Explore the vast range of titles available.

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.

Purpose PET quantification based on standardized uptake values (SUV) is hampered by several factors, in particular by variability in PET acquisition settings and data analysis methods. Quantitative PET/CT studies acquired during a multicentre trial require harmonization of imaging procedures to maximize study power. The aims of this study were to determine which phantoms are most suitable for detecting differences in image quality and quantification, and which methods for defining volumes of interest (VOI) are least sensitive to these differences. Methods The most common accreditation phantoms used in oncology FDG PET/CT trials were scanned on the same scanner. These phantoms were those used by the Society of Nuclear Medicine Clinical Trials Network (SNM-CTN), the European Association of Nuclear Medicine/National Electrical Manufacturers Association (EANM/NEMA) and the American College of Radiology (ACR). In addition, tumour SUVs were derived from ten oncology whole-body examinations performed on the same PET/CT system. Both phantom and clinical data were reconstructed using different numbers of iterations, subsets and time-of-flight kernel widths. Subsequently, different VOI methods (VOI A50%, VOI max , VOI 3Dpeak, VOI 2Dpeak ) were applied to assess the impact of changes in image reconstruction settings on SUV and recovery coefficients (RC). Results All phantoms demonstrated sensitivity for detecting changes in SUV and RC measures in response to changes in image reconstruction settings and VOI analysis methods. The SNM-CTN and EANM/NEMA phantoms showed almost equal sensitivity in detecting RC differences with changes in image characteristics. Phantom and clinical data demonstrated that the VOI analysis methods VOI A50% and VOI max gave SUV and RC values with large variability in relation to image characteristics, whereas VOI 3Dpeak and VOI 2Dpeak were less sensitive to these differences. Conclusion All three phantoms may be used to harmonize parameters for data acquisition, processing and analysis. However, the SNM-CTN and EANM/NEMA phantoms are the most sensitive to parameter changes and are suitable for harmonizing SUV quantification based on 3D VOIs, such as VOI A50% and VOI 3Dpeak , and VOI max . Variability in SUV quantification after harmonization could be further minimized using VOI 3Dpeak analysis, which was least sensitive to residual variability in image quality and quantification.

Quantitative biomarkers from medical images are becoming important tools for clinical diagnosis, staging, monitoring, treatment planning, and development of new therapies. While there is a rich history of the development of quantitative imaging biomarker (QIB) techniques, little attention has been paid to the validation and comparison of the computer algorithms that implement the QIB measurements. In this paper we provide a framework for QIB algorithm comparisons. We first review and compare various study designs, including designs with the true value (e.g. phantoms, digital reference images, and zero-change studies), designs with a reference standard (e.g. studies testing equivalence with a reference standard), and designs without a reference standard (e.g. agreement studies and studies of algorithm precision). The statistical methods for comparing QIB algorithms are then presented for various study types using both aggregate and disaggregate approaches. We propose a series of steps for establishing the performance of a QIB algorithm, identify limitations in the current statistical literature, and suggest future directions for research.

Background Patients undergoing chemoradiation and immune checkpoint inhibitor (ICI) therapy for locally advanced non-small cell lung cancer (NSCLC) experience pulmonary toxicity at higher rates than historical reports. Identifying biomarkers beyond conventional clinical factors and radiation dosimetry is especially relevant in the modern cancer immunotherapy era. We investigated the role of novel functional lung radiomics, relative to functional lung dosimetry and clinical characteristics, for pneumonitis risk stratification in locally advanced NSCLC. Methods Patients with locally advanced NSCLC were prospectively enrolled on the FLARE-RT trial (NCT02773238). All received concurrent chemoradiation using functional lung avoidance planning, while approximately half received consolidation durvalumab ICI. Within tumour-subtracted lung regions, 110 radiomics features (size, shape, intensity, texture) were extracted on pre-treatment [ 99m Tc]MAA SPECT/CT perfusion images using fixed-bin-width discretization. The performance of functional lung radiomics for pneumonitis (CTCAE v4 grade 2 or higher) risk stratification was benchmarked against previously reported lung dosimetric parameters and clinical risk factors. Multivariate least absolute shrinkage and selection operator Cox models of time-varying pneumonitis risk were constructed, and prediction performance was evaluated using optimism-adjusted concordance index (c-index) with 95% confidence interval reporting throughout. Results Thirty-nine patients were included in the study and pneumonitis occurred in 16/39 (41%) patients. Among clinical characteristics and anatomic/functional lung dosimetry variables, only the presence of baseline chronic obstructive pulmonary disease (COPD) was significantly associated with the development of pneumonitis (HR 4.59 [1.69–12.49]) and served as the primary prediction benchmark model (c-index 0.69 [0.59–0.80]). Discrimination of time-varying pneumonitis risk was numerically higher when combining COPD with perfused lung radiomics size (c-index 0.77 [0.65–0.88]) or shape feature classes (c-index 0.79 [0.66–0.91]) but did not reach statistical significance compared to benchmark models (p > 0.26). COPD was associated with perfused lung radiomics size features, including patients with larger lung volumes (AUC 0.75 [0.59–0.91]). Perfused lung radiomic texture features were correlated with lung volume (adj R 2  = 0.84–1.00), representing surrogates rather than independent predictors of pneumonitis risk. Conclusions In patients undergoing chemoradiation with functional lung avoidance therapy and optional consolidative immune checkpoint inhibitor therapy for locally advanced NSCLC, the strongest predictor of pneumonitis was the presence of baseline chronic obstructive pulmonary disease. Results from this novel functional lung radiomics exploratory study can inform future validation studies to refine pneumonitis risk models following combinations of radiation and immunotherapy. Our results support functional lung radiomics as surrogates of COPD for non-invasive monitoring during and after treatment. Further study of clinical, dosimetric, and radiomic feature combinations for radiation and immune-mediated pneumonitis risk stratification in a larger patient population is warranted.

Computer-extracted tumour characteristics have been incorporated into medical imaging computer-aided diagnosis (CAD) algorithms for decades. With the advent of radiomics, an extension of CAD involving high-throughput computer-extracted quantitative characterization of healthy or pathological structures and processes as captured by medical imaging, interest in such computer-extracted measurements has increased substantially. However, despite the thousands of radiomic studies, the number of settings in which radiomics has been successfully translated into a clinically useful tool or has obtained FDA clearance is comparatively small. This relative dearth might be attributable to factors such as the varying imaging and radiomic feature extraction protocols used from study to study, the numerous potential pitfalls in the analysis of radiomic data, and the lack of studies showing that acting upon a radiomic-based tool leads to a favourable benefit–risk balance for the patient. Several guidelines on specific aspects of radiomic data acquisition and analysis are already available, although a similar roadmap for the overall process of translating radiomics into tools that can be used in clinical care is needed. Herein, we provide 16 criteria for the effective execution of this process in the hopes that they will guide the development of more clinically useful radiomic tests in the future.Despite a considerable increase in research output over the past decades, the translation of radiomic research into clinically useful tests has been limited. In this Review, the authors provide 16 key criteria to guide the clinical translation of radiomics with the hope of accelerating the use of this technology to improve patient outcomes.

Purpose This study evaluated the ability of 18 F-Fluorodeoxyglucose (FDG) and 18 F-Fluorothymidine (FLT) imaging with positron emission tomography (PET) to measure early response to endocrine therapy from baseline to just prior to surgical resection in estrogen receptor positive (ER+) breast tumors. Methods In two separate studies, women with early stage ER+ breast cancer underwent either paired FDG-PET ( n  = 22) or FLT-PET ( n  = 27) scans prior to endocrine therapy and again in the pre-operative setting. Tissue samples for Ki-67 were taken for all patients both prior to treatment and at the time of surgery. Results FDG maximum standardized uptake value (SUVmax) declined in 19 of 22 lesions (mean 17% (range −45 to 28%)). FLT SUVmax declined in 24 of 27 lesions (mean 26% (range −77 to 7%)). The Ki-67 index declined in both studies, from pre-therapy (mean 23% (range 1 to 73%)) to surgery [mean 8% (range < 1 to 41%)]. Pre- and post-therapy PET measures showed strong rank-order agreement with Ki-67 percentages for both tracers; however, the percent change in FDG or FLT SUVmax did not demonstrate a strong correlation with Ki-67 index change or Ki-67 at time of surgery. Conclusions A window-of-opportunity approach using PET imaging to assess early response of breast cancer therapy is feasible. FDG and FLT-PET imaging following a short course of neoadjuvant endocrine therapy demonstrated measurable changes in SUVmax in early stage ER+ positive breast cancers. The percentage change in FDG and FLT-PET uptake did not correlate with changes in Ki-67; post-therapy SUVmax for both tracers was significantly associated with post-therapy Ki-67, an established predictor of endocrine therapy response.

Image texture analysis (radiomics) uses radiographic images to quantify characteristics that may identify tumour heterogeneity and associated patient outcomes. Using fluoro‐deoxy‐glucose positron emission tomography/computed tomography (FDG‐PET/CT)‐derived data, including quantitative metrics, image texture analysis and other clinical risk factors, we aimed to develop a prognostic model that predicts survival in patients with previously untreated diffuse large B‐cell lymphoma (DLBCL) from GOYA (NCT01287741). Image texture features and clinical risk factors were combined into a random forest model and compared with the international prognostic index (IPI) for DLBCL based on progression‐free survival (PFS) and overall survival (OS) predictions. Baseline FDG‐PET scans were available for 1263 patients, 832 patients of these were cell‐of‐origin (COO)‐evaluable. Patients were stratified by IPI or radiomics features plus clinical risk factors into low‐, intermediate‐ and high‐risk groups. The random forest model with COO subgroups identified a clearer high‐risk population (45% 2‐year PFS [95% confidence interval (CI) 40%–52%]; 65% 2‐year OS [95% CI 59%–71%]) than the IPI (58% 2‐year PFS [95% CI 50%–67%]; 69% 2‐year OS [95% CI 62%–77%]). This study confirms that standard clinical risk factors can be combined with PET‐derived image texture features to provide an improved prognostic model predicting survival in untreated DLBCL.

Background Standard measures of response such as Response Evaluation Criteria in Solid Tumors are ineffective for bone lesions, often making breast cancer patients that have bone-dominant metastases ineligible for clinical trials with potentially helpful therapies. In this study we prospectively evaluated the test-retest uptake variability of 2-deoxy-2-[18F]fluoro-D-glucose ( 18 F-FDG) in a cohort of breast cancer patients with bone-dominant metastases to determine response criteria. The thresholds for 95% specificity of change versus no-change were then applied to a second cohort of breast cancer patients with bone-dominant metastases. Methods For this study, nine patients with 38 bone lesions were imaged with 18 F-FDG in the same calibrated scanner twice within 14 days. Tumor uptake was quantified by the most commonly used PET parameter, the maximum tumor voxel normalized by dose and body weight (SUVmax) and also by the mean of a 1-cc maximal uptake volume normalized by dose and lean-body-mass (SULpeak). The asymmetric repeatability coefficients with confidence intervals for SUVmax and SULpeak were used to determine the limits of 18 F-FDG uptake variability. A second cohort of 28 breast cancer patients with bone-dominant metastases that had 146 metastatic bone lesions was imaged with 18 F-FDG before and after standard-of-care therapy for response assessment. Results The mean relative difference of SUVmax and SULpeak in 38 bone tumors of the first cohort were 4.3% and 6.7%. The upper and lower asymmetric limits of the repeatability coefficient were 19.4% and − 16.3% for SUVmax, and 21.2% and − 17.5% for SULpeak. 18 F-FDG repeatability coefficient confidence intervals resulted in the following patient stratification using SULpeak for the second patient cohort: 11-progressive disease, 5-stable disease, 7-partial response, and 1-complete response with three inevaluable patients. The asymmetric repeatability coefficients response criteria for SULpeak changed the status of 3 patients compared to the standard Positron Emission Tomography Response Criteria in Solid Tumors of ± 30% SULpeak. Conclusion In evaluating bone tumor response for breast cancer patients with bone-dominant metastases using 18 F-FDG SUVmax, the repeatability coefficients from test-retest studies show that reductions of more than 17% and increases of more than 20% are unlikely to be due to measurement variability. Serial 18 F-FDG imaging in clinical trials investigating bone lesions in these patients, such as the ECOG-ACRIN EA1183 trial, benefit from confidence limits that allow interpretation of response.

The purpose of this study was to measure the errors introduced by regular calibration of PET/CT scanners and to minimize the effect of calibration error on standardized uptake value measurements. Global calibration factors from 2 PET/CT scanners were recorded for 3.5 and 1.8 y, comparing manufacturer-recommended protocols with modified protocols to evaluate error contributions due to operator-influenced procedures. Dose calibrator measurements were evaluated using National Institute of Standards and Technology-traceable sources. Dose calibrator variability was less than 1%, although there was a consistent bias. Global scaling variability was reduced from 6% to 4% for scanner 1 and from 11% to 4% for scanner 2 when quality assurance and quality control procedures were applied to the calibration protocol. When calibrations were done using a (68)Ge/(68)Ga phantom, the variability for both scanners was reduced to approximately 3%. Applying quality assurance and quality control procedures to scanner calibration reduces variability, but there is a still a residual longitudinal scanner variability of 3%-4%. The procedures proposed here reduce the impact of operator error on scanner calibration and thereby minimize longitudinal variability in standardized uptake value measurements.

This work aims to leverage generative modeling-based anomaly detection to enhance interpretability in AI failure detection systems and to aid data curation for large repositories. For failure detection interpretability, this retrospective study utilized 3339 CT scans (525 patients), divided patient-wise into training, baseline test, and anomaly (having failure-causing attributes—e.g., needles, ascites) test datasets. For data curation, 112,120 ChestX-ray14 radiographs were used for training and 2036 radiographs from the Medical Imaging and Data Resource Center for testing, categorized as baseline or anomalous based on attribute alignment with ChestX-ray14. StyleGAN2 networks modeled the training distributions. Test images were reconstructed with backpropagation and scored using mean squared error (MSE) and Wasserstein distance (WD). Scores should be high for anomalous images, as StyleGAN2 cannot model unseen attributes. Area under the receiver operating characteristic curve (AUROC) evaluated anomaly detection, i.e., baseline and anomaly dataset differentiation. The proportion of highest-scoring patches containing needles or ascites assessed anomaly localization. Permutation tests determined statistical significance. StyleGAN2 did not reconstruct anomalous attributes (e.g., needles, ascites), enabling the unsupervised detection of these attributes: mean (±standard deviation) AUROCs were 0.86 (±0.13) for failure detection and 0.82 (±0.11) for data curation. 81% (±13%) of the needles and ascites were localized. WD outperformed MSE on CT (p < 0.001), while MSE outperformed WD on radiography (p < 0.001). Generative models detected anomalous image attributes, demonstrating promise for model failure detection interpretability and large-scale data curation.