Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017;14:749-762. [PMID: 28975929 DOI: 10.1038/nrclinonc.2017.141]

Radiographic Image Radiomics Feature Reproducibility: A Preliminary Study on the Impact of Field Size

RATIONALE AND OBJECTIVES

Radiomics is an approach to quantifying diseases. Recently, several studies have indicated that radiomics features are vulnerable against imaging parameters. The aim of this study is to assess how radiomics features change with radiographic field sizes, positions in the field size, and mAs.

MATERIALS AND METHODS

A large and small wood phantom and a cotton phantom were prepared and imaged in different field sizes, mAs, and placement in the radiographic field size. A region of interest was drawn on the image features, and twenty two features were extracted. Radiomics feature reproducibility was obtained based on coefficient of variation, Bland-Altman analysis, and intraclass correlation coefficient. Features with coefficient of variation ≤ 5%, intraclass correlation coefficient ≤ 90%, and 1% ≤ U/LRL ≤30% were introduced as robust features. U/LRL is upper/lower reproducibility limits in Bland-Altman.

RESULTS

For all field sizes and all phantoms, features including Difference Variance, Inverse Different Moment, Fraction, Long Run Emphasis, Run Length Non Uniformity, and Short Run Emphasis were found as highly reproducible features. For change in the position of field size, Fraction was the most reproducible in all field sizes and all phantoms. On the mAs change, we found that feature, Short Run Emphasis field 15 × 15 for small wood phantom, and Correlation in all field sizes for Cotton are the most reproducible features.

CONCLUSION

We demonstrated that radiomics features are strongly vulnerable against radiographic field size, positions in the radiation field, mAs, and phantom materials, and reproducibility analyses should be performed before each radiomics study. Moreover, these changing parameters should be considered, and their effects should be minimized in future radiomics studies.

Radiomic features of Pk-DCE MRI parameters based on the extensive Tofts model in application of breast cancer

To explore radiomic features of pharmacokinetic dynamic contrast-enhanced (Pk-DCE) MRI on the extensive Tofts model to diagnose breast cancer and predict molecular phenotype. Breast lesions enrolled must undergo Pk-DCE MRI before treatment or puncture, and be identified as primary lesions by pathology. K^trans, K_ep, V_e and V_p were generated on the extensive Tofts model. Radiomic features (histogram, geometry and texture features) were extracted from parametric maps and selected by LASSO. The subjects were divided into training and validation cohort with a ratio of 4:1 to construct model in diagnosis of breast cancer. Feature analysis was made to predict the molecular phenotype. Area under curve (AUC), sensitivity, specificity and accuracy were used to evaluate radiomic features. DeLong's test was performed to compare AUC values. 228 breast lesions met the criteria were used to discrimination and 126 malignant lesions were used to study molecular phenotypes. The number of training cohort and validation cohort were 182 and 46, respectively. The AUC of K^trans, K_ep, V_e, and V_p was 0.95, 0.93, 0.89, and 0.96, and their accuracy was 85%, 89%, 89%, 94% respectively in diagnosis of breast lesions, while their AUC was 0.71 to 0.77, 0.61 to 0.68, and 0.67 to 0.74 to predict ER/PR, Her-2, and Ki-67. There was no significant difference among parameters (P > 0.05). Radiomic features based on Pk-DCE MRI have an advantage to diagnose breast cancer and less ability to predict molecular phenotypes, which are beneficial to guide clinical treatment of breast lesions in some extent.

Radiomic profiles in diffuse glioma reveal distinct subtypes with prognostic value

PURPOSE

To evaluate a radiomic approach for the stratification of diffuse gliomas with distinct prognosis and provide additional resolution of their clinicopathological and molecular characteristics.

METHODS

For this retrospective study, a total of 704 radiomic features were extracted from the multi-channel MRI data of 166 diffuse gliomas. Survival-associated radiomic features were identified and submitted to distinguish glioma subtypes using consensus clustering. Multi-layered molecular data were used to observe the different clinical and molecular characteristics between radiomic subtypes. The relative profiles of an array of immune cell infiltrations were measured gene set variation analysis approach to explore differences in tumor immune microenvironment.

RESULTS

A total of 6 categories, including 318 radiomic features were significantly correlated with the overall survival of glioma patients. Two subgroups with distinct prognosis were separated by consensus clustering of radiomic features that significantly associated with survival. Histological stage and molecular factors, including IDH status and MGMT promoter methylation status were significant differences between the two subtypes. Furthermore, gene functional enrichment analysis and immune infiltration pattern analysis also hinted that the inferior prognosis subtype may more response to immunotherapy.

CONCLUSION

A radiomic model derived from multi-parameter MRI of the gliomas was successful in the risk stratification of diffuse glioma patients. These data suggested that radiomics provided an alternative approach for survival estimation and may improve clinical decision-making.

Introduction to Radiomics

Radiomics is a rapidly evolving field of research concerned with the extraction of quantitative metrics-the so-called radiomic features-within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity and shape and may, alone or in combination with demographic, histologic, genomic, or proteomic data, be used for clinical problem solving. The goal of this continuing education article is to provide an introduction to the field, covering the basic radiomics workflow: feature calculation and selection, dimensionality reduction, and data processing. Potential clinical applications in nuclear medicine that include PET radiomics-based prediction of treatment response and survival will be discussed. Current limitations of radiomics, such as sensitivity to acquisition parameter variations, and common pitfalls will also be covered.

Radiogenomics predicts the expression of microRNA-1246 in the serum of esophageal cancer patients

Radiogenomics is a new field that provides clinically useful prognostic predictions by linking molecular characteristics such as the genetic aberrations of malignant tumors with medical images. The abnormal expression of serum microRNA-1246 (miR-1246) has been reported as a prognostic factor of esophageal squamous cell carcinoma (ESCC). To evaluate the power of the miR-1246 level predicted with radiogenomics techniques as a predictor of the prognosis of ESCC patients. The real miR-1246 expression (miR-1246_real) was measured in 92 ESCC patients. Forty-five image features (IFs) were extracted from tumor regions on contrast-enhanced computed tomography. A prediction model for miR-1246_real was constructed using linear regression with selected features identified in a correlation analysis of miR-1246_real and each IF. A threshold to divide the patients into two groups was defined according to a receiver operating characteristic analysis for miR-1246_real. Survival analyses were performed between two groups. Six IFs were correlated with miR-1246_real and were included in the prediction model. The survival curves of high and low groups of miR-1246_real and miR-1246_pred showed significant differences (p = 0.001 and 0.016). Both miR-1246_real and miR-1246_pred were independent predictors of overall survival (p = 0.030 and 0.035). miR-1246_pred produced by radiogenomics had similar power to miR-1246_real for predicting the prognosis of ESCC.

A radiomics model to predict the invasiveness of thymic epithelial tumors based on contrast‑enhanced computed tomography

In the present study, we aimed to construct a radiomics model using contrast‑enhanced computed tomography (CT) to predict the pathological invasiveness of thymic epithelial tumors (TETs). We retrospectively reviewed the records of 179 consecutive patients (89 females) with histologically confirmed TETs from two hospitals. The 82 low‑ and 97 high‑risk TETs were assigned to training (90 tumors), internal validation (49 tumors) and external validation (40 tumors) cohorts. Radiomics features extracted from preoperative contrast‑enhanced chest CT were selected using least absolute shrinkage and selection operator logistic regression. Three prediction models were developed using multivariate logistic regression analysis. Their performance and clinical utility were assessed using receiver operating characteristic curves and the DeLong test, respectively. Eight radiomics features with non‑zero coefficients were used to develop a radiomics score, which significantly differed between low‑ and high‑risk TETs (P<0.001). The subjective finding, infiltration, was independently associated with high‑risk TETs. Prediction models based on infiltration alone, the radiomics signature alone, and both these parameters showed diagnostic accuracies of 72.2% [area under curve (AUC), 0.731; 95% confidence interval (CI): 0.627‑0.819; sensitivity, 85.7%; specificity, 60.4%], 88.9% (AUC, 0.944; 95% CI: 0.874‑0.981; sensitivity, 92.9%; specificity, 85.4%), and 90.0% (AUC, 0.953; 95% CI: 0.887‑0.987; sensitivity, 92.9%; specificity, 87.5%), respectively. Decision‑curve analysis showed that the combined model added more net benefit than the single‑parameter models. In conclusion, a radiomics signature based on contrast‑enhanced CT has the potential to differentiate between low‑ and high‑risk TETs. The model incorporating the radiomics signature and subjective finding may facilitate the individualized, preoperative prediction of the pathological invasiveness of TETs.

[Use of artificial intelligence for image reconstruction]

CLINICAL/METHODOLOGICAL PROBLEM

In the reconstruction of three-dimensional image data, artifacts that interfere with the appraisal often occur as a result of trying to minimize the dose or due to missing data. Used iterative reconstruction methods are time-consuming and have disadvantages.

STANDARD RADIOLOGICAL METHODS

These problems are known to occur in computed tomography (CT), cone beam CT, interventional imaging, magnetic resonance imaging (MRI) and nuclear medicine imaging (PET and SPECT).

METHODOLOGICAL INNOVATIONS

Using techniques based on the use of artificial intelligence (AI) in data analysis and data supplementation, a number of problems can be solved up to a certain extent.

PERFORMANCE

The performance of the methods varies greatly. Since the generated image data usually look very good using the AI-based methods presented here while their results depend strongly on the study design, reliable comparable quantitative statements on the performance are not yet available in broad terms.

EVALUATION

In principle, the methods of image reconstruction based on AI algorithms offer many possibilities for improving and optimizing three-dimensional image datasets. However, the validity strongly depends on the design of the respective study in the structure of the individual procedure. It is therefore essential to have a suitable test prior to use in clinical practice.

PRACTICAL RECOMMENDATIONS

Before the widespread use of AI-based reconstruction methods can be recommended, it is necessary to establish meaningful test procedures that can characterize the actual performance and applicability in terms of information content and a meaningful study design during the learning phase of the algorithms.

Potential value of CT radiomics in the distinction of intestinal-type gastric adenocarcinomas

OBJECTIVE

The purpose of the study was to investigate the role of CT radiomics for the preoperative distinction of intestinal-type gastric adenocarcinomas.

MATERIALS AND METHODS

A total of 187 consecutive patients with preoperative contrast CT examination and pathologically proven gastric adenocarcinoma were retrospectively collected. Patients were divided into a training set (n = 150) and a test set (n = 37). Arterial phase (AP), portal phase (PP), and delay phase (DP) images were retrieved for analysis. A dedicated postprocessing software was used to segment the lesions and extract radiomics features. Random forest (RF) algorithm was applied to construct the classifier models. A nomogram was developed by incorporating multiphase radiomics scores. Receiver operating characteristic (ROC) curves were used to evaluate the performance of the radiomics model and nomogram in both sets.

RESULTS

The radiomics model showed a favorable capability in the distinction of intestinal-type gastric adenocarcinomas. The areas under curves (AUCs) of the AP, PP, and DP radiomics models were 0.754 (95% CI: 0.676, 0.820), 0.815 (95% CI: 0.744, 0.874), and 0.764 (95% CI: 0.688, 0.829) in the training set, respectively, which were confirmed in the test set with AUCs of 0.742 (95% CI: 0.572, 0.872), 0.775 (95% CI: 0.608, 0.895), and 0.857 (95% CI: 0.703, 0.950), respectively. The nomogram yielded excellent performance for distinguishing intestinal-type adenocarcinomas in both sets, with AUCs of 0.928 (95%: 0.875, 0.964) and 0.904 (95% CI: 0.761, 0.976).

CONCLUSIONS

The multiphase CT radiomics nomogram holds promise for the individual preoperative discrimination of intestinal-type gastric adenocarcinoma.

KEY POINTS

• CT radiomics has a potential role in the distinction of intestinal-type gastric adenocarcinomas. • Single-phase enhanced CT-based radiomics showed favorable capability in distinguishing intestinal-type tumors. • The nomogram which incorporates the multiphase radiomics scores could facilitate the individual prediction of intestinal-type lesions.

Multiparametric radiomics methods for breast cancer tissue characterization using radiological imaging

BACKGROUND AND PURPOSE

Multiparametric radiological imaging is vital for detection, characterization, and diagnosis of many different diseases. Radiomics provide quantitative metrics from radiological imaging that may infer potential biological meaning of the underlying tissue. However, current methods are limited to regions of interest extracted from a single imaging parameter or modality, which limits the amount of information available within the data. This limitation can directly affect the integration and applicable scope of radiomics into different clinical settings, since single image radiomics are not capable of capturing the true underlying tissue characteristics in the multiparametric radiological imaging space. To that end, we developed a multiparametric imaging radiomic (mpRad) framework for extraction of first and second order radiomic features from multiparametric radiological datasets.

METHODS

We developed five different radiomic techniques that extract different aspects of the inter-voxel and inter-parametric relationships within the high-dimensional multiparametric magnetic resonance imaging breast datasets. Our patient cohort consisted of 138 breast patients, where, 97 patients had malignant lesions and 41 patients had benign lesions. Sensitivity, specificity, receiver operating characteristic (ROC) and areas under the curve (AUC) analysis were performed to assess diagnostic performance of the mpRad parameters. Statistical significance was set at p < 0.05.

RESULTS

The mpRad features successfully classified malignant from benign breast lesions with excellent sensitivity and specificity of 82.5% and 80.5%, respectively, with Area Under the receiver operating characteristic Curve (AUC) of 0.87 (0.81-0.93). mpRad provided a 9-28% increase in AUC metrics over single radiomic parameters.

CONCLUSIONS

We have introduced the mpRad framework that extends radiomic analysis from single images to multiparametric datasets for better characterization of the underlying tissue biology.

The diagnostic accuracy of artificial intelligence in thoracic diseases: A protocol for systematic review and meta-analysis

INTRODUCTION

Thoracic diseases include a variety of common human primary malignant tumors, among which lung cancer and esophageal cancer are among the top 10 in cancer incidence and mortality. Early diagnosis is an important part of cancer treatment, so artificial intelligence (AI) systems have been developed for the accurate and automated detection and diagnosis of thoracic tumors. However, the complicated AI structure and image processing made the diagnosis result of AI-based system unstable. The purpose of this study is to systematically review published evidence to explore the accuracy of AI systems in diagnosing thoracic cancers.

METHODS AND ANALYSIS

We will conduct a systematic review and meta-analysis of the diagnostic accuracy of AI systems for the prediction of thoracic diseases. The primary objective is to assess the diagnostic accuracy of thoracic cancers, including assessing potential biases and calculating combined estimates of sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). The secondary objective is to evaluate the factors associated with different models, classifiers, and radiomics information. We will search databases such as PubMed/MEDLINE, Embase (via OVID), and the Cochrane Library. Two reviewers will independently screen titles and abstracts, perform full article reviews and extract study data. We will report study characteristics and assess methodological quality using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. RevMan 5.3 and Meta-disc 1.4 software will be used for data synthesis. If pooling is appropriate, we will produce summary receiver operating characteristic (SROC) curves, summary operating points (pooled sensitivity and specificity), and 95% confidence intervals around the summary operating points. Methodological subgroup and sensitivity analyses will be performed to explore heterogeneity.

PROSPERO REGISTRATION NUMBER

CRD42019135247.

Magnetic resonance-guided radiation therapy: A review

Magnetic resonance-guided radiation therapy (MRgRT) is a promising approach to improving clinical outcomes for patients treated with radiation therapy. The roles of image guidance, adaptive planning and magnetic resonance imaging in radiation therapy have been increasing over the last two decades. Technical advances have led to the feasible combination of magnetic resonance imaging and radiation therapy technologies, leading to improved soft-tissue visualisation, assessment of inter- and intrafraction motion, motion management, online adaptive radiation therapy and the incorporation of functional information into treatment. MRgRT can potentially transform radiation oncology by improving tumour control and quality of life after radiation therapy and increasing convenience of treatment by shortening treatment courses for patients. Multiple groups have developed clinical implementations of MRgRT predominantly in the abdomen and pelvis, with patients having been treated since 2014. While studies of MRgRT have primarily been dosimetric so far, an increasing number of trials are underway examining the potential clinical benefits of MRgRT, with coordinated efforts to rigorously evaluate the benefits of the promising technology. This review discusses the current implementations, studies, potential benefits and challenges of MRgRT.

Grading of Clear Cell Renal Cell Carcinomas by Using Machine Learning Based on Artificial Neural Networks and Radiomic Signatures Extracted From Multidetector Computed Tomography Images

RATIONALE AND OBJECTIVES

To evaluate the ability of artificial neural networks (ANN) fed with radiomic signatures (RSs) extracted from multidetector computed tomography images in differentiating the histopathological grades of clear cell renal cell carcinomas (ccRCCs).

MATERIALS AND METHODS

The multidetector computed tomography images of 227 ccRCCs were retrospectively analyzed. For each ccRCC, 14 conventional image features (CIFs) were extracted manually by two radiologists, and 556 texture features (TFs) were extracted by a free software application, MaZda (version 4.6). The high-dimensional dataset of these RSs was reduced using the least absolute shrinkage and selection operator. Five minimum mean squared error models (minMSEMs) for predicting the ccRCC histopathological grades were constructed from the CIFs, the TFs of the corticomedullary phase images (CMP), and the TFs of the parenchyma phase (PP) images and their combinations, respectively abbreviated as CIF-minMSEM, CMP-minMSEM, PP-minMSEM, CIF+CMP-minMSEM, and CIF+PP-minMSEM. The RSs of each model were fed 30 times consecutively into an ANN for machine learning, and the predictive accuracy of each time ML was recorded for the statistical analysis.

RESULTS

The five predictive models were constructed from 12, 19, and 10 features selected from the CIFs, the TFs of the CMP images, and that of PP images, respectively. On the basis of their accuracy across the whole cohort, the five models were ranked as follows: CIF+CMP-minMSEM (accuracy: 94.06% ± 1.14%), CIF + PP-minMSEM (accuracy: 93.32% ± 1.23%), CIF-minMSEM (accuracy: 92.26% ± 1.65%), CMP-minMSEM (accuracy: 91.76% ± 1.74%), and PP-minMSEM (accuracy: 90.89% ± 1.47%).

CONCLUSION

Machine learning based on ANN helped establish an optimal predictive model, and TFs contributed to the development of high accuracy predictive models. The CIF+CMP-minMSEM showed the greatest accuracy for differentiating low- and high-grade ccRCCs.

Preoperative CT-based radiomics combined with intraoperative frozen section is predictive of invasive adenocarcinoma in pulmonary nodules: a multicenter study

Objectives

Develop a CT-based radiomics model and combine it with frozen section (FS) and clinical data to distinguish invasive adenocarcinomas (IA) from preinvasive lesions/minimally invasive adenocarcinomas (PM).

Methods

This multicenter study cohort of 623 lung adenocarcinomas was split into training (n = 331), testing (n = 143), and external validation dataset (n = 149). Random forest models were built using selected radiomics features, results from FS, lesion volume, clinical and semantic features, and combinations thereof. The area under the receiver operator characteristic curves (AUC) was used to evaluate model performances. The diagnosis accuracy, calibration, and decision curves of models were tested.

Results

The radiomics-based model shows good predictive performance and diagnostic accuracy for distinguishing IA from PM, with AUCs of 0.89, 0.89, and 0.88, in the training, testing, and validation datasets, respectively, and with corresponding accuracies of 0.82, 0.79, and 0.85. Adding lesion volume and FS significantly increases the performance of the model with AUCs of 0.96, 0.97, and 0.96, and with accuracies of 0.91, 0.94, and 0.93 in the three datasets. There is no significant difference in AUC between the FS model enriched with radiomics and volume against an FS model enriched with volume alone, while the former has higher accuracy. The model combining all available information shows minor non-significant improvements in AUC and accuracy compared with an FS model enriched with radiomics and volume.

Conclusions

Radiomics signatures are potential biomarkers for the risk of IA, especially in combination with FS, and could help guide surgical strategy for pulmonary nodules patients.

Key Points

• A CT-based radiomics model may be a valuable tool for preoperative prediction of invasive adenocarcinoma for patients with pulmonary nodules.

• Radiomics combined with frozen sections could help in guiding surgery strategy for patients with pulmonary nodules.

Electronic supplementary material

The online version of this article (10.1007/s00330-019-06597-8) contains supplementary material, which is available to authorized users.

Pancreatic ductal adenocarcinoma: a radiomics nomogram outperforms clinical model and TNM staging for survival estimation after curative resection

OBJECTIVES

To identify a CT-based radiomics nomogram for survival prediction in patients with resected pancreatic ductal adenocarcinoma (PDAC).

METHODS

A total of 220 patients (training cohort n = 147; validation cohort n = 73) with PDAC were enrolled. A total of 300 radiomics features were extracted from CT images. And the least absolute shrinkage and selection operator algorithm were applied to select features and develop a radiomics score (Rad-score). The radiomics nomogram was constructed by multivariate regression analysis. Nomogram discrimination, calibration, and clinical usefulness were evaluated. The association of the Rad-score and recurrence pattern in PDAC was evaluated.

RESULTS

The Rad-score was significantly associated with PDAC patient's disease-free survival (DFS) and overall survival (OS) (both p < 0.001 in two cohorts). Incorporating the Rad-score into the radiomics nomogram resulted in better performance of the survival prediction than that of the clinical model and TNM staging system. In addition, the radiomics nomogram exhibited good discrimination, calibration, and clinical usefulness in both the training and validation cohorts. There was no association between the Rad-score and recurrence pattern.

CONCLUSIONS

The radiomics nomogram integrating the Rad-score and clinical data provided better prognostic prediction in resected PDAC patients, which may hold great potential for guiding personalized care for these patients. The Rad-score was not a predictor of the recurrence pattern in resected PDAC patients.

KEY POINTS

• The Rad-score developed by CT radiomics features was significantly associated with PDAC patients' prognosis. • The radiomics nomogram integrating the Rad-score and clinical data has value to permit non-invasive, low-cost, and personalized evaluation of prognosis in PDAC patients. • The radiomics nomogram outperformed clinical model and the TNM staging system in terms of survival estimation.

Personalized CT-based radiomics nomogram preoperative predicting Ki-67 expression in gastrointestinal stromal tumors: a multicenter development and validation cohort

Background and Aim

To develop and validate radiomic prediction models using contrast-enhanced computed tomography (CE-CT) to preoperatively predict Ki-67 expression in gastrointestinal stromal tumors (GISTs).

Method

A total of 339 GIST patients from four centers were categorized into the training, internal validation, and external validation cohort. By filtering unstable features, minimum redundancy, maximum relevance, Least Absolute Shrinkage and Selection Operator (LASSO) algorithm, a radiomic signature was built to predict the malignant potential of GISTs. Individual nomograms of Ki-67 expression incorporating the radiomic signature or clinical factors were developed using the multivariate logistic model and evaluated regarding its calibration, discrimination, and clinical usefulness.

Results

The radiomic signature, consisting of 6 radiomic features had AUC of 0.787 [95% confidence interval (CI) 0.632–0.801], 0.765 (95% CI 0.683–0.847), and 0.754 (95% CI 0.666–0.842) in the prediction of high Ki-67 expression in the training, internal validation and external validation cohort, respectively. The radiomic nomogram including the radiomic signature and tumor size demonstrated significant calibration, and discrimination with AUC of 0.801 (95% CI 0.726–0.876), 0.828 (95% CI 0.681–0.974), and 0.784 (95% CI 0.701–0.868) in the training, internal validation and external validation cohort respectively. Based on the Decision curve analysis, the radiomics nomogram was found to be clinically significant and useful.

Conclusions

The radiomic signature from CE-CT was significantly associated with Ki-67 expression in GISTs. A nomogram consisted of radiomic signature, and tumor size had maximum accuracy in the prediction of Ki-67 expression in GISTs. Results from our study provide vital insight to make important preoperative clinical decisions.

Deep Learning vs. Radiomics for Predicting Axillary Lymph Node Metastasis of Breast Cancer Using Ultrasound Images: Don't Forget the Peritumoral Region

Objective: Axillary lymph node (ALN) metastasis status is important in guiding treatment in breast cancer. The aims were to assess how deep convolutional neural network (CNN) performed compared with radiomics analysis in predicting ALN metastasis using breast ultrasound, and to investigate the value of both intratumoral and peritumoral regions in ALN metastasis prediction.

Methods: We retrospectively enrolled 479 breast cancer patients with 2,395 breast ultrasound images. Based on the intratumoral, peritumoral, and combined intra- and peritumoral regions, three CNNs were built using DenseNet, and three radiomics models were built using random forest, respectively. By combining the molecular subtype, another three CNNs and three radiomics models were built. All models were built on training cohort (343 patients 1,715 images) and evaluated on testing cohort (136 patients 680 images) with ROC analysis. Another prospective cohort of 16 patients was enrolled to further test the models.

Results: AUCs of image-only CNNs in both training/testing cohorts were 0.957/0.912 for combined region, 0.944/0.775 for peritumoral region, and 0.937/0.748 for intratumoral region, which were numerically higher than their corresponding radiomics models with AUCs of 0.940/0.886, 0.920/0.724, and 0.913/0.693. The overall performance of image-molecular CNNs in terms of AUCs on training/testing cohorts slightly increased to 0.962/0.933, 0.951/0.813, and 0.931/0.794, respectively. AUCs of both CNNs and radiomics models built on combined region were significantly better than those on either intratumoral or peritumoral region on the testing cohort (p < 0.05). In the prospective study, the CNN model built on combined region achieved the highest AUC of 0.95 among all image-only models.

Conclusions: CNNs showed numerically better overall performance compared with radiomics models in predicting ALN metastasis in breast cancer. For both CNNs and radiomics models, combining intratumoral, and peritumoral regions achieved significantly better performance.

Noninvasive CT radiomic model for preoperative prediction of lymph node metastasis in early cervical carcinoma

OBJECTIVE

To build and validate a CT radiomic model for pre-operatively predicting lymph node metastasis in early cervical carcinoma.

METHODS AND MATERIALS

A data set of 150 patients with Stage IB1 to IIA2 cervical carcinoma was retrospectively collected from the Nanfang hospital and separated into a training cohort (n = 104) and test cohort (n = 46). A total of 348 radiomic features were extracted from the delay phase of CT images. Mann-Whitney U test, recursive feature elimination, and backward elimination were used to select key radiomic features. Ridge logistics regression was used to build a radiomic model for prediction of lymph node metastasis (LNM) status by combining radiomic and clinical features. The area under the receiver operating characteristic curve (AUC) and κ test were applied to verify the model.

RESULTS

Two radiomic features from delay phase CT images and one clinical feature were associated with LNM status: log-sigma-2-0 mm-3D_glcm_Idn (p = 0.01937), wavelet-HL_firstorder_Median (p = 0.03592), and Stage IB (p = 0.03608). Radiomic model was built consisting of the three features, and the AUCs were 0.80 (95% confidence interval: 0.70 ~ 0.90) and 0.75 (95% confidence intervalI: 0.53 ~ 0.93) in training and test cohorts, respectively. The κ coefficient was 0.84, showing excellent consistency.

CONCLUSION

A non-invasive radiomic model, combining two radiomic features and a International Federation of Gynecology and Obstetrics stage, was built for prediction of LNM status in early cervical carcinoma. This model could serve as a pre-operative tool.

ADVANCES IN KNOWLEDGE

A noninvasive CT radiomic model, combining two radiomic features and the International Federation of Gynecology and Obstetrics stage, was built for prediction of LNM status in early cervical carcinoma.

Radiomics and Machine Learning in Oral Healthcare

The increasing storage of information, data, and forms of knowledge has led to the development of new technologies that can help to accomplish complex tasks in different areas, such as in dentistry. In this context, the role of computational methods, such as radiomics and Artificial Intelligence (AI) applications, has been progressing remarkably for dentomaxillofacial radiology (DMFR). These tools bring new perspectives for diagnosis, classification, and prediction of oral diseases, treatment planning, and for the evaluation and prediction of outcomes, minimizing the possibilities of human errors. A comprehensive review of the state-of-the-art of using radiomics and machine learning (ML) for imaging in oral healthcare is presented in this paper. Although the number of published studies is still relatively low, the preliminary results are very promising and in a near future, an augmented dentomaxillofacial radiology (ADMFR) will combine the use of radiomics-based and AI-based analyses with the radiologist's evaluation. In addition to the opportunities and possibilities, some challenges and limitations have also been discussed for further investigations.

The Emerging Role of Radiomics in COPD and Lung Cancer

Medical imaging plays a key role in evaluating and monitoring lung diseases such as chronic obstructive pulmonary disease (COPD) and lung cancer. The application of artificial intelligence in medical imaging has transformed medical images into mineable data, by extracting and correlating quantitative imaging features with patients' outcomes and tumor phenotype - a process termed radiomics. While this process has already been widely researched in lung oncology, the evaluation of COPD in this fashion remains in its infancy. Here we outline the main applications of radiomics in lung cancer and briefly review the workflow from image acquisition to the evaluation of model performance. Finally, we discuss the current assessments of COPD and the potential application of radiomics in COPD.

Quantification in Musculoskeletal Imaging Using Computational Analysis and Machine Learning: Segmentation and Radiomics

Although still limited in clinical practice, quantitative analysis is expected to increase the value of musculoskeletal (MSK) imaging. Segmentation aims at isolating the tissues and/or regions of interest in the image and is crucial to the extraction of quantitative features such as size, signal intensity, or image texture. These features may serve to support the diagnosis and monitoring of disease. Radiomics refers to the process of extracting large amounts of features from radiologic images and combining them with clinical, biological, genetic, or any other type of complementary data to build diagnostic, prognostic, or predictive models. The advent of machine learning offers promising prospects for automatic segmentation and integration of large amounts of data. We present commonly used segmentation methods and describe the radiomics pipeline, highlighting the challenges to overcome for adoption in clinical practice. We provide some examples of applications from the MSK literature.

High-order radiomics features based on T2 FLAIR MRI predict multiple glioma immunohistochemical features: A more precise and personalized gliomas management

Objective

To investigate the performance of high-order radiomics features and models based on T2-weighted fluid-attenuated inversion recovery (T2 FLAIR) in predicting the immunohistochemical biomarkers of glioma, in order to execute a non-invasive, more precise and personalized glioma disease management.

Methods

51 pathologically confirmed gliomas patients committed in our hospital from March 2015 to June 2018 were retrospective analysis, and Ki-67, vimentin, S-100 and CD34 immunohistochemical data were collected. The volumes of interest (VOIs) were manually sketched and the radiomics features were extracted. Feature reduction was performed by ANOVA+ Mann-Whiney, spearman correlation analysis, least absolute shrinkage and selection operator (LASSO) and Gradient descent algorithm (GBDT). SMOTE technique was used to solve the data bias between two groups. Comprehensive binary logistic regression models were established. Area under the ROC curves (AUC), sensitivity, specificity and accuracy were used to evaluate the predict performance of models. Models reliability were decided according to the standard net benefit of the decision curves.

Results

Four clusters of significant features were screened out and four predicting models were constructed. AUC of Ki-67, S-100, vimentin and CD34 models were 0.713, 0.923, 0.854 and 0.745, respectively. The sensitivities were 0.692, 0.893, 0.875 and 0.556, respectively. The specificities were: 0.667, 0.905, 0.722, and 0.875, with accuracy of 0.660, 0.898, 0.738, and 0.667, respectively. According to the decision curves, the Ki-67, S-100 and vimentin models had reference values.

Conclusion

The radiomics features based on T2 FLAIR can potentially predict the Ki-67, S-100, vimentin and CD34 expression. Radiomics model were expected to be a computer-intelligent, non-invasive, accurate and personalized management method for gliomas.

Transcriptomics and Epigenomics in head and neck cancer: available repositories and molecular signatures

For many years, head and neck squamous cell carcinoma (HNSCC) has been considered as a single entity. However, in the last decades HNSCC complexity and heterogeneity have been recognized. In parallel, high-throughput omics techniques had allowed picturing a larger spectrum of the behavior and characteristics of molecules in cancer and a large set of omics web-based tools and informative repository databases have been developed. The objective of the present review is to provide an overview on biological, prognostic and predictive molecular signatures in HNSCC. To contextualize the selected data, our literature survey includes a short summary of the main characteristics of omics data repositories and web-tools for data analyses. The timeframe of our analysis was fixed, encompassing papers published between January 2015 and January 2019. From more than 1000 papers evaluated, 61 omics studies were selected: 33 investigating mRNA signatures, 11 and 13 related to miRNA and other non-coding-RNA signatures and 4 analyzing DNA methylation signatures. More than half of identified signatures (36) had a prognostic value but only in 10 studies selection of a specific anatomical sub-site (8 oral cavity, 1 oropharynx and 1 both oral cavity and oropharynx) was performed. Noteworthy, although the sample size included in many studies was limited, about one-half of the retrieved studies reported an external validation on independent dataset(s), strengthening the relevance of the obtained data. Finally, we highlighted the development and exploitation of three gene-expression signatures, whose clinical impact on prognosis/prediction of treatment response could be high. Based on this overview on omics-related literature in HNSCC, we identified some limits and strengths. The major limits are represented by the low number of signatures associated to DNA methylation and to non-coding RNA (miRNA, lncRNA and piRNAs) and the availability of a single dataset with multiple omics on more than 500 HNSCC (i.e. TCGA). The major strengths rely on the integration of multiple datasets through meta-analysis approaches and on the growing integration among omics data obtained on the same cohort of patients. Moreover, new approaches based on artificial intelligence and informatic analyses are expected to be available in the next future.

Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer

BACKGROUND

Non-invasive discrimination between lung squamous cell carcinoma (LUSC) and lung adenocarcinoma (LUAD) subtypes of non-small-cell lung cancer (NSCLC) could be very beneficial to the patients unfit for the invasive diagnostic procedures. The aim of this study was to investigate the feasibility of utilizing the multimodal magnetic resonance imaging (MRI) radiomics and clinical features in classifying NSCLC. This retrospective study involved 148 eligible patients with postoperative pathologically confirmed NSCLC. The study was conducted in three steps: (1) feature extraction was performed using the online freely available package with the multimodal MRI data; (2) feature selection was performed using the Student's t test and support vector machine (SVM)-based recursive feature elimination method with the training cohort (n = 100), and the performance of these selected features was evaluated using both the training and the validation cohorts (n = 48) with a non-linear SVM classifier; (3) a Radscore model was then generated using logistic regression algorithm; (4) Integrating the Radscore with the semantic clinical features, a radiomics-clinical nomogram was developed, and its overall performance was evaluated with both cohorts.

RESULTS

Thirteen optimal features achieved favorable discrimination performance with both cohorts, with area under the curve (AUC) of 0.819 and 0.824, respectively. The radiomics-clinical nomogram integrating the Radscore with the independent clinical predictors exhibited more favorable discriminative power, with AUC improved to 0.901 and 0.872 in both cohorts, respectively. The Hosmer-Lemeshow test and decision curve analysis results furtherly showed good predictive precision and clinical usefulness of the nomogram.

CONCLUSION

Non-invasive histological subtype stratification of NSCLC can be done favorably using multimodal MRI radiomics features. Integrating the radiomics features with the clinical features could further improve the performance of the histological subtype stratification in patients with NSCLC.

Optimal Statistical Incorporation of Independent Feature Stability Information into Radiomics Studies

Conducting side experiments termed robustness experiments, to identify features that are stable with respect to rescans, annotation, or other confounding effects is an important element in radiomics research. However, the matter of how to include the finding of these experiments into the model building process still needs to be explored. Three different methods for incorporating prior knowledge into a radiomics modelling process were evaluated: the naïve approach (ignoring feature quality), the most common approach consisting of removing unstable features, and a novel approach using data augmentation for information transfer (DAFIT). Multiple experiments were conducted using both synthetic and publicly available real lung imaging patient data. Ignoring additional information from side experiments resulted in significantly overestimated model performances meaning the estimated mean area under the curve achieved with a model was increased. Removing unstable features improved the performance estimation, while slightly decreasing the model performance, i.e. decreasing the area under curve achieved with the model. The proposed approach was superior both in terms of the estimation of the model performance and the actual model performance. Our experiments show that data augmentation can prevent biases in performance estimation and has several advantages over the plain omission of the unstable feature. The actual gain that can be obtained depends on the quality and applicability of the prior information on the features in the given domain. This will be an important topic of future research.

Dual-energy CT-based deep learning radiomics can improve lymph node metastasis risk prediction for gastric cancer

OBJECTIVES

To build a dual-energy CT (DECT)-based deep learning radiomics nomogram for lymph node metastasis (LNM) prediction in gastric cancer.

MATERIALS AND METHODS

Preoperative DECT images were retrospectively collected from 204 pathologically confirmed cases of gastric adenocarcinoma (mean age, 58 years; range, 28-81 years; 157 men [mean age, 60 years; range, 28-81 years] and 47 women [mean age, 54 years; range, 28-79 years]) between November 2011 and October 2018, They were divided into training (n = 136) and test (n = 68) sets. Radiomics features were extracted from monochromatic images at arterial phase (AP) and venous phase (VP). Clinical information, CT parameters, and follow-up data were collected. A radiomics nomogram for LNM prediction was built using deep learning approach and evaluated in test set using ROC analysis. Its prognostic performance was determined with Harrell's concordance index (C-index) based on patients' outcomes.

RESULTS

The dual-energy CT radiomics signature was associated with LNM in two sets (Mann-Whitney U test, p < 0.001) and an achieved area under the ROC curve (AUC) of 0.71 for AP and 0.76 for VP in test set. The nomogram incorporated the two radiomics signatures and CT-reported lymph node status exhibited AUCs of 0.84 in the training set and 0.82 in the test set. The C-indices of the nomogram for progression-free survival and overall survival prediction were 0.64 (p = 0.004) and 0.67 (p = 0.002).

CONCLUSION

The DECT-based deep learning radiomics nomogram showed good performance in predicting LNM in gastric cancer. Furthermore, it was significantly associated with patients' prognosis.

KEY POINTS

• This study investigated the value of deep learning dual-energy CT-based radiomics in predicting lymph node metastasis in gastric cancer. • The dual-energy CT-based radiomics nomogram outweighed the single-energy model and the clinical model. • The nomogram also exhibited a significant prognostic ability for patient survival and enriched radiomics studies.

Novel cancer therapies for advanced cutaneous melanoma: The added value of radiomics in the decision making process-A systematic review

Advanced malignant melanoma represents a public health matter due to its rising incidence and aggressiveness. Novel therapies such as immunotherapy are showing promising results with improved progression free and overall survival in melanoma patients. However, novel targeted and immunotherapies could generate atypical patterns of response which are nowadays a big challenge since imaging criteria (ie Recist 1.1) have not been proven to be always reliable to assess response. Radiomics and in particular texture analysis (TA) represent new quantitative methodologies which could reduce the impact of these limitations providing most robust data in support of clinical decision process. The aim of this paper was to review the state of the art of radiomics/TA when it is applied to the imaging of metastatic melanoma patients.

Radiomics for personalised medicine: the long road ahead

Radiomics is well placed to make clinically effective and cost-effective contributions to cancer care as a decision-making tool for personalised medicine. However, a systematic evaluative framework needs to be established so that these benefits can be demonstrated with confidence.

MRI-based radiomics model for preoperative prediction of 5-year survival in patients with hepatocellular carcinoma

Background

Recurrence is the major cause of mortality in patients with resected HCC. However, without a standard approach to evaluate prognosis, it is difficult to select candidates for additional therapy.

Methods

A total of 201 patients with HCC who were followed up for at least 5 years after curative hepatectomy were enrolled in this retrospective, multicentre study. A total of 3144 radiomics features were extracted from preoperative MRI. The random forest method was used for radiomics signature building, and five-fold cross-validation was applied. A radiomics model incorporating the radiomics signature and clinical risk factors was developed.

Results

Patients were divided into survivor (n = 97) and non-survivor (n = 104) groups based on the 5-year survival after surgery. The 30 most survival-related radiomics features were selected for the radiomics signature. Preoperative AFP and AST were integrated into the model as independent clinical risk factors. The model demonstrated good calibration and satisfactory discrimination, with a mean AUC of 0.9804 and 0.7578 in the training and validation sets, respectively.

Conclusions

This radiomics model is a valid method to predict 5-year survival in patients with HCC and may be used to identify patients for clinical trials of perioperative therapies and for additional surveillance.

Radiomic Features at Contrast-enhanced CT Predict Recurrence in Early Stage Hepatocellular Carcinoma: A Multi-Institutional Study

Background Early stage hepatocellular carcinoma (HCC) is the ideal candidate for resection in patients with preserved liver function; however, cancer will recur in half of these patients and no reliable prognostic tool has been established. Purpose To investigate the effectiveness of radiomic features in predicting tumor recurrence after resection of early stage HCC. Materials and Methods In total, 295 patients (median age, 58 years; interquartile range, 50-65 years; 221 men) who underwent contrast material-enhanced CT and curative resection for early stage HCC that met the Milan criteria between February 2009 and December 2016 were retrospectively recruited from three independent institutions. Follow-up consisted of serum α-fetoprotein level, liver function tests, and dynamic imaging examinations every 3 months during the first 2 years and then every 6 months thereafter. In the development cohort of 177 patients from institution 1, recurrence-related radiomic features were computationally extracted from the tumor and its periphery and a radiomics signature was built with least absolute shrinkage and selection operator regression. Two models, one integrating preoperative and one integrating pre- and postoperative variables, were created by using multivariable Cox regression analysis. An independent external cohort of 118 patients from institutions 2 and 3 was used to validate the proposed models. Results The preoperative model integrated radiomics signature with serum α-fetoprotein level and tumor number; the postoperative model incorporated microvascular invasion and satellite nodules into the above-mentioned predictors. In both study cohorts, two radiomics-based models provided better predictive performance (concordance index ≥0.77, P < .05 for all), lower prediction error (integrated Brier score ≤0.14), and larger net benefits, as determined by means of decision curve analysis, than rival models without radiomics and widely adopted staging systems. The radiomics-based models gave three risk strata with high, intermediate, or low risk of recurrence and distinct profiles of recurrent tumor number. Conclusion The proposed radiomics models with pre- and postresection features helped predict tumor recurrence for early stage hepatocellular carcinoma. © RSNA, 2020 Online supplemental material is available for this article.

A Delta-radiomics model for preoperative evaluation of Neoadjuvant chemotherapy response in high-grade osteosarcoma

Background

The difficulty of assessment of neoadjuvant chemotherapeutic response preoperatively may hinder personalized-medicine strategies that depend on the results from pathological examination.

Methods

A total of 191 patients with high-grade osteosarcoma (HOS) were enrolled retrospectively from November 2013 to November 2017 and received neoadjuvant chemotherapy (NCT). A cutoff time of November 2016 was used to divide the training set and validation set. All patients underwent diagnostic CTs before and after chemotherapy. By quantifying the tumor regions on the CT images before and after NCT, 540 delta-radiomic features were calculated. The interclass correlation coefficients for segmentations of inter/intra-observers and feature pair-wise correlation coefficients (Pearson) were used for robust feature selection. A delta-radiomics signature was constructed using the lasso algorithm based on the training set. Radiomics signatures built from single-phase CT were constructed for comparison purpose. A radiomics nomogram was then developed from the multivariate logistic regression model by combining independent clinical factors and the delta-radiomics signature. The prediction performance was assessed using area under the ROC curve (AUC), calibration curves and decision curve analysis (DCA).

Results

The delta-radiomics signature showed higher AUC than single-CT based radiomics signatures in both training and validation cohorts. The delta-radiomics signature, consisting of 8 selected features, showed significant differences between the pathologic good response (pGR) (necrosis fraction ≥90%) group and the non-pGR (necrosis fraction < 90%) group (P < 0.0001, in both training and validation sets). The delta-radiomics nomogram, which consisted of the delta-radiomics signature and new pulmonary metastasis during chemotherapy showed good calibration and great discrimination capacity with AUC 0.871 (95% CI, 0.804 to 0.923) in the training cohort, and 0.843 (95% CI, 0.718 to 0.927) in the validation cohort. The DCA confirmed the clinical utility of the radiomics model.

Conclusion

The delta-radiomics nomogram incorporating the radiomics signature and clinical factors in this study could be used for individualized pathologic response evaluation after chemotherapy preoperatively and help tailor appropriate chemotherapy and further treatment plans.

Radiomics approaches in gastric cancer: a frontier in clinical decision making

Objective:

To review the application of radiomics in gastric cancer and its challenges as well as future prospects.

Data sources:

A research for relevant studies were performed in PubMed with the terms of “radiomics,” “texture analysis,” and “gastric cancer.” The search was updated until February 28^th, 2019.

Study selection:

All original articles regarding the investigation of texture analysis or radiomics in gastric cancer were retrieved. Only papers written in English were included.

Results:

A total of 17 original articles were selected in final. It is shown that radiomics has yielded moderate to excellent performance in a spectrum of respects including differential diagnosis, assessment of histological differential degree, evaluation of tumor stage, prediction of response to therapy, and prognosis in gastric cancer. Yet, a number of challenges are facing both radiomics itself and its application in gastric cancer.

Conclusions:

Radiomics holds great potential in facilitating decision-making in gastric cancer. With the standardization of work-flow and advancement of machine learning methods, radiomics is expected to make great breakthroughs in precision medicine of gastric cancer.

A systematic review reporting quality of radiomics research in neuro-oncology: toward clinical utility and quality improvement using high-dimensional imaging features

Background

To evaluate radiomics analysis in neuro-oncologic studies according to a radiomics quality score (RQS) system to find room for improvement in clinical use.

Methods

Pubmed and Embase were searched up the terms radiomics or radiogenomics and gliomas or glioblastomas until February 2019. From 189 articles, 51 original research articles reporting the diagnostic, prognostic, or predictive utility were selected. The quality of the methodology was evaluated according to the RQS. The adherence rates for the six key domains were evaluated: image protocol and reproducibility, feature reduction and validation, biologic/clinical utility, performance index, a high level of evidence, and open science. Subgroup analyses for journal type (imaging vs. clinical) and biomarker (diagnostic vs. prognostic/predictive) were performed.

Results

The median RQS was 11 out of 36 and adherence rate was 37.1%. Only 29.4% performed external validation. The adherence rate was high for reporting imaging protocol (100%), feature reduction (94.1%), and discrimination statistics (96.1%), but low for conducting test-retest analysis (2%), prospective study (3.9%), demonstrating potential clinical utility (2%), and open science (5.9%). None of the studies conducted a phantom study or cost-effectiveness analysis. Prognostic/predictive studies received higher score than diagnostic studies in comparison to gold standard (P < .001), use of calibration (P = .02), and cut-off analysis (P = .001).

Conclusions

The quality of reporting of radiomics studies in neuro-oncology is currently insufficient. Validation is necessary using external dataset, and improvements need to be made to feature reproducibility, demonstrating clinical utility, pursuits of a higher level of evidence, and open science.

Application of radiomics for the prediction of HPV status for patients with head and neck cancers

PURPOSE

To perform radiomic analysis of primary tumors extracted from pretreatment contrast-enhanced computed tomography (CE-CT) images for patients with oropharyngeal cancers to identify discriminant features and construct an optimal classifier for the characterization and prediction of human papilloma virus (HPV) status.

MATERIALS AND METHODS

One hundred and eighty seven patients with oropharyngeal cancers with known HPV status (confirmed by immunohistochemistry-p16 protein testing) were retrospectively studied as follows: Group A: 95 patients (19HPV- and 76HPV+) from the MICAII grand challenge. Group B: 92 patients (52HPV- and 40HPV+) from our institution. Radiomic features (172) were extracted from pretreatment diagnostic CE-CT images of the gross tumor volume (GTV). Levene and Kolmogorov-Smirnov's tests with absolute biserial correlation (>0.48) were used to identify the discriminant features between the HPV+ and HPV- groups. The discriminant features were used to train and test eight different classifiers. Area under receiver operating characteristic (AUC), positive predictive and negative predictive values (PPV and NPV, respectively) were used to evaluate the performance of the classifiers. Principal component analysis (PCA) was applied on the discriminant feature set and seven PCs were used to train and test a generalized linear model (GLM) classifier.

RESULTS

Among 172 radiomic features only 12 radiomic features (from 3 categories) were significantly different (P < 0.05, |BSC| > 0.48) between the HPV+ and HPV- groups. Among the eight classifiers trained and applied for prediction of HPV status, the GLM showed the highest performance for each discriminant feature and the combined 12 features: AUC/PPV/NPV = 0.878/0.834/0.811. The GLM high prediction power was AUC/PPV/NPV = 0.849/0.731/0.788 and AUC/PPV/NPV = 0.869/0.807/0.870 for unseen test datasets for groups A and B, respectively. After eliminating the correlation among discriminant features by applying PCA analysis, the performance of the GLM was improved by 3.3%, 2.2%, and 1.8% for AUC, PPV, and NPV, respectively.

CONCLUSIONS

Results imply that GTV's for HPV+ patients exhibit higher intensities, smaller lesion size, greater sphericity/roundness, and higher spatial intensity-variation/heterogeneity. Results are suggestive that radiomic features primarily associated with the spatial arrangement and morphological appearance of the tumor on contrast-enhanced diagnostic CT datasets may be potentially used for classification of HPV status.

CT Densitometry and Morphology of Radiofrequency-Ablated Stage IA Non-Small Cell Lung Cancer: Results from the American College of Surgeons Oncology Group Z4033 (Alliance) Trial

PURPOSE

To evaluate tumor and ablation zone morphology and densitometry related to tumor recurrence in participants with Stage IA non-small cell lung cancer undergoing radiofrequency ablation in a prospective, multicenter trial.

MATERIALS AND METHODS

Forty-five participants (median 76 years old; 25 women; 20 men) from 16 sites were followed for 2 years (December 2006 to November 2010) with computed tomography (CT) densitometry. Imaging findings before and after ablation were recorded, including maximum CT attenuation (in Hounsfield units) at precontrast and 45-, 90-, 180-, and 300-s postcontrast.

RESULTS

Every 1-cm increase in the largest axial diameter of the ablation zone at 3-months' follow-up compared to the index tumor reduced the odds of 2-year recurrence by 52% (P = .02). A 1-cm difference performed the best (sensitivity, 0.56; specificity, 0.93; positive likelihood ratio of 8). CT densitometry precontrast and at 45 seconds showed significantly different enhancement patterns in a comparison among pretreated lung cancer (delta = +61.2 HU), tumor recurrence (delta = +57 HU), and treated tumor/ablation zone (delta [change in attenuation] = +16.9 HU), (P < .0001). Densitometry from 45 to 300 s was also different among pretreated tumor (delta = -6.8 HU), recurrence (delta = -11.2 HU), and treated tumor (delta = +12.1 HU; P = .01). Untreated and residual tumor demonstrated washout, whereas treated tumor demonstrated increased attenuation.

CONCLUSIONS

An ablation zone ≥1 cm larger than the initial tumor, based on 3-month follow-up imaging, is recommended to decrease odds of recurrence. CT densitometry can delineate tumor versus treatment zones.

Neuroanatomical Features That Predict Response to Electroconvulsive Therapy Combined With Antipsychotics in Schizophrenia: A Magnetic Resonance Imaging Study Using Radiomics Strategy

OBJECTIVE

Neuroimaging-based brain signatures may be informative in identifying patients with psychosis who will respond to antipsychotics. However, signatures that inform the electroconvulsive therapy (ECT) health care professional about the response likelihood remain unclear in psychosis with radiomics strategy. This study investigated whether brain structure-based signature in the prediction of ECT response in a sample of schizophrenia patients using radiomics approach.

METHODS

This high-resolution structural magnetic resonance imaging study included 57 patients at baseline. After ECT combined with antipsychotics, 28 and 29 patients were classified as responders and non-responders. Features of gray matter were extracted and compared. The logistic regression model/support vector machine (LRM/SVM) analysis was used to explore the predictive performance.

RESULTS

The regularized multivariate LRM accurately discriminated responders from non-responders, with an accuracy of 90.91%. The structural features were further confirmed in the validating data set, resulting in an accuracy of 87.59%. The accuracy of the SVM in the training set was 90.91%, and the accuracy in the validation set was 91.78%.

CONCLUSION

Our results support the possible use of structural brain feature-based radiomics as a potential tool for predicting ECT response in patients with schizophrenia undergoing antipsychotics, paving the way for utilization of markers in psychosis.

Radiomics study for predicting the expression of PD-L1 in non-small cell lung cancer based on CT images and clinicopathologic features

PURPOSE

To predict programmed death-ligand 1 (PD-L1) expression of tumor cells in non-small cell lung cancer (NSCLC) patients by using a radiomics study based on CT images and clinicopathologic features.

MATERIALS AND METHODS

A total of 390 confirmed NSCLC patients who performed chest CT scan and immunohistochemistry (IHC) examination of PD-L1 of lung tumors with clinic data were collected in this retrospective study, which were divided into two cohorts namely, training (n = 260) and validation (n = 130) cohort. Clinicopathologic features were compared between two cohorts. Lung tumors were segmented by using ITK-snap kit on CT images. Total 200 radiomic features in the segmented images were calculated using in-house texture analysis software, then filtered and minimized by least absolute shrinkage and selection operator (LASSO) regression to select optimal radiomic features based on its relevance of PD-L1 expression status in IHC results and develop radiomics signature. Radiomics signature and clinicopathologic risk factors were incorporated to develop prediction model by using multivariable logistic regression analysis. The receiver operating characteristic (ROC) curves were generated and the areas under the curves (AUC) were reckoned to predict PD-L1 expression in both training and validation cohorts.

RESULTS

In 200 extracted radiomic features, 9 were selected to develop radiomics signature. In univariate analysis, PD-L1 expression of lung tumors was significantly correlated with radiomics signature, histologic type, and histologic grade (p < 0.05, respectively). However, PD-L1 expression was not correlated with gender, age, tumor location, CEA level, TNM stage, and smoking (p > 0.05). For prediction of PD-L1 expression, the prediction model that combines radiomics signature and clinicopathologic features resulted in AUCs of 0.829 and 0.848 in the training and validation cohort, respectively.

CONCLUSION

The prediction model that incorporates the radiomics signature and clinical risk factors has potential to facilitate the individualized prediction of PD-L1 expression in NSCLC patients and identify patients who can benefit from anti-PD-L1 immunotherapy.

Artificial intelligence in clinical imaging: a health system approach

The development and application of artificial intelligence (AI) to radiology requires an approach that encompasses a health system. The UK government and National Health Service (NHS) are creating an ecosystem to facilitate academic/industrial partnerships aimed at accelerating the creation of relevant and robust AI tools, which will improve the development and delivery of healthcare imaging. A series of recent initiatives are described, which will drive the development and adoption of AI in clinical imaging.

Nuclear imaging approaches facilitating nanomedicine translation

Nanomedicine approaches can effectively modulate the biodistribution and bioavailability of therapeutic agents, improving their therapeutic index. However, despite the ever-increasing amount of literature reporting on preclinical nanomedicine, the number of nanotherapeutics receiving FDA approval remains relatively low. Several barriers exist that hamper the effective preclinical evaluation and clinical translation of nanotherapeutics. Key barriers include insufficient understanding of nanomedicines' in vivo behavior, inadequate translation from murine models to larger animals, and a lack of patient stratification strategies. Integrating quantitative non-invasive imaging techniques in nanomedicine development offers attractive possibilities to address these issues. Among the available imaging techniques, nuclear imaging by positron emission tomography (PET) and single-photon emission computed tomography (SPECT) are highly attractive in this context owing to their quantitative nature and uncontested sensitivity. In basic and translational research, nuclear imaging techniques can provide critical quantitative information about pharmacokinetic parameters, biodistribution profiles or target site accumulation of nanocarriers and their associated payload. During clinical evaluation, nuclear imaging can be used to select patients amenable to nanomedicine treatment. Here, we review how nuclear imaging-based approaches are increasingly being integrated into nanomedicine development and discuss future developments that will accelerate their clinical translation.

Multiparametric MRI-based radiomics analysis for prediction of breast cancers insensitive to neoadjuvant chemotherapy

PURPOSE

To evaluate the value of multiparametric magnetic resonance imaging (MRI) in pretreatment prediction of breast cancers insensitive to neoadjuvant chemotherapy (NAC).

METHODS

A total of 125 breast cancer patients (63 in the primary cohort and 62 in the validation cohort) who underwent MRI before receiving NAC were enrolled. All patients received surgical resection, and Miller-Payne grading system was applied to assess the response to NAC. Grade 1-2 cases were classified as insensitive to NAC. We extracted 1941 features in the primary cohort. After feature selection, the optimal feature set was used to construct a radiomic signature using machine learning. We built a combined prediction model incorporating the radiomic signature and independent clinical risk factors selected by multivariable logistic regression. The performance of the combined model was assessed with the results of independent validation.

RESULTS

Four features were selected for the construction of the radiomic signature based on the primary cohort. Combining with independent clinical factors, the combined prediction model for identifying the Grade 1-2 group reached a better discrimination power than the radiomic signature, with an area under the receiver operating characteristic curve of 0.935 (95% confidence interval 0.848-1) in the validation cohort, and its clinical utility was confirmed by the decision curve analysis.

CONCLUSION

The combined model based on radiomics and clinical variables has potential in predicting drug-insensitive breast cancers.

Open access image repositories: high-quality data to enable machine learning research

Originally motivated by the need for research reproducibility and data reuse, large-scale, open access information repositories have become key resources for training and testing of advanced machine learning applications in biomedical and clinical research. To be of value, such repositories must provide large, high-quality data sets, where quality is defined as minimising variance due to data collection protocols and data misrepresentations. Curation is the key to quality. We have constructed a large public access image repository, The Cancer Imaging Archive, dedicated to the promotion of open science to advance the global effort to diagnose and treat cancer. Drawing on this experience and our experience in applying machine learning techniques to the analysis of radiology and pathology image data, we will review the requirements placed on such information repositories by state-of-the-art machine learning applications and how these requirements can be met.

Prognostic and predictive value of radiomics signatures in stage I-III colon cancer

Accurate identification of patients with poor prognosis after radical surgery is essential for clinical management of colon cancer. Thus, we aimed to develop death and relapse specific radiomics signatures to individually estimate overall survival (OS) and relapse free survival (RFS) of colon cancer patients. In this study, 701 stage I-III colon cancer patients were identified from Fudan University Shanghai Cancer Center. A total of 647 three-dimensional features were extracted from computed tomography images. LASSO Cox was used to identify the significantly death- and relapse-associated features and to build death and relapse specific radiomics signatures, respectively. A total of 13 death-specific and 26 relapse-specific features were identified from 647 screened radiomics features. The developed signatures can divide patients into two groups with significantly different death (Hazard Ratio (HR): 3.053; 95% CI, 1.78-5.23; P < .001) or relapse risk (HR: 2.794; 95% CI, 1.87-4.16; P < .001). Time-dependent Relative operating characteristic curve showed that the signatures performed better than any other clinicopathological factors in predicting OS (AUC: 0.768; 95% CI, 0.745-0.791) and RFS (AUC: 0.744; 95% CI, 0.687-0.801). Further, survival decision curve analyses confirmed the good clinical utility of the two radiomics signatures. In conclusion, we successfully developed death- and relapse-specific radiomics signatures that can accurately predict OS and RFS, which may facilitate personalized treatment.

Application of Radiomics for Personalized Treatment of Cancer Patients

Radiomics is a novel concept that relies on obtaining image data from examinations such as computed tomography (CT), magnetic resonance imaging (MRI), or positron emission tomography (PET). With the appropriate algorithm, the extracted results have broad applicability and potential for a massive positive impact in radiology. For example, clinicians can verify treatment efficiency, predict the location of tumor metastasis, correlate results with a histopathological examination, or more accurately define the type of cancer. Combining radiomics with other testing techniques allows every patient to have a personalized treatment plan that is essential for advanced examination and treatment. This article explains the process of radiomics, including data collection mechanisms, combined use with genomics, and artificial intelligence and immunology techniques, which may solve many of the challenges faced by doctors in diagnosing and treating their patients.

Impact of image preprocessing methods on reproducibility of radiomic features in multimodal magnetic resonance imaging in glioblastoma

To investigate the effect of image preprocessing, in respect to intensity inhomogeneity correction and noise filtering, on the robustness and reproducibility of the radiomics features extracted from the Glioblastoma (GBM) tumor in multimodal MR images (mMRI). In this study, for each patient 1461 radiomics features were extracted from GBM subregions (i.e., edema, necrosis, enhancement, and tumor) of mMRI (i.e., FLAIR, T1, T1C, and T2) volumes for five preprocessing combinations (in total 116 880 radiomics features). The robustness and reproducibility of the radiomics features were assessed under four comparisons: (a) Baseline versus modified bias field; (b) Baseline versus modified bias field followed by noise filtering; (c) Baseline versus modified noise, and (d) Baseline versus modified noise followed bias field correction. The concordance correlation coefficient (CCC), dynamic range (DR), and interclass correlation coefficient (ICC) were used as metrics. Shape features and subsequently, local binary pattern (LBP) filtered images were highly stable and reproducible against bias field correction and noise filtering in all measurements. In all MRI modalities, necrosis regions (NC: n ® ~449/1461, 30%) had the highest number of highly robust features, with CCC and DR >= 0.9, in comparison with edema (ED: n ® ~296/1461, 20%), enhanced (EN: n ® ~ 281/1461, 19%) and active‐tumor regions (TM: n ® ~254/1461, 17%). The necrosis regions (NC: n¯ ~ 449/1461, 30%) had a higher number of highly robust features (CCC and DR >= 0.9) than edema (ED: n¯ ~ 296/1461, 20%), enhanced (EN: n¯ ~ 281/1461, 19%) and active‐tumor (TM: n¯ ~ 254/1461, 17%) regions across all modalities. Furthermore, our results identified that the percentage of high reproducible features with ICC >= 0.9 after bias field correction (23.2%), and bias field correction followed by noise filtering (22.4%) were higher in contrast with noise smoothing and also noise smoothing follow by bias correction. These preliminary findings imply that preprocessing sequences can also have a significant impact on the robustness and reproducibility of mMRI‐based radiomics features and identification of generalizable and consistent preprocessing algorithms is a pivotal step before imposing radiomics biomarkers into the clinic for GBM patients.

Robustness and Reproducibility of Radiomics in Magnetic Resonance Imaging: A Phantom Study

OBJECTIVES

The aim of this study was to investigate the robustness and reproducibility of radiomic features in different magnetic resonance imaging sequences.

MATERIALS AND METHODS

A phantom was scanned on a clinical 3 T system using fluid-attenuated inversion recovery (FLAIR), T1-weighted (T1w), and T2-weighted (T2w) sequences with low and high matrix size. For retest data, scans were repeated after repositioning of the phantom. Test and retest datasets were segmented using a semiautomated approach. Intraobserver and interobserver comparison was performed. Radiomic features were extracted after standardized preprocessing of images. Test-retest robustness was assessed using concordance correlation coefficients, dynamic range, and Bland-Altman analyses. Reproducibility was assessed by intraclass correlation coefficients.

RESULTS

The number of robust features (concordance correlation coefficient and dynamic range ≥ 0.90) was higher for features calculated from FLAIR than from T1w and T2w images. High-resolution FLAIR images provided the highest percentage of robust features (n = 37/45, 81%). No considerable difference in the number of robust features was observed between low- and high-resolution T1w and T2w images (T1w low: n = 26/45, 56%; T1w high: n = 25/45, 54%; T2 low: n = 21/45, 46%; T2 high: n = 24/45, 52%). A total of 15 (33%) of 45 features showed excellent robustness across all sequences and demonstrated excellent intraobserver and interobserver reproducibility (intraclass correlation coefficient ≥ 0.75).

CONCLUSIONS

FLAIR delivers the most robust substrate for radiomic analyses. Only 15 of 45 features showed excellent robustness and reproducibility across all sequences. Care must be taken in the interpretation of clinical studies using nonrobust features.

Measurement Variability in Treatment Response Determination for Non-Small Cell Lung Cancer: Improvements Using Radiomics

Multimodality imaging measurements of treatment response are critical for clinical practice, oncology trials, and the evaluation of new treatment modalities. The current standard for determining treatment response in non-small cell lung cancer (NSCLC) is based on tumor size using the RECIST criteria. Molecular targeted agents and immunotherapies often cause morphological change without reduction of tumor size. Therefore, it is difficult to evaluate therapeutic response by conventional methods. Radiomics is the study of cancer imaging features that are extracted using machine learning and other semantic features. This method can provide comprehensive information on tumor phenotypes and can be used to assess therapeutic response in this new age of immunotherapy. Delta radiomics, which evaluates the longitudinal changes in radiomics features, shows potential in gauging treatment response in NSCLC. It is well known that quantitative measurement methods may be subject to substantial variability due to differences in technical factors and require standardization. In this review, we describe measurement variability in the evaluation of NSCLC and the emerging role of radiomics.