A ROI-based quantitative pipeline for 18F-FDG PET metabolism and pCASL perfusion joint analysis: Validation of the 18F-FDG PET line.

In Mild Cognitive Impairment (MCI), the study of brain metabolism, provided by 18F-FluoroDeoxyGlucose Positron Emission Tomography (18F-FDG PET) can be integrated with brain perfusion through pseudo-Continuous Arterial Spin Labeling Magnetic Resonance sequences (MR pCASL). Cortical hypometabolism identification generally relies on wide control group datasets; pCASL control groups are instead not publicly available yet, due to lack of standardization in the acquisition parameters. This study presents a quantitative pipeline to be applied to PET and pCASL data to coherently analyze metabolism and perfusion inside 16 matching cortical regions of interest (ROIs) derived from the AAL3 atlas. The PET line is tuned on 36 MCI patients and 107 healthy control subjects, to agree in identifying hypometabolic regions with clinical reference methods (visual analysis supported by a vendor tool and Statistical Parametric Mapping, SPM, with two parametrizations here identified as SPM-A and SPM-B). The analysis was conducted for each ROI separately. The proposed PET analysis pipeline obtained accuracy 78 % and Cohen's к 60 % vs visual analysis, accuracy 79 % and Cohen's к 58 % vs SPM-A, accuracy 77 % and Cohen's к 54 % vs SPM-B. Cohen's к resulted not significantly different from SPM-A and SPM-B Cohen's к when assuming visual analysis as reference method (p-value 0.61 and 0.31 respectively). Considering SPM-A as reference method, Cohen's к is not significantly different from SPM-B Cohen's к as well (p-value = 1.00). The complete PET-pCASL pipeline was then preliminarily applied on 5 MCI patients and metabolism-perfusion regional correlations were assessed. The proposed approach can be considered as a promising tool for PET-pCASL joint analyses in MCI, even in the absence of a pCASL control group, to perform metabolism-perfusion regional correlation studies, and to assess and compare perfusion in hypometabolic or normo-metabolic areas.

Radiomics and liver: Where we are and where we are headed?

Hepatic diffuse conditions and focal liver lesions represent two of the most common scenarios to face in everyday radiological clinical practice. Thanks to the advances in technology, radiology has gained a central role in the management of patients with liver disease, especially due to its high sensitivity and specificity. Since the introduction of computed tomography (CT) and magnetic resonance imaging (MRI), radiology has been considered the non-invasive reference modality to assess and characterize liver pathologies. In recent years, clinical practice has moved forward to a quantitative approach to better evaluate and manage each patient with a more fitted approach. In this setting, radiomics has gained an important role in helping radiologists and clinicians characterize hepatic pathological entities, in managing patients, and in determining prognosis. Radiomics can extract a large amount of data from radiological images, which can be associated with different liver scenarios. Thanks to its wide applications in ultrasonography (US), CT, and MRI, different studies were focused on specific aspects related to liver diseases. Even if broadly applied, radiomics has some advantages and different pitfalls. This review aims to summarize the most important and robust studies published in the field of liver radiomics, underlying their main limitations and issues, and what they can add to the current and future clinical practice and literature.

Towards the Definition of Radiomic Features and Clinical Indices to Enhance the Diagnosis of Clinically Significant Cancers in PI-RADS 4 and 5 Lesions.

Prostate cancer (PC) is the most frequently diagnosed cancer among adult men, and its incidence is increasing worldwide [...].

Artificial intelligence for precision medicine in autoimmune liver disease.

Autoimmune liver diseases (AiLDs) are rare autoimmune conditions of the liver and the biliary tree with unknown etiology and limited treatment options. AiLDs are inherently characterized by a high degree of complexity, which poses great challenges in understanding their etiopathogenesis, developing novel biomarkers and risk-stratification tools, and, eventually, generating new drugs. Artificial intelligence (AI) is considered one of the best candidates to support researchers and clinicians in making sense of biological complexity. In this review, we offer a primer on AI and machine learning for clinicians, and discuss recent available literature on its applications in medicine and more specifically how it can help to tackle major unmet needs in AiLDs.

Radiomics in PI-RADS 3 Multiparametric MRI for Prostate Cancer Identification: Literature Models Re-Implementation and Proposal of a Clinical-Radiological Model.

PI-RADS 3 prostate lesions clinical management is still debated, with high variability among different centers. Identifying clinically significant tumors among PI-RADS 3 is crucial. Radiomics applied to multiparametric MR (mpMR) seems promising. Nevertheless, reproducibility assessment by external validation is required. We retrospectively included all patients with at least one PI-RADS 3 lesion (PI-RADS v2.1) detected on a 3T prostate MRI scan at our Institution (June 2016-March 2021). An MRI-targeted biopsy was used as ground truth. We assessed reproducible mpMRI radiomic features found in the literature. Then, we proposed a new model combining PSA density and two radiomic features (texture regularity (T2) and size zone heterogeneity (ADC)). All models were trained/assessed through 100-repetitions 5-fold cross-validation. Eighty patients were included (26 with GS ≥ 7). In total, 9/20 T2 features (Hector's model) and 1 T2 feature (Jin's model) significantly correlated to biopsy on our dataset. PSA density alone predicted clinically significant tumors (sensitivity: 66%; specificity: 71%). Our model obtained a sensitivity of 80% and a specificity of 76%. Standard-compliant works with detailed methodologies achieve comparable radiomic feature sets. Therefore, efforts to facilitate reproducibility are needed, while complex models and imaging protocols seem not, since our model combining PSA density and two radiomic features from routinely performed sequences appeared to differentiate clinically significant cancers.

The "digital biopsy" in non-small cell lung cancer (NSCLC): a pilot study to predict the PD-L1 status from radiomics features of [18F]FDG PET/CT.

PURPOSE: The present pilot study investigates the putative role of radiomics from [18F]FDG PET/CT scans to predict PD-L1 expression status in non-small cell lung cancer (NSCLC) patients. METHODS: In a retrospective cohort of 265 patients with biopsy-proven NSCLC, 86 with available PD-L1 immunohistochemical (IHC) assessment and [18F]FDG PET/CT scans have been selected to find putative metabolic markers that predict PD-L1 status (< 1%, 1-49%, and ≥ 50% as per tumor proportion score, clone 22C3). Metabolic parameters have been extracted from three different PET/CT scanners (Discovery 600, Discovery IQ, and Discovery MI) and radiomics features were computed with IBSI compliant algorithms on the original image and on images filtered with LLL and HHH coif1 wavelet, obtaining 527 features per tumor. Univariate and multivariate analysis have been performed to compare PD-L1 expression status and selected radiomic features. RESULTS: Of the 86 analyzed cases, 46 (53%) were negative for PD-L1 IHC, 13 (15%) showed low PD-L1 expression (1-49%), and 27 (31%) were strong expressors (≥ 50%). Maximum standardized uptake value (SUVmax) demonstrated a significant ability to discriminate strong expressor cases at univariate analysis (p = 0.032), but failed to discriminate PD-L1 positive patients (PD-L1 ≥ 1%). Three radiomics features appeared the ablest to discriminate strong expressors: (1) a feature representing the average high frequency lesion content in a spherical VOI (p = 0.009); (2) a feature assessing the correlation between adjacent voxels on the high frequency lesion content (p = 0.004); (3) a feature that emphasizes the presence of small zones with similar grey levels inside the lesion (p = 0.003). The tri-variate linear discriminant model combining the three features achieved a sensitivity of 81% and a specificity of 82% in the test. The ability of radiomics to predict PD-L1 positive patients was instead scarce. CONCLUSIONS: Our data indicate a possible role of the [18F]FDG PET radiomics in predicting strong PD-L1 expression; these preliminary data need to be confirmed on larger or single-scanner series.

Evaluation of a 2D UNet-Based Attenuation Correction Methodology for PET/MR Brain Studies.

Deep learning (DL) strategies applied to magnetic resonance (MR) images in positron emission tomography (PET)/MR can provide synthetic attenuation correction (AC) maps, and consequently PET images, more accurate than segmentation or atlas-registration strategies. As first objective, we aim to investigate the best MR image to be used and the best point of the AC pipeline to insert the synthetic map in. Sixteen patients underwent a 18F-fluorodeoxyglucose (FDG) PET/computed tomography (CT) and a PET/MR brain study in the same day. PET/CT images were reconstructed with attenuation maps obtained: (1) from CT (reference), (2) from MR with an atlas-based and a segmentation-based method and (3) with a 2D UNet trained on MR image/attenuation map pairs. As for MR, T1-weighted and Zero Time Echo (ZTE) images were considered; as for attenuation maps, CTs and 511 keV low-resolution attenuation maps were assessed. As second objective, we assessed the ability of DL strategies to provide proper AC maps in presence of cranial anatomy alterations due to surgery. Three 11C-methionine (METH) PET/MR studies were considered. PET images were reconstructed with attenuation maps obtained: (1) from diagnostic coregistered CT (reference), (2) from MR with an atlas-based and a segmentation-based method and (3) with 2D UNets trained on the sixteen FDG anatomically normal patients. Only UNets taking ZTE images in input were considered. FDG and METH PET images were quantitatively evaluated. As for anatomically normal FDG patients, UNet AC models generally provide an uptake estimate with lower bias than atlas-based or segmentation-based methods. The intersubject average bias on images corrected with UNet AC maps is always smaller than 1.5%, except for AC maps generated on too coarse grids. The intersubject bias variability is the lowest (always lower than 2%) for UNet AC maps coming from ZTE images, larger for other methods. UNet models working on MR ZTE images and generating synthetic CT or 511 keV low-resolution attenuation maps therefore provide the best results in terms of both accuracy and variability. As for METH anatomically altered patients, DL properly reconstructs anatomical alterations. Quantitative results on PET images confirm those found on anatomically normal FDG patients.

Imaging Metformin Efficacy as Add-On Therapy in Cells and Mouse Models of Human EGFR Glioblastoma.

Glioblastoma (GBM) is a highly aggressive tumor of the brain. Despite the efforts, response to current therapies is poor and 2-years survival rate ranging from 6-12%. Here, we evaluated the preclinical efficacy of Metformin (MET) as add-on therapy to Temozolomide (TMZ) and the ability of [18F]FLT (activity of thymidine kinase 1 related to cell proliferation) and [18F]VC701 (translocator protein, TSPO) Positron Emission Tomography (PET) radiotracers to predict tumor response to therapy. Indeed, TSPO is expressed on the outer mitochondrial membrane of activated microglia/macrophages, tumor cells, astrocytes and endothelial cells. TMZ-sensitive (Gli36ΔEGFR-1 and L0627) or -resistant (Gli36ΔEGFR-2) GBM cell lines representative of classical molecular subtype were tested in vitro and in vivo in orthotopic mouse models. Our results indicate that in vitro, MET increased the efficacy of TMZ on TMZ-sensitive and on TMZ-resistant cells by deregulating the balance between pro-survival (bcl2) and pro-apoptotic (bax/bad) Bcl-family members and promoting early apoptosis in both Gli36ΔEGFR-1 and Gli36ΔEGFR-2 cells. In vivo, MET add-on significantly extended the median survival of tumor-bearing mice compared to TMZ-treated ones and reduced the rate of recurrence in the TMZ-sensitive models. PET studies with the cell proliferation radiopharmaceutical [18F]FLT performed at early time during treatment were able to distinguish responder from non-responder to TMZ but not to predict the duration of the effect. On the contrary, [18F]VC701 uptake was reduced only in mice treated with MET plus TMZ and levels of uptake negatively correlated with animals' survival. Overall, our data showed that MET addition improved TMZ efficacy in GBM preclinical models representative of classical molecular subtype increasing survival time and reducing tumor relapsing rate. Finally, results from PET imaging suggest that the reduction of cell proliferation represents a common mechanism of TMZ and combined treatment, whereas only the last was able to reduce TSPO. This reduction was associated with the duration of treatment response. TSPO-ligand may be used as a complementary molecular imaging marker to predict tumor microenvironment related treatment effects.

Combining positron emission tomography/computed tomography, radiomics, and sentinel lymph node mapping for nodal staging of endometrial cancer patients.

OBJECTIVE: To evaluate the combination of positron emission tomography/computed tomography (PET/CT) and sentinel lymph node (SLN) biopsy in women with apparent early-stage endometrial carcinoma. The correlation between radiomics features extracted from PET images of the primary tumor and the presence of nodal metastases was also analyzed. METHODS: From November 2006 to March 2019, 167 patients with endometrial cancer were included. All women underwent PET/CT and surgical staging: 60/167 underwent systematic lymphadenectomy (Group 1) while, more recently, 107/167 underwent SLN biopsy (Group 2) with technetium-99m +blue dye or indocyanine green. Histology was used as standard reference. PET endometrial lesions were segmented (n=98); 167 radiomics features were computed inside tumor contours using standard Image Biomarker Standardization Initiative (IBSI) methods. Radiomics features associated with lymph node metastases were identified (Mann-Whitney test) in the training group (A); receiver operating characteristic (ROC) curves, area under the curve (AUC) values were computed and optimal cut-off (Youden index) were assessed in the test group (B). RESULTS: In Group 1, eight patients had nodal metastases (13%): seven correctly ridentified by PET/CT true-positive with one false-negative case. In Group 2, 27 patients (25%) had nodal metastases: 13 true-positive and 14 false-negative. Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of PET/CT for pelvic nodal metastases were 87%, 94%, 93%, 70%, and 98% in Group 1 and 48%, 97%, 85%, 87%, and 85% in Group 2, respectively. On radiomics analysis a significant association was found between the presence of lymph node metastases and 64 features. Volume-density, a measurement of shape irregularity, was the most predictive feature (p=0001, AUC=0,77, cut-off 0.35). When testing cut-off in Group B to discriminate metastatic tumors, PET false-negative findings were reduced from 14 to 8 (-43%). CONCLUSIONS: PET/CT demonstrated high specificity in detecting nodal metastases. SLN and histologic ultrastaging increased false-negative PET/CT findings, reducing the sensitivity of the technique. PET radiomics features of the primary tumor seem promising for predicting the presence of nodal metastases not detected by visual analysis.

Radiomics of the primary tumour as a tool to improve 18F-FDG-PET sensitivity in detecting nodal metastases in endometrial cancer.

BACKGROUND: A radiomic approach was applied in 18F-FDG PET endometrial cancer, to investigate if imaging features computed on the primary tumour could improve sensitivity in nodal metastases detection. One hundred fifteen women with histologically proven endometrial cancer who underwent preoperative 18F-FDG PET/CT were retrospectively considered. SUV, MTV, TLG, geometrical shape, histograms and texture features were computed inside tumour contours. On a first group of 86 patients (DB1), univariate association with LN metastases was computed by Mann-Whitney test and a neural network multivariate model was developed. Univariate and multivariate models were assessed with leave one out on 20 training sessions and on a second group of 29 patients (DB2). A unified framework combining LN metastases visual detection results and radiomic analysis was also assessed. RESULTS: Sensitivity and specificity of LN visual detection were 50% and 99% on DB1 and 33% and 95% on DB2, respectively. A unique heterogeneity feature computed on the primary tumour (the zone percentage of the grey level size zone matrix, GLSZM ZP) was able to predict LN metastases better than any other feature or multivariate model (sensitivity and specificity of 75% and 81% on DB1 and of 89% and 80% on DB2). Tumours with LN metastases are in fact generally characterized by a lower GLSZM ZP value, i.e. by the co-presence of high-uptake and low-uptake areas. The combination of visual detection and GLSZM ZP values in a unified framework obtained sensitivity and specificity of 94% and 67% on DB1 and of 89% and 75% on DB2, respectively. CONCLUSIONS: The computation of imaging features on the primary tumour increases nodal staging detection sensitivity in 18F-FDG PET and can be considered for a better patient stratification for treatment selection. Results need a confirmation on larger cohort studies.

Developmental writing disorders: assess to rehabilitate.

BACKGROUND: Writing ability requires to use and control several processes of visual and phonological information processing and an adequate programming and coordination of motor sequences. We studied a writing precursor gesture in children with developmental dysorthography and/or developmental dysgraphia in order to point out anomalies to be treated with specific rehabilitative interventions. METHODS: Twenty-five children affected by developmental dysortography (ICD 9 CM: 315.09; ICD 10: F81.1) and/or developmental dysgraphia (ICD 9 CM: 315.2; ICD 10: F81.8) (mean age 9.1 years [range: 6.3-11.4 years]) ran a maze, project in front of them, using a wireless mouse. Data regarding angular excursions, execution times and gesture accuracy were collected and elaborated using Dartfish 6.0 software and the labyrinth generating program (PRINC), and compared with normative data previously obtained from a sample of 226 healthy children of the same age and grade. RESULTS: The comparison did not evidence significant differences regarding gesture structure (trajectories of arm segments and angular excursions of interested joints). Angular and temporal execution patterns were reached in delay in these children. No correlation was found with general cognitive and visuomotor integration skills; a deficit of visual attention was associated with an abnormal elbow range of motion. CONCLUSIONS: Although these findings need to be confirmed in larger studies, data obtained evidence that children with developmental writing disorders have a time delay in the acquisition of writing motor patterns and not an alteration of gesture structure itself. This has relevant implications for the rehabilitative approach.

Toward a standard for the evaluation of PET-Auto-Segmentation methods following the recommendations of AAPM task group No. 211: Requirements and implementation.

PURPOSE: The aim of this paper is to define the requirements and describe the design and implementation of a standard benchmark tool for evaluation and validation of PET-auto-segmentation (PET-AS) algorithms. This work follows the recommendations of Task Group 211 (TG211) appointed by the American Association of Physicists in Medicine (AAPM). METHODS: The recommendations published in the AAPM TG211 report were used to derive a set of required features and to guide the design and structure of a benchmarking software tool. These items included the selection of appropriate representative data and reference contours obtained from established approaches and the description of available metrics. The benchmark was designed in a way that it could be extendable by inclusion of bespoke segmentation methods, while maintaining its main purpose of being a standard testing platform for newly developed PET-AS methods. An example of implementation of the proposed framework, named PETASset, was built. In this work, a selection of PET-AS methods representing common approaches to PET image segmentation was evaluated within PETASset for the purpose of testing and demonstrating the capabilities of the software as a benchmark platform. RESULTS: A selection of clinical, physical, and simulated phantom data, including "best estimates" reference contours from macroscopic specimens, simulation template, and CT scans was built into the PETASset application database. Specific metrics such as Dice Similarity Coefficient (DSC), Positive Predictive Value (PPV), and Sensitivity (S), were included to allow the user to compare the results of any given PET-AS algorithm to the reference contours. In addition, a tool to generate structured reports on the evaluation of the performance of PET-AS algorithms against the reference contours was built. The variation of the metric agreement values with the reference contours across the PET-AS methods evaluated for demonstration were between 0.51 and 0.83, 0.44 and 0.86, and 0.61 and 1.00 for DSC, PPV, and the S metric, respectively. Examples of agreement limits were provided to show how the software could be used to evaluate a new algorithm against the existing state-of-the art. CONCLUSIONS: PETASset provides a platform that allows standardizing the evaluation and comparison of different PET-AS methods on a wide range of PET datasets. The developed platform will be available to users willing to evaluate their PET-AS methods and contribute with more evaluation datasets.

First clinical investigation of a 4D maximum likelihood reconstruction for 4D PET-based treatment verification in ion beam therapy.

BACKGROUND AND PURPOSE: In clinical applications of Positron Emission Tomography (PET)-based treatment verification in ion beam therapy (PT-PET), detection and interpretation of inconsistencies between Measured PET and Expected PET are mostly limited by Measured PET noise, due to low count statistics, and by Expected PET bias, especially due to inaccurate washout modelling in off-line implementations. In this work, a recently proposed 4D Maximum Likelihood (ML) reconstruction algorithm which considers Measured PET and Expected PET as two different motion phases of a 4D dataset is assessed on clinical 4D PET-CT datasets acquired after carbon ion therapy. MATERIAL AND METHODS: The 4D ML reconstruction algorithm estimates: (1) Measured PET of enhanced image quality with respect to the conventional Measured PET, thanks to the exploitation of Expected PET; (2) the deformation field mapping the Expected PET onto the Measured PET as a measure of the occurred displacements. RESULTS: Results demonstrate the desired sensitivity to inconsistencies due to breathing motion and/or setup modification, robustness to noise in different count statistics scenarios, but a limited sensitivity to Expected PET washout inaccuracy. CONCLUSIONS: The 4D ML reconstruction algorithm supports clinical 4D PT-PET in ion beam therapy. The limited sensitivity to washout inaccuracy can be detected and potentially overcome.

Reconstruction of uptake patterns in PET: The influence of regularizing prior.

PURPOSE: The effects of regularizing priors on the maximum likelihood (ML) reconstruction of activity patterns in Positron Emission Tomography (PET) were assessed. METHODS: Two edge-preserving priors (one originally proposed by Nuyts et al. and nowadays implemented and commercialized by General Electric Medical Systems as Q.Clear software, and a second one originally proposed by Rapisarda et al. and our group) were assessed and compared to a standard Ordered Subset (OS)-ML reconstruction, assumed as reference. The main difference between the two priors is that Nuyts prior (NY-p) penalizes relative voxel differences while Rapisarda prior (RP-p) absolute ones. Prior parameters were selected by imposing a reference noise texture inside uniform regions with activity comparable to that measured in 18 F-FluoroDeoxyGlucose (FDG) patient livers overall the field of view. Comparisons were then made: (a) on phantom data in terms of sphere recovery coefficients, ability to correctly reconstruct uniform irregularly shaped objects and heterogeneous patterns in patient backgrounds; (b) on patient data in terms of lesion detectability and image quality. RESULTS: On phantoms, both priors succeeded in improving all the assessed features with respect to standard OS-ML reconstruction, mainly thanks to the better signal convergence and to the noise breakup control. On 10 mm spheres, an average recovery coefficient augment of 9% (NY-p) and 34% (RP-p) was obtained; homogeneity of uniform activity objects augmented of 4% (NY-p) and 11% (RP-p); accuracy in reconstructing heterogeneous lesions improved on average of 5% (NY-p) and 15% (RP-p). On patients, lesion detectability resulted improved (on 27 of 30 lesions), regardless of lesion anatomical districts and position in the scanner field of view. NY-p provides a spatial resolution and a noise texture more uniform in the field of view and an image quality similar to standard OS-ML. RP-p has instead a behavior more dependent on the local counting statistics that imposes a trade-off between spatial resolution uniformity and noise texture homogeneity. CONCLUSIONS: The assessed regularizing priors improve PET uptake pattern reconstruction accuracy. Therefore, they should be considered both for oncological lesion detection and uptake spatial distribution assessment. Pitfalls and open challenges are also discussed.

Classification and evaluation strategies of auto-segmentation approaches for PET: Report of AAPM task group No. 211.

PURPOSE: The purpose of this educational report is to provide an overview of the present state-of-the-art PET auto-segmentation (PET-AS) algorithms and their respective validation, with an emphasis on providing the user with help in understanding the challenges and pitfalls associated with selecting and implementing a PET-AS algorithm for a particular application. APPROACH: A brief description of the different types of PET-AS algorithms is provided using a classification based on method complexity and type. The advantages and the limitations of the current PET-AS algorithms are highlighted based on current publications and existing comparison studies. A review of the available image datasets and contour evaluation metrics in terms of their applicability for establishing a standardized evaluation of PET-AS algorithms is provided. The performance requirements for the algorithms and their dependence on the application, the radiotracer used and the evaluation criteria are described and discussed. Finally, a procedure for algorithm acceptance and implementation, as well as the complementary role of manual and auto-segmentation are addressed. FINDINGS: A large number of PET-AS algorithms have been developed within the last 20 years. Many of the proposed algorithms are based on either fixed or adaptively selected thresholds. More recently, numerous papers have proposed the use of more advanced image analysis paradigms to perform semi-automated delineation of the PET images. However, the level of algorithm validation is variable and for most published algorithms is either insufficient or inconsistent which prevents recommending a single algorithm. This is compounded by the fact that realistic image configurations with low signal-to-noise ratios (SNR) and heterogeneous tracer distributions have rarely been used. Large variations in the evaluation methods used in the literature point to the need for a standardized evaluation protocol. CONCLUSIONS: Available comparison studies suggest that PET-AS algorithms relying on advanced image analysis paradigms provide generally more accurate segmentation than approaches based on PET activity thresholds, particularly for realistic configurations. However, this may not be the case for simple shape lesions in situations with a narrower range of parameters, where simpler methods may also perform well. Recent algorithms which employ some type of consensus or automatic selection between several PET-AS methods have potential to overcome the limitations of the individual methods when appropriately trained. In either case, accuracy evaluation is required for each different PET scanner and scanning and image reconstruction protocol. For the simpler, less robust approaches, adaptation to scanning conditions, tumor type, and tumor location by optimization of parameters is necessary. The results from the method evaluation stage can be used to estimate the contouring uncertainty. All PET-AS contours should be critically verified by a physician. A standard test, i.e., a benchmark dedicated to evaluating both existing and future PET-AS algorithms needs to be designed, to aid clinicians in evaluating and selecting PET-AS algorithms and to establish performance limits for their acceptance for clinical use. The initial steps toward designing and building such a standard are undertaken by the task group members.

Technical Note: A new zeolite PET phantom to test segmentation algorithms on heterogeneous activity distributions featured with ground-truth contours.

PURPOSE: Design, realization, scan, and characterization of a phantom for PET Automatic Segmentation (PET-AS) assessment are presented. Radioactive zeolites immersed in a radioactive heterogeneous background simulate realistic wall-less lesions with known irregular shape and known homogeneous or heterogeneous internal activity. METHOD: Three different zeolite families were evaluated in terms of radioactive uptake homogeneity, necessary to define activity and contour ground truth. Heterogeneous lesions were simulated by the perfect matching of two portions of a broken zeolite, soaked in two different 18 F-FDG radioactive solutions. Heterogeneous backgrounds were obtained with tissue paper balls and sponge pieces immersed into radioactive solutions. RESULTS: Natural clinoptilolite proved to be the most suitable zeolite for the construction of artificial objects mimicking homogeneous and heterogeneous uptakes in 18 F-FDG PET lesions. Heterogeneous backgrounds showed a coefficient of variation equal to 269% and 443% of a uniform radioactive solution. Assembled phantom included eight lesions with volumes ranging from 1.86 to 7.24 ml and lesion to background contrasts ranging from 4.8:1 to 21.7:1. CONCLUSIONS: A novel phantom for the evaluation of PET-AS algorithms was developed. It is provided with both reference contours and activity ground truth, and it covers a wide range of volumes and lesion to background contrasts. The dataset is open to the community of PET-AS developers and utilizers.

Integrating and monitoring hand burn rehabilitative treatment using Virtual Reality.

OBJECTIVES: Hand burn is not a common condition in the clinical practice and needs a long and laboured rehabilitative treatment to restore the lost function. METHODS: This case report illustrates the achievable improvements in mobility and function by using innovative inertial systems for occupational exercise in a Virtual Reality, in addition to a traditional rehabilitative treatment. RESULTS: Through these instruments, we could promote and concurrently assess the recovery of a functional grasp and the ability in the execution of Activities of Daily Living.

Background based Gaussian mixture model lesion segmentation in PET.

PURPOSE: Quantitative (18)F-fluorodeoxyglucose positron emission tomography is limited by the uncertainty in lesion delineation due to poor SNR, low resolution, and partial volume effects, subsequently impacting oncological assessment, treatment planning, and follow-up. The present work develops and validates a segmentation algorithm based on statistical clustering. The introduction of constraints based on background features and contiguity priors is expected to improve robustness vs clinical image characteristics such as lesion dimension, noise, and contrast level. METHODS: An eight-class Gaussian mixture model (GMM) clustering algorithm was modified by constraining the mean and variance parameters of four background classes according to the previous analysis of a lesion-free background volume of interest (background modeling). Hence, expectation maximization operated only on the four classes dedicated to lesion detection. To favor the segmentation of connected objects, a further variant was introduced by inserting priors relevant to the classification of neighbors. The algorithm was applied to simulated datasets and acquired phantom data. Feasibility and robustness toward initialization were assessed on a clinical dataset manually contoured by two expert clinicians. Comparisons were performed with respect to a standard eight-class GMM algorithm and to four different state-of-the-art methods in terms of volume error (VE), Dice index, classification error (CE), and Hausdorff distance (HD). RESULTS: The proposed GMM segmentation with background modeling outperformed standard GMM and all the other tested methods. Medians of accuracy indexes were VE <3%, Dice >0.88, CE <0.25, and HD <1.2 in simulations; VE <23%, Dice >0.74, CE <0.43, and HD <1.77 in phantom data. Robustness toward image statistic changes (±15%) was shown by the low index changes: <26% for VE, <17% for Dice, and <15% for CE. Finally, robustness toward the user-dependent volume initialization was demonstrated. The inclusion of the spatial prior improved segmentation accuracy only for lesions surrounded by heterogeneous background: in the relevant simulation subset, the median VE significantly decreased from 13% to 7%. Results on clinical data were found in accordance with simulations, with absolute VE <7%, Dice >0.85, CE <0.30, and HD <0.81. CONCLUSIONS: The sole introduction of constraints based on background modeling outperformed standard GMM and the other tested algorithms. Insertion of a spatial prior improved the accuracy for realistic cases of objects in heterogeneous backgrounds. Moreover, robustness against initialization supports the applicability in a clinical setting. In conclusion, application-driven constraints can generally improve the capabilities of GMM and statistical clustering algorithms.

Regularized ML reconstruction for time/dose reduction in (18)F-fluoride PET/CT studies.

We are proposing a regularized reconstruction strategy for the detection of bone lesions in (18)F-fluoride whole body PET images obtained with 1 min/bed using the anatomical information provided by co-registered CT images. Bones are recognized on CT images and then transposed into the PET volume framework. During PET reconstruction, two different priors are used for bone and non-bone voxels: the relative difference prior in bone and the P-Gaussian prior in non-bone. After a tuning of the priors' parameters, the reconstruction strategy has been tested on 6 (18)F-fluoride PET/CT studies, on a total of 67 lesions. Regularized images provided results comparable to the standard 3 min/bed images, in terms image quality, lesion activity, noise level and noise correlation. The proposed strategy therefore appears to be a useful tool to reduce the acquisition time or the injected dose in (18)F-fluoride PET studies.

Regional MLEM reconstruction strategy for PET-based treatment verification in ion beam radiotherapy.

In ion beam radiotherapy, PET-based treatment verification provides a consistency check of the delivered treatment with respect to a simulation based on the treatment planning. In this work the region-based MLEM reconstruction algorithm is proposed as a new evaluation strategy in PET-based treatment verification. The comparative evaluation is based on reconstructed PET images in selected regions, which are automatically identified on the expected PET images according to homogeneity in activity values. The strategy was tested on numerical and physical phantoms, simulating mismatches between the planned and measured ß+ activity distributions. The region-based MLEM reconstruction was demonstrated to be robust against noise and the sensitivity of the strategy results were comparable to three voxel units, corresponding to 6 mm in numerical phantoms. The robustness of the region-based MLEM evaluation outperformed the voxel-based strategies. The potential of the proposed strategy was also retrospectively assessed on patient data and further clinical validation is envisioned.