Dataset Information

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

ABSTRACT: 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.

SUBMITTER: Wei L

PROVIDER: S-EPMC7726084 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Tumor response prediction in <sup>90</sup>Y radioembolization with PET-based radiomics features and absorbed dose metrics.

Wei Lise L Cui Can C Xu Jiarui J Kaza Ravi R El Naqa Issam I Dewaraja Yuni K YK

EJNMMI physics 20201209 1

<h4>Purpose</h4>To evaluate whether lesion radiomics features and absorbed dose metrics extracted from post-therapy <sup>90</sup>Y PET can be integrated to better predict outcomes in microsphere radioembolization of liver malignancies METHODS: Given the noisy nature of <sup>90</sup>Y 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 procedu ...[more]

PMID: 33296050

Similar Datasets

Project description:The aim of this work was to develop models for tumor control probability (TCP) in radioembolization with 90Y PET/CT-derived radiobiologic dose metrics. Methods: Patients with primary liver cancer or liver metastases who underwent radioembolization with glass microspheres were imaged with 90Y PET/CT for voxel-level dosimetry to determine lesion absorbed dose (AD) metrics, biological effective dose (BED) metrics, equivalent uniform dose, and equivalent uniform BED for 28 treatments (89 lesions). The lesion dose-shrinkage correlation was assessed on the basis of RECIST and, when available, modified RECIST (mRECIST) at first follow-up. For a subset with mRECIST, logit regression TCP models were fit via maximum likelihood to relate lesion-level binary response to the dose metrics. As an exploratory analysis, the nontumoral liver dose-toxicity relationship was also evaluated. Results: Lesion dose-shrinkage analysis showed that there were no significant differences between model parameters for primary and metastatic subgroups and that correlation coefficients were superior with mRECIST. Therefore, subsequent TCP analysis was performed for the combined group using mRECIST only. The overall lesion-level mRECIST response rate was 57%. The AD and BED metrics yielding 50% TCP were 292 and 441 Gy, respectively. All dose metrics considered for TCP modeling, including mean AD, were significantly associated with the probability of response, with high areas under the curve (0.87-0.90, P < 0.0001) and high sensitivity (>0.75) and specificity (>0.83) calculated using a threshold corresponding to 50% TCP. Because nonuniform AD deposition by microspheres cannot be determined by PET at a microscopic scale, radiosensitivity values extracted here by fitting models to clinical response data were substantially lower than reported for in vitro cell cultures or for external-beam radiotherapy clinical studies. There was no correlation between nontumoral liver AD and toxicity measures. Conclusion: Despite the heterogeneous patient cohort, logistic regression TCP models showed a strong association between various dose metrics and the probability of response. The performance of mean AD was comparable to that of radiobiologic dose metrics that involve more complex calculations. These results demonstrate the importance of considering TCP in treatment planning for radioembolization.

Project description:BackgroundThe purpose was to validate 90Y PET gradient-based tumor segmentation in phantoms and to evaluate the impact of the segmentation method on reported tumor absorbed dose (AD) and biological effective dose (BED) in 90Y microsphere radioembolization (RE) patients. A semi-automated gradient-based method was applied to phantoms and patient tumors on the 90Y PET with the initial bounding volume for gradient detection determined from a registered diagnostic CT or MR; this PET-based segmentation (PS) was compared with radiologist-defined morphologic segmentation (MS) on CT or MRI. AD and BED volume histogram metrics (D90, D70, mean) were calculated using both segmentations and concordance/correlations were investigated. Spatial concordance was assessed using Dice similarity coefficient (DSC) and mean distance to agreement (MDA). PS was repeated to assess intra-observer variability.ResultsIn phantoms, PS demonstrated high accuracy in lesion volumes (within 15%), AD metrics (within 11%), high spatial concordance relative to morphologic segmentation (DSC?>?0.86 and MDA?<?1.5 mm), and low intra-observer variability (DSC?>?0.99, MDA?<?0.2 mm, AD/BED metrics within 2%). For patients (58 lesions), spatial concordance between PS and MS was degraded compared to in-phantom (average DSC = 0.54, average MDA = 4.8 mm); the average mean tumor AD was 226?±?153 and 197?±?138 Gy, respectively for PS and MS. For patient AD metrics, the best Pearson correlation (r) and concordance correlation coefficient (ccc) between segmentation methods was found for mean AD (r?=?0.94, ccc?=?0.92), but worsened as the metric approached the minimum dose (for D90, r?=?0.77, ccc?=?0.69); BED metrics exhibited a similar trend. Patient PS showed low intra-observer variability (average DSC = 0.81, average MDA = 2.2 mm, average AD/BED metrics within 3.0%).Conclusions90Y PET gradient-based segmentation led to accurate/robust results in phantoms, and showed high concordance with MS for reporting mean tumor AD/BED in patients. However, tumor coverage metrics such as D90 exhibited worse concordance between segmentation methods, highlighting the need to standardize segmentation methods when reporting AD/BED metrics from post-therapy 90Y PET. Estimated differences in reported AD/BED metrics due to segmentation method will be useful for interpreting RE dosimetry results in the literature including tumor response data.

Project description:BackgroundCoincidence imaging of low-abundance yttrium-90 (90Y) internal pair production by positron emission tomography with integrated computed tomography (PET/CT) achieves high-resolution imaging of post-radioembolization microsphere biodistribution. Part 2 analyzes tumor and non-target tissue dose-response by 90Y PET quantification and evaluates the accuracy of tumor 99mTc macroaggregated albumin (MAA) single-photon emission computed tomography with integrated CT (SPECT/CT) predictive dosimetry.MethodsRetrospective dose quantification of 90Y resin microspheres was performed on the same 23-patient data set in part 1. Phantom studies were performed to assure quantitative accuracy of our time-of-flight lutetium-yttrium-oxyorthosilicate system. Dose-responses were analyzed using 90Y dose-volume histograms (DVHs) by PET voxel dosimetry or mean absorbed doses by Medical Internal Radiation Dose macrodosimetry, correlated to follow-up imaging or clinical findings. Intended tumor mean doses by predictive dosimetry were compared to doses by 90Y PET.ResultsPhantom studies demonstrated near-perfect detector linearity and high tumor quantitative accuracy. For hepatocellular carcinomas, complete responses were generally achieved at D70 > 100 Gy (D70, minimum dose to 70% tumor volume), whereas incomplete responses were generally at D70 < 100 Gy; smaller tumors (<80 cm3) achieved D70 > 100 Gy more easily than larger tumors. There was complete response in a cholangiocarcinoma at D70 90 Gy and partial response in an adrenal gastrointestinal stromal tumor metastasis at D70 53 Gy. In two patients, a mean dose of 18 Gy to the stomach was asymptomatic, 49 Gy caused gastritis, 65 Gy caused ulceration, and 53 Gy caused duodenitis. In one patient, a bilateral kidney mean dose of 9 Gy (V20 8%) did not cause clinically relevant nephrotoxicity. Under near-ideal dosimetric conditions, there was excellent correlation between intended tumor mean doses by predictive dosimetry and those by 90Y PET, with a low median relative error of +3.8% (95% confidence interval, -1.2% to +13.2%).ConclusionsTumor and non-target tissue absorbed dose quantification by 90Y PET is accurate and yields radiobiologically meaningful dose-response information to guide adjuvant or mitigative action. Tumor 99mTc MAA SPECT/CT predictive dosimetry is feasible. 90Y DVHs may guide future techniques in predictive dosimetry.

Project description:BackgroundYttrium-90 (90Y) positron emission tomography with integrated computed tomography (PET/CT) represents a technological leap from 90Y bremsstrahlung single-photon emission computed tomography with integrated computed tomography (SPECT/CT) by coincidence imaging of low abundance internal pair production. Encouraged by favorable early experiences, we implemented post-radioembolization 90Y PET/CT as an adjunct to 90Y bremsstrahlung SPECT/CT in diagnostic reporting.MethodsThis is a retrospective review of all paired 90Y PET/CT and 90Y bremsstrahlung SPECT/CT scans over a 1-year period. We compared image resolution, ability to confirm technical success, detection of non-target activity, and providing conclusive information about 90Y activity within targeted tumor vascular thrombosis. 90Y resin microspheres were used. 90Y PET/CT was performed on a conventional time-of-flight lutetium-yttrium-oxyorthosilicate scanner with minor modifications to acquisition and reconstruction parameters. Specific findings on 90Y PET/CT were corroborated by 90Y bremsstrahlung SPECT/CT, 99mTc macroaggregated albumin SPECT/CT, follow-up diagnostic imaging or review of clinical records.ResultsDiagnostic reporting recommendations were developed from our collective experience across 44 paired scans. Emphasis on the continuity of care improved overall diagnostic accuracy and reporting confidence of the operator. With proper technique, the presence of background noise did not pose a problem for diagnostic reporting. A counter-intuitive but effective technique of detecting non-target activity is proposed, based on the pattern of activity and its relation to underlying anatomy, instead of its visual intensity. In a sub-analysis of 23 patients with a median follow-up of 5.4 months, 90Y PET/CT consistently outperformed 90Y bremsstrahlung SPECT/CT in all aspects of qualitative analysis, including assessment for non-target activity and tumor vascular thrombosis. Parts of viscera closely adjacent to the liver remain challenging for non-target activity detection, compounded by a tendency for mis-registration.ConclusionsAdherence to proper diagnostic reporting technique and emphasis on continuity of care are vital to the clinical utility of post-radioembolization 90Y PET/CT. 90Y PET/CT is superior to 90Y bremsstrahlung SPECT/CT for the assessment of target and non-target activity.

Project description:BackgroundPrior radioembolization, a simulation using 99mTc-macroaggregated albumin as 90Y-microspheres surrogate is performed. Gamma scintigraphy images (planar, SPECT, or SPECT-CT) are acquired to evaluate intrahepatic 90Y-microspheres distribution and detect possible extrahepatic and lung shunting. These images may be used for pre-treatment dosimetry evaluation to calculate the 90Y activity that would get an optimal tumor response while sparing healthy tissues. Several dosimetry methods are available, but there is still no consensus on the best methodology to calculate absorbed doses. The goal of this study was to retrospectively evaluate the impact of using different dosimetry approaches on the resulting 90Y-radioembolization pre-treatment absorbed dose evaluation based on 99mTc-MAA images.MethodsAbsorbed doses within volumes of interest resulting from partition model (PM) and 3D voxel dosimetry methods (3D-VDM) (dose-point kernel convolution and local deposition method) were evaluated. Additionally, a new "Multi-tumor Partition Model" (MTPM) was developed. The differences among dosimetry approaches were evaluated in terms of mean absorbed dose and dose volume histograms within the volumes of interest.ResultsDifferences in mean absorbed dose among dosimetry methods are higher in tumor volumes than in non-tumoral ones. The differences between MTPM and both 3D-VDM were substantially lower than those observed between PM and any 3D-VDM. A poor correlation and concordance were found between PM and the other studied dosimetry approaches. DVH obtained from either 3D-VDM are pretty similar in both healthy liver and individual tumors. Although no relevant global differences, in terms of absorbed dose in Gy, between both 3D-VDM were found, important voxel-by-voxel differences have been observed.ConclusionsSignificant differences among the studied dosimetry approaches for 90Y-radioembolization treatments exist. Differences do not yield a substantial impact in treatment planning for healthy tissue but they do for tumoral liver. An individual segmentation and evaluation of the tumors is essential. In patients with multiple tumors, the application of PM is not optimal and the 3D-VDM or the new MTPM are suggested instead. If a 3D-VDM method is not available, MTPM is the best option. Furthermore, both 3D-VDM approaches may be indistinctly used.

Project description:We present a probabilistic approach to identify patients with primary and secondary hepatic malignancies as responders or nonresponders to yttrium-90 radioembolization therapy. Recent advances in computer-aided detection have decreased false-negative and false-positive rates of perceived abnormalities; however, there is limited research in using similar concepts to predict treatment response. Our approach is driven by the goal of precision medicine to determine pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging parameters to facilitate the identification of patients who would benefit most from yttrium-90 radioembolization therapy, while avoiding complex and costly procedures for those who would not. Our algorithm seeks to predict a patient's response by discovering common co-occurring image patterns in the lesions of baseline fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scans by extracting invariant shape and texture features. The extracted imaging features were represented as a distribution of each subject based on the bag-of-feature paradigm. The distribution was applied in a multinomial naive Bayes classifier to predict whether a patient would be a responder or nonresponder to yttrium-90 radioembolization therapy based on the imaging features of a pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography scan. Comprehensive published criteria were used to determine lesion-based clinical treatment response based on fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography imaging findings. Our results show that the model is able to predict a patient with liver cancer as a responder or nonresponder to yttrium-90 radioembolization therapy with a sensitivity of 0.791 using extracted invariant imaging features from the pretherapy fluorine-18-2-fluoro-2-deoxy-d-glucose positron emission tomography and computed tomography test. The sensitivity increased to 0.821 when combining extracted invariant image features with variable features of tumor volume.

Project description:The assessment of gliomas by 18F-FDOPA PET imaging as an adjunct to MRI showed high performance by combining static and dynamic features to noninvasively predict the isocitrate dehydrogenase (IDH) mutations and the 1p/19q codeletion, which the World Health Organization classified as significant parameters in 2016. The current study evaluated whether other 18F-FDOPA PET radiomics features further improve performance and the contributions of each of these features to performance. Methods: Our study included 72 retrospectively selected, newly diagnosed glioma patients with 18F-FDOPA PET dynamic acquisitions. A set of 114 features, including conventional static features and dynamic features, as well as other radiomics features, were extracted and machine-learning models trained to predict IDH mutations and the 1p/19q codeletion. Models were based on a machine-learning algorithm built from stable, relevant, and uncorrelated features selected by hierarchic clustering followed by a bootstrapped feature selection process. Models were assessed by comparing area under the curve using a nested cross-validation approach. Feature importance was assessed using Shapley additive explanations values. Results: The best models were able to predict IDH mutations (logistic regression with L2 regularization) and the 1p/19q codeletion (support vector machine with radial basis function kernel) with an area under the curve of 0.831 (95% CI, 0.790-0.873) and 0.724 (95% CI, 0.669-0.782), respectively. For the prediction of IDH mutations, dynamic features were the most important features in the model (time to peak, 35.5%). In contrast, other radiomics features were the most useful for predicting the 1p/19q codeletion (up to 14.5% of importance for the small-zone low-gray-level emphasis). Conclusion: 18F-FDOPA PET is an effective tool for the noninvasive prediction of glioma molecular parameters using a full set of amino-acid PET radiomics features. The contribution of each feature set shows the importance of systematically integrating dynamic acquisition for prediction of the IDH mutations as well as developing the use of radiomics features in routine practice for prediction of the 1p/19q codeletion.

Dataset Information

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

Publications

Tumor response prediction in <sup>90</sup>Y radioembolization with PET-based radiomics features and absorbed dose metrics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Dataset Information

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

Publications

Tumor response prediction in <sup>90</sup>Y radioembolization with PET-based radiomics features and absorbed dose metrics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

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