The role of quantitative PET in predicting cancer treatment outcomes

The prognostic value of F18 Fluorothymidine positron emission tomography for assessing the response of malignant pleural mesothelioma to chemotherapy - A prospective cohort study

INTRODUCTION

Malignant pleural mesothelioma is difficult to prognosticate. F18-Fluorodeoxyglucose positron emission tomography (FDG PET) shows promise for response assessment but is confounded by talc pleurodesis. F18-Fluorothymidine (FLT) PET is an alternative tracer specific for proliferation. We compared the prognostic value of FDG and FLT PET and determined the influence of talc pleurodesis on these parameters.

METHODS

Overall, 29 prospectively recruited patients had FLT PET, FDG PET and CT-scans performed prior to and post one chemotherapy cycle; 10 had prior talc pleurodesis. Patients were followed for overall survival. CT response was assessed using mRECIST. Radiomic features were extracted using the MiM software platform. Changes in maximum SUV (SUVmax), mean SUV (SUVmean), FDG total lesion glycolysis (TLG), FLT total lesion proliferation (TLP) and metabolic tumour volume (MTV) after one chemotherapy cycle.

RESULTS

Cox univariate analysis demonstrated FDG PET radiomics were confounded by talc pleurodesis, and that percentage change in FLT MTV was predictive of overall survival. Cox multivariate analysis showed a 10% increase in FLT tumour volume corresponded with 9.5% worsened odds for overall survival (P = 0.028, HR = 1.095, 95% CI [1.010, 1.187]). No other variables were significant on multivariate analysis.

CONCLUSION

This is the first prospective study showing the statistical significance of FLT PET tumour volumes for measuring mesothelioma treatment response. FLT may be better than FDG for monitoring mesothelioma treatment response, which could help optimise mesothelioma treatment regimes.

Metabolic factors associated with the prognosis of oligometastatic patients treated with stereotactic body radiotherapy

Over the past two decades, it has been established that cancer patients with oligometastases, i.e., only a few detectable metastases confined to one or a few organs, may benefit from an aggressive local treatment approach such as the application of high-precision stereotactic body radiotherapy (SBRT). Specifically, some studies have indicated that achieving long-term local tumor control of oligometastases is associated with prolonged overall survival. This motivates investigations into which factors may modify the dose-response relationship of SBRT by making metastases more or less radioresistant. One such factor relates to the uptake of the positron emission tomography tracer 2-deoxy-2-[18F]fluoro-D-glucose (FDG) which reflects the extent of tumor cell glycolysis or the Warburg effect, respectively. Here we review the biological mechanisms how the Warburg effect drives tumor cell radioresistance and metastasis and draw connections to clinical studies reporting associations between high FDG uptake and worse clinical outcomes after SBRT for oligometastases. We further review the evidence for distinct metabolic phenotypes of metastases preferentially seeding to specific organs and their possible translation into distinct radioresistance. Finally, evidence that obesity and hyperglycemia also affect outcomes after SBRT will be presented. While delivered dose is the main determinant of a high local tumor control probability, there might be clinical scenarios when metabolic targeting could make the difference between achieving local control or not, for example when doses have to be compromised in order to spare neighboring high-risk organs, or when tumors are expected to be highly therapy-resistant due to heavy pretreatment such as chemotherapy and/or radiotherapy.

68Ga-PSMA-11 PET/CT Features Extracted from Different Radiomic Zones Predict Response to Androgen Deprivation Therapy in Patients with Advanced Prostate Cancer

Purpose: Prediction of treatment response to androgen deprivation therapy (ADT) prior to treatment initiation remains difficult. This study was undertaken to investigate whether 68Ga-PSMA-11 PET/CT features extracted from different radiomic zones within the prostate gland might predict response to ADT in patients with advanced prostate cancer (PCa). Methods: A total of 35 patients with prostate adenocarcinoma underwent two 68Ga-PSMA-11 PET/CT scans—termed PET-1 and PET-2—before and after 3 months of ADT, respectively. The prostate was divided into three radiomic zones, with zone-1 being the metabolic tumor zone, zone-2 the proximal peripheral tumor zone, and zone-3 the extended peripheral tumor zone. Patients in the response group were those who showed a reduction ratio > 30% for PET-derived parameters measured at PET-1 and PET-2. The remaining patients were classified as non-responders. Results: Seven features (glcm_idmn, glcm_idn, glcm_imc1, ngtdm_Contrast, glrlm_rln, gldm_dn, and shape_MeshVolume) from zone-1, two features (gldm_sdlgle and shape_MinorAxisLength) from zone-2, and two features (diagnostics_Mask-interpolated_Minimum and shape_Sphericity) from zone-3 successfully distinguished responders from non-responders to ADT. One predictive feature (shape_SurfaceVolumeRatio) was consistently identified in all of the three zones. Conclusions: this study demonstrates the potential usefulness of radiomic features extracted from different prostatic zones in distinguishing responders from non-responders prior to ADT initiation.

Short 2-[18F]Fluoro-2-Deoxy-D-Glucose PET Dynamic Acquisition Protocol to Evaluate the Influx Rate Constant by Regional Patlak Graphical Analysis in Patients With Non-Small-Cell Lung Cancer

Purpose: To test a short 2-[¹⁸F]Fluoro-2-deoxy-D-glucose (2-[¹⁸F]FDG) PET dynamic acquisition protocol to calculate K_i using regional Patlak graphical analysis in patients with non-small-cell lung cancer (NSCLC).

Methods: 24 patients with NSCLC who underwent standard dynamic 2-[¹⁸F]FDG acquisitions (60 min) were randomly divided into two groups. In group 1 (n = 10), a population-based image-derived input function (pIDIF) was built using a monoexponential trend (10–60 min), and a leave-one-out cross-validation (LOOCV) method was performed to validate the pIDIF model. In group 2 (n = 14), K_i was obtained by standard regional Patlak plot analysis using IDIF (0–60 min) and tissue response (10–60 min) curves from the volume of interests (VOIs) placed on descending thoracic aorta and tumor tissue, respectively. Moreover, with our method, the Patlak analysis was performed to obtain K_i,s using IDIF_Fitted curve obtained from PET counts (0–10 min) followed by monoexponential coefficients of pIDIF (10–60 min) and tissue response curve obtained from PET counts at 10 min and between 40 and 60 min, simulating two short dynamic acquisitions. Both IDIF and IDIF_Fitted curves were modeled to assume the value of 2-[¹⁸F]FDG plasma activity measured in the venous blood sampling performed at 45 min in each patient. Spearman's rank correlation, coefficient of determination, and Passing–Bablok regression were used for the comparison between K_i and K_i,s. Finally, K_i,s was obtained with our method in a separate group of patients (group 3, n = 8) that perform two short dynamic acquisitions.

Results: Population-based image-derived input function (10–60 min) was modeled with a monoexponential curve with the following fitted parameters obtained in group 1: a = 9.684, b = 16.410, and c = 0.068 min⁻¹. The LOOCV error was 0.4%. In patients of group 2, the mean values of K_i and K_i,s were 0.0442 ± 0.0302 and 0.33 ± 0.0298, respectively (R² = 0.9970). The Passing–Bablok regression for comparison between K_i and K_i,s showed a slope of 0.992 (95% CI: 0.94–1.06) and intercept value of −0.0003 (95% CI: −0.0033–0.0011).

Conclusions: Despite several practical limitations, like the need to position the patient twice and to perform two CT scans, our method contemplates two short 2-[¹⁸F]FDG dynamic acquisitions, a population-based input function model, and a late venous blood sample to obtain robust and personalized input function and tissue response curves and to provide reliable regional K_i estimation.

Clinical Application of Artificial Intelligence in Positron Emission Tomography: Imaging of Prostate Cancer

PET imaging with targeted novel tracers has been commonly used in the clinical management of prostate cancer. The use of artificial intelligence (AI) in PET imaging is a relatively new approach and in this review article, we will review the current trends and categorize the currently available research into the quantification of tumor burden within the organ, evaluation of metastatic disease, and translational/supplemental research which aims to improve other AI research efforts.

Radiomics for Identification and Prediction in Metastatic Prostate Cancer: A Review of Studies

Metastatic Prostate Cancer (mPCa) is associated with a poor patient prognosis. mPCa spreads throughout the body, often to bones, with spatial and temporal variations that make the clinical management of the disease difficult. The evolution of the disease leads to spatial heterogeneity that is extremely difficult to characterise with solid biopsies. Imaging provides the opportunity to quantify disease spread. Advanced image analytics methods, including radiomics, offer the opportunity to characterise heterogeneity beyond what can be achieved with simple assessment. Radiomics analysis has the potential to yield useful quantitative imaging biomarkers that can improve the early detection of mPCa, predict disease progression, assess response, and potentially inform the choice of treatment procedures. Traditional radiomics analysis involves modelling with hand-crafted features designed using significant domain knowledge. On the other hand, artificial intelligence techniques such as deep learning can facilitate end-to-end automated feature extraction and model generation with minimal human intervention. Radiomics models have the potential to become vital pieces in the oncology workflow, however, the current limitations of the field, such as limited reproducibility, are impeding their translation into clinical practice. This review provides an overview of the radiomics methodology, detailing critical aspects affecting the reproducibility of features, and providing examples of how artificial intelligence techniques can be incorporated into the workflow. The current landscape of publications utilising radiomics methods in the assessment and treatment of mPCa are surveyed and reviewed. Associated studies have incorporated information from multiple imaging modalities, including bone scintigraphy, CT, PET with varying tracers, multiparametric MRI together with clinical covariates, spanning the prediction of progression through to overall survival in varying cohorts. The methodological quality of each study is quantified using the radiomics quality score. Multiple deficits were identified, with the lack of prospective design and external validation highlighted as major impediments to clinical translation. These results inform some recommendations for future directions of the field.

Convolutional neural network based attenuation correction for123I-FP-CIT SPECT with focused striatum imaging

SPECT imaging with¹²³I-FP-CIT is used for diagnosis of neurodegenerative disorders like Parkinson's disease. Attenuation correction (AC) can be useful for quantitative analysis of¹²³I-FP-CIT SPECT. Ideally, AC would be performed based on attenuation maps (μ-maps) derived from perfectly registered CT scans. Suchμ-maps, however, are most times not available and possible errors in image registration can induce quantitative inaccuracies in AC corrected SPECT images. Earlier, we showed that a convolutional neural network (CNN) based approach allows to estimate SPECT-alignedμ-maps for full brain perfusion imaging using only emission data. Here we investigate the feasibility of similar CNN methods for axially focused¹²³I-FP-CIT scans. We tested our approach on a high-resolution multi-pinhole prototype clinical SPECT system in a Monte Carlo simulation study. Three CNNs that estimateμ-maps in a voxel-wise, patch-wise and image-wise manner were investigated. As the added value of AC on clinical¹²³I-FP-CIT scans is still debatable, the impact of AC was also reported to check in which cases CNN based AC could be beneficial. AC using the ground truthμ-maps (GT-AC) and CNN estimatedμ-maps (CNN-AC) were compared with the case when no AC was done (No-AC). Results show that the effect of using GT-AC versus CNN-AC or No-AC on striatal shape and symmetry is minimal. Specific binding ratios (SBRs) from localized regions show a deviation from GT-AC≤2.5% for all three CNN-ACs while No-AC systematically underestimates SBRs by 13.1%. A strong correlation (r≥0.99) was obtained between GT-AC based SBRs and SBRs from CNN-ACs and No-AC. Absolute quantification (in kBq ml^-1) shows a deviation from GT-AC within 2.2% for all three CNN-ACs and of 71.7% for No-AC. To conclude, all three CNNs show comparable performance in accurateμ-map estimation and¹²³I-FP-CIT quantification. CNN-estimatedμ-map can be a promising substitute for CT-basedμ-map.

Tumor response prediction in 90Y radioembolization with PET-based radiomics features and absorbed dose metrics

Purpose

To evaluate whether lesion radiomics features and absorbed dose metrics extracted from post-therapy ⁹⁰Y PET can be integrated to better predict outcomes in microsphere radioembolization of liver malignancies

Methods

Given the noisy nature of ⁹⁰Y PET, first, a liver phantom study with repeated acquisitions and varying reconstruction parameters was used to identify a subset of robust radiomics features for the patient analysis. In 36 radioembolization procedures, ⁹⁰Y PET/CT was performed within a couple of hours to extract 46 radiomics features and estimate absorbed dose in 105 primary and metastatic liver lesions. Robust radiomics modeling was based on bootstrapped multivariate logistic regression with shrinkage regularization (LASSO) and Cox regression with LASSO. Nested cross-validation and bootstrap resampling were used for optimal parameter/feature selection and for guarding against overfitting risks. Spearman rank correlation was used to analyze feature associations. Area under the receiver-operating characteristics curve (AUC) was used for lesion response (at first follow-up) analysis while Kaplan-Meier plots and c-index were used to assess progression model performance. Models with absorbed dose only, radiomics only, and combined models were developed to predict lesion outcome.

Results

The phantom study identified 15/46 reproducible and robust radiomics features that were subsequently used in the patient models. A lesion response model with zone percentage (ZP) and mean absorbed dose achieved an AUC of 0.729 (95% CI 0.702–0.758), and a progression model with zone size nonuniformity (ZSN) and absorbed dose achieved a c-index of 0.803 (95% CI 0.790–0.815) on nested cross-validation (CV). Although the combined models outperformed the radiomics only and absorbed dose only models, statistical significance was not achieved with the current limited data set to establish expected superiority.

Conclusion

We have developed new lesion-level response and progression models using textural radiomics features, derived from ⁹⁰Y PET combined with mean absorbed dose for predicting outcome in radioembolization. These encouraging, but limited results, will need further validation in independent and larger datasets prior to any clinical adoption.

Supplementary Information

Supplementary information accompanies this paper at 10.1186/s40658-020-00340-9.

Mini review: Personalization of the radiation therapy management of prostate cancer using MRI-based radiomics

Decisions on how to treat prostate cancer with radiation therapy are guideline-based but as such guidelines have been developed for populations of patients, this invariably leads to overly aggressive treatment in some patients and insufficient treatment in others. Heterogeneity within prostate tumors and in metastatic sites, even within the same patient, is believed to be a major cause of treatment failure. Radiomics biomarkers, more commonly referred to as radiomics 'features", provide readily available, cost-effective, non-invasive tools for screening, detecting tumors and serial monitoring of patients, including assessments of response to therapy and identification of therapeutic complications. Radiomics offers the potential to analyse whole tumors in 3D, as well as sub-regions or 'habitats' within tumors. Combining quantitative information from imaging with pathology, demographic details and other biomarkers will pave the way for personalised treatment selection and monitoring in prostate cancer. The aim of this review is to consider if MRI-based radiomics can bridge the gap between population-based management and personalised management of prostate cancer.

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.

Exploratory Study of a CT Radiomics Model for the Classification of Small Cell Lung Cancer and Non-small-Cell Lung Cancer

Background: Radiomics can quantify tumor phenotypic characteristics non-invasively by applying feature algorithms to medical imaging data. In this study, we investigated the association between radiomics features and the tumor histological subtypes, and we aimed to establish a nomogram for the classification of small cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC). Methods: This was a retrospective single center study. In total, 468 cases including 202 patients with SCLC and 266 patients with NSCLC were enrolled in our study, and were randomly divided into a training set (n = 327) and a validation set (n = 141) in a 7:3 ratio. The clinical data of the patients, including age, sex, smoking history, tumor maximum diameter, clinical stage, and serum tumor markers, were collected. All patients underwent enhanced computed tomography (CT) scans, and all lesions were pathologically confirmed. A radiomics signature was generated from the training set using the least absolute shrinkage and selection operator algorithm. Independent risk factors were identified by multivariate logistic regression analysis, and a radiomics nomogram based on the radiomics signature and clinical features was constructed. The capability of the nomogram was evaluated in the training set and validated in the validation set. Results: Fourteen of 396 radiomics parameters were screened as important factors for establishing the radiomics model. The radiomics signature performed well in differentiating SCLC and NSCLC, with an area under the curve (AUC) of 0.86 (95% CI: 0.82-0.90) in the training set and 0.82 (95% CI: 0.75-0.89) in the validation set. The radiomics nomogram had better predictive performance [AUC = 0.94 (95% CI: 0.90-0.98) in the validation set] than the clinical model [AUC = 0.86 (95% CI: 0.80-0.93)] and the radiomics signature [AUC = 0.82 (95% CI: 0.75-0.89)], and the accuracy was 86.2% (95% CI: 0.79-0.92) in the validation set. Conclusion: The enhanced CT radiomics signature performed well in the classification of SCLC and NSCLC. The nomogram based on the radiomics signature and clinical factors has better diagnostic performance for the classification of SCLC and NSCLC than the simple application of the radiomics signature.

Machine learning in quantitative PET: A review of attenuation correction and low-count image reconstruction methods

The rapid expansion of machine learning is offering a new wave of opportunities for nuclear medicine. This paper reviews applications of machine learning for the study of attenuation correction (AC) and low-count image reconstruction in quantitative positron emission tomography (PET). Specifically, we present the developments of machine learning methodology, ranging from random forest and dictionary learning to the latest convolutional neural network-based architectures. For application in PET attenuation correction, two general strategies are reviewed: 1) generating synthetic CT from MR or non-AC PET for the purposes of PET AC, and 2) direct conversion from non-AC PET to AC PET. For low-count PET reconstruction, recent deep learning-based studies and the potential advantages over conventional machine learning-based methods are presented and discussed. In each application, the proposed methods, study designs and performance of published studies are listed and compared with a brief discussion. Finally, the overall contributions and remaining challenges are summarized.

The impact of iterative reconstruction protocol, signal-to-background ratio and background activity on measurement of PET spatial resolution

OBJECTIVES

The present study aims to assess the impact of acquisition time, different iterative reconstruction protocols as well as image context (including contrast levels and background activities) on the measured spatial resolution in PET images.

METHODS

Discovery 690 PET/CT scanner was used to quantify spatial resolutions in terms of full width half maximum (FWHM) as derived (i) directly from capillary tubes embedded in air and (ii) indirectly from 10 mm-diameter sphere of the NEMA phantom. Different signal-to-background ratios (SBRs), background activity levels and acquisition times were applied. The emission data were reconstructed using iterative reconstruction protocols. Various combinations of iterations and subsets (it × sub) were evaluated.

RESULTS

For capillary tubes, improved FWHM values were obtained for higher it × sub, with improved performance for PSF algorithms relative to non-PSF algorithms. For the NEMA phantom, by increasing acquisition times from 1 to 5 min, intrinsic FWHM for reconstructions with it × sub 32 (54) was improved by 15.3% (13.2%), 15.1% (13.8%), 14.5% (12.8%) and 13.7% (12.7%) for OSEM, OSEM + PSF, OSEM + TOF and OSEM + PSF + TOF, respectively. Furthermore, for all reconstruction protocols, the FWHM improved with more impact for higher it × sub.

CONCLUSION

Our results indicate that PET spatial resolution is greatly affected by SBR, background activity and the choice of the reconstruction protocols.

The role of artificial intelligence in medical imaging research

Without doubt, artificial intelligence (AI) is the most discussed topic today in medical imaging research, both in diagnostic and therapeutic. For diagnostic imaging alone, the number of publications on AI has increased from about 100-150 per year in 2007-2008 to 1000-1100 per year in 2017-2018. Researchers have applied AI to automatically recognizing complex patterns in imaging data and providing quantitative assessments of radiographic characteristics. In radiation oncology, AI has been applied on different image modalities that are used at different stages of the treatment. i.e. tumor delineation and treatment assessment. Radiomics, the extraction of a large number of image features from radiation images with a high-throughput approach, is one of the most popular research topics today in medical imaging research. AI is the essential boosting power of processing massive number of medical images and therefore uncovers disease characteristics that fail to be appreciated by the naked eyes. The objectives of this paper are to review the history of AI in medical imaging research, the current role, the challenges need to be resolved before AI can be adopted widely in the clinic, and the potential future.

Joint compensation of motion and partial volume effects by iterative deconvolution incorporating wavelet-based denoising in oncologic PET/CT imaging

OBJECTIVES

We aim to develop and rigorously evaluate an image-based deconvolution method to jointly compensate respiratory motion and partial volume effects (PVEs) for quantitative oncologic PET imaging, including studying the impact of various reconstruction algorithms on quantification performance.

PROCEDURES

An image-based deconvolution method that incorporated wavelet-based denoising within the Lucy-Richardson algorithm was implemented and assessed. The method was evaluated using phantom studies with signal-to-background ratios (SBR) of 4 and 8, and clinical data of 10 patients with 42 lung lesions ≤30 mm in diameter. In each study, PET images were reconstructed using four different algorithms: OSEM-basic, PSF, TOF, and TOFPSF. The performance was quantified using contrast recovery (CR), coefficient of variation (COV) and contrast-to-noise-ratio (CNR) metrics. Further, in each study, variabilities arising due to the four different reconstruction algorithms were assessed.

RESULTS

In phantom studies, incorporation of wavelet-based denoising improved COV in all cases. Processing images using proposed method yielded significantly higher CR and CNR particularly in small spheres, for all reconstruction algorithms and all SBRs (P < 0.05). In patient studies, processing images using the proposed method yielded significantly higher CR and CNR (P < 0.05). The choice of the reconstruction algorithm impacted quantification performance for changes in motion amplitude, tumor size and SBRs.

CONCLUSIONS

Our results provide strong evidence that the proposed joint-compensation method can yield improved PET quantification. The choice of the reconstruction algorithm led to changes in quantitative accuracy, emphasizing the need to carefully select the right combination of reconstruction-image-based compensation methods.

Changes on Midchemoradiation Therapy Fluorodeoxyglucose Positron Emission Tomography for Cervical Cancer Are Associated with Prognosis

PURPOSE

To assess whether radiographic and metabolic changes on midchemoradiation therapy (CRT) fluorodeoxyglucose positron emission tomography and computed tomography (FDG-PET/CT) for cervical cancer predict outcome.

METHODS AND MATERIALS

Women with International Federation of Gynecology and Obstetrics stage IB1-IVB cervical cancer treated with concurrent cisplatin-based CRT and brachytherapy were enrolled on a single-institution prospective clinical trial; FDG-PET/CT was obtained before CRT and at 30 to 36 Gy. Max and mean standard uptake values, metabolic tumor volume, and total lesion glycolysis (TLG) for the primary tumor and clinically involved lymph nodes from the pre-CRT and intra-CRT FDG-PET/CT were recorded. Clinical endpoints analyzed include overall survival (OS), disease-free survival (DFS), and rates of cervical recurrence (CR), nodal recurrence (NR), and distant metastasis (DM). FDG-PET/CT variables and other prognostic factors associated with clinical endpoints were identified via univariate Cox proportional hazards modeling and competing risk analysis.

RESULTS

Thirty women were enrolled from 2012 to 2016. After a median follow-up of 24 months, 2-year rates of OS, DFS, DM, NR, and CR were 68% (95% confidence interval [CI], 51%-85%), 44% (95% CI, 26%-63%), 42% (95% CI, 23%-59%), 14% (95% CI, 4%-30%), and 10% (95% CI, 2%-24%), respectively. Intra-PET metrics and TLG across all PET scans were most consistently associated with OS, DFS, DM, and NR on univariate analysis. Intra-CRT TLG was associated with OS (hazard ratio [HR] 1.35; 95% CI, 1.15-1.55; P = .001), DFS (HR 1.19; 95% CI, 1.04-1.34; P = .018), and NR (HR 1.25; 95% CI, 1.10-1.40; P = .002). No absolute or relative changes between parameters of baseline and mid-CRT FDG-PET/CT were associated with disease outcomes on univariate analysis, with the exception of relative change in mean standard uptake values and CR (P = .004).

CONCLUSIONS

In this group of patients with high-risk cervical cancer treated with CRT and brachytherapy, TLG and metabolic tumor volume on intra-CRT FDG-PET/CT was associated with OS. These metrics may provide an early signal for selective treatment intensification with either dose escalation or adjuvant chemotherapy.

Integrating radiomics into clinical trial design

In radiomics, quantitative features that describe phenotypic tumor characteristics are derived from radiographic images. Because radiomics generates information from routine medical images, it is a powerful way to non-invasively examine the spatial and temporal heterogeneity of disease, and thus has potential to significantly impact clinical trial design, execution, and ultimately patient care. The aim of this review article is to discuss how radiomics may address some of the current challenges in clinical randomized control trials, and the difficulties of integrating robust and repeatable radiomics analysis into trial design. Each step of the radiomics process, including image acquisition and reconstruction, image segmentation, feature extraction, and computational analysis, requires extensive standardization in order to be successfully incorporated into clinical trials and inform clinical decision making. By addressing these challenges, the potential of radiomics may be realized.

NCTN Assessment on Current Applications of Radiomics in Oncology

Radiomics is a fast-growing research area based on converting standard-of-care imaging into quantitative minable data and building subsequent predictive models to personalize treatment. Radiomics has been proposed as a study objective in clinical trial concepts and a potential biomarker for stratifying patients across interventional treatment arms. In recognizing the growing importance of radiomics in oncology, a group of medical physicists and clinicians from NRG Oncology reviewed the current status of the field and identified critical issues, providing a general assessment and early recommendations for incorporation in oncology studies.

Machine Learning and Imaging Informatics in Oncology

In the era of personalized and precision medicine, informatics technologies utilizing machine learning (ML) and quantitative imaging are witnessing a rapidly increasing role in medicine in general and in oncology in particular. This expanding role ranges from computer-aided diagnosis to decision support of treatments with the potential to transform the current landscape of cancer management. In this review, we aim to provide an overview of ML methodologies and imaging informatics techniques and their recent application in modern oncology. We will review example applications of ML in oncology from the literature, identify current challenges and highlight future potentials.

Novel Quantitative PET Techniques for Clinical Decision Support in Oncology

Quantitative image analysis has deep roots in the usage of positron emission tomography (PET) in clinical and research settings to address a wide variety of diseases. It has been extensively employed to assess molecular and physiological biomarkers in vivo in healthy and disease states, in oncology, cardiology, neurology, and psychiatry. Quantitative PET allows relating the time-varying activity concentration in tissues/organs of interest and the basic functional parameters governing the biological processes being studied. Yet, quantitative PET is challenged by a number of degrading physical factors related to the physics of PET imaging, the limitations of the instrumentation used, and the physiological status of the patient. Moreover, there is no consensus on the most reliable and robust image-derived PET metric(s) that can be used with confidence in clinical oncology owing to the discrepancies between the conclusions reported in the literature. There is also increasing interest in the use of artificial intelligence based techniques, particularly machine learning and deep learning techniques in a variety of applications to extract quantitative features (radiomics) from PET including image segmentation and outcome prediction in clinical oncology. These novel techniques are revolutionizing clinical practice and are now offering unique capabilities to the clinical molecular imaging community and biomedical researchers at large. In this report, we summarize recent developments and future tendencies in quantitative PET imaging and present example applications in clinical decision support to illustrate its potential in the context of clinical oncology.

A multiobjective Bayesian networks approach for joint prediction of tumor local control and radiation pneumonitis in nonsmall-cell lung cancer (NSCLC) for response-adapted radiotherapy

PURPOSE

Individualization of therapeutic outcomes in NSCLC radiotherapy is likely to be compromised by the lack of proper balance of biophysical factors affecting both tumor local control (LC) and side effects such as radiation pneumonitis (RP), which are likely to be intertwined. Here, we compare the performance of separate and joint outcomes predictions for response-adapted personalized treatment planning.

METHODS

A total of 118 NSCLC patients treated on prospective protocols with 32 cases of local progression and 20 cases of RP grade 2 or higher (RP2) were studied. Sixty-eight patients with 297 features before and during radiotherapy were used for discovery and 50 patients were reserved for independent testing. A multiobjective Bayesian network (MO-BN) approach was developed to identify important features for joint LC/RP2 prediction using extended Markov blankets as inputs to develop a BN predictive structure. Cross-validation (CV) was used to guide the MO-BN structure learning. Area under the free-response receiver operating characteristic (AU-FROC) curve was used to evaluate joint prediction performance.

RESULTS

Important features including single nucleotide polymorphisms (SNPs), micro RNAs, pretreatment cytokines, pretreatment PET radiomics together with lung and tumor gEUDs were selected and their biophysical inter-relationships with radiation outcomes (LC and RP2) were identified in a pretreatment MO-BN. The joint LC/RP2 prediction yielded an AU-FROC of 0.80 (95% CI: 0.70-0.86) upon internal CV. This improved to 0.85 (0.75-0.91) with additional two SNPs, changes in one cytokine and two radiomics PET image features through the course of radiotherapy in a during-treatment MO-BN. This MO-BN model outperformed combined single-objective Bayesian networks (SO-BNs) during-treatment [0.78 (0.67-0.84)]. AU-FROC values in the evaluation of the MO-BN and individual SO-BNs on the testing dataset were 0.77 and 0.68 for pretreatment, and 0.79 and 0.71 for during-treatment, respectively.

CONCLUSIONS

MO-BNs can reveal possible biophysical cross-talks between competing radiotherapy clinical endpoints. The prediction is improved by providing additional during-treatment information. The developed MO-BNs can be an important component of decision support systems for personalized response-adapted radiotherapy.

Development of a Fully Cross-Validated Bayesian Network Approach for Local Control Prediction in Lung Cancer

The purpose of this study is to demonstrate that a Bayesian network (BN) approach can explore hierarchical biophysical relationships that influence tumor response and predict tumor local control (LC) in non-small-cell lung cancer (NSCLC) patients before and during radiotherapy from a large-scale dataset. Our BN building approach has two steps. First, relevant biophysical predictors influencing LC before and during the treatment are selected through an extended Markov blanket (eMB) method. From this eMB process, the most robust BN structure for LC prediction was found via a wrapper-based approach. Sixty-eight patients with complete feature information were used to identify a full BN model for LC prediction before and during the treatment. Fifty more recent patients with some missing information were reserved for independent testing of the developed pre- and during-therapy BNs. A nested cross-validation (N-CV) was developed to evaluate the performance of the two-step BN approach. An ensemble BN model is generated from the N-CV sampling process to assess its similarity with the corresponding full BN model, and thus evaluate the sensitivity of our BN approach. Our results show that the proposed BN development approach is a stable and robust approach to identify hierarchical relationships among biophysical features for LC prediction. Furthermore, BN predictions can be improved by incorporating during treatment information.

Investigating multi-radiomic models for enhancing prediction power of cervical cancer treatment outcomes

Quantitative image features, also known as radiomic features, have shown potential for predicting treatment outcomes in several body sites. We quantitatively analyzed ¹⁸Fluorine-fluorodeoxyglucose (¹⁸F-FDG) Positron Emission Tomography (PET) uptake heterogeneity in the Metabolic Tumor Volume (MTV) of eighty cervical cancer patients to investigate the predictive performance of radiomic features for two treatment outcomes: the development of distant metastases (DM) and loco-regional recurrent disease (LRR). We aimed to fit the highest predictive features in multiple logistic regression models (MLRs). To generate such models, we applied backward feature selection method as part of Leave-One-Out Cross Validation (LOOCV) within a training set consisting of 70% of the original patient cohort. The trained MLRs were tested on an independent set consisted of 30% of the original cohort. We evaluated the performance of the final models using the Area under the Receiver Operator Characteristic Curve (AUC). Accordingly, six models demonstrated superior predictive performance for both outcomes (four for DM and two for LRR) when compared to both univariate-radiomic feature models and Standard Uptake Value (SUV) measurements. This demonstrated approach suggests that the ability of the pre-radiochemotherapy PET radiomics to stratify patient risk for DM and LRR could potentially guide management decisions such as adjuvant systemic therapy or radiation dose escalation.

Deep reinforcement learning for automated radiation adaptation in lung cancer

PURPOSE

To investigate deep reinforcement learning (DRL) based on historical treatment plans for developing automated radiation adaptation protocols for nonsmall cell lung cancer (NSCLC) patients that aim to maximize tumor local control at reduced rates of radiation pneumonitis grade 2 (RP2).

METHODS

In a retrospective population of 114 NSCLC patients who received radiotherapy, a three-component neural networks framework was developed for deep reinforcement learning (DRL) of dose fractionation adaptation. Large-scale patient characteristics included clinical, genetic, and imaging radiomics features in addition to tumor and lung dosimetric variables. First, a generative adversarial network (GAN) was employed to learn patient population characteristics necessary for DRL training from a relatively limited sample size. Second, a radiotherapy artificial environment (RAE) was reconstructed by a deep neural network (DNN) utilizing both original and synthetic data (by GAN) to estimate the transition probabilities for adaptation of personalized radiotherapy patients' treatment courses. Third, a deep Q-network (DQN) was applied to the RAE for choosing the optimal dose in a response-adapted treatment setting. This multicomponent reinforcement learning approach was benchmarked against real clinical decisions that were applied in an adaptive dose escalation clinical protocol. In which, 34 patients were treated based on avid PET signal in the tumor and constrained by a 17.2% normal tissue complication probability (NTCP) limit for RP2. The uncomplicated cure probability (P+) was used as a baseline reward function in the DRL.

RESULTS

Taking our adaptive dose escalation protocol as a blueprint for the proposed DRL (GAN + RAE + DQN) architecture, we obtained an automated dose adaptation estimate for use at ∼2/3 of the way into the radiotherapy treatment course. By letting the DQN component freely control the estimated adaptive dose per fraction (ranging from 1-5 Gy), the DRL automatically favored dose escalation/de-escalation between 1.5 and 3.8 Gy, a range similar to that used in the clinical protocol. The same DQN yielded two patterns of dose escalation for the 34 test patients, but with different reward variants. First, using the baseline P+ reward function, individual adaptive fraction doses of the DQN had similar tendencies to the clinical data with an RMSE = 0.76 Gy; but adaptations suggested by the DQN were generally lower in magnitude (less aggressive). Second, by adjusting the P+ reward function with higher emphasis on mitigating local failure, better matching of doses between the DQN and the clinical protocol was achieved with an RMSE = 0.5 Gy. Moreover, the decisions selected by the DQN seemed to have better concordance with patients eventual outcomes. In comparison, the traditional temporal difference (TD) algorithm for reinforcement learning yielded an RMSE = 3.3 Gy due to numerical instabilities and lack of sufficient learning.

CONCLUSION

We demonstrated that automated dose adaptation by DRL is a feasible and a promising approach for achieving similar results to those chosen by clinicians. The process may require customization of the reward function if individual cases were to be considered. However, development of this framework into a fully credible autonomous system for clinical decision support would require further validation on larger multi-institutional datasets.

The influence of ketogenic therapy on the 5 R's of radiobiology

PURPOSE

Radiotherapy (RT) is a mainstay in the treatment of solid tumors and works by inducing free radical stress in tumor cells, leading to loss of reproductive integrity. The optimal treatment strategy has to consider damage to both tumor and normal cells and is determined by five factors known as the 5 R's of radiobiology: Reoxygenation, DNA repair, radiosensitivity, redistribution in the cell cycle and repopulation. The aim of this review is (i) to present evidence that these 5 R's are strongly influenced by cellular and whole-body metabolism that in turn can be modified through ketogenic therapy in form of ketogenic diets and short-term fasting and (ii) to stimulate new research into this field including some research questions deserving further study.

CONCLUSIONS

Preclinical and some preliminary clinical data support the hypothesis that ketogenic therapy could be utilized as a complementary treatment in order to improve the outcome after RT, both in terms of higher tumor control and in terms of lower normal tissue complication probability. The first effect relates to the metabolic shift from glycolysis toward mitochondrial metabolism that selectively increases ROS production and impairs ATP production in tumor cells. The second effect is based on the differential stress resistance phenomenon, which is achieved when glucose and growth factors are reduced and ketone bodies are elevated, reprogramming normal but not tumor cells from proliferation toward maintenance and stress resistance. Underlying both effects are metabolic differences between normal and tumor cells that ketogenic therapy seeks to exploit. Specifically, the recently discovered role of the ketone body β-hydroxybutyrate as an endogenous class-I histone deacetylase inhibitor suggests a dual role as a radioprotector of normal cells and a radiosensitzer of tumor cells that opens up exciting possibilities to employ ketogenic therapy as a cost-effective adjunct to radiotherapy against cancer.

Development and clinical application of radiomics in lung cancer

Since the discovery of X-rays at the end of the 19^th century, medical imageology has progressed for 100 years, and medical imaging has become an important auxiliary tool for clinical diagnosis. With the launch of the human genome project (HGP) and the development of various high-throughput detection techniques, disease exploration in the post-genome era has extended beyond investigations of structural changes to in-depth analyses of molecular abnormalities in tissues, organs and cells, on the basis of gene expression and epigenetics. These techniques have given rise to genomics, proteomics, metabolomics and other systems biology subspecialties, including radiogenomics. Radiogenomics is an important revolution in the traditional visually identifiable imaging technology and constitutes a new branch, radiomics. Radiomics is aimed at extracting quantitative imaging features automatically and developing models to predict lesion phenotypes in a non-invasive manner. Here, we summarize the advent and development of radiomics, the basic process and challenges in clinical practice, with a focus on applications in pulmonary nodule evaluations, including diagnostics, pathological and molecular classifications, treatment response assessments and prognostic predictions, especially in radiotherapy.

Reproducibility of F18-FDG PET radiomic features for different cervical tumor segmentation methods, gray-level discretization, and reconstruction algorithms

Site‐specific investigations of the role of radiomics in cancer diagnosis and therapy are emerging. We evaluated the reproducibility of radiomic features extracted from ¹⁸Flourine–fluorodeoxyglucose (¹⁸F‐FDG) PET images for three parameters: manual versus computer‐aided segmentation methods, gray‐level discretization, and PET image reconstruction algorithms. Our cohort consisted of pretreatment PET/CT scans from 88 cervical cancer patients. Two board‐certified radiation oncologists manually segmented the metabolic tumor volume (MTV₁ and MTV₂) for each patient. For comparison, we used a graphical‐based method to generate semiautomated segmented volumes (GBSV). To address any perturbations in radiomic feature values, we down‐sampled the tumor volumes into three gray‐levels: 32, 64, and 128 from the original gray‐level of 256. Finally, we analyzed the effect on radiomic features on PET images of eight patients due to four PET 3D‐reconstruction algorithms: maximum likelihood‐ordered subset expectation maximization (OSEM) iterative reconstruction (IR) method, fourier rebinning‐ML‐OSEM (FOREIR), FORE‐filtered back projection (FOREFBP), and 3D‐Reprojection (3DRP) analytical method. We extracted 79 features from all segmentation method, gray‐levels of down‐sampled volumes, and PET reconstruction algorithms. The features were extracted using gray‐level co‐occurrence matrices (GLCM), gray‐level size zone matrices (GLSZM), gray‐level run‐length matrices (GLRLM), neighborhood gray‐tone difference matrices (NGTDM), shape‐based features (SF), and intensity histogram features (IHF). We computed the Dice coefficient between each MTV and GBSV to measure segmentation accuracy. Coefficient values close to one indicate high agreement, and values close to zero indicate low agreement. We evaluated the effect on radiomic features by calculating the mean percentage differences (d¯) between feature values measured from each pair of parameter elements (i.e. segmentation methods: MTV₁‐MTV₂, MTV₁‐GBSV, MTV₂‐GBSV; gray‐levels: 64‐32, 64‐128, and 64‐256; reconstruction algorithms: OSEM‐FORE‐OSEM, OSEM‐FOREFBP, and OSEM‐3DRP). We used |d¯| as a measure of radiomic feature reproducibility level, where any feature scored |d¯| ±SD ≤ |25|% ± 35% was considered reproducible. We used Bland–Altman analysis to evaluate the mean, standard deviation (SD), and upper/lower reproducibility limits (U/LRL) for radiomic features in response to variation in each testing parameter. Furthermore, we proposed U/LRL as a method to classify the level of reproducibility: High— ±1% ≤ U/LRL ≤ ±30%; Intermediate— ±30% < U/LRL ≤ ±45%; Low— ±45 < U/LRL ≤ ±50%. We considered any feature below the low level as nonreproducible (NR). Finally, we calculated the interclass correlation coefficient (ICC) to evaluate the reliability of radiomic feature measurements for each parameter. The segmented volumes of 65 patients (81.3%) scored Dice coefficient >0.75 for all three volumes. The result outcomes revealed a tendency of higher radiomic feature reproducibility among segmentation pair MTV₁‐GBSV than MTV₂‐GBSV, gray‐level pairs of 64‐32 and 64‐128 than 64‐256, and reconstruction algorithm pairs of OSEM‐FOREIR and OSEM‐FOREFBP than OSEM‐3DRP. Although the choice of cervical tumor segmentation method, gray‐level value, and reconstruction algorithm may affect radiomic features, some features were characterized by high reproducibility through all testing parameters. The number of radiomic features that showed insensitivity to variations in segmentation methods, gray‐level discretization, and reconstruction algorithms was 10 (13%), 4 (5%), and 1 (1%), respectively. These results suggest that a careful analysis of the effects of these parameters is essential prior to any radiomics clinical application.

Radiogenomics and radiotherapy response modeling

Advances in patient-specific information and biotechnology have contributed to a new era of computational medicine. Radiogenomics has emerged as a new field that investigates the role of genetics in treatment response to radiation therapy. Radiation oncology is currently attempting to embrace these recent advances and add to its rich history by maintaining its prominent role as a quantitative leader in oncologic response modeling. Here, we provide an overview of radiogenomics starting with genotyping, data aggregation, and application of different modeling approaches based on modifying traditional radiobiological methods or application of advanced machine learning techniques. We highlight the current status and potential for this new field to reshape the landscape of outcome modeling in radiotherapy and drive future advances in computational oncology.

Beyond imaging: The promise of radiomics

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

No-gold-standard evaluation of image-acquisition methods using patient data

Several new and improved modalities, scanners, and protocols, together referred to as image-acquisition methods (IAMs), are being developed to provide reliable quantitative imaging. Objective evaluation of these IAMs on the clinically relevant quantitative tasks is highly desirable. Such evaluation is most reliable and clinically decisive when performed with patient data, but that requires the availability of a gold standard, which is often rare. While no-gold-standard (NGS) techniques have been developed to clinically evaluate quantitative imaging methods, these techniques require that each of the patients be scanned using all the IAMs, which is expensive, time consuming, and could lead to increased radiation dose. A more clinically practical scenario is where different set of patients are scanned using different IAMs. We have developed an NGS technique that uses patient data where different patient sets are imaged using different IAMs to compare the different IAMs. The technique posits a linear relationship, characterized by a slope, bias, and noise standard-deviation term, between the true and measured quantitative values. Under the assumption that the true quantitative values have been sampled from a unimodal distribution, a maximum-likelihood procedure was developed that estimates these linear relationship parameters for the different IAMs. Figures of merit can be estimated using these linear relationship parameters to evaluate the IAMs on the basis of accuracy, precision, and overall reliability. The proposed technique has several potential applications such as in protocol optimization, quantifying difference in system performance, and system harmonization using patient data.

Outcome modeling techniques for prostate cancer radiotherapy: Data, models, and validation

Prostate cancer is a frequently diagnosed malignancy worldwide and radiation therapy is a first-line approach in treating localized as well as locally advanced cases. The limiting factor in modern radiotherapy regimens is dose to normal structures, an excess of which can lead to aberrant radiation-induced toxicities. Conversely, dose reduction to spare adjacent normal structures risks underdosing target volumes and compromising local control. As a result, efforts aimed at predicting the effects of radiotherapy could invaluably optimize patient treatments by mitigating such toxicities and simultaneously maximizing biochemical control. In this work, we review the types of data, frameworks and techniques used for prostate radiotherapy outcome modeling. Consideration is given to clinical and dose-volume metrics, such as those amassed by the QUANTEC initiative, and also to newer methods for the integration of biological and genetic factors to improve prediction performance. We furthermore highlight trends in machine learning that may help to elucidate the complex pathophysiological mechanisms of tumor control and radiation-induced normal tissue side effects.

A no-gold-standard technique for objective assessment of quantitative nuclear-medicine imaging methods

The objective optimization and evaluation of nuclear-medicine quantitative imaging methods using patient data is highly desirable but often hindered by the lack of a gold standard. Previously, a regression-without-truth (RWT) approach has been proposed for evaluating quantitative imaging methods in the absence of a gold standard, but this approach implicitly assumes that bounds on the distribution of true values are known. Several quantitative imaging methods in nuclear-medicine imaging measure parameters where these bounds are not known, such as the activity concentration in an organ or the volume of a tumor. We extended upon the RWT approach to develop a no-gold-standard (NGS) technique for objectively evaluating such quantitative nuclear-medicine imaging methods with patient data in the absence of any ground truth. Using the parameters estimated with the NGS technique, a figure of merit, the noise-to-slope ratio (NSR), can be computed, which can rank the methods on the basis of precision. An issue with NGS evaluation techniques is the requirement of a large number of patient studies. To reduce this requirement, the proposed method explored the use of multiple quantitative measurements from the same patient, such as the activity concentration values from different organs in the same patient. The proposed technique was evaluated using rigorous numerical experiments and using data from realistic simulation studies. The numerical experiments demonstrated that the NSR was estimated accurately using the proposed NGS technique when the bounds on the distribution of true values were not precisely known, thus serving as a very reliable metric for ranking the methods on the basis of precision. In the realistic simulation study, the NGS technique was used to rank reconstruction methods for quantitative single-photon emission computed tomography (SPECT) based on their performance on the task of estimating the mean activity concentration within a known volume of interest. Results showed that the proposed technique provided accurate ranking of the reconstruction methods for 97.5% of the 50 noise realizations. Further, the technique was robust to the choice of evaluated reconstruction methods. The simulation study pointed to possible violations of the assumptions made in the NGS technique under clinical scenarios. However, numerical experiments indicated that the NGS technique was robust in ranking methods even when there was some degree of such violation.

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.

Respiration-Averaged CT for Attenuation Correction of PET Images - Impact on PET Texture Features in Non-Small Cell Lung Cancer Patients

PURPOSE

We compared attenuation correction of PET images with helical CT (PET/HCT) and respiration-averaged CT (PET/ACT) in patients with non-small-cell lung cancer (NSCLC) with the goal of investigating the impact of respiration-averaged CT on 18F FDG PET texture parameters.

MATERIALS AND METHODS

A total of 56 patients were enrolled. Tumors were segmented on pretreatment PET images using the adaptive threshold. Twelve different texture parameters were computed: standard uptake value (SUV) entropy, uniformity, entropy, dissimilarity, homogeneity, coarseness, busyness, contrast, complexity, grey-level nonuniformity, zone-size nonuniformity, and high grey-level large zone emphasis. Comparisons of PET/HCT and PET/ACT were performed using Wilcoxon signed-rank tests, intraclass correlation coefficients, and Bland-Altman analysis. Receiver operating characteristic (ROC) curves as well as univariate and multivariate Cox regression analyses were used to identify the parameters significantly associated with disease-specific survival (DSS). A fixed threshold at 45% of the maximum SUV (T45) was used for validation.

RESULTS

SUV maximum and total lesion glycolysis (TLG) were significantly higher in PET/ACT. However, texture parameters obtained with PET/ACT and PET/HCT showed a high degree of agreement. The lowest levels of variation between the two modalities were observed for SUV entropy (9.7%) and entropy (9.8%). SUV entropy, entropy, and coarseness from both PET/ACT and PET/HCT were significantly associated with DSS. Validation analyses using T45 confirmed the usefulness of SUV entropy and entropy in both PET/HCT and PET/ACT for the prediction of DSS, but only coarseness from PET/ACT achieved the statistical significance threshold.

CONCLUSIONS

Our results indicate that 1) texture parameters from PET/ACT are clinically useful in the prediction of survival in NSCLC patients and 2) SUV entropy and entropy are robust to attenuation correction methods.

Pretreatment 18F-FDG PET Textural Features in Locally Advanced Non-Small Cell Lung Cancer: Secondary Analysis of ACRIN 6668/RTOG 0235

In a secondary analysis of American College of Radiology Imaging Network (ACRIN) 6668/RTOG 0235, high pretreatment metabolic tumor volume (MTV) on (18)F-FDG PET was found to be a poor prognostic factor for patients treated with chemoradiotherapy for locally advanced non-small cell lung cancer (NSCLC). Here we utilize the same dataset to explore whether heterogeneity metrics based on PET textural features can provide additional prognostic information.

METHODS

Patients with locally advanced NSCLC underwent (18)F-FDG PET prior to treatment. A gradient-based segmentation tool was used to contour each patient's primary tumor. MTV, maximum SUV, and 43 textural features were extracted for each tumor. To address overfitting and high collinearity among PET features, the least absolute shrinkage and selection operator (LASSO) method was applied to identify features that were independent predictors of overall survival (OS) after adjusting for MTV. Recursive binary partitioning in a conditional inference framework was utilized to identify optimal thresholds. Kaplan-Meier curves and log-rank testing were used to compare outcomes among patient groups.

RESULTS

Two hundred one patients met inclusion criteria. The LASSO procedure identified 1 textural feature (SumMean) as an independent predictor of OS. The optimal cutpoint for MTV was 93.3 cm(3), and the optimal SumMean cutpoint for tumors above 93.3 cm(3) was 0.018. This grouped patients into three categories: low tumor MTV (n = 155; median OS, 22.6 mo), high tumor MTV and high SumMean (n = 23; median OS, 20.0 mo), and high tumor MTV and low SumMean (n = 23; median OS, 6.2 mo; log-rank P < 0.001).

CONCLUSION

We have described an appropriate methodology to evaluate the prognostic value of textural PET features in the context of established prognostic factors. We have also identified a promising feature that may have prognostic value in locally advanced NSCLC patients with large tumors who are treated with chemoradiotherapy. Validation studies are warranted.

The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis

FDG-PET-derived textural features describing intra-tumor heterogeneity are increasingly investigated as imaging biomarkers. As part of the process of quantifying heterogeneity, image intensities (SUVs) are typically resampled into a reduced number of discrete bins. We focused on the implications of the manner in which this discretization is implemented. Two methods were evaluated: (1) R_D, dividing the SUV range into D equally spaced bins, where the intensity resolution (i.e. bin size) varies per image; and (2) R_B, maintaining a constant intensity resolution B. Clinical feasibility was assessed on 35 lung cancer patients, imaged before and in the second week of radiotherapy. Forty-four textural features were determined for different D and B for both imaging time points. Feature values depended on the intensity resolution and out of both assessed methods, R_B was shown to allow for a meaningful inter- and intra-patient comparison of feature values. Overall, patients ranked differently according to feature values–which was used as a surrogate for textural feature interpretation–between both discretization methods. Our study shows that the manner of SUV discretization has a crucial effect on the resulting textural features and the interpretation thereof, emphasizing the importance of standardized methodology in tumor texture analysis.

An update on novel quantitative techniques in the context of evolving whole-body PET imaging

Since its foundation PET has established itself as one of the standard imaging modalities enabling the quantitative assessment of molecular targets in vivo. In the past two decades, quantitative PET has become a necessity in clinical oncology. Despite introduction of various measures for quantification and correction of PET parameters, there is debate on the selection of the appropriate methodology in specific diseases and conditions. In this review, we have focused on these techniques with special attention to topics such as static and dynamic whole body PET imaging, tracer kinetic modeling, global disease burden, texture analysis and radiomics, dual time point imaging and partial volume correction.