Quantification of intra-tumour cell proliferation heterogeneity using imaging descriptors of 18F fluorothymidine-positron emission tomography

Application of Artificial Intelligence in Oncologic Molecular PET-Imaging: A Narrative Review on Beyond [18F]F-FDG Tracers Part II. [18F]F-FLT, [18F]F-FET, [11C]C-MET and Other Less-Commonly Used Radiotracers

Following the previous part of the narrative review on artificial intelligence (AI) applications in positron emission tomography (PET) using tracers rather than 18F-fluorodeoxyglucose ([18F]F-FDG), in this part we review the impact of PET-derived radiomics data on the diagnostic performance of other PET radiotracers, 18F-O-(2-fluoroethyl)-L-tyrosine ([18F]F-FET), 18F-Fluorothymidine ([18F]F-FLT) and 11C-Methionine ([11C]C-MET). [18F]F-FET-PET, using an artificial amino acid taken up into upregulated tumoral cells, showed potential in lesion detection and tumor characterization, especially with its ability to reflect glioma heterogeneity. [18F]F-FET-PET-derived textural features appeared to have the potential to reveal considerable information for accurate delineation for guiding biopsy and treatment, differentiate between low-grade and high-grade glioma and related wild-type genotypes, and distinguish pseudoprogression from true progression. In addition, models built using clinical parameters and [18F]F-FET-PET-derived radiomics features showed acceptable results for survival stratification of glioblastoma patients. [18F]F-FLT-PET-based characteristics also showed potential in evaluating glioma patients, correlating with Ki-67 and patient prognosis. AI-based PET-volumetry using this radiotracer as a proliferation marker also revealed promising preliminary results in terms of guide-targeting bone marrow-preserving adaptive radiation therapy. Similar to [18F]F-FET, the other amino acid tracer which reflects cellular proliferation, [11C]C-MET, has also shown acceptable performance in predicting tumor grade, distinguishing brain tumor recurrence from radiation necrosis, and treatment monitoring by PET-derived radiomics models. In addition, PET-derived radiomics features of various radiotracers such as [18F]F-DOPA, [18F]F-FACBC, [18F]F-NaF, [68Ga]Ga-CXCR-4 and [18F]F-FMISO may also provide useful information for tumor characterization and predict of disease outcome. In conclusion, AI using tracers beyond [18F]F-FDG could improve the diagnostic performance of PET-imaging for specific indications and help clinicians in their daily routine by providing features that are often not detectable by the naked eye.

Metabolic Imaging as a Tool to Characterize Chemoresistance and Guide Therapy in Triple-Negative Breast Cancer (TNBC)

After an initial response to chemotherapy, tumor relapse is frequent. This event is reflective of both the spatiotemporal heterogeneities of the tumor microenvironment as well as the evolutionary propensity of cancer cell populations to adapt to variable conditions. Because the cause of this adaptation could be genetic or epigenetic, studying phenotypic properties such as tumor metabolism is useful as it reflects molecular, cellular, and tissue-level dynamics. In triple-negative breast cancer (TNBC), the characteristic metabolic phenotype is a highly fermentative state. However, during treatment, the spatial and temporal dynamics of the metabolic landscape are highly unstable, with surviving populations taking on a variety of metabolic states. Thus, longitudinally imaging tumor metabolism provides a promising approach to inform therapeutic strategies, and to monitor treatment responses to understand and mitigate recurrence. Here we summarize some examples of the metabolic plasticity reported in TNBC following chemotherapy and review the current metabolic imaging techniques available in monitoring chemotherapy responses clinically and preclinically. The ensemble of imaging technologies we describe has distinct attributes that make them uniquely suited for a particular length scale, biological model, and/or features that can be captured. We focus on TNBC to highlight the potential of each of these technological advances in understanding evolution-based therapeutic resistance.

PET-Derived Radiomics and Artificial Intelligence in Breast Cancer: A Systematic Review

Breast cancer (BC) is a heterogeneous malignancy that still represents the second cause of cancer-related death among women worldwide. Due to the heterogeneity of BC, the correct identification of valuable biomarkers able to predict tumor biology and the best treatment approaches are still far from clear. Although molecular imaging with positron emission tomography/computed tomography (PET/CT) has improved the characterization of BC, these methods are not free from drawbacks. In recent years, radiomics and artificial intelligence (AI) have been playing an important role in the detection of several features normally unseen by the human eye in medical images. The present review provides a summary of the current status of radiomics and AI in different clinical settings of BC. A systematic search of PubMed, Web of Science and Scopus was conducted, including all articles published in English that explored radiomics and AI analyses of PET/CT images in BC. Several studies have demonstrated the potential role of such new features for the staging and prognosis as well as the assessment of biological characteristics. Radiomics and AI features appear to be promising in different clinical settings of BC, although larger prospective trials are needed to confirm and to standardize this evidence.

Haralick texture features extracted from Ga-68 PSMA PET/CT to differentiate normal prostate from prostate cancer: a feasibility study

OBJECTIVE

Role of texture parameters on the basis of Ga-68 PSMA PET/CT in prostate cancer (Pca) is largely unexplored. Present work done is a preliminary study that aims to evaluate the role of Haralick texture features on the basis of Ga-68 PSMA PET/CT in Pca in which texture features were used to differentiate between normal prostate and Pca tissue.

METHODS

The study retrospectively enrolled patients in two groups: group 1 included 30 patients with biopsy-proven adenocarcinoma prostate and median age 64 years (range: 50-82 years) who underwent baseline Ga-68 PSMA PET/CT prior to therapy; group 2 included 24 patients with pathologies other than Pca and median age 53.5 years (range: 18-80 years) who underwent Ga-68 PSMA PET/CT as part of another study in our department. Patients in group 2 did not have any prostate pathology and served as controls for the study. The segmented images of prostate (3-D image) were used to calculate 11 Haralick texture features in MATLAB. SUVmax was also evaluated. All parameters were compared among the two groups using appropriate statistical analysis and P value <0.05 was considered significant.

RESULTS

All 11 Haralick texture features, as well as SUVmax, were significantly different among Pca and controls (P < 0.05). Among the texture features, contrast was most significant (P value of Mann-Whitney U <0.001) in differentiating Pca from normal prostate with AUROC curve of 82.9% with sensitivity and specificity 83.30% and 73.30%, respectively at cut-off 0.640. SUVmax was also significant with AUROC curve 94.0% and sensitivity and specificity 62.5% and 90%, respectively at cut-off 5.7. A significant negative correlation of SUVmax was observed with contrast.

CONCLUSION

Haralick texture features have a significant role in differentiating Pca and normal prostate.

Radiomics feature reliability assessed by intraclass correlation coefficient: a systematic review

Radiomics research is rapidly growing in recent years, but more concerns on radiomics reliability are also raised. This review attempts to update and overview the current status of radiomics reliability research in the ever expanding medical literature from the perspective of a single reliability metric of intraclass correlation coefficient (ICC). To conduct this systematic review, Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. After literature search and selection, a total of 481 radiomics studies using CT, PET, or MRI, covering a wide range of subject and disease types, were included for review. In these highly heterogeneous studies, feature reliability to image segmentation was much more investigated than reliability to other factors, such as image acquisition, reconstruction, post-processing, and feature quantification. The reported ICCs also suggested high radiomics feature reliability to image segmentation. Image acquisition was found to introduce much more feature variability than image segmentation, in particular for MRI, based on the reported ICC values. Image post-processing and feature quantification yielded different levels of radiomics reliability and might be used to mitigate image acquisition-induced variability. Some common flaws and pitfalls in ICC use were identified, and suggestions on better ICC use were given. Due to the extremely high study heterogeneities and possible risks of bias, the degree of radiomics feature reliability that has been achieved could not yet be safely synthesized or derived in this review. More future researches on radiomics reliability are warranted.

The exploration of quantitative intra-tumoral metabolic heterogeneity in dual-time 18F-FDG PET/CT of pancreatic cancer

PURPOSE

We aimed to analyze the change of quantitative intra-tumoral metabolic heterogeneity consisting of texture features and conventional metabolic parameters of pancreatic cancer (PC) in dual-time 2-deoxy-2(18F) fluoro-D-glucose (18F-FDG) positron emission tomography-computed tomography (PET/CT).

METHODS

A retrospective analysis was conducted considering the texture features and conventional metabolic parameters in dual-time 18F-FDG PET/CT scans of PC patients. Features were extracted based on spatial distribution of 18F-FDG uptake in image. Firstly, the texture features and the conventional metabolic parameters of the delayed scan were both compared with that of the early scan. Statistically different data was defined among them. Secondly, the study evaluated the correlations between retention index (RI) of the texture features and the conventional metabolic parameters. Finally, the variation of texture features in dual-time PET/CT of resectable PC patients and unresectable PC patients was calculated separately.

RESULTS

In total, 183 PC patients were analyzed retrospectively in this research. The conventional metabolic parameters were all statistically different between the early and delayed scans except for metabolic tumor volume (MTV). In the radiomics, there were 59 textural features. Nineteen of 59 texture features were statistically different between the early and delayed scans. Features that were more than 10% different during two scans were observed in a substantial percentage of patients. Weak correlations were only found between MTV, TLG (Total lesion glycolysis), SUVpeak and the RI of some texture features in early or delayed scans. There were obviously fewer features with significant difference in resectable PC group than in unresectable PC group. Most features showing the difference in unresectable group while no significant difference in resectable group.

CONCLUSIONS

This study investigated the change and inner correlations of quantitative tumoral metabolic heterogeneity in the dual-time 18F-FDG-PET/CT scan of PC patients. Some features displayed the difference between dual-time scans. Conventional metabolic parameters were weakly related to the change of texture feature. The change of texture feature in resectable PC group was different from that in unresectable PC group. This result is potential to provide more information for the image evaluation of PC.

Why did European Radiology reject my radiomic biomarker paper? How to correctly evaluate imaging biomarkers in a clinical setting

This review explains in simple terms, accessible to the non-statistician, general principles regarding the correct research methods to develop and then evaluate imaging biomarkers in a clinical setting, including radiomic biomarkers. The distinction between diagnostic and prognostic biomarkers is made and emphasis placed on the need to assess clinical utility within the context of a multivariable model. Such models should not be restricted to imaging biomarkers and must include relevant disease and patient characteristics likely to be clinically useful. Biomarker utility is based on whether its addition to the basic clinical model improves diagnosis or prediction. Approaches to both model development and evaluation are explained and the need for adequate amounts of representative data stressed so as to avoid underpowering and overfitting. Advice is provided regarding how to report the research correctly. KEY POINTS: • Imaging biomarker research is common but methodological errors are encountered frequently that may mean the research is not clinically useful. • The clinical utility of imaging biomarkers is best assessed by their additive effect on multivariable models based on clinical factors known to be important. • The data used to develop such models should be sufficient for the number of variables investigated and the model should be evaluated, preferably using data unrelated to development.

A Phantom Study to Investigate Robustness and Reproducibility of Grey Level Co-Occurrence Matrix (GLCM)-Based Radiomics Features for PET

Quantification and classification of heterogeneous radiotracer uptake in Positron Emission Tomography (PET) using textural features (termed as radiomics) and artificial intelligence (AI) has the potential to be used as a biomarker of diagnosis and prognosis. However, textural features have been predicted to be strongly correlated with volume, segmentation and quantization, while the impact of image contrast and noise has not been assessed systematically. Further continuous investigations are required to update the existing standardization initiatives. This study aimed to investigate the relationships between textural features and these factors with 18F filled torso NEMA phantom to yield different contrasts and reconstructed with different durations to represent varying levels of noise. The phantom was also scanned with heterogeneous spherical inserts fabricated with 3D printing technology. All spheres were delineated using: (1) the exact boundaries based on their known diameters; (2) 40% fixed; and (3) adaptive threshold. Six textural features were derived from the gray level co-occurrence matrix (GLCM) using different quantization levels. The results indicate that homogeneity and dissimilarity are the most suitable for measuring PET tumor heterogeneity with quantization 64 provided that the segmentation method is robust to noise and contrast variations. To use these textural features as prognostic biomarkers, changes in textural features between baseline and treatment scans should always be reported along with the changes in volumes.

3D DESI-MS lipid imaging in a xenograft model of glioblastoma: a proof of principle

Desorption electrospray ionisation mass spectrometry (DESI-MS) can image hundreds of molecules in a 2D tissue section, making it an ideal tool for mapping tumour heterogeneity. Tumour lipid metabolism has gained increasing attention over the past decade; and here, lipid heterogeneity has been visualised in a glioblastoma xenograft tumour using 3D DESI-MS imaging. The use of an automatic slide loader automates 3D imaging for high sample-throughput. Glioblastomas are highly aggressive primary brain tumours, which display heterogeneous characteristics and are resistant to chemotherapy and radiotherapy. It is therefore important to understand biochemical contributions to their heterogeneity, which may be contributing to treatment resistance. Adjacent sections to those used for DESI-MS imaging were used for H&E staining and immunofluorescence to identify different histological regions, and areas of hypoxia. Comparing DESI-MS imaging with biological staining allowed association of different lipid species with hypoxic and viable tissue within the tumour, and hence mapping of molecularly different tumour regions in 3D space. This work highlights that lipids are playing an important role in the heterogeneity of this xenograft tumour model, and DESI-MS imaging can be used for lipid 3D imaging in an automated fashion to reveal heterogeneity, which is not apparent in H&E stains alone.

Beyond tissue biopsy: a diagnostic framework to address tumor heterogeneity in lung cancer

PURPOSE OF REVIEW

The objective of this review is to discuss the strength and limitations of tissue and liquid biopsy and functional imaging to capture spatial and temporal tumor heterogeneity either alone or as part of a diagnostic framework in non-small cell lung cancer (NSCLC).

RECENT FINDINGS

NSCLC displays genetic and phenotypic heterogeneity - a detailed knowledge of which is crucial to personalize treatment. Tissue biopsy often lacks spatial and temporal resolution. Thus, NSCLC needs to be characterized by complementary diagnostic methods to resolve heterogeneity. Liquid biopsy offers detection of tumor biomarkers and for example, the classification and monitoring of EGFR mutations in NSCLC. It allows repeated sampling, and therefore, appears promising to address temporal aspects of tumor heterogeneity. Functional imaging methods and emerging image analytic tools, such as radiomics capture temporal and spatial heterogeneity. Further standardization of radiomics is required to allow introduction into clinical routine.

SUMMARY

To augment the potential of precision therapy, improved diagnostic characterization of tumors is pivotal. We suggest a comprehensive diagnostic framework combining tissue and liquid biopsy and functional imaging to address the known aspects of spatial and temporal tumor heterogeneity on the example of NSCLC. We envision how this framework might be implemented in clinical practice.

Intratumoral heterogeneity of hepatocellular carcinoma: From single-cell to population-based studies

Hepatocellular carcinoma (HCC) is characterized by high heterogeneity in both intratumoral and interpatient manners. While interpatient heterogeneity is related to personalized therapy, intratumoral heterogeneity (ITH) largely influences the efficacy of therapies in individuals. ITH contributes to tumor growth, metastasis, recurrence, and drug resistance and consequently limits the prognosis of patients with HCC. There is an urgent need to understand the causes, characteristics, and consequences of tumor heterogeneity in HCC for the purposes of guiding clinical practice and improving survival. Here, we summarize the studies and technologies that describe ITH in HCC to gain insight into the origin and evolutionary process of heterogeneity. In parallel, evidence is collected to delineate the dynamic relationship between ITH and the tumor ecosystem. We suggest that conducting comprehensive studies of ITH using single-cell approaches in temporal and spatial dimensions, combined with population-based clinical trials, will help to clarify the clinical implications of ITH, develop novel intervention strategies, and improve patient prognosis.

Transcriptomics in cancer revealed by Positron Emission Tomography radiomics

Metabolic images from Positron Emission Tomography (PET) are used routinely for diagnosis, follow-up or treatment planning purposes of cancer patients. In this study we aimed at determining if radiomic features extracted from 18F-Fluoro Deoxy Glucose (FDG) PET images could mirror tumor transcriptomics. In this study we analyzed 45 patients with locally advanced head and neck cancer (H&N) that underwent FDG-PET scans at the time of diagnosis and transcriptome analysis using RNAs from both cancer and healthy tissues on microarrays. Association between PET radiomics and transcriptomics was carried out with the Genomica software and a functional annotation was used to associate PET radiomics, gene expression and altered biological pathways. We identified relationships between PET radiomics and genes involved in cell-cycle, disease, DNA repair, extracellular matrix organization, immune system, metabolism or signal transduction pathways, according to the Reactome classification. Our results suggest that these FDG PET radiomic features could be used to infer tissue gene expression and cellular pathway activity in H&N cancers. These observations strengthen the value of radiomics as a promising approach to personalize treatments through targeting tumor-specific molecular processes.

FLT PET Radiomics for Response Prediction to Chemoradiation Therapy in Head and Neck Squamous Cell Cancer

Radiomics is an image analysis approach for extracting large amounts of quantitative information from medical images using a variety of computational methods. Our goal was to evaluate the utility of radiomic feature analysis from ¹⁸F-fluorothymidine positron emission tomography (FLT PET) obtained at baseline in prediction of treatment response in patients with head and neck cancer. Thirty patients with advanced-stage oropharyngeal or laryngeal cancer, treated with definitive chemoradiation therapy, underwent FLT PET imaging before treatment. In total, 377 radiomic features of FLT uptake and feature variants were extracted from volumes of interest; these features variants were defined by either the primary tumor or the total lesion burden, which consisted of the primary tumor and all FLT-avid nodes. Feature variants included normalized measurements of uptake, which were calculated by dividing lesion uptake values by the mean uptake value in the bone marrow. Feature reduction was performed using clustering to remove redundancy, leaving 172 representative features. Effects of these features on progression-free survival were modeled with Cox regression and P-values corrected for multiple comparisons. In total, 9 features were considered significant. Our results suggest that smaller, more homogenous lesions at baseline were associated with better prognosis. In addition, features extracted from total lesion burden had a higher concordance index than primary tumor features for 8 of the 9 significant features. Furthermore, total lesion burden features showed lower interobserver variability.

PET/CT radiomics in breast cancer: Mind the step

The aim of the present review was to assess the current status of positron emission tomography/computed tomography (PET/CT) radiomics research in breast cancer, and in particular to analyze the strengths and weaknesses of the published papers in order to identify challenges and suggest possible solutions and future research directions. Various combinations of the terms "breast", "radiomic", "PET", "radiomics", "texture", and "textural" were used for the literature search, extended until 8 July 2019, within the PubMed/MEDLINE database. Twenty-six articles fulfilling the inclusion/exclusion criteria were retrieved in full text and analyzed. The studies had technical and clinical objectives, including diagnosis, biological characterization (correlation with histology, molecular subtypes and IHC marker expression), prediction of response to neoadjuvant chemotherapy, staging, and outcome prediction. We reviewed and discussed the selected investigations following the radiomics workflow steps related to the clinical, technical, analysis, and reporting issues. Most of the current evidence on the clinical role of PET/CT radiomics in breast cancer is at the feasibility level. Harmonized methods in image acquisition, post-processing and features calculation, predictive models and classifiers trained and validated on sufficiently representative datasets, adherence to consensus guidelines, and transparent reporting will give validity and generalizability to the results.

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.

Texture analysis of pretreatment [18F]FDG PET/CT for the prognostic prediction of locally advanced salivary gland carcinoma treated with interstitial brachytherapy

Background

The aim of this study was to evaluate the prognostic value of positron emission tomography (PET) parameters and the PET texture features of fluorine 18-fluorodeoxyglucose ([¹⁸F]FDG) uptake on pretreatment PET/computed tomography (CT) in patients with locally advanced salivary gland carcinoma treated with interstitial brachytherapy.

Methods

Forty-three patients with locally advanced salivary gland carcinoma of the head and neck were treated with ¹²⁵I interstitial brachytherapy as the sole modality and underwent [¹⁸F]FDG PET/CT scanning before treatment. Tumor segmentation and texture analysis were performed using the 3D slicer software. In total, 54 features were extracted and categorized as first-order statistics, morphology and shape, gray-level co-occurrence matrix, and gray-level run length matrix. Up to November 2018, the follow-up time ranged from 6 to 120 months (median 18 months). Cumulative survival was calculated by the Kaplan-Meier method. Factors between groups were compared by the log-rank test. Multivariate Cox regression analysis with a backward conditional method was used to predict progression-free survival (PFS).

Results

The 3- and 5-year locoregional control (LC) rates were 55.4% and 37.0%, respectively. The 3- and 5-year PFS rates were 51.2% and 34.1%, respectively. The 3- and 5-year overall survival (OS) rates were 77.0% and 77.0%, respectively. Univariate analysis revealed that minimum intensity, mean intensity, median intensity, root mean square, and long run emphasis (LRE) were significant predictors of PFS, whereas clinicopathological factors, conventional PET parameters, and PET texture features failed to show significance. Multivariate Cox regression analysis showed that minimum intensity and LRE were significant predictors of PFS.

Conclusions

The texture analysis of pretreatment [¹⁸F]FDG PET/CT provided more information than conventional PET parameters for predicting patient prognosis of locally advanced salivary gland carcinoma treated with interstitial brachytherapy. The minimum intensity was a risk factor for PFS, and LRE was a favorable factor in prognostic prediction according to the primary results.

3'-Deoxy-3'-[18F]Fluorothymidine Positron Emission Tomography Depicts Heterogeneous Proliferation Pathology in Idiopathic Pulmonary Arterial Hypertension Patient Lung

BACKGROUND

Pulmonary vascular cell hyperproliferation is characteristic of pulmonary vascular remodeling in pulmonary arterial hypertension. A noninvasive imaging biomarker is needed to track the pathology and assess the response to novel treatments targeted at resolving the structural changes. Here, we evaluated the application of radioligand 3'-deoxy-3'-[18F]-fluorothymidine (¹⁸FLT) using positron emission tomography.

METHODS AND RESULTS

We performed dynamic ¹⁸FLT positron emission tomography in 8 patients with idiopathic pulmonary arterial hypertension (IPAH) and applied in-depth kinetic analysis with a reversible 2-compartment 4k model. Our results show significantly increased lung ¹⁸FLT phosphorylation (k₃) in patients with IPAH compared with nonpulmonary arterial hypertension controls (0.086±0.034 versus 0.054±0.009 min^-1; P<0.05). There was heterogeneity in the lung ¹⁸FLT signal both between patients with IPAH and within the lungs of each patient, compatible with histopathologic reports of lungs from patients with IPAH. Consistent with ¹⁸FLT positron emission tomographic data, TK1 (thymidine kinase 1) expression was evident in the remodeled vessels in IPAH patient lung. In addition, hyperproliferative pulmonary vascular fibroblasts isolated from patients with IPAH exhibited upregulated expression of TK1 and the thymidine transporter, ENT1 (equilibrative nucleoside transporter 1). In the monocrotaline and SuHx (Sugen hypoxia) rat pulmonary arterial hypertension models, increased lung ¹⁸FLT uptake was strongly associated with peripheral pulmonary vascular muscularization and the proliferation marker, Ki-67 score, together with prominent TK1 expression in remodeled vessels. Importantly, lung ¹⁸FLT uptake was attenuated by 2 antiproliferative treatments: dichloroacetate and the tyrosine kinase inhibitor, imatinib.

CONCLUSIONS

Dynamic ¹⁸FLT positron emission tomography imaging can be used to report hyperproliferation in pulmonary hypertension and merits further study to evaluate response to treatment in patients with IPAH.

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

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

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

PURPOSE

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

PATIENTS AND METHODS

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

RESULTS

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

CONCLUSION

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

Challenges and Promises of PET Radiomics

PURPOSE

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

METHODS AND MATERIALS

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

RESULTS

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

CONCLUSIONS

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

Breast cancer intratumour heterogeneity: current status and clinical implications

Breast cancer (BC) is a heterogeneous disease that varies in presentation, morphological features, behaviour, and response to therapy. High-throughput molecular profiling studies have revolutionised our understanding of BC heterogeneity, and have demonstrated that molecular profiles of tumours are variable not only between tumours, but also within individual tumours. Current evidence indicates that spatial and temporal intratumour heterogeneity of BC exists at levels beyond what are commonly expected. Intratumour heterogeneity poses critical challenges in the diagnosis, prediction of behaviour and management of BC. For instance, heterogeneous expression of oestrogen receptor, progesterone receptor and human epidermal growth factor receptor 2 can be seen not only in primary tumours between different regions, but also between primary tumours and their corresponding metastatic/recurrent lesions. The demonstration of molecularly distinct subclones within individual tumours may explain, at least in part, the mechanisms controlling the variable behaviour of BC, and may change our approach to BC sampling and treatment. In this review, BC intratumour heterogeneity is highlighted, with a special emphasis on the current knowledge pertaining to the relationship between intratumour heterogeneity and BC pathogenesis, evolution, and progression, with consideration of its impact on disease diagnosis, management, and the emergence of novel therapeutic targets. The key role of high-throughput molecular and imaging techniques is also addressed.

Machine learning based brain tumour segmentation on limited data using local texture and abnormality

Brain tumour segmentation in medical images is a very challenging task due to the large variety in tumour shape, position, appearance, scanning modalities and scanning parameters. Most existing segmentation algorithms use information from four different MRI-sequences, but since this is often not available, there is need for a method able to delineate the different tumour tissues based on a minimal amount of data. We present a novel approach using a Random Forests model combining voxelwise texture and abnormality features on a contrast-enhanced T1 and FLAIR MRI. We transform the two scans into 275 feature maps. A random forest model next calculates the probability to belong to 4 tumour classes or 5 normal classes. Afterwards, a dedicated voxel clustering algorithm provides the final tumour segmentation. We trained our method on the BraTS 2013 database and validated it on the larger BraTS 2017 dataset. We achieve median Dice scores of 40.9% (low-grade glioma) and 75.0% (high-grade glioma) to delineate the active tumour, and 68.4%/80.1% for the total abnormal region including edema. Our fully automated brain tumour segmentation algorithm is able to delineate contrast enhancing tissue and oedema with high accuracy based only on post-contrast T1-weighted and FLAIR MRI, whereas for non-enhancing tumour tissue and necrosis only moderate results are obtained. This makes the method especially suitable for high-grade glioma.

Prediction of tumor biological characteristics in different colorectal cancer liver metastasis animal models using 18F-FDG and 18F-FLT

BACKGROUND

Positron emission tomography (PET) is a noninvasive method to characterize different metabolic activities of tumors, providing information for staging, prognosis, and therapeutic response of patients with cancer. The aim of this study was to evaluate the feasibility of ¹⁸F-fludeoxyglucose (¹⁸F-FDG) and 3'-deoxy-3'-¹⁸F-fluorothymidine (¹⁸F-FLT) PET in predicting tumor biological characteristics of colorectal cancer liver metastasis.

METHODS

The uptake rate of ¹⁸F-FDG and ¹⁸F-FLT in SW480 and SW620 cells was measured via an in vitro cell uptake assay. The region of interest was drawn over the tumor and liver to calculate the maximum standardized uptake value ratio (tumor/liver) from PET images in liver metastasis model. The correlation between tracer uptake in liver metastases and VEGF, Ki67 and CD44 expression was evaluated by linear regression.

RESULTS

Compared to SW620 tumor-bearing mice, SW480 tumor-bearing mice presented a higher rate of liver metastases. The uptake rate of ¹⁸F-FDG in SW480 and SW620 cells was 6.07% ± 1.19% and 2.82% ± 0.15%, respectively (t = 4.69, P = 0.04); that of ¹⁸F-FLT was 24.81% ± 0.45% and 15.57% ± 0.66%, respectively (t = 19.99, P < 0.001). Micro-PET scan showed that all parameters of FLT were significantly higher in SW480 tumors than those in SW620 tumors. A moderate relationship was detected between metastases in the liver and ¹⁸F-FLT uptake in primary tumors (r = 0.73, P = 0.0019). ¹⁸F-FLT uptake was also positively correlated with the expression of CD44 in liver metastases (r = 0.81, P = 0.0049).

CONCLUSIONS

The uptake of ¹⁸F-FLT in metastatic tumor reflects different biological behaviors of colon cancer cells. ¹⁸F-FLT can be used to evaluate the metastatic potential of colorectal cancer in nude mice.

Validation of [18F]FLT as a perfusion-independent imaging biomarker of tumour response in EGFR-mutated NSCLC patients undergoing treatment with an EGFR tyrosine kinase inhibitor

Background

3′-Deoxy-3′-[¹⁸F]fluorothymidine ([¹⁸F]FLT) was proposed as an imaging biomarker for the assessment of in vivo cellular proliferation with positron emission tomography (PET). The current study aimed to validate [¹⁸F]FLT as a perfusion-independent PET tracer, by gaining insight in the intra-tumoural relationship between [¹⁸F]FLT uptake and perfusion in non-small cell lung cancer (NSCLC) patients undergoing treatment with a tyrosine kinase inhibitor (TKI).

Six patients with metastatic NSCLC, having an activating epidermal growth factor receptor (EGFR) mutation, were included in this study. Patients underwent [¹⁵O]H₂O and [¹⁸F]FLT PET/CT scans at three time points: before treatment and 7 and 28 days after treatment with a TKI (erlotinib or gefitinib). Parametric analyses were performed to generate quantitative 3D images of both perfusion measured with [¹⁵O]H₂O and proliferation measured with [¹⁸F]FLT volume of distribution (V_T). A multiparametric classification was performed by classifying voxels as low and high perfusion and/or low and high [¹⁸F]FLT V_T using a single global threshold for all scans and subjects. By combining these initial classifications, voxels were allocated to four categories (low perfusion-low V_T, low perfusion-high V_T, high perfusion-low V_T and high perfusion-high V_T).

Results

A total of 17 perfusion and 18 [¹⁸F]FLT PET/CT scans were evaluated. The average tumour values across all lesions were 0.53 ± 0.26 mL cm^− 3 min^− 1 and 4.25 ± 1.71 mL cm^− 3 for perfusion and [¹⁸F]FLT V_T, respectively. Multiparametric analysis suggested a shift in voxel distribution, particularly regarding the V_T: from an average of ≥ 77% voxels classified in the “high V_T category” to ≥ 85% voxels classified in the “low V_T category”. The shift was most prominent 7 days after treatment and remained relatively similar afterwards. Changes in perfusion and its spatial distribution were minimal.

Conclusion

The present study suggests that [¹⁸F]FLT might be a perfusion-independent PET tracer for measuring tumour response as parametric changes in [¹⁸F]FLT uptake occurred independent from changes in perfusion.

Trial registration

Nederlands Trial Register (NTR), NTR3557. Registered 2 August 2012

Electronic supplementary material

The online version of this article (10.1186/s13550-018-0376-6) contains supplementary material, which is available to authorized users.

A Novel Framework for Automated Segmentation and Labeling of Homogeneous Versus Heterogeneous Lung Tumors in [18F]FDG-PET Imaging

PURPOSE

Determination of intra-tumor high-uptake area using 2-deoxy-2-[¹⁸F]fluoro-D-glucose ([¹⁸F]FDG) positron emission tomography (PET) imaging is an important consideration for dose painting in radiation treatment applications. The aim of our study was to develop a framework towards automated segmentation and labeling of homogeneous vs. heterogeneous tumors in clinical lung [¹⁸F]FDG-PET with the capability of intra-tumor high-uptake region delineation.

PROCEDURES

We utilized and extended a fuzzy random walk PET tumor segmentation algorithm to delineate intra-tumor high-uptake areas. Tumor textural feature (TF) analysis was used to find a relationship between tumor type and TF values. Segmentation accuracy was evaluated quantitatively utilizing 70 clinical [¹⁸F]FDG-PET lung images of patients with a total of 150 solid tumors. For volumetric analysis, the Dice similarity coefficient (DSC) and Hausdorff distance (HD) measures were extracted with respect to gold-standard manual segmentation. A multi-linear regression model was also proposed for automated tumor labeling based on TFs, including cross-validation analysis.

RESULTS

Two-tailed t test analysis of TFs between homogeneous and heterogeneous tumors revealed significant statistical difference for size-zone variability (SZV), intensity variability (IV), zone percentage (ZP), proposed parameters II and III, entropy and tumor volume (p < 0.001), dissimilarity, high intensity emphasis (HIE), and SUV_min (p < 0.01). Lower statistical differences were observed for proposed parameter I (p = 0.02), and no significant differences were observed for SUV_max and SUV_mean. Furthermore, the Spearman rank analysis between visual tumor labeling and TF analysis depicted a significant correlation for SZV, IV, entropy, parameters II and III, and tumor volume (0.68 ≤ ρ ≤ 0.84) and moderate correlation for ZP, HIE, homogeneity, dissimilarity, parameter I, and SUV_min (0.22 ≤ ρ ≤ 0.52), while no correlations were observed for SUV_max and SUV_mean (ρ < 0.08). The multi-linear regression model for automated tumor labeling process resulted in R ² and RMSE values of 0.93 and 0.14, respectively (p < 0.001), and generated tumor labeling sensitivity and specificity of 0.93 and 0.89. With respect to baseline random walk segmentation, the results showed significant (p < 0.001) mean DSC, HD, and SUV_mean error improvements of 21.4 ± 11.5 %, 1.4 ± 0.8 mm, and 16.8 ± 8.1 % in homogeneous tumors and 7.4 ± 4.4 %, 1.5 ± 0.6 mm, and 7.9 ± 2.7 % in heterogeneous lesions. In addition, significant (p < 0.001) mean DSC, HD, and SUV_mean error improvements were observed for tumor sub-volume delineations, namely 5 ± 2 %, 1.5 ± 0.6 mm, and 7 ± 3 % for the proposed Fuzzy RW method compared to RW segmentation.

CONCLUSION

We proposed and demonstrated an automatic framework for significantly improved segmentation and labeling of homogeneous vs. heterogeneous tumors in lung [¹⁸F]FDG-PET images.

Quantitative image variables reflect the intratumoral pathologic heterogeneity of lung adenocarcinoma

We aimed to compare quantitative radiomic parameters from dual-energy computed tomography (DECT) of lung adenocarcinoma and pathologic complexity.

A total 89 tumors with clinical stage I/II lung adenocarcinoma were prospectively included. Fifty one radiomic features were assessed both from iodine images and non-contrast images of DECT datasets. Comprehensive histologic subtyping was evaluated with all surgically resected tumors. The degree of pathologic heterogeneity was assessed using pathologic index and the number of mixture histologic subtypes in a tumor. Radiomic parameters were correlated with pathologic index. Tumors were classified as three groups according to the number of mixture histologic subtypes and radiomic parameters were compared between the three groups.

Tumor density and 50^th through 97.5^th percentile Hounsfield units (HU) of histogram on non-contrast images showed strong correlation with the pathologic heterogeneity. Radiomic parameters including 75^th and 97.5^th percentile HU of histogram, entropy, and inertia on 1-, 2- and 3 voxel distance on non-contrast images showed incremental changes while homogeneity showed detrimental change according to the number of mixture histologic subtypes (all Ps < 0.05).

Radiomic variables from DECT of lung adenocarcinoma reflect pathologic intratumoral heterogeneity, which may help in the prediction of intratumoral heterogeneity of the whole tumor.

Extended logistic growth model for heterogeneous populations

Cell proliferation is the most important cellular-level mechanism responsible for regulating cell population dynamics in living tissues. Modern experimental procedures show that the proliferation rates of individual cells can vary significantly within the same cell line. However, in the mathematical biology literature, cell proliferation is typically modelled using a classical logistic equation which neglects variations in the proliferation rate. In this work, we consider a discrete mathematical model of cell migration and cell proliferation, modulated by volume exclusion (crowding) effects, with variable rates of proliferation across the total population. We refer to this variability as heterogeneity. Constructing the continuum limit of the discrete model leads to a generalisation of the classical logistic growth model. Comparing numerical solutions of the model to averaged data from discrete simulations shows that the new model captures the key features of the discrete process. Applying the extended logistic model to simulate a proliferation assay using rates from recent experimental literature shows that neglecting the role of heterogeneity can, at times, lead to misleading results.

Automated High-Throughput Damage Scoring of Zebrafish Lateral Line Hair Cells After Ototoxin Exposure

Zebrafish have emerged as a powerful biological system for drug development against hearing loss. Zebrafish hair cells, contained within neuromasts along the lateral line, can be damaged with exposure to ototoxins, and therefore, pre-exposure to potentially otoprotective compounds can be a means of identifying promising new drug candidates. Unfortunately, anatomical assays of hair cell damage are typically low-throughput and labor intensive, requiring trained experts to manually score hair cell damage in fluorescence or confocal images. To enhance throughput and consistency, our group has developed an automated damage-scoring algorithm based on machine-learning techniques that produce accurate damage scores, eliminate potential operator bias, provide more fidelity in determining damage scores that are between two levels, and deliver consistent results in a fraction of the time required for manual analysis. The system has been validated against trained experts using linear regression, hypothesis testing, and the Pearson's correlation coefficient. Furthermore, performance has been quantified by measuring mean absolute error for each image and the time taken to automatically compute damage scores. Coupling automated analysis of zebrafish hair cell damage to behavioral assays for ototoxicity produces a novel drug discovery platform for rapid translation of candidate drugs into preclinical mammalian models of hearing loss.

Multiplexed imaging for diagnosis and therapy

Complex molecular and metabolic phenotypes depict cancers as a constellation of different diseases with common themes. Precision imaging of such phenotypes requires flexible and tunable modalities capable of identifying phenotypic fingerprints by using a restricted number of parameters while ensuring sensitivity to dynamic biological regulation. Common phenotypes can be detected by in vivo imaging technologies, and effectively define the emerging standards for disease classification and patient stratification in radiology. However, for the imaging data to accurately represent a complex fingerprint, the individual imaging parameters need to be measured and analysed in relation to their wider spatial and molecular context. In this respect, targeted palettes of molecular imaging probes facilitate the detection of heterogeneity in oncogene-driven alterations and their response to treatment, and lead to the expansion of rational-design elements for the combination of imaging experiments. In this Review, we evaluate criteria for conducting multiplexed imaging, and discuss its opportunities for improving patient diagnosis and the monitoring of therapy.

Characterization of PET/CT images using texture analysis: the past, the present… any future?

After seminal papers over the period 2009 - 2011, the use of texture analysis of PET/CT images for quantification of intratumour uptake heterogeneity has received increasing attention in the last 4 years. Results are difficult to compare due to the heterogeneity of studies and lack of standardization. There are also numerous challenges to address. In this review we provide critical insights into the recent development of texture analysis for quantifying the heterogeneity in PET/CT images, identify issues and challenges, and offer recommendations for the use of texture analysis in clinical research. Numerous potentially confounding issues have been identified, related to the complex workflow for the calculation of textural features, and the dependency of features on various factors such as acquisition, image reconstruction, preprocessing, functional volume segmentation, and methods of establishing and quantifying correspondences with genomic and clinical metrics of interest. A lack of understanding of what the features may represent in terms of the underlying pathophysiological processes and the variability of technical implementation practices makes comparing results in the literature challenging, if not impossible. Since progress as a field requires pooling results, there is an urgent need for standardization and recommendations/guidelines to enable the field to move forward. We provide a list of correct formulae for usual features and recommendations regarding implementation. Studies on larger cohorts with robust statistical analysis and machine learning approaches are promising directions to evaluate the potential of this approach.

Progress in the clinical detection of heterogeneity in breast cancer

Breast cancer is currently the most common form of cancer and the second‐leading cause of death from cancer in women. Though considerable progress has been made in the treatment of breast cancer, the heterogeneity of tumors (both inter‐ and intratumor) remains a considerable diagnostic and prognostic challenge. From clinical observation to genetic mutations, the history of understanding the heterogeneity of breast cancer is lengthy and detailed. Effectively detecting heterogeneity in breast cancer is important during treatment. Various methods of depicting this heterogeneity are now available and include genetic, pathologic, and imaging analysis. These methods allow characterization of the heterogeneity of breast cancer on a genetic level, providing greater insight during the process of establishing an effective therapeutic plan. This study reviews how the understanding of tumor heterogeneity in breast cancer evolved, and further summarizes recent advances in the detection and monitoring of this heterogeneity in patients with breast cancer.

Reliability of PET/CT Shape and Heterogeneity Features in Functional and Morphologic Components of Non-Small Cell Lung Cancer Tumors: A Repeatability Analysis in a Prospective Multicenter Cohort

The main purpose of this study was to assess the reliability of shape and heterogeneity features in both the PET and the low-dose CT components of PET/CT. A secondary objective was to investigate the impact of image quantization. Methods: A Health Insurance Portability and Accountability Act-compliant secondary analysis of deidentified prospectively acquired PET/CT test-retest datasets of 74 patients from multicenter Merck and American College of Radiology Imaging Network trials was performed. Metabolically active volumes were automatically delineated on PET with a fuzzy locally adaptive bayesian algorithm. Software was used to semiautomatically delineate the anatomic volumes on the low-dose CT component. Two quantization methods were considered: a quantization into a set number of bins (quantization B) and an alternative quantization with bins of fixed width (quantization W). Four shape descriptors, 10 first-order metrics, and 26 textural features were evaluated. Bland-Altman analysis was used to quantify repeatability. Features were subsequently categorized as very reliable, reliable, moderately reliable, or poorly reliable with respect to the corresponding volume variability. Results: Repeatability was highly variable among features. Numerous metrics were identified as poorly or moderately reliable. Others were reliable or very reliable in both modalities and in all categories (shape and first-, second-, and third-order metrics). Image quantization played a major role in feature repeatability. Features were more reliable in PET with quantization B, whereas quantization W showed better results in CT. Conclusion: The test-retest repeatability of shape and heterogeneity features in PET and low-dose CT varied greatly among metrics. The level of repeatability also depended strongly on the quantization step, with different optimal choices for each modality. The repeatability of PET and low-dose CT features should be carefully considered when selecting metrics to build multiparametric models.

Identification of low variability textural features for heterogeneity quantification of 18F-FDG PET/CT imaging

OBJECTIVE

To identify those textural features that are insensitive to both technical and biological factors in order to standardise heterogeneity studies on ¹⁸F-FDG PET imaging.

MATERIALS AND METHODS

Two different studies were performed. First, nineteen series from a cylindrical phantom filled with different ¹⁸F-FDG activity concentration were acquired and reconstructed using three different protocols. Seventy-two texture features were calculated inside a circular region of interest. The variability of each feature was obtained. Second, the data for 15 patients showing non-pathological liver were acquired. Anatomical and physiological features such as patient's weight, height, body mass index, metabolic active volume, blood glucose level, SUV and SUV standard deviation were also recorded. A liver covering region of interest was delineated and low variability textural features calculated in each patient. Finally, a multivariate Spearman's correlation analysis between biological factors and texture features was performed.

RESULTS

Only eight texture features analysed show small variability (<5%) with activity concentration and reconstruction protocol making them suitable for heterogeneity quantification. On the other hand, there is a high statistically significant correlation between MAV and entropy (P<0.05). Entropy feature is, indeed, correlated (P<0.05) with all patient parameters, except body mass index.

CONCLUSIONS

The textural features that are correlated with neither technical nor biological factors are run percentage, short-zone emphasis and intensity, making them suitable for quantifying functional changes or classifying patients. Other textural features are correlated with technical and biological factors and are, therefore, a source of errors if used for this purpose.

Functional imaging of hepatocellular carcinoma

Imaging plays a key role in the clinical management of hepatocellular carcinoma (HCC), but conventional imaging techniques have limited sensitivity in visualizing small tumors and assessing response to locoregional treatments and sorafenib. Functional imaging techniques allow visualization of organ and tumor physiology. Assessment of functional characteristics of tissue, such as metabolism, proliferation and stiffness, may overcome some of the limitations of structural imaging. In particular, novel molecular imaging agents offer a potential tool for early diagnosis of HCC, and radiomics may aid in response assessment and generate prognostic models. Further prospective research is warranted to evaluate emerging techniques and their cost-effectiveness in the context of HCC in order to improve detection and response assessment.

Comparison of Tumor Uptake Heterogeneity Characterization Between Static and Parametric 18F-FDG PET Images in Non-Small Cell Lung Cancer

(18)F-FDG PET is well established in the field of oncology for diagnosis and staging purposes and is increasingly being used to assess therapeutic response and prognosis. Many quantitative indices can be used to characterize tumors on (18)F-FDG PET images, such as SUVmax, metabolically active tumor volume (MATV), total lesion glycolysis, and, more recently, the proposed intratumor uptake heterogeneity features. Although most PET data considered within this context concern the analysis of activity distribution using images obtained from a single static acquisition, parametric images generated from dynamic acquisitions and reflecting radiotracer kinetics may provide additional information. The purpose of this study was to quantify differences between volumetry, uptake, and heterogeneity features extracted from static and parametric PET images of non-small cell lung carcinoma (NSCLC) in order to provide insight on the potential added value of parametric images.

METHODS

Dynamic (18)F-FDG PET/CT was performed on 20 therapy-naive NSCLC patients for whom primary surgical resection was planned. Both static and parametric PET images were analyzed, with quantitative parameters (MATV, SUVmax, SUVmean, heterogeneity) being extracted from the segmented tumors. Differences were investigated using Spearman rank correlation and Bland-Altman analysis.

RESULTS

MATV was slightly smaller on static images (-2% ± 7%), but the difference was not significant (P = 0.14). All derived parameters, including those characterizing tumor functional heterogeneity, correlated strongly between static and parametric images (r = 0.70-0.98, P ≤ 0.0006), exhibiting differences of less than ±25%.

CONCLUSION

In NSCLC primary tumors, parametric and static baseline (18)F-FDG PET images provided strongly correlated quantitative features for both standard (MATV, SUVmax, SUVmean) and heterogeneity quantification. Consequently, heterogeneity quantification on parametric images does not seem to provide significant complementary information compared with static SUV images.

Development of a nomogram combining clinical staging with (18)F-FDG PET/CT image features in non-small-cell lung cancer stage I-III

PURPOSE

Our goal was to develop a nomogram by exploiting intratumour heterogeneity on CT and PET images from routine (18)F-FDG PET/CT acquisitions to identify patients with the poorest prognosis.

METHODS

This retrospective study included 116 patients with NSCLC stage I, II or III and with staging (18)F-FDG PET/CT imaging. Primary tumour volumes were delineated using the FLAB algorithm and 3D Slicer™ on PET and CT images, respectively. PET and CT heterogeneities were quantified using texture analysis. The reproducibility of the CT features was assessed on a separate test-retest dataset. The stratification power of the PET/CT features was evaluated using the Kaplan-Meier method and the log-rank test. The best standard metric (functional volume) was combined with the least redundant and most prognostic PET/CT heterogeneity features to build the nomogram.

RESULTS

PET entropy and CT zone percentage had the highest complementary values with clinical stage and functional volume. The nomogram improved stratification amongst patients with stage II and III disease, allowing identification of patients with the poorest prognosis (clinical stage III, large tumour volume, high PET heterogeneity and low CT heterogeneity).

CONCLUSION

Intratumour heterogeneity quantified using textural features on both CT and PET images from routine staging (18)F-FDG PET/CT acquisitions can be used to create a nomogram with higher stratification power than staging alone.

Variability of Image Features Computed from Conventional and Respiratory-Gated PET/CT Images of Lung Cancer

Radiomics is being explored for potential applications in radiation therapy. How various imaging protocols affect quantitative image features is currently a highly active area of research. To assess the variability of image features derived from conventional [three-dimensional (3D)] and respiratory-gated (RG) positron emission tomography (PET)/computed tomography (CT) images of lung cancer patients, image features were computed from 23 lung cancer patients. Both protocols for each patient were acquired during the same imaging session. PET tumor volumes were segmented using an adaptive technique which accounted for background. CT tumor volumes were delineated with a commercial segmentation tool. Using RG PET images, the tumor center of mass motion, length, and rotation were calculated. Fifty-six image features were extracted from all images consisting of shape descriptors, first-order features, and second-order texture features. Overall, 26.6% and 26.2% of total features demonstrated less than 5% difference between 3D and RG protocols for CT and PET, respectively. Between 10 RG phases in PET, 53.4% of features demonstrated percent differences less than 5%. The features with least variability for PET were sphericity, spherical disproportion, entropy (first and second order), sum entropy, information measure of correlation 2, Short Run Emphasis (SRE), Long Run Emphasis (LRE), and Run Percentage (RPC); and those for CT were minimum intensity, mean intensity, Root Mean Square (RMS), Short Run Emphasis (SRE), and RPC. Quantitative analysis using a 3D acquisition versus RG acquisition (to reduce the effects of motion) provided notably different image feature values. This study suggests that the variability between 3D and RG features is mainly due to the impact of respiratory motion.

18F-FDG PET-Derived Textural Indices Reflect Tissue-Specific Uptake Pattern in Non-Small Cell Lung Cancer

Purpose

Texture indices (TI) calculated from 18F-FDG PET tumor images show promise for predicting response to therapy and survival. Their calculation involves a resampling of standardized uptake values (SUV) within the tumor. This resampling can be performed differently and significantly impacts the TI values. Our aim was to investigate how the resampling approach affects the ability of TI to reflect tissue-specific pattern of metabolic activity.

Methods

18F-FDG PET were acquired for 48 naïve-treatment patients with non-small cell lung cancer and for a uniform phantom. We studied 7 TI, SUVmax and metabolic volume (MV) in the phantom, tumors and healthy tissue using the usual relative resampling (RR) method and an absolute resampling (AR) method. The differences in TI values between tissue types and cancer subtypes were investigated using Wilcoxon’s tests.

Results

Most RR-based TI were highly correlated with MV for tumors less than 60 mL (Spearman correlation coefficient r between 0.74 and 1), while this correlation was reduced for AR-based TI (r between 0.06 and 0.27 except for RLNU where r = 0.91). Most AR-based TI were significantly different between tumor and healthy tissues (pvalues <0.01 for all 7 TI) and between cancer subtypes (pvalues<0.05 for 6 TI). Healthy tissue and adenocarcinomas exhibited more homogeneous texture than tumor tissue and squamous cell carcinomas respectively.

Conclusion

TI computed using an AR method vary as a function of the tissue type and cancer subtype more than the TI involving the usual RR method. AR-based TI might be useful for tumor characterization.

A Phase II Study of 3'-Deoxy-3'-18F-Fluorothymidine PET in the Assessment of Early Response of Breast Cancer to Neoadjuvant Chemotherapy: Results from ACRIN 6688

Our objective was to determine whether early change in standardized uptake values (SUVs) of 3'deoxy-3'-(18)F-fluorothymidine ((18)F-FLT) using PET with CT could predict pathologic complete response (pCR) of primary breast cancer to neoadjuvant chemotherapy (NAC). The key secondary objective was to correlate SUV with the proliferation marker Ki-67 at baseline and after NAC.

METHODS

This prospective, multicenter phase II study did not specify the therapeutic regimen, thus, NAC varied among centers. All evaluable patients underwent (18)F-FLT PET/CT at baseline (FLT1) and after 1 cycle of NAC (FLT2); 43 patients were imaged at FLT1, FLT2, and after NAC completion (FLT3). The percentage change in maximum SUV (%ΔSUVmax) between FLT1 and FLT2 and FLT3 was calculated for the primary tumors. The predictive value of ΔSUVmax for pCR was determined using receiver-operating-characteristic curve analysis. The correlation between SUVmax and Ki-67 was also assessed.

RESULTS

Fifty-one of 90 recruited patients (median age, 54 y; stage IIA-IIIC) met the eligibility criteria for the primary objective analysis, with an additional 22 patients totaling 73 patients for secondary analyses. A pCR in the primary breast cancer was achieved in 9 of 51 patients. NAC resulted in a significant reduction in %SUVmax (mean Δ, 39%; 95% confidence interval, 31-46). There was a marginal difference in %ΔSUVmax_FLT1-FLT2 between pCR and no-pCR patient groups (Wilcoxon 1-sided P = 0.050). The area under the curve for ΔSUVmax in the prediction of pCR was 0.68 (90% confidence interval, 0.50-0.83; Delong 1-sided P = 0.05), with slightly better predictive value for percentage mean SUV (P = 0.02) and similar prediction for peak SUV (P = 0.04). There was a weak correlation with pretherapy SUVmax and Ki-67 (r = 0.29, P = 0.04), but the correlation between SUVmax and Ki-67 after completion of NAC was stronger (r = 0.68, P < 0.0001).

CONCLUSION

(18)F-FLT PET imaging of breast cancer after 1 cycle of NAC weakly predicted pCR in the setting of variable NAC regimens. Posttherapy (18)F-FLT uptake correlated with Ki-67 on surgical specimens. These results suggest some efficacy of (18)F-FLT as an indicator of early therapeutic response of breast cancer to NAC and support future multicenter studies to test (18)F-FLT PET in a more uniformly treated patient population.

Prognostic value and clinical correlations of 18-fluorodeoxyglucose metabolism quantifiers in gastric cancer

AIM: To investigate the correlations of pre-treatment positron emission tomography-computer tomography (PET-CT) metabolic quantifiers with clinical data of unstratified gastric cancer (GC) patients.

METHODS: Forty PET-CT scans utilising 18-fluorodeoxyglucose in patients who received no prior treatment were analysed. Analysis involved measurements of maximum and mean standardised uptake volumes (SUV), coefficient of variation (COV), metabolic tumour volumes and total lesion glycolysis of different thresholds above which the tumor volumes were identified. The threshold values were: SUV absolute value of 2.5, 30% of SUVmax, 40% of SUVmax, and liver uptake-based (marked _2.5, ₃₀, ₄₀ and _liv, respectively). Clinical variables such as age, sex, clinical stage, performance index, weight loss, tumor histological type and grade, and CEA and CA19.9 levels were included in survival analysis. Patients received various treatment modalities appropriate to their disease stage and the outcome was defined by time to metastasis (TTM) and overall survival (OS). Clinical and metabolic parameters were evaluated by analysis of variance, receiver operating characteristics, univariate Kaplan-Meier, and multivariate Cox models. P < 0.05 was considered statistically significant.

RESULTS: Significant differences were observed between initially disseminated and non-disseminated patients in mean SUV (6.05 vs 4.13, P = 0.008), TLG_2.5 (802 cm³vs 226 cm³; P = 0.031), and TLG₃₀ (436 cm³vs 247 cm³, P = 0.018). Higher COV was associated with poor tumour differentiation (0.47 for G3 vs 0.28 for G1 and G2; P = 0.03). MTV_2.5 was positively correlated to patient weight loss (< 5%, 5%-10% and > 10%: 40.4 cm³vs 123.6 cm³vs 181.8 cm³, respectively, P = 0.003). In multivariate Cox analysis, TLG₃₀ was prognostic for OS (HR = 1.001, 95%CI: 1.0009-1.0017; P = 0.047) for the whole group of patients. In the same model yet only including patients without initial disease dissemination TLG₃₀ (HR = 1.009, 95%CI: 1.003-1.014; P = 0.004) and MTV_2.5 (HR = 1.02, 95%CI: 1.002-1.036; P = 0.025) were prognostic for OS; for TTM TLG₃₀ was the only significant prognostic variable (HR = 1.006, 95%CI: 1.001-1.012; P = 0.02).

CONCLUSION: PET-CT in GC may represent a valuable diagnostic and prognostic tool that requires further evaluation in highly standardised environments such as randomised clinical trials.

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

Purpose

A number of recent publications have proposed that a family of image-derived indices, called texture features, can predict clinical outcome in patients with cancer. However, the investigation of multiple indices on a single data set can lead to significant inflation of type-I errors. We report a systematic review of the type-I error inflation in such studies and review the evidence regarding associations between patient outcome and texture features derived from positron emission tomography (PET) or computed tomography (CT) images.

Methods

For study identification PubMed and Scopus were searched (1/2000–9/2013) using combinations of the keywords texture, prognostic, predictive and cancer. Studies were divided into three categories according to the sources of the type-I error inflation and the use or not of an independent validation dataset. For each study, the true type-I error probability and the adjusted level of significance were estimated using the optimum cut-off approach correction, and the Benjamini-Hochberg method. To demonstrate explicitly the variable selection bias in these studies, we re-analyzed data from one of the published studies, but using 100 random variables substituted for the original image-derived indices. The significance of the random variables as potential predictors of outcome was examined using the analysis methods used in the identified studies.

Results

Fifteen studies were identified. After applying appropriate statistical corrections, an average type-I error probability of 76% (range: 34–99%) was estimated with the majority of published results not reaching statistical significance. Only 3/15 studies used a validation dataset. For the 100 random variables examined, 10% proved to be significant predictors of survival when subjected to ROC and multiple hypothesis testing analysis.

Conclusions

We found insufficient evidence to support a relationship between PET or CT texture features and patient survival. Further fit for purpose validation of these image-derived biomarkers should be supported by appropriate biological and statistical evidence before their association with patient outcome is investigated in prospective studies.

Metabolically active tumour volume segmentation from dynamic [(18)F]FLT PET studies in non-small cell lung cancer

BACKGROUND

Positron emission tomography (PET) with (18)F-3'-deoxy-3'-fluorothymidine ([(18)F]FLT) can be used to assess tumour proliferation. A kinetic-filtering (KF) classification algorithm has been suggested for segmentation of tumours in dynamic [(18)F]FLT PET data. The aim of the present study was to evaluate KF segmentation and its test-retest performance in [(18)F]FLT PET in non-small cell lung cancer (NSCLC) patients.

METHODS

Nine NSCLC patients underwent two 60-min dynamic [(18)F]FLT PET scans within 7 days prior to treatment. Dynamic scans were reconstructed with filtered back projection (FBP) as well as with ordered subsets expectation maximisation (OSEM). Twenty-eight lesions were identified by an experienced physician. Segmentation was performed using KF applied to the dynamic data set and a source-to-background corrected 50% threshold (A50%) was applied to the sum image of the last three frames (45- to 60-min p.i.). Furthermore, several adaptations of KF were tested. Both for KF and A50% test-retest (TRT) variability of metabolically active tumour volume and standard uptake value (SUV) were evaluated.

RESULTS

KF performed better on OSEM- than on FBP-reconstructed PET images. The original KF implementation segmented 15 out of 28 lesions, whereas A50% segmented each lesion. Adapted KF versions, however, were able to segment 26 out of 28 lesions. In the best performing adapted versions, metabolically active tumour volume and SUV TRT variability was similar to those of A50%. KF misclassified certain tumour areas as vertebrae or liver tissue, which was shown to be related to heterogeneous [(18)F]FLT uptake areas within the tumour.

CONCLUSIONS

For [(18)F]FLT PET studies in NSCLC patients, KF and A50% show comparable tumour volume segmentation performance. The KF method needs, however, a site-specific optimisation. The A50% is therefore a good alternative for tumour segmentation in NSCLC [(18)F]FLT PET studies in multicentre studies. Yet, it was observed that KF has the potential to subsegment lesions in high and low proliferative areas.

Imaging intratumor heterogeneity: role in therapy response, resistance, and clinical outcome

Tumors exhibit genomic and phenotypic heterogeneity, which has prognostic significance and may influence response to therapy. Imaging can quantify the spatial variation in architecture and function of individual tumors through quantifying basic biophysical parameters such as CT density or MRI signal relaxation rate; through measurements of blood flow, hypoxia, metabolism, cell death, and other phenotypic features; and through mapping the spatial distribution of biochemical pathways and cell signaling networks using PET, MRI, and other emerging molecular imaging techniques. These methods can establish whether one tumor is more or less heterogeneous than another and can identify subregions with differing biology. In this article, we review the image analysis methods currently used to quantify spatial heterogeneity within tumors. We discuss how analysis of intratumor heterogeneity can provide benefit over more simple biomarkers such as tumor size and average function. We consider how imaging methods can be integrated with genomic and pathology data, instead of being developed in isolation. Finally, we identify the challenges that must be overcome before measurements of intratumoral heterogeneity can be used routinely to guide patient care.

Texture analysis of collagen second-harmonic generation images based on local difference local binary pattern and wavelets differentiates human skin abnormal scars from normal scars

Quantitative methods for noninvasive diagnosis of scars are a challenging issue in medicine. This work aims to implement a texture analysis method for quantitatively discriminating abnormal scars from normal scars based on second-harmonic generation (SHG) images. A local difference local binary pattern (LD-LBP) operator combined with a wavelet transform was explored to extract diagnosis features from scar SHG images that were related to the alteration in collagen morphology. Based on the quantitative parameters including the homogeneity, directional and coarse features in SHG images, the scar collagen SHG images were classified into normal or abnormal scars by a support vector machine classifier in a leave-one-out cross-validation procedure. Our experiments and data analyses demonstrated apparent differences between normal and abnormal scars in terms of their morphological structure of collagen. By comparing with gray level co-occurrence matrix, wavelet transform, and combined basic local binary pattern and wavelet transform with respect to the accuracy and receiver operating characteristic analysis, the method proposed herein was demonstrated to achieve higher accuracy and more reliable classification of SHG images. This result indicated that the extracted texture features with the proposed method were effective in the classification of scars. It could provide assistance for physicians in the diagnostic process.