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

The Current State of Radiomics for Meningiomas: Promises and Challenges

Meningiomas are the most common primary tumors of the central nervous system. Given the fact that the majority of meningiomas are benign, the preoperative risk stratification and treatment strategy decision-making highly rely on the conventional subjective radiologic evaluation. However, this traditional diagnostic and treatment modality may not be effective in patients with aggressive-growing tumors or symptomatic patients with potential risk of recurrence after surgical resection or radiotherapy, as this passive “wait and see” strategy could miss the optimal opportunity of intervention. Radiomics, a new rising discipline, translates high-dimensional image information into abundant mathematical data by multiple computational algorithms. It provides an objective and quantitative approach to interpret the imaging data, rather than the subjective and qualitative interpretation from relatively limited human visual observation. In fact, the enormous amount of information generated by radiomics analyses provides radiological to histopathological tumor information, which are visually imperceptible, and offers technological basis to its applications amid diagnosis, treatment, and prognosis. Here, we review the latest advancements of radiomics and its applications in the prediction of the pathological grade, pathological subtype, recurrence possibility, and differential diagnosis of meningiomas, and the potential and challenges in general clinical applications. In this review, we highlight the generalization of shared radiomic features among different studies and compare different performances of popular algorithms. At last, we discuss several possible aspects of challenges and future directions in the development of radiomic applications in meningiomas.

Contrast-Enhanced CT-based Textural Parameters as Potential Prognostic Factors of Survival for Colorectal Cancer Patients Receiving Targeted Therapy

PURPOSE

This study was designed to estimate the clinical significance of the contrast-enhanced computed tomography (CT) textural features for prediction of survival in colorectal cancer (CRC) patients receiving targeted therapy (bevacizumab and cetuximab).

PROCEDURES

The LifeX software was used to extract the textural parameters of the tumor lesions in the contrast-enhanced CT. We used the least absolute shrinkage and selection operator (LASSO) Cox regression and random forest method to screen the non-redundant radiomic features and constructed the CT imaging score. Univariate and multivariate analyses through the Cox proportional hazards model were performed to assess the prognostic clinical factor. Based on the result of multivariate analysis and CT imaging score, combined nomogram model was constructed to predict the overall survival (OS) of patients. Decision curves analysis was employed to evaluate the performance of the combined model and clinical model.

RESULTS

After comparative analysis of the area under curve of the receiver operating characteristic (ROC) curve, we chose the result of random forest model as CT imaging score. Considering the clinical practice and the result of analysis, age, surgery, and lactate dehydrogenase (LDH) level have been introduced into clinical model. Based on the result of analysis and the CT imaging score, we constructed the nomogram combined model. C-index and calibration curve verified the goodness of fit and discrimination of the combined model. Decision curve analysis (DCA) demonstrated that the combined model showed the better net benefit for a 3-year OS than clinical model.

CONCLUSIONS

In conclusion, the study provides preliminary evidences that several radiomic parameters of tumor lesions derived from CT images were prognostic factors and predictive markers for CRC patients who are candidates for targeted therapy (bevacizumab and cetuximab).

Validating the SumMean 18F-FDG PET Textural Feature as a Prognostic Marker in an Independent Cohort of Locally Advanced Non-Small Cell Lung Cancer Patients Undergoing Concurrent Chemoradiation Therapy

PURPOSE

Analyses from the ACRIN6668/RTOG0235 trial data identified the SumMean textural feature, calculated from 18-fluorodeoxyglucose positron emission tomography for tumors with a metabolic tumor volume >93 cm³, as a predictor of overall survival (OS) for patients with locally advanced non-small cell lung cancer (LA-NSCLC) receiving concurrent chemoradiation therapy. Here, we validated that finding in a completely independent patient cohort from a single institution.

METHODS AND MATERIALS

We identified patients with LA-NSCLC who underwent staging 18-fluorodeoxyglucose positron emission tomography and received definitive chemoradiation therapy at our institution between 2007 and 2018. Primary tumors were segmented semiautomatically, and SumMean score was calculated for each tumor and categorized according to the previously proposed cutoff of 0.018. In patients with metabolic tumor volume >93 cm³, SumMean was evaluated as a predictor of progression-free survival (PFS) and OS using log rank and Cox proportional hazards testing.

RESULTS

One hundred forty-eight patients met inclusion criteria, and 34 had large tumors (>93 cm³). Twelve (35%) had high SumMean, and 22 (65%) had low SumMean. SumMean was not significantly associated with other clinical variables. Median PFS for patients with large tumors and low SumMean was 5.8 months, compared with 41.1 months for patients with large tumors and high SumMean (log rank P = .022). Median OS for patients with large tumors and low SumMean was 15.0 months; median OS was not reached for patients with large tumors and high SumMean (log rank P = .014). In multivariable analysis, high SumMean was an independent predictor of improved OS (hazard ratio, 0.26; 95% confidence interval, 0.07-0.94; P = .041) and PFS (hazard ratio, 0.30; 95% confidence interval, 0.10-0.86; P = .026).

CONCLUSIONS

We externally validated SumMean as a prognostic marker for patients with LA-NSCLC treated with chemoradiation therapy in an independent patient cohort. Future studies will explore potential mechanisms for this association and how textural features may help guide treatment decisions.

Utility of Radiomics for Predicting Patient Survival in Hepatocellular Carcinoma With Portal Vein Tumor Thrombosis Treated With Stereotactic Body Radiotherapy

Introduction: This study aimed to develop and validate the combination of radiomic features and clinical characteristics that can predict patient survival in hepatocellular carcinoma (HCC) with portal vein tumor thrombosis (PVTT) treated with stereotactic body radiotherapy (SBRT).

Materials and Methods: The prediction model was developed in a primary cohort of 70 patients with HCC and PVTT treated with SBRT, using data acquired between December 2015 and June 2017. The radiomic features were extracted from computed tomography (CT) scans. A least absolute shrinkage and selection operator regression model was used to build the model. Multivariate Cox-regression hazard models were created for analyzing survival outcomes and the radiomic features and clinical characteristics were presented with a nomogram. The area under the receiver operating characteristic curve (AUROC) was used to evaluate the model. Participants were divided into a high-risk group and a low-risk group based on the radiomic features.

Results: A total of four radiomic features and six clinical characteristics were extracted for survival analysis. A combination of the radiomic features and clinical characteristics resulted in better performance for the estimation of overall survival (OS) [area under the curve (AUC) = 0.859 (CI: 0.770–0.948)] than that with clinical characteristics alone [AUC = 0.761 (CI: 0.641–0.881)]. These patients were divided into high-risk and low-risk groups according to the radiomic features.

Conclusion: This study demonstrated that a nomogram of combined radiomic features and clinical characteristics can be conveniently used to assess individualized preoperative prediction of OS in patients with HCC with PVTT before SBRT.

Artificial Intelligence for the Characterization of Pulmonary Nodules, Lung Tumors and Mediastinal Nodes on PET/CT

Lung cancer is the leading cause of cancer related death around the world although early diagnosis remains vital to enabling access to curative treatment options. This article briefly describes the current role of imaging, in particular 2-deoxy-2-[¹⁸F]fluoro-D-glucose (FDG) PET/CT, in lung cancer and specifically the role of artificial intelligence with CT followed by a detailed review of the published studies applying artificial intelligence (ie, machine learning and deep learning), on FDG PET or combined PET/CT images with the purpose of early detection and diagnosis of pulmonary nodules, and characterization of lung tumors and mediastinal lymph nodes. A comprehensive search was performed on Pubmed, Embase, and clinical trial databases. The studies were analyzed with a modified version of the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) and Prediction model Risk Of Bias Assessment Tool (PROBAST) statement. The search resulted in 361 studies; of these 29 were included; all retrospective; none were clinical trials. Twenty-two records evaluated standard machine learning (ML) methods on imaging features (ie, support vector machine), and 7 studies evaluated new ML methods (ie, deep learning) applied directly on PET or PET/CT images. The studies mainly reported positive results regarding the use of ML methods for diagnosing pulmonary nodules, characterizing lung tumors and mediastinal lymph nodes. However, 22 of the 29 studies were lacking a relevant comparator and/or lacking independent testing of the model. Application of ML methods with feature and image input from PET/CT for diagnosing and characterizing lung cancer is a relatively young area of research with great promise. Nevertheless, current published studies are often under-powered and lacking a clinically relevant comparator and/or independent testing.

Integration of PET/CT Radiomics and Semantic Features for Differentiation between Active Pulmonary Tuberculosis and Lung Cancer

PURPOSE

We aim to accurately differentiate between active pulmonary tuberculosis (TB) and lung cancer (LC) based on radiomics and semantic features as extracted from pre-treatment positron emission tomography/X-ray computed tomography (PET/CT) images.

PROCEDURES

A total of 174 patients (77/97 pulmonary TB/LC as confirmed by pathology) were retrospectively selected, with 122 in the training cohort and 52 in the validation cohort. Four hundred eighty-seven radiomics features were initially extracted to quantify phenotypic characteristics of the lesion region in both PET and CT images. Eleven semantic features were additionally defined by two experienced nuclear medicine physicians. Feature selection was performed in 5 steps to enable derivation of robust and effective signatures. Multivariable logistic regression analysis was subsequently used to develop a radiomics nomogram. The calibration, discrimination, and clinical usefulness of the nomogram were evaluated in both the training and independent validation cohorts.

RESULTS

The individualized radiomics nomogram, which combined PET/CT radiomics signature with semantic features, demonstrated good calibration and significantly improved the diagnostic performance with respect to the semantic model alone or PET/CT signature alone in training cohort (AUC 0.97 vs. 0.94 or 0.91, p = 0.0392 or 0.0056), whereas did not significantly improve the performance in validation cohort (AUC 0.93 vs. 0.89 or 0.91, p = 0.3098 or 0.3323).

CONCLUSION

The radiomics nomogram showed potential for individualized differential diagnosis between solid active pulmonary TB and solid LC, although the improvement of performance was not significant relative to semantic model.

Correlations between baseline 18F-FDG PET tumour parameters and circulating DNA in diffuse large B cell lymphoma and Hodgkin lymphoma

Background

¹⁸F-FDG PET/CT is a standard for many B cell malignancies, while blood DNA measurements are emerging tools. Our objective was to evaluate the correlations between baseline PET parameters and circulating DNA in diffuse large B cell lymphoma (DLBCL) and classical Hodgkin lymphoma (cHL).

Methods

Twenty-seven DLBCL and forty-eight cHL were prospectively included. Twelve PET parameters were analysed. Spearman’s correlations were used to compare PET parameters each other and to circulating cell-free DNA ([cfDNA]) and circulating tumour DNA ([ctDNA]). p values were controlled by Benjamini–Hochberg correction.

Results

Among the PET parameters, three different clusters for tumour burden, fragmentation/massiveness and dispersion parameters were observed. Some PET parameters were significantly correlated with blood DNA parameters, including the total metabolic tumour surface (TMTS) describing the tumour–host interface (e.g. ρ = 0.81 p < 0.001 for [ctDNA] of DLBLC), the tumour median distance between the periphery and the centroid (medPCD) describing the tumour’s massiveness (e.g. ρ = 0.81 p < 0.001 for [ctDNA] of DLBLC) and the volume of the bounding box including tumours (TumBB) describing the disease’s dispersion (e.g. ρ = 0.83 p < 0.001 for [ctDNA] of DLBLC).

Conclusions

Some PET parameters describing tumour burden, fragmentation/massiveness and dispersion are significantly correlated with circulating DNA parameters of DLBCL and cHL patients. These results could help to understand the pathophysiology of B cell malignancies.

Radiomics and Bladder Cancer: Current Status

PURPOSE: To systematically review the current literature and discuss the applications and limitations of radiomics and machine-learning augmented radiomics in the management of bladder cancer. METHODS: Pubmed ®, Scopus ®, and Web of Science ® databases were searched systematically for all full-text English-language articles assessing the impact of Artificial Intelligence OR Radiomics OR Machine Learning AND Bladder Cancer AND (staging OR grading OR prognosis) published up to January 2020. RESULTS: Of the 686 articles that were identified, 13 studies met the criteria for quantitative analysis. Staging, Grading and Tumor Classification, Prognosis, and Therapy Response were discussed in 7, 3, 2 and 7 studies, respectively. Data on cost of implementation were not reported. CT and MRI were the most common imaging approaches. CONCLUSION: Radiomics shows potential in bladder cancer detection, staging, grading, and response to therapy, thereby supporting the physician in personalizing patient management. Extension and validation of this promising technology in large multisite prospective trials is warranted to pave the way for its clinical translation.

Value of Shape and Texture Features from 18F-FDG PET/CT to Discriminate between Benign and Malignant Solitary Pulmonary Nodules: An Experimental Evaluation

In this paper, we investigate the role of shape and texture features from 18F-FDG PET/CT to discriminate between benign and malignant solitary pulmonary nodules. To this end, we retrospectively evaluated cross-sectional data from 111 patients (64 males, 47 females, age = 67.5 ± 11.0) all with histologically confirmed benign (n=39) or malignant (n=72) solitary pulmonary nodules. Eighteen three-dimensional imaging features, including conventional, texture, and shape features from PET and CT were tested for significant differences (Wilcoxon-Mann-Withney) between the benign and malignant groups. Prediction models based on different feature sets and three classification strategies (Classification Tree, k-Nearest Neighbours, and Naïve Bayes) were also evaluated to assess the potential benefit of shape and texture features compared with conventional imaging features alone. Eight features from CT and 15 from PET were significantly different between the benign and malignant groups. Adding shape and texture features increased the performance of both the CT-based and PET-based prediction models with overall accuracy gain being 3.4-11.2 pp and 2.2-10.2 pp, respectively. In conclusion, we found that shape and texture features from 18F-FDG PET/CT can lead to a better discrimination between benign and malignant lung nodules by increasing the accuracy of the prediction models by an appreciable margin.

In Vivo Assessment of Water Content, Trans-Epidermial Water Loss and Thickness in Human Facial Skin

Mapping facial skin in terms of its biophysical properties plays a fundamental role in many practical applications, including, among others, forensics, medical and beauty treatments, and cosmetic and restorative surgery. In this paper we present an in vivo evaluation of the water content, trans-epidermial water loss and skin thickness in six areas of the human face: cheeks, chin, forehead, lips, neck and nose. The experiments were performed on a population of healthy subjects through innovative sensing devices which enable fast yet accurate evaluations of the above parameters. A statistical analysis was carried out to determine significant differences between the facial areas investigated and clusters of statistically-indistinguishable areas. We found that water content was higher in the cheeks and neck and lower in the lips, whereas trans-epidermal water loss had higher values for the lips and lower ones for the neck. In terms of thickness the dermis exhibited three clusters, which, from thickest to thinnest were: chin and nose, cheek and forehead and lips and neck. The epidermis showed the same three clusters too, but with a different ordering in term of thickness. Finally, the stratum corneum presented two clusters: the thickest, formed by lips and neck, and the thinnest, formed by all the remaining areas. The results of this investigation can provide valuable guidelines for the evaluation of skin moisturisers and other cosmetic products, and can help guide choices in re-constructive/cosmetic surgery.

Radiomics: an overview in lung cancer management-a narrative review

Radiomics is a novel approach for optimizing the analysis massive data from medical images to provide auxiliary guidance in clinical issues. Quantitative feature extraction is one of the critical steps of radiomics. The association between radiomics features and the clinicopathological information of diseases can be identified by several statistics methods. For instance, although significant progress has been made in the field of lung cancer, too many questions remain, especially for the individualized decisions. Radiomics offers a new tool to encode the characteristics of lung cancer which is the leading cause of cancer-related deaths worldwide. Here, we reviewed the workflow and clinical utility of radiomics in lung cancer management, including pulmonary nodules detection, classification, histopathology and genetics evaluation, clinical staging, therapy response, and prognosis prediction. Most of these studies showed positive results, indicating the potential value of radiomics in clinical practice. The implementation of radiomics is both feasible and invaluable, and has aided clinicians in ascertaining the nature of a disease with greater precision. However, it should be noted that radiomics in its current state cannot completely replace the work of therapists or tissue examination. The potential future trends of this modality were also remarked. More efforts are needed to overcome the limitations identified above in order to facilitate the widespread application of radiomics in the reasonably near future.

Variability and Standardization of Quantitative Imaging: Monoparametric to Multiparametric Quantification, Radiomics, and Artificial Intelligence

Radiological images have been assessed qualitatively in most clinical settings by the expert eyes of radiologists and other clinicians. On the other hand, quantification of radiological images has the potential to detect early disease that may be difficult to detect with human eyes, complement or replace biopsy, and provide clear differentiation of disease stage. Further, objective assessment by quantification is a prerequisite of personalized/precision medicine. This review article aims to summarize and discuss how the variability of quantitative values derived from radiological images are induced by a number of factors and how these variabilities are mitigated and standardization of the quantitative values are achieved. We discuss the variabilities of specific biomarkers derived from magnetic resonance imaging and computed tomography, and focus on diffusion-weighted imaging, relaxometry, lung density evaluation, and computer-aided computed tomography volumetry. We also review the sources of variability and current efforts of standardization of the rapidly evolving techniques, which include radiomics and artificial intelligence.

Characterization of FDG PET Images Using Texture Analysis in Tumors of the Gastro-Intestinal Tract: A Review

Radiomics or textural feature extraction obtained from positron emission tomography (PET) images through complex mathematical models of the spatial relationship between multiple image voxels is currently emerging as a new tool for assessing intra-tumoral heterogeneity in medical imaging. In this paper, available literature on texture analysis using FDG PET imaging in patients suffering from tumors of the gastro-intestinal tract is reviewed. While texture analysis of FDG PET images appears clinically promising, due to the lack of technical specifications, a large variability in the implemented methodology used for texture analysis and lack of statistical robustness, at present, no firm conclusions can be drawn regarding the predictive or prognostic value of FDG PET texture analysis derived indices in patients suffering from gastro-enterologic tumors. In order to move forward in this field, a harmonized image acquisition and processing protocol as well as a harmonized protocol for texture analysis of tumor volumes, allowing multi-center studies excluding statistical biases should be considered. Furthermore, the complementary and additional value of CT-imaging, as part of the PET/CT imaging technique, warrants exploration.

Radiomics in medical imaging-"how-to" guide and critical reflection

Radiomics is a quantitative approach to medical imaging, which aims at enhancing the existing data available to clinicians by means of advanced mathematical analysis. Through mathematical extraction of the spatial distribution of signal intensities and pixel interrelationships, radiomics quantifies textural information by using analysis methods from the field of artificial intelligence. Various studies from different fields in imaging have been published so far, highlighting the potential of radiomics to enhance clinical decision-making. However, the field faces several important challenges, which are mainly caused by the various technical factors influencing the extracted radiomic features.The aim of the present review is twofold: first, we present the typical workflow of a radiomics analysis and deliver a practical "how-to" guide for a typical radiomics analysis. Second, we discuss the current limitations of radiomics, suggest potential improvements, and summarize relevant literature on the subject.

Recent and Current Advances in FDG-PET Imaging within the Field of Clinical Oncology in NSCLC: A Review of the Literature

Lung cancer is the leading cause of cancer-related deaths around the world, the most common type of which is non-small-cell lung cancer (NSCLC). Computed tomography (CT) is required for patients with NSCLC, but often involves diagnostic issues and large intra- and interobserver variability. The anatomic data obtained using CT can be supplemented by the metabolic data obtained using fluorodeoxyglucose F 18 (FDG) positron emission tomography (PET); therefore, the use of FDG-PET/CT for staging NSCLC is recommended, as it provides more accuracy than either modality alone. Furthermore, FDG-PET/magnetic resonance imaging (MRI) provides useful information on metabolic activity and tumor cellularity, and has become increasingly popular. A number of studies have described FDG-PET/MRI as having a high diagnostic performance in NSCLC staging. Therefore, multidimensional functional imaging using FDG-PET/MRI is promising for evaluating the activity of the intratumoral environment. Radiomics is the quantitative extraction of imaging features from medical scans. The chief advantages of FDG-PET/CT radiomics are the ability to capture information beyond the capabilities of the human eye, non-invasiveness, the (virtually) real-time response, and full-field analysis of the lesion. This review summarizes the recent advances in FDG-PET imaging within the field of clinical oncology in NSCLC, with a focus on surgery and prognostication, and investigates the site-specific strengths and limitations of FDG-PET/CT. Overall, the goal of treatment for NSCLC is to provide the best opportunity for long-term survival; therefore, FDG-PET/CT is expected to play an increasingly important role in deciding the appropriate treatment for such patients.

Multi-energy computed tomography and material quantification: Current barriers and opportunities for advancement

Computed tomography (CT) technology has rapidly evolved since its introduction in the 1970s. It is a highly important diagnostic tool for clinicians as demonstrated by the significant increase in utilization over several decades. However, much of the effort to develop and advance CT applications has been focused on improving visual sensitivity and reducing radiation dose. In comparison to these areas, improvements in quantitative CT have lagged behind. While this could be a consequence of the technological limitations of conventional CT, advanced dual-energy CT (DECT) and photon-counting detector CT (PCD-CT) offer new opportunities for quantitation. Routine use of DECT is becoming more widely available and PCD-CT is rapidly developing. This review covers efforts to address an unmet need for improved quantitative imaging to better characterize disease, identify biomarkers, and evaluate therapeutic response, with an emphasis on multi-energy CT applications. The review will primarily discuss applications that have utilized quantitative metrics using both conventional and DECT, such as bone mineral density measurement, evaluation of renal lesions, and diagnosis of fatty liver disease. Other topics that will be discussed include efforts to improve quantitative CT volumetry and radiomics. Finally, we will address the use of quantitative CT to enhance image-guided techniques for surgery, radiotherapy and interventions and provide unique opportunities for development of new contrast agents.

Applications of radiomics in genitourinary tumors

Genitourinary tumors are heterogeneous groups of tumors with high morbidity and mortality rates. Confronted with existing problems in the management of genitourinary tumors, a personalized imaging method called radiomics shows great potential in areas including detection, grading, and treatment response assessment. Radiomics is characterized by extraction of quantitative imaging features which are not visible to the naked eye from conventional imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI) and positron emission tomography-computed tomography (PET-CT), followed by data analysis and model building. It outperforms other invasive methods in terms of non-invasiveness, low cost and high efficiency. Recently, a number of studies have evaluated the application of radiomics in patients with genitourinary tumors with promising data. The combination of radiomics and clinical/laboratory factors provides added value in many studies. Despite this, there are limitations and challenges to be overcome before a more extensive clinical application in the future. In this article, we will introduce the concept, significance and workflow of radiomics, review their current applications in patients with genitourinary tumors and discuss limitations and future directions of radiomics. It would help multidisciplinary team involved in the treatment of patients with genitourinary tumors to achieve a better understanding of the results of radiomics study toward a personalized medicine.

CT-Based Radiomics Score for Distinguishing Between Grade 1 and Grade 2 Nonfunctioning Pancreatic Neuroendocrine Tumors

OBJECTIVE. The objective of our study was to explore the relationship between a CT-based radiomics score and grade of nonfunctioning pancreatic neuroendocrine tumors (PNETs) and to evaluate the ability of a calculated CT radiomics score to distinguish between grade 1 and grade 2 nonfunctioning PNETs. MATERIALS AND METHODS. This retrospective study assessed 102 patients with surgically resected, pathologically confirmed nonfunctioning PNETs who underwent MDCT from January 2014 to December 2017. Radiomic methods were used to extract features from portal venous phase CT scans, and the least absolute shrinkage and selection operator (LASSO) method was used to select the features. Multivariate logistic regression models were used to analyze the association between the CT radiomics score and nonfunctioning PNET grades. The performance of the CT radiomics score was assessed on the basis of its discriminative ability and clinical usefulness. RESULTS. The CT radiomics score, which consisted of four selected features, was significantly associated with nonfunctioning PNET grades. Every 1-point increase in radiomics score was associated with a 57% increased risk of grade 2 disease. The score also showed high accuracy (AUC = 0.86 for all PNETs; AUC = 0.81 for PNETs ≤ 2 cm). The best cutoff point for maximal sensitivity and specificity was a CT radiomics score of -0.134. Decision curve analysis showed that the CT radiomics score is clinically useful. CONCLUSION. The CT radiomics score shows a significant association with the grade of nonfunctioning PNETs and provides a potentially valuable noninvasive tool for distinguishing between different grades of nonfunctioning PNET, especially among patients with tumors 2 cm or smaller.

Radiomics and Artificial Intelligence for Renal Mass Characterization

Radiomics allows for high throughput extraction of quantitative data from images. This is an area of active research as groups try to capture and quantify imaging parameters and convert these into descriptive phenotypes of organs or tumors. Texture analysis is one radiomics tool that extracts information about heterogeneity within a given region of interest. This is used with or without associated machine learning classifiers or a deep learning approach is applied to similar types of data. These tools have shown utility in characterizing renal masses, renal cell carcinoma, and assessing response to targeted therapeutic agents in metastatic renal cell carcinoma.

Radiomics nomogram for the prediction of 2019 novel coronavirus pneumonia caused by SARS-CoV-2

Objectives

To develop and validate a radiomics model for predicting 2019 novel coronavirus (COVID-19) pneumonia.

Methods

For this retrospective study, a radiomics model was developed on the basis of a training set consisting of 136 patients with COVID-19 pneumonia and 103 patients with other types of viral pneumonia. Radiomics features were extracted from the lung parenchyma window. A radiomics signature was built on the basis of reproducible features, using the least absolute shrinkage and selection operator method (LASSO). Multivariable logistic regression model was adopted to establish a radiomics nomogram. Nomogram performance was determined by its discrimination, calibration, and clinical usefulness. The model was validated in 90 consecutive patients, of which 56 patients had COVID-19 pneumonia and 34 patients had other types of viral pneumonia.

Results

The radiomics signature, consisting of 3 selected features, was significantly associated with COVID-19 pneumonia (p < 0.05) in both training and validation sets. The multivariable logistic regression model included the radiomics signature and distribution; maximum lesion, hilar, and mediastinal lymph node enlargement; and pleural effusion. The individualized prediction nomogram showed good discrimination in the training sample (area under the receiver operating characteristic curve [AUC], 0.959; 95% confidence interval [CI], 0.933–0.985) and in the validation sample (AUC, 0.955; 95% CI, 0.899–0.995) and good calibration. The mixed model achieved better predictive efficacy than the clinical model. Decision curve analysis demonstrated that the radiomics nomogram was clinically useful.

Conclusions

The radiomics model derived has good performance for predicting COVID-19 pneumonia and may help in clinical decision-making.

Key Points

• A radiomics model showed good performance for prediction 2019 novel coronavirus pneumonia and favorable discrimination for other types of pneumonia on CT images.

• A central or peripheral distribution, a maximum lesion range > 10 cm, the involvement of all five lobes, hilar and mediastinal lymph node enlargement, and no pleural effusion is associated with an increased risk of 2019 novel coronavirus pneumonia.

• A radiomics model was superior to a clinical model in predicting 2019 novel coronavirus pneumonia.

Electronic supplementary material

The online version of this article (10.1007/s00330-020-07032-z) contains supplementary material, which is available to authorized users.

Magnetic Resonance-Based Radiomic Analysis of Radiofrequency Lesion Predicts Outcomes After Percutaneous Cordotomy: A Feasibility Study

BACKGROUND

To date, there is limited data on evaluation of the cordotomy lesion and predicting clinical outcome.

OBJECTIVE

To evaluate the utility of magnetic resonance (MR)-based radiomic analysis to quantify microstructural changes created by the cordotomy lesion and predict outcome in patients undergoing percutaneous cordotomy for medically refractory cancer pain.

METHODS

This is a retrospective interpretation of prospectively acquired data in 10 patients (5 males, age range 43-76 yr) who underwent percutaneous computed tomography-guided high cervical cordotomy for medically refractory cancer pain between 2015 and 2016. All patients underwent magnetic resonance imaging (MRI) of the cordotomy lesion on postoperative day 1. After segmentation of T2-weighted images, 310 radiomic features were extracted. Pain outcomes were recorded on postoperative day 1 and day 7 using the visual analog scale. R software was used to build statistical models based on MRI radiomic features for prediction of pain outcomes.

RESULTS

A total of 20 relevant radiomic features were identified using the maximum relevance minimum redundanc method. Radiomics predicted postoperative day 1 pain scores with an accuracy of 90% (P = .046), 100% sensitivity, 75% specificity, 85.7% positive predictive value, and 100% negative predictive value. The radiomics model also predicted if the postoperative day 1 pain score was sustained on postoperative day 7 with an accuracy of 100% (P = .028), 100% sensitivity, 100% specificity, and 100% positive and negative predictive value.

CONCLUSION

MR-based radiomic analysis of the cordotomy lesion was predictive of pain outcomes at 1 wk after percutaneous cordotomy for intractable cancer pain.

Current status and quality of radiomics studies in lymphoma: a systematic review

OBJECTIVES

To perform a systematic review regarding the developments in the field of radiomics in lymphoma. To evaluate the quality of included articles by the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2), the phases classification criteria for image mining studies, and the radiomics quality scoring (RQS) tool.

METHODS

We searched for eligible articles in the MEDLINE/PubMed and EMBASE databases using the terms "radiomics", "texture" and "lymphoma". The included studies were divided into two categories: diagnosis-, therapy response- and outcome-related studies. The diagnosis-related studies were evaluated using the QUADAS-2; all studies were evaluated using the phases classification criteria for image mining studies and the RQS tool by two reviewers.

RESULTS

Forty-five studies were included; thirteen papers (28.9%) focused on the differential diagnosis of primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM). Thirty-two (71.1%) studies were classified as discovery science according to the phase classification criteria for image mining studies. The mean RQS score of all studies was 14.2% (ranging from 0.0 to 40.3%), and 23 studies (51.1%) were given a score of < 10%.

CONCLUSION

The radiomics features could serve as diagnostic and prognostic indicators in lymphoma. However, the current conclusions should be interpreted with caution due to the suboptimal quality of the studies. In order to introduce radiomics into lymphoma clinical settings, the lesion segmentation and selection, the influence of the pathological pattern and the extraction of multiple modalities and multiple time points features need to be further studied.

KEY POINTS

• The radiomics approach may provide useful information for diagnosis, prediction of the therapy response, and outcome of lymphoma. • The quality of published radiomics studies in lymphoma has been suboptimal to date. • More studies are needed to examine lesion selection and segmentation, the influence of pathological patterns, and the extraction of multiple modalities and multiple time point features.

18F-Fluorodeoxyglucose PET in Locally Advanced Non-small Cell Lung Cancer: From Predicting Outcomes to Guiding Therapy

PET using 18-fluorodeoxyglucose (FDG) has become an important part of the work-up for non-small cell lung cancer (NSCLC). This article summarizes advancements in using FDG-PET for patients with locally advanced NSCLC treated with definitive radiation therapy (RT). This article discusses prognostication of outcome based on pretreatment or midtreatment PET metrics, using textural image features to predict treatment outcomes, and using PET to define RT target volumes and inform RT dose modifications. The role of PET is evolving and is moving toward using quantitative image information, with the overarching goal of individualizing therapy to improve outcomes for patients with NSCLC.

Development and validation of an 18F-FDG PET radiomic model for prognosis prediction in patients with nasal-type extranodal natural killer/T cell lymphoma

OBJECTIVES

To identify an ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography (PET) radiomics-based model for predicting progression-free survival (PFS) and overall survival (OS) of nasal-type extranodal natural killer/T cell lymphoma (ENKTL).

METHODS

In this retrospective study, a total of 110 ENKTL patients were divided into a training cohort (n = 82) and a validation cohort (n = 28). Forty-one features were extracted from pretreatment PET images of the patients. Least absolute shrinkage and selection operator (LASSO) regression was used to develop the radiomic signatures (R-signatures). A radiomics-based model was built and validated in the two cohorts and compared with a metabolism-based model.

RESULTS

The R-signatures were constructed with moderate predictive ability in the training and validation cohorts (R-signature_PFS: AUC = 0.788 and 0.473; R-signature_OS: AUC = 0.637 and 0.730). For PFS, the radiomics-based model showed better discrimination than the metabolism-based model in the training cohort (C-index = 0.811 vs. 0.751) but poorer discrimination in the validation cohort (C-index = 0.588 vs. 0.693). The calibration of the radiomics-based model was poorer than that of the metabolism-based model (training cohort: p = 0.415 vs. 0.428, validation cohort: p = 0.228 vs. 0.652). For OS, the performance of the radiomics-based model was poorer (training cohort: C-index = 0.818 vs. 0.828, p = 0.853 vs. 0.885; validation cohort: C-index = 0.628 vs. 0.753, p < 0.05 vs. 0.913).

CONCLUSIONS

Radiomic features derived from PET images can predict the outcomes of patients with ENKTL, but the performance of the radiomics-based model was inferior to that of the metabolism-based model.

KEY POINTS

• The R-signatures calculated by using ¹⁸F-FDG PET radiomic features can predict the survival of patients with ENKTL. • The radiomics-based models integrating the R-signatures and clinical factors achieved good predictive values. • The performance of the radiomics-based model was inferior to that of the metabolism-based model in the two cohorts.

Nuclear medicine radiomics in precision medicine: why we can't do without artificial intelligence

In recent years, radiomics, defined as the extraction of large amounts of quantitative features from medical images, has gained emerging interest. Radiomics consists of the extraction of handcrafted features combined with sophisticated statistical methods or machine learning algorithms for modelling, or deep learning algorithms that both learn features from raw data and perform modelling. These features have the potential to serve as non-invasive biomarkers for tumor characterization, prognostic stratification and response prediction, thereby contributing to precision medicine. However, especially in nuclear medicine, variable results are obtained when using radiomics for these purposes. Individual studies show promising results, but due to small numbers of patients per study and little standardization, it is difficult to compare and validate results on other datasets. This review describes the radiomic pipeline, its applications and the increasing role of artificial intelligence within the field. Furthermore, the challenges that need to be overcome to achieve clinical translation are discussed, so that, eventually, radiomics, combined with clinical data and other biomarkers, can contribute to precision medicine, by providing the right treatment to the right patient, with the right dose, at the right time.

How to develop a meaningful radiomic signature for clinical use in oncologic patients

During the last decade, there is an increasing usage of quantitative methods in Radiology in an effort to reduce the diagnostic variability associated with a subjective manner of radiological interpretation. Combined approaches where visual assessment made by the radiologist is augmented by quantitative imaging biomarkers are gaining attention. Advances in machine learning resulted in the rise of radiomics that is a new methodology referring to the extraction of quantitative information from medical images. Radiomics are based on the development of computational models, referred to as “Radiomic Signatures”, trying to address either unmet clinical needs, mostly in the field of oncologic imaging, or to compare radiomics performance with that of radiologists. However, to explore this new technology, initial publications did not consider best practices in the field of machine learning resulting in publications with questionable clinical value. In this paper, our effort was concentrated on how to avoid methodological mistakes and consider critical issues in the workflow of the development of clinically meaningful radiomic signatures.

A review of original articles published in the emerging field of radiomics

PURPOSE

To determine the characteristics of and trends in research in the emerging field of radiomics through bibliometric and hotspot analyses of relevant original articles published between 2013 and 2018.

METHODS

We evaluated 553 original articles concerning radiomics, published in a total of 61 peer-reviewed journals between 2013 and 2018. The following information was retrieved for each article: radiological subspecialty, imaging technique(s), machine learning technique(s), sample size, study setting and design, statistical result(s), study purpose, software used for feature calculation, funding declarations, author number, first author's affiliation, study origin, and journal name. Qualitative and quantitative analyses were performed for the manually extracted data for identification and visualization of the trends in radiomics research.

RESULTS

The annual growth rate in the number of published papers was 177.82% (p < 0.001). The characteristics and trends of research hotspots in the field of radiomics were clarified and visualized in this study. It was found that the field of radiomics is at a more mature stage for lung, breast, and prostate cancers than for other sites. Radiomics studies primarily focused on radiological characterization (215) and monitoring (182). Logistic regression and LASSO were the two most commonly used techniques for feature selection. Non-clinical researchers without a medical background dominated radiomics studies (70.52%), the vast majority of which only highlighted positive results (97.80%) while downplaying negative findings.

CONCLUSIONS

The reporting of quantifiable knowledge about the characteristics and trajectories of radiomics can inform researchers about the gaps in the field of radiomics and guide its future direction.

CT-based radiomics for preoperative prediction of early recurrent hepatocellular carcinoma: technical reproducibility of acquisition and scanners

PURPOSE

To test the technical reproducibility of acquisition and scanners of CT image-based radiomics model for early recurrent hepatocellular carcinoma (HCC).

METHODS

We included primary HCC patient undergone curative therapies, using early recurrence as endpoint. Four datasets were constructed: 109 images from hospital #1 for training (set 1: 1-mm image slice thickness), 47 images from hospital #1 for internal validation (sets 2 and 3: 1-mm and 10-mm image slice thicknesses, respectively), and 47 images from hospital #2 for external validation (set 4: vastly different from training dataset). A radiomics model was constructed. Radiomics technical reproducibility was measured by overfitting and calibration deviation in external validation dataset. The influence of slice thickness on reproducibility was evaluated in two internal validation datasets.

RESULTS

Compared with set 1, the model in set 2 indicated favorable prediction efficiency (the area under the curve 0.79 vs. 0.80, P = 0.47) and good calibration (unreliability statistic U: P = 0.33). However, in set 4, significant overfitting (0.63 vs. 0.80, P < 0.01) and calibration deviation (U: P < 0.01) were observed. Similar poor performance was also observed in set 3 (0.56 vs. 0.80, P = 0.02; U: P < 0.01).

CONCLUSIONS

CT-based radiomics has poor reproducibility between centers. Image heterogeneity, such as slice thickness, can be a significant influencing factor.

Statistical significance: p value, 0.05 threshold, and applications to radiomics-reasons for a conservative approach

Here, we summarise the unresolved debate about p value and its dichotomisation. We present the statement of the American Statistical Association against the misuse of statistical significance as well as the proposals to abandon the use of p value and to reduce the significance threshold from 0.05 to 0.005. We highlight reasons for a conservative approach, as clinical research needs dichotomic answers to guide decision-making, in particular in the case of diagnostic imaging and interventional radiology. With a reduced p value threshold, the cost of research could increase while spontaneous research could be reduced. Secondary evidence from systematic reviews/meta-analyses, data sharing, and cost-effective analyses are better ways to mitigate the false discovery rate and lack of reproducibility associated with the use of the 0.05 threshold. Importantly, when reporting p values, authors should always provide the actual value, not only statements of "p < 0.05" or "p ≥ 0.05", because p values give a measure of the degree of data compatibility with the null hypothesis. Notably, radiomics and big data, fuelled by the application of artificial intelligence, involve hundreds/thousands of tested features similarly to other "omics" such as genomics, where a reduction in the significance threshold, based on well-known corrections for multiple testing, has been already adopted.

PET/CT Radiomics in Lung Cancer: An Overview

Quantitative extraction of imaging features from medical scans (‘radiomics’) has attracted a lot of research attention in the last few years. The literature has consistently emphasized the potential use of radiomics for computer-assisted diagnosis, as well as for predicting survival and response to treatment. Radiomics is appealing in that it enables full-field analysis of the lesion, provides nearly real-time results, and is non-invasive. Still, a lot of studies suffer from a series of drawbacks such as lack of standardization and repeatability. Such limitations, along with the unmet demand for large enough image datasets for training the algorithms, are major hurdles that still limit the application of radiomics on a large scale. In this paper, we review the current developments, potential applications, limitations, and perspectives of PET/CT radiomics with specific focus on the management of patients with lung cancer.

Heterogeneity in tumours: Validating the use of radiomic features on 18F-FDG PET/CT scans of lung cancer patients as a prognostic tool

AIM

The aim was to validate promising radiomic features (RFs)1 on 18F-flourodeoxyglucose positron emission tomography/computed tomography-scans (18F-FDG PET/CT) of non-small cell lung cancer (NSCLC) patients undergoing definitive chemo-radiotherapy.

METHODS

18F-FDG PET/CT scans performed for radiotherapy (RT) planning were retrieved. Auto-segmentation with visual adaption was used to define the primary tumour on PET images. Six pre-selected prognostic and reproducible PET texture -and shape-features were calculated using texture respectively shape analysis. The correlation between these RFs and metabolic active tumour volume (MTV)3, gross tumour volume (GTV)4 and maximum and mean of standardized uptake value (SUV)5 was tested with a Spearman's Rank test. The prognostic value of RFs was tested in a univariate cox regression analysis and a multivariate cox regression analysis with GTV, clinical stage and histology. P-value ≤ 0.05 were considered significant.

RESULTS

Image analysis was performed for 233 patients: 145 males and 88 females, mean age of 65.7 and clinical stage II-IV. Mean GTV was 129.87 cm3 (SD 130.30 cm3). Texture and shape-features correlated more strongly to MTV and GTV compared to SUV-measurements. Four RFs predicted PFS in the univariate analysis. No RFs predicted PFS in the multivariate analysis, whereas GTV and clinical stage predicted PFS (p = 0.001 and p = 0.008 respectively).

CONCLUSION

The pre-selected RFs were insignificant in predicting PFS in combination with GTV, clinical stage and histology. These results might be due to variations in technical parameters. However, it is relevant to question whether RFs are stable enough to provide clinically useful information.

Robust, independent and relevant prognostic 18F-fluorodeoxyglucose positron emission tomography radiomics features in non-small cell lung cancer: Are there any?

In locally advanced lung cancer, established baseline clinical variables show limited prognostic accuracy and ¹⁸F-fluorodeoxyglucose positron emission tomography (FDG PET) radiomics features may increase accuracy for optimal treatment selection. Their robustness and added value relative to current clinical factors are unknown. Hence, we identify robust and independent PET radiomics features that may have complementary value in predicting survival endpoints. A 4D PET dataset (n = 70) was used for assessing the repeatability (Bland-Altman analysis) and independence of PET radiomics features (Spearman rank: |ρ|<0.5). Two 3D PET datasets combined (n = 252) were used for training and validation of an elastic net regularized generalized logistic regression model (GLM) based on a selection of clinical and robust independent PET radiomics features (GLM_all). The fitted model performance was externally validated (n = 40). The performance of GLM_all (measured with area under the receiver operating characteristic curve, AUC) was highest in predicting 2-year overall survival (0.66±0.07). No significant improvement was observed for GLM_all compared to a model containing only PET radiomics features or only clinical variables for any clinical endpoint. External validation of GLM_all led to AUC values no higher than 0.55 for any clinical endpoint. In this study, robust independent FDG PET radiomics features did not have complementary value in predicting survival endpoints in lung cancer patients. Improving risk stratification and clinical decision making based on clinical variables and PET radiomics features has still been proven difficult in locally advanced lung cancer patients.

How to avoid describing your radiological research study incorrectly

Abstract

This review identifies and examines terms used to describe a radiological research “study” or “trial”. A taxonomy of clinical research descriptions is explained with reference to medical imaging examples. Because many descriptive terms have precise methodological implications, it is important that these terms are understood by readers and used correctly by researchers, so that the reader is not misled.

Key Points

• Multiple different terms are being used to describe radiological research “studies” and “trials”, and many of these terms have precise methodological implications.

• Radiological researchers sometimes use titles that describe their research incorrectly. This can mislead the reader as to what was actually done.

• It is important that readers and researchers understand the correct taxonomy of clinical research and that researchers adopt the correct description for their work.

Machine learning helps identifying volume-confounding effects in radiomics

PURPOSE

Highlighting the risk of biases in radiomics-based models will help improve their quality and increase usage as decision support systems in the clinic. In this study we use machine learning-based methods to identify the presence of volume-confounding effects in radiomics features. Methods 841 radiomics features were extracted from two retrospective publicly available datasets of lung and head neck cancers using open source software. Unsupervised hierarchical clustering and principal component analysis (PCA) identified relations between radiomics and clinical outcomes (overall survival). Bootstrapping techniques with logistic regression verified features' prognostic power and robustness. Results Over 80% of the features had large pairwise correlations. Nearly 30% of the features presented strong correlations with tumor volume. Using volume-independent features for clustering and PCA did not allow risk stratification of patients. Clinical predictors outperformed radiomics features in bootstrapping and logistic regression. Conclusions The adoption of safeguards in radiomics is imperative to improve the quality of radiomics studies. We proposed machine learning (ML) - based methods for robust radiomics signatures development.

Computed tomography-based radiomics model for discriminating the risk stratification of gastrointestinal stromal tumors

PURPOSE

The pathological risk degree of gastrointestinal stromal tumors (GISTs) has become an issue of great concern. Computed tomography (CT) is beneficial for showing adjacent tissues in detail and determining metastasis or recurrence of GISTs, but its function is still limited. Radiomics has recently shown a great potential in aiding clinical decision-making. The purpose of our study is to develop and validate CT-based radiomics models for GIST risk stratification.

METHODS

Three hundred and sixty-six patients clinically suspected of primary GISTs from January 2013 to February 2018 were retrospectively enrolled, among which data from 140 patients were eventually analyzed after exclusion. Data from patient CT images were partitioned based on the National Institutes of Health Consensus Classification, including tumor segmentation, radiomics feature extraction and selection. A radiomics model was then proposed and validated.

RESULTS

The radiomics signature demonstrated discriminative performance for advanced and nonadvanced GISTs with an area under the curve (AUC) of 0.935 [95% confidence interval (CI) 0.870-1.000] and an accuracy of 90.2% for validation cohort. The radiomics signature demonstrated favorable performance for the risk stratification of GISTs with an AUC of 0.809 (95% CI 0.777-0.841) and an accuracy of 67.5% for the validation cohort. Radiomics analysis could capture features of the four risk categories of GISTs. Meanwhile, this CT-based radiomics signature showed good diagnostic accuracy to distinguish between nonadvanced and advanced GISTs, as well as the four risk stratifications of GISTs.

CONCLUSION

Our findings highlight the potential of a quantitative radiomics analysis as a complementary tool to achieve an accurate diagnosis for GISTs.

18F-FDG PET/CT radiomic predictors of pathologic complete response (pCR) to neoadjuvant chemotherapy in breast cancer patients

PURPOSE

Pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) is commonly accepted as the gold standard to assess outcome after NAC in breast cancer patients. ¹⁸F-Fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) has unique value in tumor staging, predicting prognosis, and evaluating treatment response. Our aim was to determine if we could identify radiomic predictors from PET/CT in breast cancer patient therapeutic efficacy prior to NAC.

METHODS

This retrospective study included 100 breast cancer patients who received NAC; there were 2210 PET/CT radiomic features extracted. Unsupervised and supervised machine learning models were used to identify the prognostic radiomic predictors through the following: (1) selection of the significant (p < 0.05) imaging features from consensus clustering and the Wilcoxon signed-rank test; (2) selection of the most discriminative features via univariate random forest (Uni-RF) and the Pearson correlation matrix (PCM); and (3) determination of the most predictive features from a traversal feature selection (TFS) based on a multivariate random forest (RF). The prediction model was constructed with RF and then validated with 10-fold cross-validation for 30 times and then independently validated. The performance of the radiomic predictors was measured in terms of area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

RESULTS

The PET/CT radiomic predictors achieved a prediction accuracy of 0.857 (AUC = 0.844) on the training split set and 0.767 (AUC = 0.722) on the independent validation set. When age was incorporated, the accuracy for the split set increased to 0.857 (AUC = 0.958) and 0.8 (AUC = 0.73) for the independent validation set and both outperformed the clinical prediction model. We also found a close association between the radiomic features, receptor expression, and tumor T stage.

CONCLUSION

Radiomic predictors from pre-treatment PET/CT scans when combined with patient age were able to predict pCR after NAC. We suggest that these data will be valuable for patient management.

A four-factor immune risk score signature predicts the clinical outcome of patients with spinal chordoma

BACKGROUND

Currently, the measurement of immune cells in previous studies is usually subjective, and no immune-based prognostic model has been established for chordoma. In this study, we sought to simultaneously measure tumor-infiltrating lymphocyte (TIL) subtypes in chordoma samples using an objective method and develop an immune risk score (IRS) model for survival prediction.

METHODS

Multiplexed quantitative immunofluorescence staining was used to determine the TIL levels in the tumoral and stromal subareas of 114 spinal chordoma specimens (54 in the training and 60 in the validation cohort) for programmed death-1 (PD-1), CD3, CD8, CD20 (where CD is cluster of differentiation), and FOXP3. Flow cytometry was performed to validate the immunofluorescence assay for lymphocyte measurement on an additional five fresh chordoma specimens. Subsequently, the IRS model was built using the least absolute shrinkage and selection operator (LASSO) Cox regression method.

RESULTS

Flow cytometry and quantitative immunofluorescence showed similar lymphocytic percentages and TIL subpopulation proportions in the fresh tumor specimens. With the training data, the LASSO model identified four immune features for IRS construction: tumoral FOXP3, tumoral PD-1, stromal FOXP3, and stromal CD8. In both cohorts, a high IRS was significantly associated with tumoral programmed cell death-1 ligand 1 expression, Enneking inappropriate tumor resection, and surrounding muscle invasion by tumor. Multivariate Cox regression and stratified analysis in the two cohorts revealed that the IRS was an independent predictor and could effectively separate patients with similar Enneking staging into different risk subgroups, with significantly different survival rates. Further receiver operating characteristic analysis found that the IRS classifier had a better prognostic value than the traditional clinicopathological factors and compensated for the deficiency of Enneking staging for outcome prediction. More importantly, a nomogram based on the IRS and clinical predictors showed adequate performance in estimating disease recurrence and survival of patients.

CONCLUSIONS

These data support the use of the IRS signature as a reliable prognostic tool in spinal chordoma and may facilitate individualized therapy decision making for patients.

Homological radiomics analysis for prognostic prediction in lung cancer patients

PURPOSE

This study explored a novel homological analysis method for prognostic prediction in lung cancer patients.

MATERIALS AND METHODS

The potential of homology-based radiomic features (HFs) was investigated by comparing HFs to conventional wavelet-based radiomic features (WFs) and combined radiomic features consisting of HFs and WFs (HWFs), using training (n = 135) and validation (n = 70) datasets, and Kaplan-Meier analysis. A total of 13,824 HFs were derived through homology-based texture analysis using Betti numbers, which represent the topologically invariant morphological characteristics of lung cancer. The prognostic potential of HFs was evaluated using statistically significant differences (p-values, log-rank test) to compare the survival curves of high- and low-risk patients. Those patients were stratified into high- and low-risk groups using the medians of the radiomic scores of signatures constructed with an elastic-net-regularized Cox proportional hazard model. Furthermore, deep learning (DL) based on AlexNet was utilized to compare HFs by stratifying patients into the two groups using a network that was pre-trained with over one million natural images from an ImageNet database.

RESULTS

For the training dataset, the p-values between the two survival curves were 6.7 × 10^-6 (HF), 5.9 × 10^-3 (WF), 7.4 × 10^-6 (HWF), and 1.1 × 10^-3 (DL). The p-values for the validation dataset were 3.4 × 10^-5 (HF), 6.7 × 10^-1 (WF), 1.7 × 10^-7 (HWF), and 1.2 × 10^-1 (DL).

CONCLUSION

This study demonstrates the excellent potential of HFs for prognostic prediction in lung cancer patients.

Multi-Level Multi-Modality Fusion Radiomics: Application to PET and CT Imaging for Prognostication of Head and Neck Cancer

To characterize intra-tumor heterogeneity comprehensively, we propose a multi-level fusion strategy to combine PET and CT information at the image-, matrix-and feature-levels towards improved prognosis. Specifically, we developed fusion radiomics in the context of 3 prognostic outcomes in a multi-center setting (4 centers) involving 296 head & neck cancer patients. Eight clinical parameters were first utilized to build a (1) clinical model. We also built models by extracting 127 radiomics features from (2) PET images alone; (3-8) PET and CT images fused via wavelet-based fusion (WF) using CT-weights of 0.2, 0.4, 0.6 and 0.8, gradient transfer fusion (GTF), and guided filtering-based fusion (GFF); (9) fused matrices (sumMat); (10-11) fused features constructed via feature averaging (avgFea) and feature concatenation (conFea); and finally, (12) CT images alone; above models were also expanded to include both clinical and radiomics features. Seven variations of training and testing partitions were investigated. Highest performance in 5, 6 and 5 partitions was achieved by image-level fusion strategies for RFS, MFS and OS prediction, respectively. Among all partitions, WF0.6 and WF0.8 showed significantly higher performance than CT model for RFS (C-index: 0.60 ± 0.04 vs. 0.56 ± 0.03, p-value: 0.015) and MFS (C-index: 0.71 ± 0.13 vs. 0.62 ± 0.08, p-value: 0.020) predictions, respectively. In partition CER 23 vs. 14, WF0.6 significantly outperformed Clinical model for RFS prediction (C-index: 0.67 vs. 0.53, p-value: 0.003); both avgFea and WF0.6 showed C-index of 0.64 and significantly higher than that of PET only (C-index: 0.51, p-value: 0.018 and 0.031, respectively) for OS prediction. Fusion radiomics modeling showed varying improvements compared to single modality models for different outcome predictions in different partitions, highlighting the importance of generalizing radiomics models. Image-level fusion holds potential to capture more useful characteristics.

What can artificial intelligence teach us about the molecular mechanisms underlying disease?

While molecular imaging with positron emission tomography or single-photon emission computed tomography already reports on tumour molecular mechanisms on a macroscopic scale, there is increasing evidence that there are multiple additional features within medical images that can further improve tumour characterization, treatment prediction and prognostication. Early reports have already revealed the power of radiomics to personalize and improve patient management and outcomes. What remains unclear is how these additional metrics relate to underlying molecular mechanisms of disease. Furthermore, the ability to deal with increasingly large amounts of data from medical images and beyond in a rapid, reproducible and transparent manner is essential for future clinical practice. Here, artificial intelligence (AI) may have an impact. AI encompasses a broad range of 'intelligent' functions performed by computers, including language processing, knowledge representation, problem solving and planning. While rule-based algorithms, e.g. computer-aided diagnosis, have been in use for medical imaging since the 1990s, the resurgent interest in AI is related to improvements in computing power and advances in machine learning (ML). In this review we consider why molecular and cellular processes are of interest and which processes have already been exposed to AI and ML methods as reported in the literature. Non-small-cell lung cancer is used as an exemplar and the focus of this review as the most common tumour type in which AI and ML approaches have been tested and to illustrate some of the concepts.

Radiomics signature extracted from diffusion-weighted magnetic resonance imaging predicts outcomes in osteosarcoma

OBJECTIVE

Osteosarcoma often requires multidisciplinary treatment including surgery, chemotherapy and radiotherapy. However, tumor behavior can vary widely among patients and selection of appropriate therapies in any individual patient remains a critical challenge. Radiomics seeks to quantify complex aspects of tumor images under the assumption that this information is related to tumor biology. This study tested the hypothesis that a radiomic signature extracted from Diffusion-weighted magnetic resonance images (DWI-MRI) can improve prediction of overall survival (OS) compared with clinical factors alone in localised osteosarcoma.

MATERIALS/METHODS

Pre-treatment DWI-MRI were collected from 112 patients (9-67 years of age) with histological-proven osteosarcoma that were treated with curative intent. The entire dataset was divided in two subsets: the training and validation cohorts containing 76 and 24% of the data respectively. Clinical data were extracted from our medical record. Two experienced radiotherapists evaluated DWI-MRIs for quality and segmented the tumor. A total of 103 radiomic features were calculated for each image. Least absolute shrinkage and selection operator (LASSO) regression was applied to select features. Association between the radiomics signature and OS was explored. Further validation of the radiomics signature as an independent biomarker was performed by using multivariate Cox regression. The Cox proportional-hazard regression model was also used to analyze the correlation between the prognostic factor and the survival for the clinical (C) model after the univariate analysis. Radiomics (R) model identified radiomics signature, which is the best predictor from the radiomic variable classes based on LASSO regression. Harrell's C-index was used to demonstrate the incremental value of the radiomics signature to the traditional clinical risk factors for the individualized prediction performance.

RESULTS

Cox proportional-hazard regression model shows that: Tumor size, alkaline phosphatase (ALP) status before treatment and number of courses of chemotherapy were proven as the dependent clinical prognostic factors of osteosarcoma's overall survival time. The radiomics signature was significantly associated with OS, independent of clinical risk factors (radiomics signature: HR: 5.11, 95% CI: 2.85, 9.18, P < 0.001). Incorporating the radiomics signature into the coalition (C+R) model resulted in better performance (P < .001) for the estimation of OS (C-index: 0.813; 95% CI: 0.75, 0.89) than with the clinical (C) model (C-index: 0.764; 95% CI: 0.69, 0.85), or the single radiomics (R) model (C-index: 0.712; 95% CI: 0.65, 0.78).

CONCLUSION

This study shows that the radiomics signature extracted from pre-treatment DWI-MRI improve prediction of OS over clinical features alone. Combination of the radiomics signature and the traditional clinical risk factors performed better for individualized OS estimation in patients with osteosarcoma, which might enable a step forward precise medicine. This method may help better select patients most likely to benefit from intensified multimodality diagnosis and therapies. Future studies will focus on multi-center validation of an optimized model.

Study Progress of Radiomics With Machine Learning for Precision Medicine in Bladder Cancer Management

Bladder cancer is a fatal cancer that happens in the genitourinary tract with quite high morbidity and mortality annually. The high level of recurrence rate ranging from 50 to 80% makes bladder cancer one of the most challenging and costly diseases to manage. Faced with various problems in existing methods, a recently emerging concept for the measurement of imaging biomarkers and extraction of quantitative features called "radiomics" shows great potential in the application of detection, grading, and follow-up management of bladder cancer. Furthermore, machine-learning (ML) algorithms on the basis of "big data" are fueling the powers of radiomics for bladder cancer monitoring in the era of precision medicine. Currently, the usefulness of the novel combination of radiomics and ML has been demonstrated by a large number of successful cases. It possesses outstanding strengths including non-invasiveness, low cost, and high efficiency, which may serve as a revolution to tumor assessment and emancipate workforce. However, for the extensive clinical application in the future, more efforts should be made to break down the limitations caused by technology deficiencies, inherent problems during the process of radiomic analysis, as well as the quality of present studies.

Discovery of stable and prognostic CT-based radiomic features independent of contrast administration and dimensionality in oesophageal cancer

The aim of this work was to investigate radiomic analysis of contrast and non-contrast enhanced planning CT images of oesophageal cancer (OC) patients in terms of stability, dimensionality and contrast agent dependency. The prognostic significance of CT-based radiomic features was also evaluated. Different 2D and 3D radiomic features were extracted from contrast and non-contrast enhanced CT images of 213 patients from the multi-centre SCOPE1 randomised controlled trial (RCT) in OC. Feature stability was evaluated by randomly dividing patients into three groups and identifying textures with similar distributions among groups with a Kruskal-Wallis analysis. A paired two-sided Wilcoxon signed rank test was used to assess for significant differences in the remaining corresponding 2D and 3D stable features. A prognostic model was constructed using clinical characteristics and remaining filtered features. The discriminative ability of significant variables was tested using Kaplan-Meier analysis. A total of 238 2D and 3D radiomic features were computed from oesophageal CT images. More than 75 features were stable if extracted from homogeneous cohort (contrast or non-contrast enhanced CT images) and inhomogeneous cohort (contrast and non-contrast enhanced CT images). Among the remaining corresponding stable features computed from both cohorts, only 4 features did not show a statistically significant difference if obtained in 2D or in 3D (p-value < 0.05). A Cox regression model constructed using 5 clinical variables (age, sex, tumour, node and metastasis (TNM) stage, WHO performance status and contrast administration) and 4 radiomic variables (inverse varianceGLCM, large distance emphasisGLDZM, zone distance non uniformity normGLDZM, zone distance varianceGLDZM), identified one radiomic feature (zone distance varianceGLDZM) that was significantly associated with overall survival (p-value = 0.032, HR = 1.25, 95% CI = 1.02-1.52). A significant difference in overall survival between groups was found when considering a threshold of zone distance varianceGLDZM equals to 1.70 (X2 = 7.692, df = 1, p-value = 0.006). Zone distance varianceGLDZM was identified as the only stable CT radiomic feature statistically correlated with overall survival, independent of dimensionality and contrast administration. This feature was able to identify high-risk patients and if validated, could be the subject of a future clinical trial aiming to improve clinical decision making and personalise OC treatment.

Pretreatment 18F-FDG PET/CT Radiomics Predict Local Recurrence in Patients Treated with Stereotactic Body Radiotherapy for Early-Stage Non-Small Cell Lung Cancer: A Multicentric Study

The aim of this retrospective multicentric study was to develop and evaluate a prognostic ¹⁸F-FDG PET/CT radiomic signature in early-stage non-small cell lung cancer patients treated with stereotactic body radiotherapy (SBRT). Methods: Patients from 3 different centers (n = 27, 29, and 8) were pooled to constitute the training set, whereas the patients from a fourth center (n = 23) were used as the testing set. The primary endpoint was local control. The primary tumor was semiautomatically delineated in the PET images using the fuzzy locally adaptive Bayesian algorithm, and manually in the low-dose CT images. In total, 184 Image Biomarkers Standardization Initiative-compliant radiomic features were extracted. Seven clinical and treatment parameters were included. We used ComBat to harmonize radiomic features extracted from the 4 institutions relying on different PET/CT scanners. In the training set, variables found significant in the univariate analysis were fed into a multivariate regression model, and models were built by combining independent prognostic factors. Results: Median follow-up was 21.1 mo (range, 1.7-63.4 mo) and 25.5 mo (range, 7.7-57.8 mo) in training and testing sets, respectively. In univariate analysis, none of the clinical variables, 2 PET features, and 2 CT features were significantly predictive of local control. The best predictive models in the training set were obtained by combining one feature from PET (Information Correlation 2) and one feature from CT (flatness), reaching a sensitivity of 100% and a specificity of 96%. Another model combining 2 PET features (Information Correlation 2 and strength) reached sensitivity of 100% and specificity of 88%, both with an undefined hazard ratio (P < 0.001). The latter model obtained an accuracy of 0.91 (sensitivity, 100%; specificity, 81%), with a hazard ratio undefined (P = 0.023) in the testing set; however, other models relying on CT radiomic features only or the combination of PET and CT features failed to validate in the testing set. Conclusion: We showed that 2 radiomic features derived from ¹⁸F-FDG PET were independently associated with local control in patients with non-small cell lung cancer undergoing SBRT and could be combined in an accurate predictive model. This model could provide local relapse-related information and could be helpful in clinical decision making.