The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights.

Filters are commonly used to enhance specific structures and patterns in images, such as vessels or peritumoral regions, to enable clinical insights beyond the visible image using radiomics. However, their lack of standardization restricts reproducibility and clinical translation of radiomics decision support tools. In this special report, teams of researchers who developed radiomics software participated in a three-phase study (September 2020 to December 2022) to establish a standardized set of filters. The first two phases focused on finding reference filtered images and reference feature values for commonly used convolutional filters: mean, Laplacian of Gaussian, Laws and Gabor kernels, separable and nonseparable wavelets (including decomposed forms), and Riesz transformations. In the first phase, 15 teams used digital phantoms to establish 33 reference filtered images of 36 filter configurations. In phase 2, 11 teams used a chest CT image to derive reference values for 323 of 396 features computed from filtered images using 22 filter and image processing configurations. Reference filtered images and feature values for Riesz transformations were not established. Reproducibility of standardized convolutional filters was validated on a public data set of multimodal imaging (CT, fluorodeoxyglucose PET, and T1-weighted MRI) in 51 patients with soft-tissue sarcoma. At validation, reproducibility of 486 features computed from filtered images using nine configurations × three imaging modalities was assessed using the lower bounds of 95% CIs of intraclass correlation coefficients. Out of 486 features, 458 were found to be reproducible across nine teams with lower bounds of 95% CIs of intraclass correlation coefficients greater than 0.75. In conclusion, eight filter types were standardized with reference filtered images and reference feature values for verifying and calibrating radiomics software packages. A web-based tool is available for compliance checking.

Multicenter PET image harmonization using generative adversarial networks.

PURPOSE: To improve reproducibility and predictive performance of PET radiomic features in multicentric studies by cycle-consistent generative adversarial network (GAN) harmonization approaches. METHODS: GAN-harmonization was developed to harmonize whole-body PET scans to perform image style and texture translation between different centers and scanners. GAN-harmonization was evaluated by application to two retrospectively collected open datasets and different tasks. First, GAN-harmonization was performed on a dual-center lung cancer cohort (127 female, 138 male) where the reproducibility of radiomic features in healthy liver tissue was evaluated. Second, GAN-harmonization was applied to a head and neck cancer cohort (43 female, 154 male) acquired from three centers. Here, the clinical impact of GAN-harmonization was analyzed by predicting the development of distant metastases using a logistic regression model incorporating first-order statistics and texture features from baseline 18F-FDG PET before and after harmonization. RESULTS: Image quality remained high (structural similarity: left kidney ≥ 0.800, right kidney ≥ 0.806, liver ≥ 0.780, lung ≥ 0.838, spleen ≥ 0.793, whole-body ≥ 0.832) after image harmonization across all utilized datasets. Using GAN-harmonization, inter-site reproducibility of radiomic features in healthy liver tissue increased at least by ≥ 5 ± 14% (first-order), ≥ 16 ± 7% (GLCM), ≥ 19 ± 5% (GLRLM), ≥ 16 ± 8% (GLSZM), ≥ 17 ± 6% (GLDM), and ≥ 23 ± 14% (NGTDM). In the head and neck cancer cohort, the outcome prediction improved from AUC 0.68 (95% CI 0.66-0.71) to AUC 0.73 (0.71-0.75) by application of GAN-harmonization. CONCLUSIONS: GANs are capable of performing image harmonization and increase reproducibility and predictive performance of radiomic features derived from different centers and scanners.

Fibroblast heterogeneity in solid tumors: From single cell analysis to whole-body imaging.

Cancer-Associated Fibroblasts (CAFs) represent the most prominent component of the tumor microenvironment (TME). Recent studies demonstrated that CAF are heterogeneous and composed of different subpopulations exerting distinct functions in cancer. CAF populations differentially modulate various aspects of tumor growth, including cancer cell proliferation, extra-cellular matrix remodeling, metastatic dissemination, immunosuppression and resistance to treatment. Among other markers, the Fibroblast Activation Protein (FAP) led to the identification of a specific CAF subpopulation involved in metastatic spread and immunosuppression. Expression of FAP at the surface of CAF is detected in many different cancer types of poor prognosis. Thus, FAP recently appears as an appealing target for therapeutic and molecular imaging applications. In that context, 68Ga-labeled radiopharmaceutical-FAP-inhibitors (FAPI) have been recently developed and validated for quantitatively mapping FAP expression over the whole-body using Positron Emission Tomography (PET/CT). In this review, we describe the main current knowledge on CAF subpopulations and their distinct functions in solid tumors, as well as the promising diagnostic and therapeutic implications of radionuclides targeting FAP.

Predictors of toxicity after curative reirradiation with intensity modulated radiotherapy or proton therapy for recurrent head and neck carcinoma: new dose constraints for pharyngeal constrictors muscles and oral cavity.

BACKGROUND: Our study aims to identify predictive factors of moderate to severe (grade ≥ 2) late toxicity after reirradiation (reRT) of recurrent head and neck carcinoma (HNC) and explore the correlations between dose organs at risk (OAR) and grade ≥ 2 toxicity. MATERIAL AND METHODS: Between 09/2007 and 09/2019, 55 patients were re-irradiated with IMRT or proton therapy with curative intent for advanced HNC. Our study included all patients for whom data from the first and second irradiations were available. Co-variables, including interval to reRT, size of re-irradiated PTV, and dose to OAR, were analyzed as potential predictors for developing moderate to severe long-term toxicity with death as a competing risk. Receiver-operator characteristics (ROC) analysis assessed the association between dose/volume parameters and the risk of toxicity. RESULTS: Twenty-three patients participated in our study. After a median follow-up of 41 months, 65% of the patients experienced grade ≥ 2 late toxicity. The average dose to pharyngeal constrictor muscles (PCM) at the time of reRT showed an association with the risk of grade ≥ 2 dysphagia: AUC = 0.78 (95% CI: 0.53-1), optimal cut-off value = 36.7 Gy (sensitivity 62%/specificity 100%). The average dose to the oral cavity at the time of reRT showed an association with the risk of grade ≥ 2 dysgeusia: AUC = 0.96 (0.89-1), optimal cut-off value = 20.5 Gy (sensitivity 100%/specificity 88%). CONCLUSION: Our analysis depicted an association between the dose to OAR and the risk of developing moderate to severe dysphagia and dysgeusia and proposed new dose constraints for PCM (36.7 Gy) and oral cavity (20.5 Gy).

[18F]-FDG PET and MRI radiomic signatures to predict the risk and the location of tumor recurrence after re-irradiation in head and neck cancer.

PURPOSE: To evaluate whether radiomics from [18F]-FDG PET and/or MRI before re-irradiation (reRT) of recurrent head and neck cancer (HNC) could predict the occurrence and the location "in-field" or "outside" of a second locoregional recurrence (LR). METHODS: Among the 55 patients re-irradiated at curative intend for HNC from 2012 to 2019, 48 had an MRI and/or PET before the start of the reRT. Thirty-nine radiomic features (RF) were extracted from the re-irradiated GTV (rGTV) using LIFEx software. Student t tests and Spearman correlation coefficient were used to select the RF that best separate patients who recurred from those who did not, and "in-field" from "outside" recurrences. Principal component analysis involving these features only was used to create a prediction model. Leave-one-out cross-validation was performed to evaluate the models. RESULTS: After a median follow-up of 17 months, 40/55 patients had developed a second LR, including 18 "in-field" and 22 "outside" recurrences. From pre-reRT MRI, a model based on three RF (GLSZM_SZHGLE, GLSZM_LGLZE, and skewness) predicted whether patients would recur with a balanced accuracy (BA) of 83.5%. Another model from pre-reRT MRI based on three other RF (GLSZM_ LZHGE, NGLDM_Busyness, and GLZLM_SZE) predicted whether patients would recur "in-field" or "outside" with a BA of 78.5%. From pre-reRT PET, a model based on four RF (Kurtosis, SUVbwmin, GLCM_Correlation, and GLCM_Contrast) predicted the LR location with a BA of 84.5%. CONCLUSION: RF characterizing tumor heterogeneity extracted from pre-reRT PET and MRI predicted whether patients would recur, and whether they would recur "in-field" or "outside".

[18F]FDG PET/CT for predicting triple-negative breast cancer outcomes after neoadjuvant chemotherapy with or without pembrolizumab.

PURPOSE: To determine if pretreatment [18F]FDG PET/CT could contribute to predicting complete pathological complete response (pCR) in patients with early-stage triple-negative breast cancer (TNBC) undergoing neoadjuvant chemotherapy with or without pembrolizumab. METHODS: In this retrospective bicentric study, we included TNBC patients who underwent [18F]FDG PET/CT before neoadjuvant chemotherapy (NAC) or chemo-immunotherapy (NACI) between March 2017 and August 2022. Clinical, biological, and pathological data were collected. Tumor SUVmax and total metabolic tumor volume (TMTV) were measured from the PET images. Cut-off values were determined using ROC curves and a multivariable model was developed using logistic regression to predict pCR. RESULTS: N = 191 patients were included. pCR rates were 53 and 70% in patients treated with NAC (N = 91) and NACI (N = 100), respectively (p < 0.01). In univariable analysis, high Ki67, high tumor SUVmax (> 12.3), and low TMTV (≤ 3.0 cm3) were predictors of pCR in the NAC cohort while tumor staging classification (< T3), BRCA1/2 germline mutation, high tumor SUVmax (> 17.2), and low TMTV (≤ 7.3 cm3) correlated with pCR in the NACI cohort. In multivariable analysis, only high tumor SUVmax (NAC: OR 8.8, p < 0.01; NACI: OR 3.7, p = 0.02) and low TMTV (NAC: OR 6.6, p < 0.01; NACI: OR 3.5, p = 0.03) were independent factors for pCR in both cohorts, albeit at different thresholds. CONCLUSION: High tumor metabolism (SUVmax) and low tumor burden (TMTV) could predict pCR after NAC regardless of the addition of pembrolizumab. Further studies are warranted to validate such findings and determine how these biomarkers could be used to guide neoadjuvant therapy in TNBC patients.

An [18F]FDG-PET/CT deep learning method for fully automated detection of pathological mediastinal lymph nodes in lung cancer patients.

PURPOSE: The identification of pathological mediastinal lymph nodes is an important step in the staging of lung cancer, with the presence of metastases significantly affecting survival rates. Nodes are currently identified by a physician, but this process is time-consuming and prone to errors. In this paper, we investigate the use of artificial intelligence-based methods to increase the accuracy and consistency of this process. METHODS: Whole-body 18F-labelled fluoro-2-deoxyglucose ([18F]FDG) positron emission tomography/computed tomography ([18F]FDG-PET/CT) scans (Philips Gemini TF) from 134 patients were retrospectively analysed. The thorax was automatically located, and then slices were fed into a U-Net to identify candidate regions. These regions were split into overlapping 3D cubes, which were individually predicted as positive or negative using a 3D CNN. From these predictions, pathological mediastinal nodes could be identified. A second cohort of 71 patients was then acquired from a different, newer scanner (GE Discovery MI), and the performance of the model on this dataset was tested with and without transfer learning. RESULTS: On the test set from the first scanner, our model achieved a sensitivity of 0.87 (95% confidence intervals [0.74, 0.94]) with 0.41 [0.22, 0.71] false positives/patient. This was comparable to the performance of an expert. Without transfer learning, on the test set from the second scanner, the corresponding results were 0.53 [0.35, 0.70] and 0.24 [0.10, 0.49], respectively. With transfer learning, these metrics were 0.88 [0.73, 0.97] and 0.69 [0.43, 1.04], respectively. CONCLUSION: Model performance was comparable to that of an expert on data from the same scanner. With transfer learning, the model can be applied to data from a different scanner. To our knowledge it is the first study of its kind to go directly from whole-body [18F]FDG-PET/CT scans to pathological mediastinal lymph node localisation.

Prognostic value of lesion dissemination in doxorubicin, bleomycin, vinblastine, and dacarbazine-treated, interimPET-negative classical Hodgkin Lymphoma patients: A radio-genomic study.

We evaluated the prognostic role of the largest distance between two lesions (Dmax), defined by positron emission tomography (PET) in a retrospective cohort of newly diagnosed classical Hodgkin Lymphoma (cHL) patients. We also explored the molecular bases underlying Dmax through a gene expression analysis of diagnostic biopsies. We included patients diagnosed with cHL from 2007 to 2020, initially treated with ABVD, with available baseline PET for review, and with at least two FDG avid lesions. Patients with available RNA from diagnostic biopsy were eligible for gene expression analysis. Dmax was deduced from the three-dimensional coordinates of the baseline metabolic tumor volume (MTV) and its effect on progression free survival (PFS) was evaluated. Gene expression profiles were correlated with Dmax and analyzed using CIBERSORTx algorithm to perform deconvolution. The study was conducted on 155 eligible cHL patients. Using its median value of 20 cm, Dmax was the only variable independently associated with PFS (HR = 2.70, 95% CI 1.1-6.63, pValue = 0.03) in multivariate analysis of PFS for all patients and for those with early complete metabolic response (iPET-). Among patients with iPET-low Dmax was associated with a 4-year PFS of 90% (95% CI 82.0-98.9) significantly better compared to high Dmax (4-year PFS 72.4%, 95% CI 61.9-84.6). From the analysis of gene expression profiles differences in Dmax were mostly associated with variations in the expression of microenvironmental components. In conclusion our results support tumor dissemination measured through Dmax as novel prognostic factor for cHL patients treated with ABVD.

Potentials and caveats of AI in hybrid imaging.

State-of-the-art patient management frequently mandates the investigation of both anatomy and physiology of the patients. Hybrid imaging modalities such as the PET/MRI, PET/CT and SPECT/CT have the ability to provide both structural and functional information of the investigated tissues in a single examination. With the introduction of such advanced hardware fusion, new problems arise such as the exceedingly large amount of multi-modality data that requires novel approaches of how to extract a maximum of clinical information from large sets of multi-dimensional imaging data. Artificial intelligence (AI) has emerged as one of the leading technologies that has shown promise in facilitating highly integrative analysis of multi-parametric data. Specifically, the usefulness of AI algorithms in the medical imaging field has been heavily investigated in the realms of (1) image acquisition and reconstruction, (2) post-processing and (3) data mining and modelling. Here, we aim to provide an overview of the challenges encountered in hybrid imaging and discuss how AI algorithms can facilitate potential solutions. In addition, we highlight the pitfalls and challenges in using advanced AI algorithms in the context of hybrid imaging and provide suggestions for building robust AI solutions that enable reproducible and transparent research.

Total metabolic tumor volume and spleen metabolism on baseline [18F]-FDG PET/CT as independent prognostic biomarkers of recurrence in resected breast cancer.

PURPOSE: We evaluated whether biomarkers on baseline [18F]-FDG PET/CT are associated with recurrence after surgery in patients with invasive breast cancer of no special type (NST). METHODS: In this retrospective single-center study, we included consecutive patients with non-metastatic breast cancer of NST who underwent [18F]-FDG PET/CT before treatment, including surgery, between 2011 and 2016. Clinicopathological data were collected. Tumor SUVmax, total metabolic tumor volume (TMTV), and spleen- and bone marrow-to-liver SUVmax ratios (SLR, BLR) were measured from the PET images. Cut-off values were determined using predictiveness curves to predict 5-year recurrence-free survival (5y-RFS). A multivariable prediction model was developed using Cox regression. The association with stromal tumor-infiltrating lymphocytes (TILs) levels (low if <50%) was studied by logistic regression. RESULTS: Three hundred and three women were eligible, including 93 (31%) with triple-negative breast carcinoma. After a median follow-up of 6.2 years, 56 and 35 patients experienced recurrence and death, respectively. The 5y-RFS rate was 86%. In multivariable analyses, high TMTV (>20 cm3) and high SLR (>0.76) were associated with shorter 5y-RFS (HR 2.4, 95%CI 1.3-4.5, and HR 1.9, 95%CI 1.0-3.6). In logistic regression, high SLR was the only independent factor associated with low stromal TILs (OR 2.8, 95%CI 1.4-5.7). CONCLUSION: High total metabolic tumor volume and high spleen glucose metabolism on baseline [18F]-FDG PET/CT were associated with poor 5y-RFS after surgical resection in patients with breast cancer of NST. Spleen metabolism was inversely correlated with stromal TILs and might be a surrogate for an immunosuppressive tumor microenvironment.

Just another "Clever Hans"? Neural networks and FDG PET-CT to predict the outcome of patients with breast cancer.

BACKGROUND: Manual quantification of the metabolic tumor volume (MTV) from whole-body 18F-FDG PET/CT is time consuming and therefore usually not applied in clinical routine. It has been shown that neural networks might assist nuclear medicine physicians in such quantification tasks. However, little is known if such neural networks have to be designed for a specific type of cancer or whether they can be applied to various cancers. Therefore, the aim of this study was to evaluate the accuracy of a neural network in a cancer that was not used for its training. METHODS: Fifty consecutive breast cancer patients that underwent 18F-FDG PET/CT were included in this retrospective analysis. The PET-Assisted Reporting System (PARS) prototype that uses a neural network trained on lymphoma and lung cancer 18F-FDG PET/CT data had to detect pathological foci and determine their anatomical location. Consensus reads of two nuclear medicine physicians together with follow-up data served as diagnostic reference standard; 1072 18F-FDG avid foci were manually segmented. The accuracy of the neural network was evaluated with regard to lesion detection, anatomical position determination, and total tumor volume quantification. RESULTS: If PERCIST measurable foci were regarded, the neural network displayed high per patient sensitivity and specificity in detecting suspicious 18F-FDG foci (92%; CI = 79-97% and 98%; CI = 94-99%). If all FDG-avid foci were regarded, the sensitivity degraded (39%; CI = 30-50%). The localization accuracy was high for body part (98%; CI = 95-99%), region (88%; CI = 84-90%), and subregion (79%; CI = 74-84%). There was a high correlation of AI derived and manually segmented MTV (R2 = 0.91; p < 0.001). AI-derived whole-body MTV (HR = 1.275; CI = 1.208-1.713; p < 0.001) was a significant prognosticator for overall survival. AI-derived lymph node MTV (HR = 1.190; CI = 1.022-1.384; p = 0.025) and liver MTV (HR = 1.149; CI = 1.001-1.318; p = 0.048) were predictive for overall survival in a multivariate analysis. CONCLUSION: Although trained on lymphoma and lung cancer, PARS showed good accuracy in the detection of PERCIST measurable lesions. Therefore, the neural network seems not prone to the clever Hans effect. However, the network has poor accuracy if all manually segmented lesions were used as reference standard. Both the whole body and organ-wise MTV were significant prognosticators of overall survival in advanced breast cancer.

How can we combat multicenter variability in MR radiomics? Validation of a correction procedure.

OBJECTIVE: Test a practical realignment approach to compensate the technical variability of MR radiomic features. METHODS: T1 phantom images acquired on 2 scanners, FLAIR and contrast-enhanced T1-weighted (CE-T1w) images of 18 brain tumor patients scanned on both 1.5-T and 3-T scanners, and 36 T2-weighted (T2w) images of prostate cancer patients scanned in one of two centers were investigated. The ComBat procedure was used for harmonizing radiomic features. Differences in statistical distributions in feature values between 1.5- and 3-T images were tested before and after harmonization. The prostate studies were used to determine the impact of harmonization to distinguish between Gleason grades (GGs). RESULTS: In the phantom data, 40 out of 42 radiomic feature values were significantly different between the 2 scanners before harmonization and none after. In white matter regions, the statistical distributions of features were significantly different (p < 0.05) between the 1.5- and 3-T images for 37 out of 42 features in both FLAIR and CE-T1w images. After harmonization, no statistically significant differences were observed. In brain tumors, 41 (FLAIR) or 36 (CE-T1w) out of 42 features were significantly different between the 1.5- and 3-T images without harmonization, against 1 (FLAIR) or none (CE-T1w) with harmonization. In prostate studies, 636 radiomic features were significantly different between GGs after harmonization against 461 before. The ability to distinguish between GGs using radiomic features was increased after harmonization. CONCLUSION: ComBat harmonization efficiently removes inter-center technical inconsistencies in radiomic feature values and increases the sensitivity of studies using data from several scanners. KEY POINTS: • Radiomic feature values obtained using different MR scanners or imaging protocols can be harmonized by combining off-the-shelf image standardization and feature realignment procedures. • Harmonized radiomic features enable one to pool data from different scanners and centers without a substantial loss of statistical power caused by intra- and inter-center variability. • The proposed realignment method is applicable to radiomic features from different MR sequences and tumor types and does not rely on any phantom acquisition.

A radiomics pipeline dedicated to Breast MRI: validation on a multi-scanner phantom study.

OBJECTIVE: Quantitative analysis in MRI is challenging due to variabilities in intensity distributions across patients, acquisitions and scanners and suffers from bias field inhomogeneity. Radiomic studies are impacted by these effects that affect radiomic feature values. This paper describes a dedicated pipeline to increase reproducibility in breast MRI radiomic studies. MATERIALS AND METHODS: T1, T2, and T1-DCE MR images of two breast phantoms were acquired using two scanners and three dual breast coils. Images were retrospectively corrected for bias field inhomogeneity and further normalised using Z score or histogram matching. Extracted radiomic features were harmonised between coils by the ComBat method. The whole pipeline was assessed qualitatively and quantitatively using statistical comparisons on two series of radiomic feature values computed in the gel mimicking the normal breast tissue or in dense lesions. RESULTS: Intra and inter-acquisition variabilities were strongly reduced by the standardisation pipeline. Harmonisation by ComBat lowered the percentage of radiomic features significantly different between the three coils from 87% after bias field correction and MR normalisation to 3% in the gel, while preserving or improving performance of lesion classification in the phantoms. DISCUSSION: A dedicated standardisation pipeline was developed to reduce variabilities in breast MRI, which paves the way for robust multi-scanner radiomic studies but needs to be assessed on patient data.

The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping.

Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.

Longitudinal mouse-PET imaging: a reliable method for estimating binding parameters without a reference region or blood sampling.

Longitudinal mouse PET imaging is becoming increasingly popular due to the large number of transgenic and disease models available but faces challenges. These challenges are related to the small size of the mouse brain and the limited spatial resolution of microPET scanners, along with the small blood volume making arterial blood sampling challenging and impossible for longitudinal studies. The ability to extract an input function directly from the image would be useful for quantification in longitudinal small animal studies where there is no true reference region available such as TSPO imaging. METHODS: Using dynamic, whole-body 18F-DPA-714 PET scans (60 min) in a mouse model of hippocampal sclerosis, we applied a factor analysis (FA) approach to extract an image-derived input function (IDIF). This mouse-specific IDIF was then used for 4D-resolution recovery and denoising (4D-RRD) that outputs a dynamic image with better spatial resolution and noise properties, and a map of the total volume of distribution (VT) was obtained using a basis function approach in a total of 9 mice with 4 longitudinal PET scans each. We also calculated percent injected dose (%ID) with and without 4D-RRD. The VT and %ID parameters were compared to quantified ex vivo autoradiography using regional correlations of the specific binding from autoradiography against VT and %ID parameters. RESULTS: The peaks of the IDIFs were strongly correlated with the injected dose (Pearson R = 0.79). The regional correlations between the %ID estimates and autoradiography were R = 0.53 without 4D-RRD and 0.72 with 4D-RRD over all mice and scans. The regional correlations between the VT estimates and autoradiography were R = 0.66 without 4D-RRD and 0.79 with application of 4D-RRD over all mice and scans. CONCLUSION: We present a FA approach for IDIF extraction which is robust, reproducible and can be used in quantification methods for resolution recovery, denoising and parameter estimation. We demonstrated that the proposed quantification method yields parameter estimates closer to ex vivo measurements than semi-quantitative methods such as %ID and is immune to tracer binding in tissue unlike reference tissue methods. This approach allows for accurate quantification in longitudinal PET studies in mice while avoiding repeated blood sampling.

Validation of A Method to Compensate Multicenter Effects Affecting CT Radiomics.

Background Radiomics extracts features from medical images more precisely and more accurately than visual assessment. However, radiomics features are affected by CT scanner parameters such as reconstruction kernel or section thickness, thus obscuring underlying biologically important texture features. Purpose To investigate whether a compensation method could correct for the variations of radiomic feature values caused by using different CT protocols. Materials and Methods Phantom data involving 10 texture patterns and 74 patients in cohorts 1 (19 men; 42 patients; mean age, 60.4 years; September-October 2013) and 2 (16 men; 32 patients; mean age, 62.1 years; January-September 2007) scanned by using different CT protocols were retrospectively included. For any radiomic feature, the compensation approach identified a protocol-specific transformation to express all data in a common space that were devoid of protocol effects. The differences in statistical distributions between protocols were assessed by using Friedman tests before and after compensation. Principal component analyses were performed on the phantom data to evaluate the ability to distinguish between texture patterns after compensation. Results In the phantom data, the statistical distributions of features were different between protocols for all radiomic features and texture patterns (P < .05). After compensation, the protocol effect was no longer detectable (P > .05). Principal component analysis demonstrated that each texture pattern was no longer displayed as different clusters corresponding to different imaging protocols, unlike what was observed before compensation. The correction for scanner effect was confirmed in patient data with 100% (10 of 10 features for cohort 1) and 98% (87 of 89 features for cohort 2) of P values less than .05 before compensation, compared with 30% (three of 10) and 15% (13 of 89) after compensation. Conclusion Image compensation successfully realigned feature distributions computed from different CT imaging protocols and should facilitate multicenter radiomic studies. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Steiger and Sood in this issue.

A score combining baseline neutrophilia and primary tumor SUVpeak measured from FDG PET is associated with outcome in locally advanced cervical cancer.

PURPOSE: We investigated whether a score combining baseline neutrophilia and a PET biomarker could predict outcome in patients with locally advanced cervical cancer (LACC). METHODS: Patients homogeneously treated with definitive chemoradiation plus image-guided adaptive brachytherapy (IGABT) between 2006 and 2013 were analyzed retrospectively. We divided patients into two groups depending on the PET device used: a training set (TS) and a validation set (VS). Primary tumors were semi-automatically delineated on PET images, and 11 radiomics features were calculated (LIFEx software). A PET radiomic index was selected using the time-dependent area under the curve (td-AUC) for 3-year local control (LC). We defined the neutrophil SUV grade (NSG = 0, 1 or 2) score as the number of risk factors among (i) neutrophilia (neutrophil count >7 G/L) and (ii) high risk defined from the PET radiomic index. The NSG prognostic value was evaluated for LC and overall survival (OS). RESULTS: Data from 108 patients were analyzed. Estimated 3-year LC was 72% in the TS (n = 69) and 65% in the VS (n = 39). In the TS, SUVpeak was selected as the most LC-predictive biomarker (td-AUC = 0.75), and was independent from neutrophilia (p = 0.119). Neutrophilia (HR = 2.6), high-risk SUVpeak (SUVpeak > 10, HR = 4.4) and NSG = 2 (HR = 9.2) were associated with low probability of LC in TS. In multivariate analysis, NSG = 2 was independently associated with low probability of LC (HR = 7.5, p < 0.001) and OS (HR = 5.8, p = 0.001) in the TS. Results obtained in the VS (HR = 5.2 for OS and 3.5 for LC, p < 0.02) were promising. CONCLUSION: This innovative scoring approach combining baseline neutrophilia and a PET biomarker provides an independent prognostic factor to consider for further clinical investigations.

Longitudinal positron emission tomography imaging of glial cell activation in a mouse model of mesial temporal lobe epilepsy: Toward identification of optimal treatment windows.

OBJECTIVE: Mesiotemporal lobe epilepsy is the most common type of drug-resistant partial epilepsy, with a specific history that often begins with status epilepticus due to various neurological insults followed by a silent period. During this period, before the first seizure occurs, a specific lesion develops, described as unilateral hippocampal sclerosis (HS). It is still challenging to determine which drugs, administered at which time point, will be most effective during the formation of this epileptic process. Neuroinflammation plays an important role in pathophysiological mechanisms in epilepsy, and therefore brain inflammation biomarkers such as translocator protein 18 kDa (TSPO) can be potent epilepsy biomarkers. TSPO is associated with reactive astrocytes and microglia. A unilateral intrahippocampal kainate injection mouse model can reproduce the defining features of human temporal lobe epilepsy with unilateral HS and the pattern of chronic pharmacoresistant temporal seizures. We hypothesized that longitudinal imaging using TSPO positron emission tomography (PET) with 18 F-DPA-714 could identify optimal treatment windows in a mouse model during the formation of HS. METHODS: The model was induced into the right dorsal hippocampus of male C57/Bl6 mice. Micro-PET/computed tomographic scanning was performed before model induction and along the development of the HS at 7 days, 14 days, 1 month, and 6 months. In vitro autoradiography and immunohistofluorescence were performed on additional mice at each time point. RESULTS: TSPO PET uptake reached peak at 7 days and mostly related to microglial activation, whereas after 14 days, reactive astrocytes were shown to be the main cells expressing TSPO, reflected by a continuing increased PET uptake. SIGNIFICANCE: TSPO-targeted PET is a highly potent longitudinal biomarker of epilepsy and could be of interest to determine the therapeutic windows in epilepsy and to monitor response to treatment.

Imaging the neuroimmune response to alcohol exposure in adolescent baboons: a TSPO PET study using 18 F-DPA-714.

The effects of acute alcohol exposure to the central nervous system are hypothesized to involve the innate immune system. The neuroimmune response to an initial and acute alcohol exposure was investigated using translocator protein 18 kDa (TSPO) PET imaging, a non-invasive marker of glial activation, in adolescent baboons. Three different alcohol-naive adolescent baboons (3-4 years old, 9 to 14 kg) underwent 18 F-DPA-714 PET experiments before, during and 7-12 months after this initial alcohol exposure (0.7-1.0 g/l). The brain distribution of 18 F-DPA-714 (VT ; in ml/cm3 ) was estimated in several brain regions using the Logan plot analysis and the metabolite-corrected arterial input function. Compared with alcohol-naive animals (VTbrain  = 3.7 ± 0.7 ml/cm3 ), the regional VT s of 18 F-DPA-714 were significantly increased during alcohol exposure (VTbrain  = 7.2 ± 0.4 ml/cm3 ; p < 0.001). Regional VT s estimated several months after alcohol exposure (VTbrain  = 5.7 ± 1.4 ml/cm3 ) were lower (p < 0.001) than those measured during alcohol exposure, but remained significantly higher (p < 0.001) than in alcohol-naive animals. The acute and long-term effects of ethanol exposure were observed globally across all brain regions. Acute alcohol exposure increased the binding of 18 F-DPA-714 to the brain in a non-human primate model of alcohol exposure that reflects the 'binge drinking' situation in adolescent individuals. The effect persisted for several months, suggesting a 'priming' of glial cell function after initial alcohol exposure.