Quantitative evaluation of lesion response heterogeneity for superior prognostication of clinical outcome.

PURPOSE: Standardized reporting of treatment response in oncology patients has traditionally relied on methods like RECIST, PERCIST and Deauville score. These endpoints assess only a few lesions, potentially overlooking the response heterogeneity of all disease. This study hypothesizes that comprehensive spatial-temporal evaluation of all individual lesions is necessary for superior prognostication of clinical outcome. METHODS: [18F]FDG PET/CT scans from 241 patients (127 diffuse large B-cell lymphoma (DLBCL) and 114 non-small cell lung cancer (NSCLC)) were retrospectively obtained at baseline and either during chemotherapy or post-chemoradiotherapy. An automated TRAQinform IQ software (AIQ Solutions) analyzed the images, performing quantification of change in regions of interest suspicious of cancer (lesion-ROI). Multivariable Cox proportional hazards (CoxPH) models were trained to predict overall survival (OS) with varied sets of quantitative features and lesion-ROI, compared by bootstrapping with C-index and t-tests. The best-fit model was compared to automated versions of previously established methods like RECIST, PERCIST and Deauville score. RESULTS: Multivariable CoxPH models demonstrated superior prognostic power when trained with features quantifying response heterogeneity in all individual lesion-ROI in DLBCL (C-index = 0.84, p < 0.001) and NSCLC (C-index = 0.71, p < 0.001). Prognostic power significantly deteriorated (p < 0.001) when using subsets of lesion-ROI (C-index = 0.78 and 0.67 for DLBCL and NSCLC, respectively) or excluding response heterogeneity (C-index = 0.67 and 0.70). RECIST, PERCIST, and Deauville score could not significantly associate with OS (C-index < 0.65 and p > 0.1), performing significantly worse than the multivariable models (p < 0.001). CONCLUSIONS: Quantitative evaluation of response heterogeneity of all individual lesions is necessary for the superior prognostication of clinical outcome.

Quantitative Analysis of Serial Positron Emission Tomography Imaging in Men with Metastatic Castration-resistant Prostate Cancer Treated with Enzalutamide.

BACKGROUND: The emergence of positron emission tomography (PET) in prostate cancer is impacting clinical practice, but little is known about PET imaging as a tool to determine treatment failure in metastatic castration-resistant prostate cancer (mCRPC). OBJECTIVE: To evaluate PET imaging dynamics in mCRPC patients on enzalutamide with stable computed tomography (CT) and technetium-99m (Tc99) bone scans. DESIGN, SETTING, AND PARTICIPANTS: All patients were on treatment with enzalutamide for first-line mCRPC in a clinical trial at the National Cancer Institute (Bethesda, MD, USA). A volunteer sample had serial 18F-sodium fluoride (NaF) PET in parallel with CT and Tc99. Regions of interest (ROIs) on NaF were analyzed quantitatively for response. INTERVENTION: Patients were randomized to enzalutamide with/without a cancer immunotherapy, Prostvac. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: A post hoc, descriptive analysis was performed comparing the changes seen on CT and Tc99 as per RECIST 1.1 with NaF PET scans including the use of a quantitative analysis. RESULTS AND LIMITATIONS: Eighteen mCRPC patients had 67 NaF scans. A total of 233 ROIs resolved after treatment, 52 (22%) of which eventually retuned while on therapy. In all, 394 new ROIs were seen, but 112(28%) resolved subsequently. Of 18 patients, 14 had new ROIs that ultimately resolved after appearing. Many patients experienced progression in a minority of lesions, and one patient with radiation intervention to oligoprogression had a remarkable response. This study is limited by its small number of patients and post hoc nature. CONCLUSIONS: These data highlight the dynamic nature of NaF PET in mCRPC patients treated with enzalutamide, where not all new findings were ultimately related to disease progression. This analysis also provides a potential strategy to identify and intervene in oligoprogression in prostate cancer. PATIENT SUMMARY: In this small analysis of patients with prostate cancer on enzalutamide, changes on 18F-sodium fluoride positron emission tomography (PET) imaging were not always associated with treatment failure. Caution may be indicated when using PET imaging to determine whether new therapy is needed.

Multi-organ segmentation of CT via convolutional neural network: impact of training setting and scanner manufacturer.

Objective. Automated organ segmentation on CT images can enable the clinical use of advanced quantitative software devices, but model performance sensitivities must be understood before widespread adoption can occur. The goal of this study was to investigate performance differences between Convolutional Neural Networks (CNNs) trained to segment one (single-class) versus multiple (multi-class) organs, and between CNNs trained on scans from a single manufacturer versus multiple manufacturers.Methods. The multi-class CNN was trained on CT images obtained from 455 whole-body PET/CT scans (413 for training, 42 for testing) taken with Siemens, GE, and Phillips PET/CT scanners where 16 organs were segmented. The multi-class CNN was compared to 16 smaller single-class CNNs trained using the same data, but with segmentations of only one organ per model. In addition, CNNs trained on Siemens-only (N = 186) and GE-only (N = 219) scans (manufacturer-specific) were compared with CNNs trained on data from both Siemens and GE scanners (manufacturer-mixed). Segmentation performance was quantified using five performance metrics, including the Dice Similarity Coefficient (DSC).Results. The multi-class CNN performed well compared to previous studies, even in organs usually considered difficult auto-segmentation targets (e.g., pancreas, bowel). Segmentations from the multi-class CNN were significantly superior to those from smaller single-class CNNs in most organs, and the 16 single-class models took, on average, six times longer to segment all 16 organs compared to the single multi-class model. The manufacturer-mixed approach achieved minimally higher performance over the manufacturer-specific approach.Significance. A CNN trained on contours of multiple organs and CT data from multiple manufacturers yielded high-quality segmentations. Such a model is an essential enabler of image processing in a software device that quantifies and analyzes such data to determine a patient's treatment response. To date, this activity of whole organ segmentation has not been adopted due to the intense manual workload and time required.

Performance of an automated registration-based method for longitudinal lesion matching and comparison to inter-reader variability.

Objective.Patients with metastatic disease are followed throughout treatment with medical imaging, and accurately assessing changes of individual lesions is critical to properly inform clinical decisions. The goal of this work was to assess the performance of an automated lesion-matching algorithm in comparison to inter-reader variability (IRV) of matching lesions between scans of metastatic cancer patients.Approach.Forty pairs of longitudinal PET/CT and CT scans were collected and organized into four cohorts: lung cancers, head and neck cancers, lymphomas, and advanced cancers. Cases were also divided by cancer burden: low-burden (<10 lesions), intermediate-burden (10-29), and high-burden (30+). Two nuclear medicine physicians conducted independent reviews of each scan-pair and manually matched lesions. Matching differences between readers were assessed to quantify the IRV of lesion matching. The two readers met to form a consensus, which was considered a gold standard and compared against the output of an automated lesion-matching algorithm. IRV and performance of the automated method were quantified using precision, recall, F1-score, and the number of differences.Main results.The performance of the automated method did not differ significantly from IRV for any metric in any cohort (p> 0.05, Wilcoxon paired test). In high-burden cases, the F1-score (median [range]) was 0.89 [0.63, 1.00] between the automated method and reader consensus and 0.93 [0.72, 1.00] between readers. In low-burden cases, F1-scores were 1.00 [0.40, 1.00] and 1.00 [0.40, 1.00], for the automated method and IRV, respectively. Automated matching was significantly more efficient than either reader (p< 0.001). In high-burden cases, median matching time for the readers was 60 and 30 min, respectively, while automated matching took a median of 3.9 minSignificance.The automated lesion-matching algorithm was successful in performing lesion matching, meeting the benchmark of IRV. Automated lesion matching can significantly expedite and improve the consistency of longitudinal lesion-matching.

18 F-sodium fluoride positron emission tomography quantitation of bone metastases in African American and non-African American men with metastatic prostate cancer.

BACKGROUND: Bone is the most common site of metastases in men with prostate cancer. The objective of this study was to explore potential racial differences in the distribution of tumor metastases in the axial and appendicular skeleton. METHODS: We conducted a retrospective review of patients with metastatic prostate cancer to the bone as detected by 18 F-sodium fluoride positron emission tomography/computed tomography (18 F-NaF PET/CT) scans. In addition to describing patients' demographics and clinical characteristics, the metastatic bone lesions, and healthy bone regions were detected and quantified volumetrically using a quantitative imaging platform (TRAQinform IQ, AIQ Solutions). RESULTS: Forty men met the inclusion criteria with 17 (42%) identifying as African Americans and 23 (58%) identifying as non-African Americans. Most of the patients had axial (skull, ribcage, and spine) disease. The location and the number of lesions in the skeleton of metastatic prostate cancer patients with low disease burden were not different by race. CONCLUSIONS: In low-disease burden patients with metastatic prostate cancer, there were no overall differences by race in the location and number of lesions in axial or appendicular skeleton. Therefore, given equal access to molecular imaging, African Americans might derive similar benefits. Whether this holds true for patients with a higher disease burden or for other molecular imaging techniques is a topic for further study.

Comparison of automated full-body bone metastases delineation methods and their corresponding prognostic power.

Objective.Manual disease delineation in full-body imaging of patients with multiple metastases is often impractical due to high disease burden. However, this is a clinically relevant task as quantitative image techniques assessing individual metastases, while limited, have been shown to be predictive of treatment outcome. The goal of this work was to evaluate the efficacy of deep learning-based methods for full-body delineation of skeletal metastases and to compare their performance to existing methods in terms of disease delineation accuracy and prognostic power.Approach.1833 suspicious lesions on 3718F-NaF PET/CT scans of patients with metastatic castration-resistant prostate cancer (mCRPC) were contoured and classified as malignant, equivocal, or benign by a nuclear medicine physician. Two convolutional neural network (CNN) architectures (DeepMedic and nnUNet)were trained to delineate malignant disease regions with and without three-model ensembling. Malignant disease contours using previously established methods were obtained. The performance of each method was assessed in terms of four different tasks: (1) detection, (2) segmentation, (3) PET SUV metric correlations with physician-based data, and (4) prognostic power of progression-free survival.Main Results.The nnUnet three-model ensemble achieved superior detection performance with a mean (+/- standard deviation) sensitivity of 82.9±ccc 0.1% at the selected operating point. The nnUnet single and three-model ensemble achieved comparable segmentation performance with a mean Dice coefficient of 0.80±0.12 and 0.79±0.12, respectively, both outperforming other methods. The nnUNet ensemble achieved comparable or superior SUV metric correlation performance to gold-standard data. Despite superior disease delineation performance, the nnUNet methods did not display superior prognostic power over other methods.Significance.This work showed that CNN-based (nnUNet) methods are superior to the non-CNN methods for mCRPC disease delineation in full-body18F-NaF PET/CT. The CNN-based methods, however, do not hold greater prognostic power for predicting clinical outcome. This merits more investigation on the optimal selection of delineation methods for specific clinical tasks.

Development and validation of a longitudinal soft-tissue metastatic lesion matching algorithm.

Metastatic cancer presents with many, sometimes hundreds of metastatic lesions through the body, which often respond heterogeneously to treatment. Therefore, lesion-level assessment is necessary for a complete understanding of disease response. Lesion-level assessment typically requires manual matching of corresponding lesions, which is a tedious, subjective, and error-prone task. This study introduces a fully automated algorithm for matching of metastatic lesions in longitudinal medical images. The algorithm entails four steps: (1) image registration, (2) lesion dilation, (3) lesion clustering, and (4) linear assignment. In step (1), 3D deformable registration is used to register the scans. In step (2), lesion contours are conformally dilated. In step (3), lesion clustering is evaluated based on local metrics. In step (4), matching is assigned based on non-greedy cost minimization. The algorithm was optimized (e.g. choice of deformable registration algorithm, dilatation size) and validated on 140 scan-pairs of 32 metastatic cancer patients from two independent clinical trials, who received longitudinal PET/CT scans as part of their treatment response assessment. Registration error was evaluated using landmark distance. A sensitivity study was performed to evaluate the optimal lesion dilation magnitude. Lesion matching performance accuracy was evaluated for all patients and for a subset with high disease burden. Two investigated deformable registration approaches (whole body deformable and articulated deformable registrations) led to similar performance with the overall registration accuracy between 2.3 and 2.6 mm. The optimal dilation magnitude of 25 mm yielded almost a perfect matching accuracy of 0.98. No significant matching accuracy decrease was observed in the subset of patients with high lesion disease burden. In summary, lesion matching using our new algorithm was highly accurate and a significant improvement, when compared to previously established methods. The proposed method enables accurate automated metastatic lesion matching in whole-body longitudinal scans.

Whole-Body [18F]-Fluoride PET SUV Imaging to Monitor Response to Dasatinib Therapy in Castration-Resistant Prostate Cancer Bone Metastases: Secondary Results from ACRIN 6687.

ACRIN 6687, a multi-center clinical trial evaluating differential response of bone metastases to dasatinib in men with metastatic castration-resistant prostate cancer (mCRPC), used [18F]-fluoride (NaF) PET imaging. We extend previous ACRIN 6687 dynamic imaging results by examining NaF whole-body (WB) static SUV PET scans acquired after dynamic scanning. Eighteen patients underwent WB NaF imaging prior to and 12 weeks into dasatinib treatment. Regional VOI analysis of the most NaF avid bone metastases and an automated whole-body method using Quantitative Total Bone Imaging software (QTBI; AIQ Solutions, Inc., Madison, WI, USA) were used. We assessed differences in tumor and normal bone, between pre- and on-treatment dasatinib, and evaluated parameters in association with PFS and OS. Significant decrease in average SUVmax and average SUVpeak occurred in response to dasatinib. Univariate and multivariate analysis showed NaF uptake had significant association with PFS. Pharmacodynamic changes with dasatinib in tumor bone can be identified by WB NaF PET in men with mCRPC. WB PET has the benefit of examining the entire body and is less complicated than single FOV dynamic imaging.

Exploring Spatial-Temporal Changes in 18F-Sodium Fluoride PET/CT and Circulating Tumor Cells in Metastatic Castration-Resistant Prostate Cancer Treated With Enzalutamide.

PURPOSE: Intrapatient treatment response heterogeneity is under-recognized. Quantitative total bone imaging (QTBI) using 18F-NaF positron emission tomography/computed tomography (PET/CT) scans is a tool that allows characterization of interlesional treatment response heterogeneity in bone. Understanding spatial-temporal response is important to identify individuals who may benefit from treatment beyond progression. PATIENTS AND METHODS: Men with progressive metastatic castration-resistant prostate cancer (mCRPC) with at least two lesions on bone scintigraphy were enrolled and treated with enzalutamide 160 mg daily (ClinicalTrials.gov identifier: NCT02384382). 18F-NaF PET/CT scans were obtained at baseline (PET1), week 13 (PET2), and at the time of prostate-specific antigen (PSA) progression, standard radiographic or clinical progression, or at 2 years without progression (PET3). QTBI was used to determine lesion-level response. The primary end point was the proportion of men with at least one responding bone lesion on PET3 using QTBI. RESULTS: Twenty-three men were enrolled. Duration on treatment ranged from 1.4 to 34.1 months. In general, global standardized uptake value (SUV) metrics decreased while on enzalutamide (PET2) and increased at the time of progression (PET3). The most robust predictor of PSA progression was change in SUVhetero (PET1 to PET3; hazard ratio, 3.88; 95% CI, 1.24 to 12.1). Although overall functional disease burden improved during enzalutamide treatment, an increase in total burden (SUVtotal) was seen at the time of progression, as measured by 18F-NaF PET/CT. All (22/22) evaluable men had at least one responding bone lesion at PET3 using QTBI. CONCLUSION: We found that the proportion of progressing lesions was low, indicating that a substantial number of lesions appear to continue to benefit from enzalutamide beyond progression. Selective targeting of nonresponding lesions may be a reasonable approach to extend benefit.

Phase II Trial of a DNA Vaccine Encoding Prostatic Acid Phosphatase (pTVG-HP [MVI-816]) in Patients With Progressive, Nonmetastatic, Castration-Sensitive Prostate Cancer.

PURPOSE: We previously reported the safety and immunologic effects of a DNA vaccine (pTVG-HP [MVI-816]) encoding prostatic acid phosphatase (PAP) in patients with recurrent, nonmetastatic prostate cancer. The current trial evaluated the effects of this vaccine on metastatic progression. PATIENTS AND METHODS: Ninety-nine patients with castration-sensitive prostate cancer and prostate-specific antigen (PSA) doubling time (DT) of less than 12 months were randomly assigned to treatment with either pTVG-HP co-administered intradermally with 200 µg granulocyte-macrophage colony-stimulating factor (GM-CSF) adjuvant or 200 µg GM-CSF alone six times at 14-day intervals and then quarterly for 2 years. The primary end point was 2-year metastasis-free survival (MFS). Secondary and exploratory end points were median MFS, changes in PSA DT, immunologic effects, and changes in quantitative 18F-sodium fluoride (NaF) positron emission tomography/computed tomography (PET/CT) imaging. RESULTS: Two-year MFS was not different between study arms (41.8% vaccine v 42.3%; P = .97). Changes in PSA DT and median MFS were not different between study arms (18.9 v 18.3 months; hazard ratio [HR], 1.6; P = .13). Preplanned subset analysis identified longer MFS in vaccine-treated patients with rapid (< 3 months) pretreatment PSA DT (12.0 v 6.1 months; n = 21; HR, 4.4; P = .03). PAP-specific T cells were detected in both cohorts, including multifunctional PAP-specific T-helper 1-biased T cells. Changes in total activity (total standardized uptake value) on 18F-NaF PET/CT from months 3 to 6 increased 50% in patients treated with GM-CSF alone and decreased 23% in patients treated with pTVG-HP (n = 31; P = .07). CONCLUSION: pTVG-HP treatment did not demonstrate an overall increase in 2-year MFS in patients with castration-sensitive prostate cancer, with the possible exception of a subgroup with rapidly progressive disease. Prespecified 18F-NaF PET/CT imaging conducted in a subset of patients suggests that vaccination had detectable effects on micrometastatic bone disease. Additional trials using pTVG-HP in combination with PD-1 blockade are under way.

Using neighborhood gray tone difference matrix texture features on dual time point PET/CT images to differentiate malignant from benign FDG-avid solitary pulmonary nodules.

OBJECTIVE: Lung cancer usually presents as a solitary pulmonary nodule (SPN) on diagnostic imaging during the early stages of the disease. Since the early diagnosis of lung cancer is very important for treatment, the accurate diagnosis of SPNs has much importance. The aim of this study was to evaluate the discriminant power of dual time point imaging (DTPI) PET/CT in the differentiation of malignant and benign FDG-avid solitary pulmonary nodules by using neighborhood gray-tone difference matrix (NGTDM) texture features. METHODS: Retrospective analysis was carried out on 116 patients with SPNs (35 benign and 81 malignant) who had DTPI 18F-FDG PET/CT between January 2005 and May 2015. Both PET and CT images were acquired at 1 h and 3 h after injection. The SUVmax and NGTDM texture features (coarseness, contrast, and busyness) of each nodule were calculated on dual time point images. Patients were randomly divided into training and validation datasets. Receiver operating characteristic (ROC) curve analysis was performed on all texture features in the training dataset to calculate the optimal threshold for differentiating malignant SPNs from benign SPNs. For all the lesions in the testing dataset, two visual interpretation scores were determined by two nuclear medicine physicians based on the PET/CT images with and without reference to the texture features. RESULTS: In the training dataset, the AUCs of delayed busyness, delayed coarseness, early busyness, and early SUVmax were 0.87, 0.85, 0.75 and 0.75, respectively. In the validation dataset, the AUCs of visual interpretations with and without texture features were 0.89 and 0.80, respectively. CONCLUSION: Compared to SUVmax or visual interpretation, NGTDM texture features derived from DTPI PET/CT images can be used as good predictors of SPN malignancy. Improvement in discriminating benign from malignant nodules using SUVmax and visual interpretation can be achieved by adding busyness extracted from delayed PET/CT images.

Impact of Anatomic Location of Bone Metastases on Prognosis in Metastatic Castration-Resistant Prostate Cancer.

BACKGROUND: Whole-body assessments of 18F-NaF positron emission tomography (PET)/computed tomography (CT) provide promising quantitative imaging biomarkers of metastatic castration-resistant prostate cancer (mCRPC). This study investigated whether the distribution of metastases across anatomic regions is prognostic of progression-free survival. PATIENTS AND METHODS: Fifty-four mCRPC patients with osseous metastases received baseline NaF PET/CT. Patients received chemotherapy (n = 16) or androgen receptor pathway inhibitors (n = 38). Semiautomated analysis using Quantitative Total Bone Imaging software extracted imaging metrics for the whole, axial, and appendicular skeleton as well as 11 skeletal regions. Five PET metrics were extracted for each region: number of lesions (NL), standardized maximum uptake value (SUVmax), average uptake (SUVmean), sum of uptake (SUVtotal), and diseased fraction of the skeleton (volume fraction). Progression included that discovered by clinical, biochemical, or radiographic means. Univariate and multivariate Cox proportional hazard regression analyses were performed between imaging metrics and progression-free survival, and were assessed according to their hazard ratios (HR) and concordance (C)-indices. RESULTS: The strongest univariate models of progression-free survival were pelvic NL and SUVmax with HR = 1.80 (NL: false discovery rate adjusted P = .001, SUVmax: adjusted P = .001). Three other region-specific metrics (axial NL: HR = 1.59, adjusted P = .02, axial SUVmax: HR = 1.61, adjusted P = .02, and skull SUVmax: HR = 1.58, adjusted P = .04) were found to be stronger prognosticators relative to their whole-body counterparts. Multivariate model including region-specific metrics (C-index = 0.727) outperformed that of whole-body metrics (C-index = 0.705). The best performance was obtained when region-specific and whole-body metrics were included (C-index = 0.742). CONCLUSION: Quantitative characterization of metastatic spread by anatomic location on NaF PET/CT enhances potential prognostication. Further study is warranted to optimize the prognostic and predictive value of NaF PET/CT in mCRPC patients.

Quantification of bone flare on 18F-NaF PET/CT in metastatic castration-resistant prostate cancer.

BACKGROUND: Bone flare has been observed on 99mTc-MDP bone scans of patients with metastatic castration-resistant prostate cancer (mCRPC). This exploratory study investigates bone flare in mCRPC patients receiving androgen receptor (AR) inhibitors using 18F-NaF PET/CT. METHODS: Twenty-nine mCRPC patients undergoing AR-inhibiting therapy (abiraterone, orteronel, enzalutamide) received NaF PET/CT scans at baseline, week 6, and week 12 of treatment. SUV metrics were extracted globally for each patient (SUV) and for each individual lesion (iSUV). Bone flare was defined as increasing SUV metrics or lesion number at week 6 followed by subsequent week 12 decrease. Differences in metrics across timepoints were compared using Wilcoxon tests. Cox proportional hazard regression was conducted between global metrics and progression-free survival (PFS). RESULTS: Total SUV was most sensitive for flare detection and was identified in 14/23 (61%) patients receiving CYP17A1-inhibitors (abiraterone, orteronel), and not identified in any of six patients receiving enzalutamide. The appearance of new lesions did not account for initial increases in SUV metrics. iSUV metrics followed patient-level trends: bone flare positive patients showed a median of 72% (range: 0-100%) of lesions with total iSUV flare. Increasing mean SUV at week 6 correlated with extended PFS (HR = 0.58, p = 0.02). CONCLUSION: NaF PET bone flare was present on 61% of mCRPC patients in the first 6 weeks of treatment with CYP17A1-inhibitors. Characterization provided in this study suggests favorable PFS in patients showing bone flare. This characterization of NaF flare is important for guiding treatment assessment schedules to better distinguish between patients showing bone flare and those truly progressing, and should be performed for all emerging mCRPC treatments and imaging agents.

A statistically optimized regional thresholding method (SORT) for bone lesion detection in 18F-NaF PET/CT imaging.

Identification of individual lesions on 18F-NaF PET bone scans is a time-consuming and often subjective process that makes accurate characterization of disease burden challenging. Current automated methods either underestimate disease or struggle with high false positive rates. We developed a statistically optimized regional thresholding (SORT) method that optimizes detection of bone lesions. This study assessed 18F-NaF PET/CT scans of 37 bone metastatic prostate cancer patients. Each PET image was divided into 19 skeletal regions. Areas of disease in each skeletal region were identified by an experienced nuclear medicine physician. A region of interest (ROI) was placed at each disease location and local maxima were extracted for both healthy and diseased ROIs. Secondary physician review was performed after identification of suspicious local maxima. Region-specific SUV thresholds were determined based on receiver operating characteristic (ROC) analysis optimized for detection of malignant disease. The detection performance of the SORT thresholds were compared to commonly used SUV > 10 g ml-1 (SUV10) and SUV > 15 g ml-1 (SUV15) global thresholds. The sensitivity of the SORT thresholds to various factors was evaluated, such as the number of subjects evaluated or image reconstruction settings. 1751 lesions were manually identified by the nuclear medicine physician. SORT identified different thresholds in each skeletal region (SUV range: 3-13 g ml-1). Region-specific SORT thresholding resulted in higher sensitivity (95.8%) than commonly used global thresholds (82.8% for SUV10 and 58.4% for SUV15) while maintaining a high specificity (97.1%, compared to 97.3% for SUV10 and 100.0% for SUV15). Factors, such as reconstruction settings, had minimal impact on threshold optimization, resulting in an average change of 10% (range: 2%-17%) in thresholds for each factor. Region-specific SUV thresholding of NaF PET images for bone lesion detection in metastatic prostate patients was found to be superior to current global thresholding methods.

Automated classification of benign and malignant lesions in 18F-NaF PET/CT images using machine learning.

PURPOSE: 18F-NaF PET/CT imaging of bone metastases is confounded by tracer uptake in benign diseases, such as osteoarthritis. The goal of this work was to develop an automated bone lesion classification algorithm to classify lesions in NaF PET/CT images. METHODS: A nuclear medicine physician manually identified and classified 1751 bone lesions in NaF PET/CT images from 37 subjects with metastatic castrate-resistant prostate cancer, 14 of which (598 lesions) were analyzed by three additional physicians. Lesions were classified on a five-point scale from definite benign to definite metastatic lesions. Classification agreement between physicians was assessed using Fleiss' κ. To perform fully automated lesion classification, three different lesion detection methods based on thresholding were assessed: SUV > 10 g ml-1, SUV > 15 g ml-1, and a statistically optimized regional thresholding (SORT) algorithm. For each ROI in the image, 172 different imaging features were extracted, including PET, CT, and spatial probability features. These imaging features were used as inputs into different machine learning algorithms. The impact of different deterministic factors affecting classification performance was assessed. RESULTS: The factors that most impacted classification performance were the machine learning algorithm and the lesion identification method. Random forests (RF) had the highest classification performance. For lesion segmentation, using SORT (AUC = 0.95 [95%CI = 0.94-0.95], sensitivity = 88% [86%-90%], and specificity = 0.89 [0.87-0.90]) resulted in superior classification performance (p < 0.001) compared to SUV > 10 g ml-1 (AUC = 0.87) and SUV > 15 g ml-1 (AUC = 0.86). While there was only moderate agreement between physicians in lesion classification (κ = 0.53 [95% CI = 0.52-0.53]), classification performance was high using any of the four physicians as ground truth (AUC range: 0.91-0.93). CONCLUSION: We have developed the first whole-body automatic disease classification tool for NaF PET using RF, and demonstrated its ability to replicate different physicians' classification tendencies. This enables fully-automated analysis of whole-body NaF PET/CT images.

Diagnostic classification of solitary pulmonary nodules using dual time 18F-FDG PET/CT image texture features in granuloma-endemic regions.

Lung cancer, the most commonly diagnosed cancer worldwide, usually presents as solid pulmonary nodules (SPNs) on early diagnostic images. Classification of malignant disease at this early timepoint is critical for improving the success of surgical resection and increasing 5-year survival rates. 18F-fluorodeoxyglucose (18F-FDG) PET/CT has demonstrated value for SPNs diagnosis with high sensitivity to detect malignant SPNs, but lower specificity in diagnosing malignant SPNs in populations with endemic infectious lung disease. This study aimed to determine whether quantitative heterogeneity derived from various texture features on dual time FDG PET/CT images (DTPI) can differentiate between malignant and benign SPNs in patients from granuloma-endemic regions. Machine learning methods were employed to find optimal discrimination between malignant and benign nodules. Machine learning models trained by texture features on DTPI images achieved significant improvements over standard clinical metrics and visual interpretation for discriminating benign from malignant SPNs, especially by texture features on delayed FDG PET/CT images.

Quantitative Assessment of Early [18F]Sodium Fluoride Positron Emission Tomography/Computed Tomography Response to Treatment in Men With Metastatic Prostate Cancer to Bone.

Purpose [18F]Sodium fluoride (NaF) positron emission tomography (PET)/computed tomography (CT) is a promising radiotracer for quantitative assessment of bone metastases. This study assesses changes in early NaF PET/CT response measures in metastatic prostate cancer for correlation to clinical outcomes. Patients and Methods Fifty-six patients with metastatic castration-resistant prostate cancer (mCRPC) with osseous metastases had NaF PET/CT scans performed at baseline and after three cycles of chemotherapy (n = 16) or androgen receptor pathway inhibitors (n = 40). A novel technology, Quantitative Total Bone Imaging, was used for analysis. Global imaging metrics, including maximum standardized uptake value (SUVmax) and total functional burden (SUVtotal), were extracted from composite lesion-level statistics for each patient and tracked throughout treatment. Progression-free survival (PFS) was calculated as a composite end point of progressive events using conventional imaging and/or physician discretion of clinical benefit; NaF imaging was not used for clinical evaluation. Cox proportional hazards regression analyses were conducted between imaging metrics and PFS. Results Functional burden (SUVtotal) assessed midtreatment was the strongest univariable PFS predictor (hazard ratio, 1.97; 95% CI, 1.44 to 2.71; P < .001). Classification of patients based on changes in functional burden showed stronger correlation to PFS than did the change in number of lesions. Various global imaging metrics outperformed baseline clinical markers in predicting outcome, including SUVtotal and SUVmean. No differences in imaging response or PFS correlates were found for different treatment cohorts. Conclusion Quantitative total bone imaging enables comprehensive disease quantification on NaF PET/CT imaging, showing strong correlation to clinical outcomes. Total functional burden assessed after three cycles of hormonal therapy or chemotherapy was predictive of PFS for men with mCRPC. This supports ongoing development of NaF PET/CT-based imaging biomarkers in mCRPC to bone.

Repeatability of Quantitative 18F-NaF PET: A Multicenter Study.

18F-NaF, a PET radiotracer of bone turnover, has shown potential as an imaging biomarker for assessing the response of bone metastases to therapy. This study aimed to evaluate the repeatability of 18F-NaF PET-derived SUV imaging metrics in individual bone lesions from patients in a multicenter study. METHODS: Thirty-five castration-resistant prostate cancer patients with multiple metastases underwent 2 whole-body (test-retest) 18F-NaF PET/CT scans 3 ± 2 d apart from 1 of 3 imaging sites. A total of 411 bone lesions larger than 1.5 cm3 were automatically segmented using an SUV threshold of 15 g/mL. Two levels of analysis were performed: lesion-level, in which measures were extracted from individual-lesion regions of interest (ROI), and patient-level, in which all lesions within a patient were grouped into a patient ROI for analysis. Uptake was quantified with SUVmax, SUVmean, and SUVtotal Test-retest repeatability was assessed using Bland-Altman analysis, intraclass correlation coefficient (ICC), coefficient of variation, critical percentage difference, and repeatability coefficient. The 95% limit of agreement (LOA) of the ratio between test and retest measurements was calculated. RESULTS: At the lesion level, the coefficient of variation for SUVmax, SUVmean, and SUVtotal was 14.1%, 6.6%, and 25.5%, respectively. At the patient level, it was slightly smaller: 12.0%, 5.3%, and 18.5%, respectively. ICC was excellent (>0.95) for all SUV metrics. Lesion-level 95% LOA for SUVmax, SUVmean, and SUVtotal was (0.76, 1.32), (0.88, 1.14), and (0.63, 1.71), respectively. Patient-level 95% LOA was slightly narrower, at (0.79, 1.26), (0.89, 1.10), and (0.70, 1.44), respectively. We observed significant differences in the variance and sample mean of lesion-level and patient-level measurements between imaging sites. CONCLUSION: The repeatability of SUVmax, SUVmean, and SUVtotal for 18F-NaF PET/CT was similar between lesion- and patient-level ROIs. We found significant differences in lesion-level and patient-level distributions between sites. These results can be used to establish 18F-NaF PET-based criteria for assessing treatment response at the lesion and patient levels. 18F-NaF PET demonstrates repeatability levels useful for clinically quantifying the response of bone lesions to therapy.

Differentiation of metastatic vs degenerative joint disease using semi-quantitative analysis with (18)F-NaF PET/CT in castrate resistant prostate cancer patients.

Fluorine 18 Sodium Fluoride ((18)F-NaF) (sodium fluoride) PET/CT is a highly sensitive but is a non-specific method for identifying bone metastases. Qualitative scan interpretation using low dose CT for lesion localization is often complicated by the presence of co-existing degenerative joint disease (DJD). A semi-quantitative analysis might help in accurately differentiating benign from metastatic osseous lesions. The aim of the study was to evaluate the clinical utility of (18)F-NaF PET/CT in differentiating DJD from metastatic disease in the skeleton using a qualitative analysis as well as a semi-quantitative approach using the SUVmax and to determine if there is an upper limit of SUVmax value that can reliably differentiate metastases from DJD. Baseline (18)F-NaF PET/CT scans were performed for 17 castrate resistant prostate cancer patients (CRPC). A qualitative as well as semi-quantitative analysis using maximum standardized uptake value (SUVmax) based on body weight was performed for 65 metastatic and 56 DJD sites identified on the low dose CT scan acquired as a part of whole body PET/CT scan. The SUVmax range in DJD was 2.6-49.9 (mean: 6.2). The SUVmax range for metastatic lesions was 11.2-188 (mean: 160). The SUVmax value for metastatic as well as areas of DJD showed significant variation during treatment. Bone metastases showed statistically significantly higher SUVmax than DJD using a mixed effect regression model. ROC/AUC analysis was performed based on averaging the SUVs over all lesions in each subject. The AUC was found to be fairly high at 0.964 (95% CI: 0.75-0.996). The SUVmax over 50 always represented a bone metastasis and below 12 always represented a site of DJD. The results of our preliminary data show that semi-quantitative analysis is complementary to the qualitative analysis in accurately identifying DJD from metastatic disease. The cut-off SUVmax of 50 can help in differentiating DJD from bone metastases.

Development and evaluation of an articulated registration algorithm for human skeleton registration.

Accurate registration over multiple scans is necessary to assess treatment response of bone diseases (e.g. metastatic bone lesions). This study aimed to develop and evaluate an articulated registration algorithm for the whole-body skeleton registration in human patients. In articulated registration, whole-body skeletons are registered by auto-segmenting into individual bones using atlas-based segmentation, and then rigidly aligning them. Sixteen patients (weight = 80-117 kg, height = 168-191 cm) with advanced prostate cancer underwent the pre- and mid-treatment PET/CT scans over a course of cancer therapy. Skeletons were extracted from the CT images by thresholding (HU>150). Skeletons were registered using the articulated, rigid, and deformable registration algorithms to account for position and postural variability between scans. The inter-observers agreement in the atlas creation, the agreement between the manually and atlas-based segmented bones, and the registration performances of all three registration algorithms were all assessed using the Dice similarity index-DSIobserved, DSIatlas, and DSIregister. Hausdorff distance (dHausdorff) of the registered skeletons was also used for registration evaluation. Nearly negligible inter-observers variability was found in the bone atlases creation as the DSIobserver was 96 ± 2%. Atlas-based and manual segmented bones were in excellent agreement with DSIatlas of 90 ± 3%. Articulated (DSIregsiter = 75 ± 2%, dHausdorff = 0.37 ± 0.08 cm) and deformable registration algorithms (DSIregister = 77 ± 3%, dHausdorff = 0.34 ± 0.08 cm) considerably outperformed the rigid registration algorithm (DSIregsiter = 59 ± 9%, dHausdorff = 0.69 ± 0.20 cm) in the skeleton registration as the rigid registration algorithm failed to capture the skeleton flexibility in the joints. Despite superior skeleton registration performance, deformable registration algorithm failed to preserve the local rigidity of bones as over 60% of the skeletons were deformed. Articulated registration is superior to rigid and deformable registrations by capturing global flexibility while preserving local rigidity inherent in skeleton registration. Therefore, articulated registration can be employed to accurately register the whole-body human skeletons, and it enables the treatment response assessment of various bone diseases.