Development and Validation of a Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer

Association of Adjuvant Chemotherapy With Survival in Patients With Stage II or III Gastric Cancer

Importance

The current staging system of gastric cancer is not adequate for defining a prognosis and predicting the patients most likely to benefit from chemotherapy.

Objective

To construct a survival prediction model based on specific tumor and patient characteristics that enables individualized predictions of the net survival benefit of adjuvant chemotherapy for patients with stage II or stage III gastric cancer.

Design, Setting, and Participants

In this multicenter retrospective analysis, a survival prediction model was constructed using data from a training cohort of 746 patients with stage II or stage III gastric cancer who satisfied the study's inclusion criteria and underwent surgery between January 1, 2004, and December 31, 2012, at Nanfang Hospital in Guangzhou, China. Patient and tumor characteristics were included as covariates, and their association with overall survival and disease-free survival with and without adjuvant chemotherapy was assessed. The model was internally validated for discrimination and calibration using bootstrap resampling. To externally validate the model, data were included from a validation cohort of 973 patients with stage II or stage III gastric cancer who met the inclusion criteria and underwent surgery at First Affiliated Hospital in Guangzhou, China, and at West China Hospital of Sichuan Hospital in Chendu, China, between January 1, 2000, and June 30, 2009. Data were analyzed from July 10, 2016, to September 1, 2016.

Main Outcomes and Measures

Concordance index and decision curve analysis for each measure associated with postoperative overall survival and disease-free survival.

Results

Of the 1719 patients analyzed, 1183 (68.8%) were men and 536 (31.2%) were women and the median (interquartile range) age was 57 (49-66) years. Age, location, differentiation, carcinoembryonic antigen, cancer antigen 19-9, depth of invasion, lymph node metastasis, and adjuvant chemotherapy were significantly associated with overall survival and disease-free survival, with P < .05. The survival prediction model demonstrated good calibration and discrimination, with relatively high bootstrap-corrected concordance indexes in the training and validation cohorts. In the validation cohort, the concordance index for overall survival was 0.693 (95% CI, 0.671-0.715) and for disease-free survival was 0.704 (95% CI, 0.681-0.728). Two nomograms and a calculating tool were built on the basis of specific input variables to estimate an individual's net survival gain attributable to adjuvant chemotherapy.

Conclusions and Relevance

The survival prediction model can be used to make individualized predictions of the expected survival benefit from the addition of adjuvant chemotherapy for patients with stage II or stage III gastric cancer.

Preoperative prediction of muscular invasiveness of bladder cancer with radiomic features on conventional MRI and its high-order derivative maps

PURPOSE

To determine radiomic features which are capable of reflecting muscular invasiveness of bladder cancer (BC) and propose a non-invasive strategy for the differentiation of muscular invasiveness preoperatively.

METHODS

Sixty-eight patients with clinicopathologically confirmed BC were included in this retrospective study. A total of 118 cancerous volumes of interest (VOI) were segmented from patients' T2 weighted MR images (T2WI), including 34 non-muscle invasive bladder carcinomas (NMIBCs, stage <T2) and 84 muscle invasive ones (MIBCs, stage ≥T2). The radiomic features quantifying tumor signal intensity and textures were extracted from each VOI and its high-order derivative maps to characterize heterogeneity of tumor tissues. Statistical analysis was used to build radiomic signatures with significant inter-group differences of NMIBCs and MIBCs. The synthetic minority oversampling technique (SMOTE) and a support vector machine (SVM)-based feature selection and classification strategy were proposed to first rebalance the imbalanced sample size and then further select the most predictive and compact signature subset to verify its differentiation capability.

RESULTS

From each tumor VOI, a total of 63 radiomic features were derived and 30 of them showed significant inter-group differences (P ≤ 0.01). By using the SVM-based feature selection algorithm with rebalanced samples, an optimal subset including 13 radiomic signatures was determined. The area under receiver operating characteristic curve and Youden index were improved to 0.8610 and 0.7192, respectively.

CONCLUSION

3D radiomic signatures derived from T2WI and its high-order derivative maps could reflect muscular invasiveness of bladder cancer, and the proposed strategy can be used to facilitate the preoperative prediction of muscular invasiveness in patients with bladder cancer.

Beyond imaging: The promise of radiomics

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

CT-based radiomics signature: a potential biomarker for preoperative prediction of early recurrence in hepatocellular carcinoma

PURPOSE

To develop a CT-based radiomics signature and assess its ability for preoperatively predicting the early recurrence (≤1 year) of hepatocellular carcinoma (HCC).

METHODS

A total of 215 HCC patients who underwent partial hepatectomy were enrolled in this retrospective study, and all the patients were followed up at least within 1 year. Radiomics features were extracted from arterial- and portal venous-phase CT images, and a radiomics signature was built by the least absolute shrinkage and selection operator (LASSO) logistic regression model. Preoperative clinical factors associated with early recurrence were evaluated. A radiomics signature, a clinical model, and a combined model were built, and the area under the curve (AUC) of operating characteristics (ROC) was used to explore their performance to discriminate early recurrence.

RESULTS

Twenty-one radiomics features were chosen from 300 candidate features to build a radiomics signature that was significantly associated with early recurrence (P < 0.001), and they presented good performance in the discrimination of early recurrence alone with an AUC of 0.817 (95% CI: 0.758-0.866), sensitivity of 0.794, and specificity of 0.699. The AUCs of the clinical and combined models were 0.781 (95% CI: 0.719-0.834) and 0.836 (95% CI: 0.779-0.883), respectively, with the sensitivity being 0.784 and 0.824, and the specificity being 0.619 and 0.708, respectively. Adding a radiomics signature into conventional clinical variables can significantly improve the accuracy of the preoperative model in predicting early recurrence (P = 0.01).

CONCLUSIONS

The radiomics signature was a significant predictor for early recurrence in HCC. Incorporating radiomics signature into conventional clinical factors performed better for preoperative estimation of early recurrence than with clinical variables alone.

The Rise of Radiomics and Implications for Oncologic Management

Clinical medicine, particularly oncology, is progressing toward personalized care. Whereas the terms genomics, proteomics, transcriptomics, and metabolomics have dominated personalized medicine for the past couple decades, the concept of radiomics was first described in 2012. This nascent concept has major implications for personalized cancer care and involves extracting hundreds of standardized and quantifiable imaging characteristics from diagnostic computed tomography/magnetic resonance imaging images. The central hypothesis of radiomics is that these libraries of quantitative individual voxel-based variables are more sensitively associated with various clinical endpoints compared with the more qualitative radiologic, histopathologic, and clinical data more commonly utilized today. Because radiomics offers immense potential but has not reached a mainstream oncologic audience, the authors discuss herein the role of radiomics in cancer care in the future.

Sonoelastomics for Breast Tumor Classification: A Radiomics Approach with Clustering-Based Feature Selection on Sonoelastography

A radiomics approach to sonoelastography, called "sonoelastomics," is proposed for classification of benign and malignant breast tumors. From sonoelastograms of breast tumors, a high-throughput 364-dimensional feature set was calculated consisting of shape features, intensity statistics, gray-level co-occurrence matrix texture features and contourlet texture features, which quantified the shape, hardness and hardness heterogeneity of a tumor. The high-throughput features were then selected for feature reduction using hierarchical clustering and three-feature selection metrics. For a data set containing 42 malignant and 75 benign tumors from 117 patients, seven selected sonoelastomic features achieved an area under the receiver operating characteristic curve of 0.917, an accuracy of 88.0%, a sensitivity of 85.7% and a specificity of 89.3% in a validation set via the leave-one-out cross-validation, revealing superiority over the principal component analysis, deep polynomial networks and manually selected features. The sonoelastomic features are valuable in breast tumor differentiation.

CT-based radiomics signature for differentiating Borrmann type IV gastric cancer from primary gastric lymphoma

PURPOSE

To evaluate the value of CT-based radiomics signature for differentiating Borrmann type IV gastric cancer (GC) from primary gastric lymphoma (PGL).

MATERIALS AND METHODS

40 patients with Borrmann type IV GC and 30 patients with PGL were retrospectively recruited. 485 radiomics features were extracted and selected from the portal venous CT images to build a radiomics signature. Subjective CT findings, including gastric wall peristalsis, perigastric fat infiltration, lymphadenopathy below the renal hila and enhancement pattern, were assessed to construct a subjective findings model. The radiomics signature, subjective CT findings, age and gender were integrated into a combined model by multivariate analysis. The diagnostic performance of these three models was assessed with receiver operating characteristics curves (ROC) and were compared using DeLong test.

RESULTS

The subjective findings model, the radiomics signature and the combined model showed a diagnostic accuracy of 81.43% (AUC [area under the curve], 0.806; 95% CI [confidence interval]: 0.696-0.917; sensitivity, 63.33%; specificity, 95.00%), 84.29% (AUC, 0.886 [95% CI: 0.809-0.963]; sensitivity, 86.67%; specificity, 82.50%), 87.14% (AUC, 0.903 [95%CI: 0.831-0.975]; sensitivity, 70.00%; specificity, 100%), respectively. There were no significant differences in AUC among these three models (P=0.051-0.422).

CONCLUSION

Radiomics analysis has the potential to accurately differentiate Borrmann type IV GC from PGL.

Texture analysis of medical images for radiotherapy applications

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

Associations of Radiomic Data Extracted from Static and Respiratory-Gated CT Scans with Disease Recurrence in Lung Cancer Patients Treated with SBRT

Radiomics aims to quantitatively capture the complex tumor phenotype contained in medical images to associate them with clinical outcomes. This study investigates the impact of different types of computed tomography (CT) images on the prognostic performance of radiomic features for disease recurrence in early stage non-small cell lung cancer (NSCLC) patients treated with stereotactic body radiation therapy (SBRT). 112 early stage NSCLC patients treated with SBRT that had static free breathing (FB) and average intensity projection (AIP) images were analyzed. Nineteen radiomic features were selected from each image type (FB or AIP) for analysis based on stability and variance. The selected FB and AIP radiomic feature sets had 6 common radiomic features between both image types and 13 unique features. The prognostic performances of the features for distant metastasis (DM) and locoregional recurrence (LRR) were evaluated using the concordance index (CI) and compared with two conventional features (tumor volume and maximum diameter). P-values were corrected for multiple testing using the false discovery rate procedure. None of the FB radiomic features were associated with DM, however, seven AIP radiomic features, that described tumor shape and heterogeneity, were (CI range: 0.638-0.676). Conventional features from FB images were not associated with DM, however, AIP conventional features were (CI range: 0.643-0.658). Radiomic and conventional multivariate models were compared between FB and AIP images using cross validation. The differences between the models were assessed using a permutation test. AIP radiomic multivariate models (median CI = 0.667) outperformed all other models (median CI range: 0.601-0.630) in predicting DM. None of the imaging features were prognostic of LRR. Therefore, image type impacts the performance of radiomic models in their association with disease recurrence. AIP images contained more information than FB images that were associated with disease recurrence in early stage NSCLC patients treated with SBRT, which suggests that AIP images may potentially be more optimal for the development of an imaging biomarker.

Quantitative radiomics studies for tissue characterization: a review of technology and methodological procedures

Quantitative analysis of tumour characteristics based on medical imaging is an emerging field of research. In recent years, quantitative imaging features derived from CT, positron emission tomography and MR scans were shown to be of added value in the prediction of outcome parameters in oncology, in what is called the radiomics field. However, results might be difficult to compare owing to a lack of standardized methodologies to conduct quantitative image analyses. In this review, we aim to present an overview of the current challenges, technical routines and protocols that are involved in quantitative imaging studies. The first issue that should be overcome is the dependency of several features on the scan acquisition and image reconstruction parameters. Adopting consistent methods in the subsequent target segmentation step is evenly crucial. To further establish robust quantitative image analyses, standardization or at least calibration of imaging features based on different feature extraction settings is required, especially for texture- and filter-based features. Several open-source and commercial software packages to perform feature extraction are currently available, all with slightly different functionalities, which makes benchmarking quite challenging. The number of imaging features calculated is typically larger than the number of patients studied, which emphasizes the importance of proper feature selection and prediction model-building routines to prevent overfitting. Even though many of these challenges still need to be addressed before quantitative imaging can be brought into daily clinical practice, radiomics is expected to be a critical component for the integration of image-derived information to personalize treatment in the future.

Test-Retest Data for Radiomics Feature Stability Analysis: Generalizable or Study-Specific?

Radiomics is an objective method for extracting quantitative information from medical images. However, in radiomics, standardization, overfitting, and generalization are major challenges to be overcome. Test–retest experiments can be used to select robust radiomic features that have minimal variation. Currently, it is unknown whether they should be identified for each disease (disease specific) or are only imaging device-specific (computed tomography [CT]-specific). Here, we performed a test–retest analysis on CT scans of 40 patients with rectal cancer in a clinical setting. Correlation between radiomic features was assessed using the concordance correlation coefficient (CCC). In total, only 9/542 features have a CCC > 0.85. Furthermore, results were compared with the test–retest results on CT scans of 27 patients with lung cancer with a 15-minute interval. Results show that 446/542 features have a higher CCC for the test–retest analysis of the data set of patients with lung cancer than for patients with rectal cancer. The importance of controlling factors such as scanners, imaging protocol, reconstruction methods, and time points in a radiomics analysis is shown. Moreover, the results imply that test–retest analyses should be performed before each radiomics study. More research is required to independently evaluate the effect of each factor.

Clinical Nomogram for Predicting Survival Outcomes in Early Mucinous Breast Cancer

Background

The features related to the prognosis of patients with mucinous breast cancer (MBC) remain controversial. We aimed to explore the prognostic factors of MBC and develop a nomogram for predicting survival outcomes.

Methods

The Surveillance, Epidemiology, and End Results (SEER) database was searched to identify 139611 women with resectable breast cancer from 1990 to 2007. Survival curves were generated using Kaplan-Meier methods. The 5-year and 10-year cancer-specific survival (CSS) rates were calculated using the Life-Table method. Based on Cox models, a nomogram was constructed to predict the probabilities of CSS for an individual patient. The competing risk regression model was used to analyse the specific survival of patients with MBC.

Results

There were 136569 (97.82%) infiltrative ductal cancer (IDC) patients and 3042 (2.18%) MBC patients. Patients with MBC had less lymph node involvement, a higher frequency of well-differentiated lesions, and more estrogen receptor (ER)-positive tumors. Patients with MBC had significantly higher 5 and10-year CSS rates (98.23 and 96.03%, respectively) than patients with IDC (91.44 and 85.48%, respectively). Univariate and multivariate analyses showed that MBC was an independent factor for better prognosis. As for patients with MBC, the event of death caused by another disease exceeded the event of death caused by breast cancer. A competing risk regression model further showed that lymph node involvement, poorly differentiated grade and advanced T-classification were independent factors of poor prognosis in patients with MBC. The Nomogram can accurately predict CSS with a high C-index (0.816). Risk scores developed from the nomogram can more accurately predict the prognosis of patients with MBC (C-index = 0.789) than the traditional TNM system (C-index = 0.704, P< 0.001).

Conclusions

Patients with MBC have a better prognosis than patients with IDC. Nomograms could help clinicians make more informed decisions in clinical practice. The competing risk regression model, as a more rational model, is recommended for use in the survival analysis of patients with MBC in the future.

Neuro-oncology: a selected review of ASCO 2016 abstracts

ASCO 2016, 29 May-2 June 2016, Chicago, IL, USA The largest annual clinical oncology conference the American Society of Clinical Oncology is held in the USA and gives researchers and other key opinion leaders the opportunity to present new cancer clinical trials and research data. The CNS tumors section of the American Society of Clinical Oncology 2016 covered various aspects of neuro-oncology including metastatic CNS diseases and primary brain tumors, presented via posters, oral talks and over 100 abstracts. This brief review selectively highlights presentations from this meeting in an organizational manner that reflects clinically relevant aspects of a large and multifaceted meeting.