been achieved to date; (b) identify common and unique challenges, and strategies that researchers have taken to address these challenges; and (c) identify some of the promising avenues for the future both in terms of applications as well as technical innovations. We introduce the general principles of DL and convolutional neural networks, survey five major areas of application of DL in medical imaging and radiation therapy, identify common themes, discuss methods for dataset expansion, and conclude by summarizing lessons learned, remaining challenges, and future directions.

Challenges and Promises of PET Radiomics

PURPOSE

Radiomics describes the extraction of multiple, otherwise invisible, features from medical images that, with bioinformatic approaches, can be used to provide additional information that can predict underlying tumor biology and behavior.

METHODS AND MATERIALS

Radiomic signatures can be used alone or with other patient-specific data to improve tumor phenotyping, treatment response prediction, and prognosis, noninvasively. The data describing 18F-fluorodeoxyglucose positron emission tomography radiomics, often using texture or heterogeneity parameters, are increasing rapidly.

RESULTS

In relation to radiation therapy practice, early data have reported the use of radiomic approaches to better define tumor volumes and predict radiation toxicity and treatment response.

CONCLUSIONS

Although at an early stage of development, with many technical challenges remaining and a need for standardization, promise nevertheless exists that PET radiomics will contribute to personalized medicine, especially with the availability of increased computing power and the development of machine-learning approaches for imaging.

Data-driven, voxel-based analysis of brain PET images: Application of PCA and LASSO methods to visualize and quantify patterns of neurodegeneration

Spatial patterns of radiotracer binding in positron emission tomography (PET) images may convey information related to the disease topology. However, this information is not captured by the standard PET image analysis that quantifies the mean radiotracer uptake within a region of interest (ROI). On the other hand, spatial analyses that use more advanced radiomic features may be difficult to interpret. Here we propose an alternative data-driven, voxel-based approach to spatial pattern analysis in brain PET, which can be easily interpreted. We apply principal component analysis (PCA) to identify voxel covariance patterns, and optimally combine several patterns using the least absolute shrinkage and selection operator (LASSO). The resulting models predict clinical disease metrics from raw voxel values, allowing for inclusion of clinical covariates. The analysis is performed on high-resolution PET images from healthy controls and subjects affected by Parkinson’s disease (PD), acquired with a pre-synaptic and a post-synaptic dopaminergic PET tracer. We demonstrate that PCA identifies robust and tracer-specific binding patterns in sub-cortical brain structures; the patterns evolve as a function of disease progression. Principal component LASSO (PC-LASSO) models of clinical disease metrics achieve higher predictive accuracy compared to the mean tracer binding ratio (BR) alone: the cross-validated test mean squared error of adjusted disease duration (motor impairment score) was 16.3 ± 0.17 years² (9.7 ± 0.15) with mean BR, versus 14.4 ± 0.18 years² (8.9 ± 0.16) with PC-LASSO. We interpret the best-performing PC-LASSO models in the spatial sense and discuss them with reference to the PD pathology and somatotopic organization of the striatum. PC-LASSO is thus shown to be a useful method to analyze clinically-relevant tracer binding patterns, and to construct interpretable, imaging-based predictive models of clinical metrics.

Radiomic Profiling of Head and Neck Cancer: 18F-FDG PET Texture Analysis as Predictor of Patient Survival

Background and Purpose

The accurate prediction of prognosis and pattern of failure is crucial for optimizing treatment strategies for patients with cancer, and early evidence suggests that image texture analysis has great potential in predicting outcome both in terms of local control and treatment toxicity. The aim of this study was to assess the value of pretreatment ¹⁸F-FDG PET texture analysis for the prediction of treatment failure in primary head and neck squamous cell carcinoma (HNSCC) treated with concurrent chemoradiation therapy.

Methods

We performed a retrospective analysis of 90 patients diagnosed with primary HNSCC treated between January 2010 and June 2017 with concurrent chemo-radiotherapy. All patients underwent ¹⁸F-FDG PET/CT before treatment. ¹⁸F-FDG PET/CT texture features of the whole primary tumor were measured using an open-source texture analysis package. Least absolute shrinkage and selection operator (LASSO) was employed to select the features that are associated the most with clinical outcome, as progression-free survival and overall survival. We performed a univariate and multivariate analysis between all the relevant texture parameters and local failure, adjusting for age, sex, smoking, primary tumor site, and primary tumor stage. Harrell c-index was employed to score the predictive power of the multivariate cox regression models.

Results

Twenty patients (22.2%) developed local failure, whereas the remaining 70 (77.8%) achieved durable local control. Multivariate analysis revealed that one feature, defined as low-intensity long-run emphasis (LILRE), was a significant predictor of outcome regardless of clinical variables (hazard ratio < 0.001, P=0.001).The multivariate model based on imaging biomarkers resulted superior in predicting local failure with a c-index of 0.76 against 0.65 of the model based on clinical variables alone.

Conclusion

LILRE, evaluated on pretreatment ¹⁸F-FDG PET/CT, is associated with higher local failure in patients with HNSCC treated with chemoradiotherapy. Using texture analysis in addition to clinical variables may be useful in predicting local control.

Correlation between Human Papillomavirus Status and Quantitative MR Imaging Parameters including Diffusion-Weighted Imaging and Texture Features in Oropharyngeal Carcinoma

BACKGROUND AND PURPOSE

The incidence of Oropharyngeal Squampus Cell Carcinoma (OPSCC) cases is increasing especially in the Western countries due to the spreading of human papilloma virus (HPV) infection. Radiological investigations, MRI in particular, are used in the daily clinical practice to stage OPSCC. The aim of this study was to investigate the association of quantitative MR imaging features including diffusion-weighted imaging and human papillomavirus status in oropharyngeal squamous cell carcinoma.

MATERIALS AND METHODS

We retrospectively analyzed 59 patients with untreated histologically proved T2-T4 oropharyngeal squamous cell carcinoma. Human papillomavirus status was determined by viral DNA detection on tissue samples. MR imaging protocol included T2-weighted, contrast-enhanced T1-weighted (volumetric interpolated brain examination), and DWI sequences. Parametric maps of apparent diffusion coefficient were obtained from DWI sequences. Texture analysis was performed on T2 and volumetric-interpolated brain examination sequences and on ADC maps. Differences in quantitative MR imaging features between tumors positive and negative for human papillomavirus and among subgroups of patients stratified by smoking status were tested using the nonparametric Mann-Whitney U test; the false discovery rate was controlled using the Benjamini-Hochberg correction; and a predictive model for human papillomavirus status was built using multivariable logistic regression.

RESULTS

Twenty-eight patients had human papillomavirus-positive oropharyngeal squamous cell carcinoma, while 31 patients had human papillomavirus-negative oropharyngeal squamous cell carcinoma. Tumors positive for human papillomavirus had a significantly lower mean ADC compared with those negative for it (median, 850.87 versus median, 1033.68; P < .001). Texture features had a lower discriminatory power for human papillomavirus status. Skewness on volumetric interpolated brain examination sequences was significantly higher in the subgroup of patients positive for human papillomavirus and smokers (P = .003). A predictive model based on smoking status and mean ADC yielded a sensitivity of 83.3% and specificity 92.6% in classifying human papillomavirus status.

CONCLUSIONS

ADC is significantly lower in oropharyngeal squamous cell carcinoma positive for human papillomavirus compared with oropharyngeal squamous cell carcinoma negative for it. ADC and smoking status allowed noninvasive prediction of human papillomavirus status with a good accuracy. These results should be validated and further investigated on larger prospective studies.

Radiomics analysis of multiparametric MRI for prediction of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer

OBJECTIVES

To develop and validate a radiomics predictive model based on pre-treatment multiparameter magnetic resonance imaging (MRI) features and clinical features to predict a pathological complete response (pCR) in patients with locally advanced rectal cancer (LARC) after receiving neoadjuvant chemoradiotherapy (CRT).

METHODS

One hundred and eighty-six consecutive patients with LARC (training dataset, n = 131; validation dataset, n = 55) were enrolled in our retrospective study. A total of 1,188 imaging features were extracted from pre-CRT T2-weighted (T2-w), contrast-enhanced T1-weighted (cT1-w) and ADC images for each patient. Three steps including least absolute shrinkage and selection operator (LASSO) regression were performed to select key features and build a radiomics signature. Combining clinical risk factors, a radiomics nomogram was constructed. The predictive performance was evaluated by receiver operator characteristic (ROC) curve analysis, and then assessed with respect to its calibration, discrimination and clinical usefulness.

RESULTS

Thirty-one of 186 patients (16.7%) achieved pCR. The radiomics signature derived from joint T2-w, ADC, and cT1-w images, comprising 12 selected features, was significantly associated with pCR status and showed better predictive performance than signatures derived from either of them alone in both datasets. The radiomics nomogram, incorporating the radiomics signature and MR-reported T-stages, also showed good discrimination, with areas under the ROC curves (AUCs) of 0.948 (95% CI, 0.907-0.989) and 0.966 (95% CI, 0.924-1.000), as well as good calibration in both datasets. Decision curve analysis confirmed its clinical usefulness.

CONCLUSIONS

This study demonstrated that the pre-treatment radiomics nomogram can predict pCR in patients with LARC and potentially guide treatments to select patients for a "wait-and-see" policy.

KEY POINTS

• Radiomics analysis of pre-CRT multiparameter MR images could predict pCR in patients with LARC. • Proposed radiomics signature from joint T2-w, ADC and cT1-w images showed better predictive performance than individual signatures. • Most of the clinical characteristics were unable to predict pCR.

The developing role of FDG PET imaging for prognostication and radiotherapy target volume delineation in non-small cell lung cancer

Advancements in functional imaging technology have allowed new possibilities in contouring of target volumes, monitoring therapy, and predicting treatment outcome in non-small cell lung cancer (NSCLC). Consequently, the role of ¹⁸F-fluorodeoxyglucose positron emission tomography (FDG PET) has expanded in the last decades from a stand-alone diagnostic tool to a versatile instrument integrated with computed tomography (CT), with a prominent role in lung cancer radiotherapy. This review outlines the most recent literature on developments in FDG PET imaging for prognostication and radiotherapy target volume delineation (TVD) in NSCLC. We also describe the challenges facing the clinical implementation of these developments and present new ideas for future research.