A deep neural network for parametric image reconstruction on a large axial field-of-view PET.

PURPOSE: The PET scanners with long axial field of view (AFOV) having ~ 20 times higher sensitivity than conventional scanners provide new opportunities for enhanced parametric imaging but suffer from the dramatically increased volume and complexity of dynamic data. This study reconstructed a high-quality direct Patlak Ki image from five-frame sinograms without input function by a deep learning framework based on DeepPET to explore the potential of artificial intelligence reducing the acquisition time and the dependence of input function in parametric imaging. METHODS: This study was implemented on a large AFOV PET/CT scanner (Biograph Vision Quadra) and twenty patients were recruited with 18F-fluorodeoxyglucose (18F-FDG) dynamic scans. During training and testing of the proposed deep learning framework, the last five-frame (25 min, 40-65 min post-injection) sinograms were set as input and the reconstructed Patlak Ki images by a nested EM algorithm on the vendor were set as ground truth. To evaluate the image quality of predicted Ki images, mean square error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) were calculated. Meanwhile, a linear regression process was applied between predicted and true Ki means on avid malignant lesions and tumor volume of interests (VOIs). RESULTS: In the testing phase, the proposed method achieved excellent MSE of less than 0.03%, high SSIM, and PSNR of ~ 0.98 and ~ 38 dB, respectively. Moreover, there was a high correlation (DeepPET: [Formula: see text]= 0.73, self-attention DeepPET: [Formula: see text]=0.82) between predicted Ki and traditionally reconstructed Patlak Ki means over eleven lesions. CONCLUSIONS: The results show that the deep learning-based method produced high-quality parametric images from small frames of projection data without input function. It has much potential to address the dilemma of the long scan time and dependency on input function that still hamper the clinical translation of dynamic PET.

Joint EANM/SNMMI guideline on radiomics in nuclear medicine : Jointly supported by the EANM Physics Committee and the SNMMI Physics, Instrumentation and Data Sciences Council.

PURPOSE: The purpose of this guideline is to provide comprehensive information on best practices for robust radiomics analyses for both hand-crafted and deep learning-based approaches. METHODS: In a cooperative effort between the EANM and SNMMI, we agreed upon current best practices and recommendations for relevant aspects of radiomics analyses, including study design, quality assurance, data collection, impact of acquisition and reconstruction, detection and segmentation, feature standardization and implementation, as well as appropriate modelling schemes, model evaluation, and interpretation. We also offer an outlook for future perspectives. CONCLUSION: Radiomics is a very quickly evolving field of research. The present guideline focused on established findings as well as recommendations based on the state of the art. Though this guideline recognizes both hand-crafted and deep learning-based radiomics approaches, it primarily focuses on the former as this field is more mature. This guideline will be updated once more studies and results have contributed to improved consensus regarding the application of deep learning methods for radiomics. Although methodological recommendations in the present document are valid for most medical image modalities, we focus here on nuclear medicine, and specific recommendations when necessary are made for PET/CT, PET/MR, and quantitative SPECT.

Predicting response to radiotherapy of head and neck squamous cell carcinoma using radiomics from cone-beam CT images.

INTRODUCTION: Radiotherapy (RT) for head and neck cancer is now guided by cone-beam computed tomography (CBCT). We aim to identify a CBCT radiomic signature predictive of progression to RT. MATERIAL AND METHODS: A cohort of 93 patients was split into training (n = 60) and testing (n = 33) sets. A total of 88 features were extracted from the gross tumor volume (GTV) on each CBCT. Receiver operating characteristic (ROC) curves were used to determine the power of each feature at each week of treatment to predict progression to radio(chemo)therapy. Only features with AUC > 0.65 at each week were pre-selected. Absolute differences were calculated between features from each weekly CBCT and baseline CBCT1 images. The smallest detectable change (C = 1.96 × SD, SD being the standard deviation of differences between feature values calculated on CBCT1 and CBCTn) with its confidence interval (95% confidence interval [CI]) was determined for each feature. The features for which the change was larger than C for at least 5% of patients were then selected. A radiomics-based model was built at the time-point that showed the highest AUC and compared with models relying on clinical variables. RESULTS: Seven features had an AUC > 0.65 at each week, and six exhibited a change larger than the predefined CI 95%. After exclusion of inter-correlated features, only one parameter remains, Coarseness. Among clinical variable, only hemoglobin value was significant. AUC for predicting the treatment response were 0.78 (p = .006), 0.85 (p < .001), and 0.99 (p < .001) for clinical, CBCT4-radiomics (Coarseness) and clinical + radiomics based models respectively. The mean AUC of this last model on a 5-fold cross-validation was 0.80 (±0.09). On the testing cohort, the best prediction was given by the combined model (balanced accuracy [BAcc] 0.67 , p < .001). CONCLUSIONS: We described a feature selection methodology for delta-radiomics that is able to select reproducible features which are informative due to their change during treatment. A selected delta radiomics feature may improve clinical-based prediction models.

Characterization of the Physiological Displacement of the Aortic Arch Using Non-Rigid Registration and MR Imaging.

OBJECTIVES: The aim of this work was to study physiological aortic arch three-dimensional displacement using non-rigid registration methods and magnetic resonance imaging (MRI). MATERIALS AND METHODS: Ten healthy volunteers underwent thoracic MRI. Prospective cardiac gating was performed with a 3D turbo field echo sequence to obtain end-systolic and end-diastolic MR images. The rigid and elastic behavior between these two cardiac phases was detected and compared using either an affine or an elastic registration method. To assess reproducibility, a second MRI acquisition was performed 14 days later. RESULTS: Affine registration between the end-systolic and end-diastolic MR images showed significant global translations of the aortic arch and the supra-aortic vessels in the x, y, and z directions (2.02 ± 1.6, -0.71 ± 1.1, and -1.21 ± 1.4 mm, respectively). Corresponding elastic registration indicated significant local displacement with a vector magnitude of 5.1 ± 0.89 mm for the brachiocephalic artery (BCA), of 4.26 ± 0.83 mm for the left common carotid artery (LCCA), and of 4.8 ± 0.86 mm for the left subclavian artery (LSCA). There was a difference in displacement between the supra-aortic trunks of the order of 2 mm. Vector displacement was not statistically different between the repeated acquisitions. CONCLUSIONS: The present results showed important deformations in the ostia of supra-aortic vessels during the cardiac cycle. It seems that aortic arch motions should be taken into account when designing and manufacturing fenestrated endografts. The elastic registration method provides more precise results, but is more complex and time-consuming than other methods.

CT respiratory motion synthesis using joint supervised and adversarial learning.

Objective.Four-dimensional computed tomography (4DCT) imaging consists in reconstructing a CT acquisition into multiple phases to track internal organ and tumor motion. It is commonly used in radiotherapy treatment planning to establish planning target volumes. However, 4DCT increases protocol complexity, may not align with patient breathing during treatment, and lead to higher radiation delivery.Approach.In this study, we propose a deep synthesis method to generate pseudo respiratory CT phases from static images for motion-aware treatment planning. The model produces patient-specific deformation vector fields (DVFs) by conditioning synthesis on external patient surface-based estimation, mimicking respiratory monitoring devices. A key methodological contribution is to encourage DVF realism through supervised DVF training while using an adversarial term jointly not only on the warped image but also on the magnitude of the DVF itself. This way, we avoid excessive smoothness typically obtained through deep unsupervised learning, and encourage correlations with the respiratory amplitude.Main results.Performance is evaluated using real 4DCT acquisitions with smaller tumor volumes than previously reported. Results demonstrate for the first time that the generated pseudo-respiratory CT phases can capture organ and tumor motion with similar accuracy to repeated 4DCT scans of the same patient. Mean inter-scans tumor center-of-mass distances and Dice similarity coefficients were 1.97 mm and 0.63, respectively, for real 4DCT phases and 2.35 mm and 0.71 for synthetic phases, and compares favorably to a state-of-the-art technique (RMSim).Significance.This study presents a deep image synthesis method that addresses the limitations of conventional 4DCT by generating pseudo-respiratory CT phases from static images. Although further studies are needed to assess the dosimetric impact of the proposed method, this approach has the potential to reduce radiation exposure in radiotherapy treatment planning while maintaining accurate motion representation. Our training and testing code can be found athttps://github.com/cyiheng/Dynagan.

Influence of partial volume correction in staging of head and neck squamous cell carcinoma using PET/CT.

Aim: PET/CT is widely used for the detection of lymph node involvement in head and neck squamous cell carcinoma (HNSCC). However, PET qualitative and quantitative capabilities are hindered by partial volume effects (PVE). Therefore, a retrospective study on 32 patients (57 lymph nodes) was carried out to evaluate the potential improvement of PVE correction (PVEC) in FDG PET/CT imaging for the diagnosis of HNSCC. Histopathological analysis of lymph nodes following neck dissection was used as the gold standard. Methods: A previously proposed deconvolution based PVEC approach was used to derive improved quantitative accuracy PET images, while the anatomical lymph node volumes were determined on the CT images. Different parameters including SUVmax and SUVmean were derived from both original and PVEC PET images for each patient. Results: Histopathology confirmed that SUVmax and SUVmean after PVEC allows a statistically significant differentiation of malignant and benign lymph nodes (p<0.05). The sensitivity of SUVmax and SUVmean was 64% and 57% respectively with or without PVEC. PVEC increased specificity from 71% to 76% for SUVmax and 57% to 66% for SUVmean. Corresponding accuracy increased from 66% to 71% for SUVmax and from 59% to 66% for SUVmean. However, the most accurate differentiation between benign and malignant nodes was obtained while using the magnitude of SUVmax increase after PVEC with a corresponding sensitivity, specificity and accuracy of 77%, 82% and 80% respectively. Conclusion: Our work shows that the use of partial volume effects correction allows a more accurate nodal staging using FDG PET imaging in HNSCC.

PET respiratory motion correction: quo vadis?

Positron emission tomography (PET) respiratory motion correction has been a subject of great interest for the last twenty years, prompted mainly by the development of multimodality imaging devices such as PET/computed tomography (CT) and PET/magnetic resonance imaging (MRI). PET respiratory motion correction involves a number of steps including acquisition synchronization, motion estimation and finally motion correction. The synchronization steps include the use of different external device systems or data driven approaches which have been gaining ground over the last few years. Patient specific or generic motion models using the respiratory synchronized datasets can be subsequently derived and used for correction either in the image space or within the image reconstruction process. Similar overall approaches can be considered and have been proposed for both PET/CT and PET/MRI devices. Certain variations in the case of PET/MRI include the use of MRI specific sequences for the registration of respiratory motion information. The proposed review includes a comprehensive coverage of all these areas of development in field of PET respiratory motion for different multimodality imaging devices and approaches in terms of synchronization, estimation and subsequent motion correction. Finally, a section on perspectives including the potential clinical usage of these approaches is included.

Evaluation of conventional and deep learning based image harmonization methods in radiomics studies.

Objective.To evaluate the impact of image harmonization on outcome prediction models using radiomics.Approach.234 patients from the Brain Tumor Image Segmentation Benchmark (BRATS) dataset with T1 MRI were enrolled in this study. Images were harmonized to a reference image using histogram matching (HHM) and a generative adversarial network (GAN)-based method (HGAN). 88 radiomics features were extracted on HHM, HGANand original (HNONE) images. Wilcoxon paired test was used to identify features significantly impacted by the harmonization protocol used. Radiomic prediction models were built using feature selection with the Least Absolute Shrinkage and Selection Operator (LASSO) and Kaplan-Meier analysis.Main results.More than 50% of the features (49/88) were statistically modified by the harmonization with HHMand 55 with HGAN(adjustedp-value < 0.05). The contribution of histogram and texture features selected by the LASSO, in comparison to shape features that were not impacted by harmonization, was higher in harmonized datasets (47% for Hnone, 62% for HHMand 71% for HGAN). Both image-based harmonization methods allowed to split patients into two groups with significantly different survival (p<0.05). With the HGANimages, we were also able to build and validate a model using only features impacted by the harmonization (median survivals of 189 versus 437 days,p= 0.006)Significance.Data harmonization in a multi-institutional cohort allows to recover the predictive value of some radiomics features that was lost due to differences in the image properties across centers. In terms of ability to build survival prediction models in the BRATS dataset, the loss of power from impacted histogram and heterogeneity features was compensated by the selection of additional shape features. The harmonization using a GAN-based approach outperformed the histogram matching technique, supporting the interest for the development of new advanced harmonization techniques for radiomic analysis purposes.

Radiomics analysis of 3D dose distributions to predict toxicity of radiotherapy for lung cancer.

PURPOSE: (Chemo)-radiotherapy (RT) is the gold standard treatment for patients with locally advanced lung cancer non accessible for surgery. However, current toxicity prediction models rely on clinical and dose volume histograms (DVHs) and remain unsufficient. The goal of this work is to investigate the added predictive value of the radiomics approach applied to dose maps regarding acute and late toxicities in both the lungs and esophagus. METHODS: Acute and late toxicities scored using the CTCAE v4.0 were retrospectively collected on patients treated with RT in our institution. Radiomic features were extracted from 3D dose maps considering Gy values as grey-levels in images. DVH and usual clinical factors were also considered. Three toxicity prediction models (clinical only, clinical + DVH and combined, i.e., including clinical + DVH + radiomics) were incrementally trained using a neural network on 70% of the patients for prediction of grade ≥2 acute and late pulmonary toxicities (APT/LPT) and grade ≥2 acute esophageal toxicities (AET). After bootstrapping (n = 1000), optimal cut-off values were determined based on the Youden Index. The trained models were then evaluated in the remaining 30% of patients using balanced accuracy (BAcc). RESULTS: 167 patients were treated from 2015 to 2018: 78% non small-cell lung cancers, 14% small-cell lung cancers and 8% other histology with a median age at treatment of 66 years. Respectively, 22.2%, 16.8% and 30.0% experienced APT, LPT and AET. In the training set (n = 117), the corresponding BAcc for clinical only/clinical + DVH/combined were 0.68/0.79/0.92, 0.66/0.77/0.87 and 0.68/0.73/0.84. In the testing evaluation (n = 50), these trained models obtained a corresponding BAcc of 0.69/0.69/0.92, 0.76/0.80/0.89 and 0.58/0.73/0.72. CONCLUSION: In patients with a lung cancer treated with RT, radiomic features extracted from 3D dose maps seem to surpass usual models based on clinical factors and DVHs for the prediction of APT and LPT.

Harmonization strategies for multicenter radiomics investigations.

Carrying out large multicenter studies is one of the key goals to be achieved towards a faster transfer of the radiomics approach in the clinical setting. This requires large-scale radiomics data analysis, hence the need for integrating radiomic features extracted from images acquired in different centers. This is challenging as radiomic features exhibit variable sensitivity to differences in scanner model, acquisition protocols and reconstruction settings, which is similar to the so-called 'batch-effects' in genomics studies. In this review we discuss existing methods to perform data integration with the aid of reducing the unwanted variation associated with batch effects. We also discuss the future potential role of deep learning methods in providing solutions for addressing radiomic multicentre studies.

Use of radiomics in the radiation oncology setting: Where do we stand and what do we need?

Radiomics is a field that has been growing rapidly for the past ten years in medical imaging and more particularly in oncology where the primary objective is to contribute to personalised and predictive medicine. This short review aimed at providing some insights regarding the potential value of radiomics for cancer patients treated with radiotherapy. Radiomics may contribute to each stage of the patients' management: diagnosis, planning, treatment monitoring and post-treatment follow-up (toxicity and response). However, its applicability in clinical routine is currently hindered by several factors, including lack of automation, standardisation and harmonisation. A major effort must be carried out to automate the workflow, standardise radiomics good practices and carry out large-scale studies before any transfer to daily clinical practice.

Performance comparison of modified ComBat for harmonization of radiomic features for multicenter studies.

Multicenter studies are needed to demonstrate the clinical potential value of radiomics as a prognostic tool. However, variability in scanner models, acquisition protocols and reconstruction settings are unavoidable and radiomic features are notoriously sensitive to these factors, which hinders pooling them in a statistical analysis. A statistical harmonization method called ComBat was developed to deal with the "batch effect" in gene expression microarray data and was used in radiomics studies to deal with the "center-effect". Our goal was to evaluate modifications in ComBat allowing for more flexibility in choosing a reference and improving robustness of the estimation. Two modified ComBat versions were evaluated: M-ComBat allows to transform all features distributions to a chosen reference, instead of the overall mean, providing more flexibility. B-ComBat adds bootstrap and Monte Carlo for improved robustness in the estimation. BM-ComBat combines both modifications. The four versions were compared regarding their ability to harmonize features in a multicenter context in two different clinical datasets. The first contains 119 locally advanced cervical cancer patients from 3 centers, with magnetic resonance imaging and positron emission tomography imaging. In that case ComBat was applied with 3 labels corresponding to each center. The second one contains 98 locally advanced laryngeal cancer patients from 5 centers with contrast-enhanced computed tomography. In that specific case, because imaging settings were highly heterogeneous even within each of the five centers, unsupervised clustering was used to determine two labels for applying ComBat. The impact of each harmonization was evaluated through three different machine learning pipelines for the modelling step in predicting the clinical outcomes, across two performance metrics (balanced accuracy and Matthews correlation coefficient). Before harmonization, almost all radiomic features had significantly different distributions between labels. These differences were successfully removed with all ComBat versions. The predictive ability of the radiomic models was always improved with harmonization and the improved ComBat provided the best results. This was observed consistently in both datasets, through all machine learning pipelines and performance metrics. The proposed modifications allow for more flexibility and robustness in the estimation. They also slightly but consistently improve the predictive power of resulting radiomic models.

Incorporation of wavelet-based denoising in iterative deconvolution for partial volume correction in whole-body PET imaging.

PURPOSE: Partial volume effects (PVEs) are consequences of the limited resolution of emission tomography. The aim of the present study was to compare two new voxel-wise PVE correction algorithms based on deconvolution and wavelet-based denoising. MATERIALS AND METHODS: Deconvolution was performed using the Lucy-Richardson and the Van-Cittert algorithms. Both of these methods were tested using simulated and real FDG PET images. Wavelet-based denoising was incorporated into the process in order to eliminate the noise observed in classical deconvolution methods. RESULTS: Both deconvolution approaches led to significant intensity recovery, but the Van-Cittert algorithm provided images of inferior qualitative appearance. Furthermore, this method added massive levels of noise, even with the associated use of wavelet-denoising. On the other hand, the Lucy-Richardson algorithm combined with the same denoising process gave the best compromise between intensity recovery, noise attenuation and qualitative aspect of the images. CONCLUSION: The appropriate combination of deconvolution and wavelet-based denoising is an efficient method for reducing PVEs in emission tomography.

Ensemble of neural networks for 3D position estimation in monolithic PET detectors.

We propose an ensemble of multilayer feedforward neural networks to estimate the 3D position of photoelectric interactions in monolithic detectors. The ensemble is trained with data generated from optical Monte Carlo simulations only. The originality of our approach is to exploit simulations to obtain reference data, in combination with a variability reduction that the network ensembles offer, thus, removing the need of extensive per-detector calibration measurements. This procedure delivers an ensemble valid for any detector of the same design. We show the capability of the ensemble to solve the 3D positioning problem through testing four different detector designs with Monte Carlo data, measurements from physical detectors and reconstructed images from the MindView scanner. Network ensembles allow the detector to achieve a 2-2.4 mm FWHM, depending on its design, and the associated reconstructed images present improved SNR, CNR and SSIM when compared to those based on the MindView built-in positioning algorithm.

Prognostic value of initial fluorodeoxyglucose-PET in esophageal cancer: a prospective study.

OBJECTIVES: Esophageal cancer outcome greatly depends on the pathological stage. Our objectives were to assess prognosis on the basis of the initial fluorodeoxyglucose (FDG)-PET scan, focusing on the correlation between overall survival and FDG uptake in the primary, as well as the presence of FDG-positive lymph nodes or distant metastases. METHODS: Fifty-two esophageal cancer patients undergoing FDG-PET as part of initial routine staging procedure before treatment were included. The maximum standardized uptake value (SUV max) was determined in each primary lesion and the number of abnormalities including primary, lymph nodes, or distant metastases was recorded. Correlation with overall survival was performed using Kaplan-Meier method and Cox regression analysis was used to assess the prognostic value of PET parameters. RESULTS: Half of the patients were planned for initial curative surgery (52%). Using univariate survival analysis, either surgery, SUV max >9, two or more PET abnormalities or the presence of FDG-positive nodes were significant overall survival prognostic predictors. After multivariate analysis, only SUV max >9 and FDG-positive lymph nodes were found as independent predictors of poor outcome. CONCLUSION: In this prospective study, FDG-PET was found to provide prognostic information supporting a new indication for initial FDG-PET examination in esophageal cancer.

Contrast enhancement in emission tomography by way of synergistic PET/CT image combination.

UNLABELLED: The display of image fusion is well accepted as a powerful tool in visual image analysis and comparison. In clinical practice, this is a mandatory step when studying images from a dual PET/CT scanner. However, the display methods that are implemented on most workstations simply show both images side by side, in separate and synchronized windows. Sometimes images are presented superimposed in a single window, preventing the user from doing quantitative analysis. In this article a new image fusion scheme is presented, allowing performing quantitative analysis directly on the fused images. METHODS: The objective is to preserve the functional information provided by PET while incorporating details of higher resolution from the CT image. The process relies on a discrete wavelet-based image merging: both images are decomposed into successive details layers by using the "à trous" transform. This algorithm performs wavelet decomposition of images and provides coarser and coarser spatial resolution versions of them. The high-spatial frequencies of the CT, or details, can be easily obtained at any level of resolution. A simple model is then inferred to compute the lacking details of the PET scan from the high frequency detail layers of the CT. These details are then incorporated in the PET image on a voxel-to-voxel basis, giving the fused PET/CT image. RESULTS: Aside from the expected visual enhancement, quantitative comparison of initial PET and CT images with fused images was performed in 12 patients. The obtained results were in accordance with the objectives of the study, in the sense that the organs' mean intensity in PET was preserved in the fused image. CONCLUSION: This alternative approach to PET/CT fusion display should be of interest for people interested in a more quantitative aspect of image fusion. The proposed method is actually complementary to more classical visualization tools.

Improved Woodcock tracking on Monte Carlo simulations for medical applications.

This paper presents a new variance reduction technique called super voxel Woodcock (SVW), which combines Woodcock tracking technique with the super voxel concept, used in computer graphics. It consists in grouping the voxels of the volume in a super voxel grid (pre-processing step) by associating to each of the super voxels a local value of the most attenuate medium which will later serve to the interaction distances sampling. SVW allows reducing the sampling of the particle path while a high-density material is present within the simulated phantom. In order to evaluate the performance of the SVW method compare to both standard and Woodcock tracking methods, algorithms were implemented within the same GPU MCS framework GGEMS. This method improves the performance of the standard Woodcock method by a factor of 4.5 and 4.3 for x-ray imaging application and intraoperative radiotherapy respectively. The proposed SVW method did not introduce any bias on the simulations.

A method for synchronizing an external respiratory signal with a list-mode PET acquisition.

A method is proposed to synchronize positron emission tomography (PET) list-mode data with an externally recorded respiratory signal in the absence of a master clock. When the respiratory signal reaches a user-defined threshold, a trigger mark is stored in the list-mode file. After the acquisition, synchronization is achieved when the stored trigger marks are superimposed on the respiratory curve to form a horizontal line over time at the user-defined threshold. Synchronization was possible and unequivocal for ten out of ten clinical studies. The list-mode acquisition actually started approximately 40 and 4 s after acquisition initiation at the user interface of the Philips Gemini and the GE DLS PET-CT systems, respectively.

Respiratory motion correction for PET oncology applications using affine transformation of list mode data.

Respiratory motion is a source of artefacts and reduced image quality in PET. Proposed methodology for correction of respiratory effects involves the use of gated frames, which are however of low signal-to-noise ratio. Therefore a method accounting for respiratory motion effects without affecting the statistical quality of the reconstructed images is necessary. We have implemented an affine transformation of list mode data for the correction of respiratory motion over the thorax. The study was performed using datasets of the NCAT phantom at different points throughout the respiratory cycle. List mode data based PET simulated frames were produced by combining the NCAT datasets with a Monte Carlo simulation. Transformation parameters accounting for respiratory motion were estimated according to an affine registration and were subsequently applied on the original list mode data. The corrected and uncorrected list mode datasets were subsequently reconstructed using the one-pass list mode EM (OPL-EM) algorithm. Comparison of corrected and uncorrected respiratory motion average frames suggests that an affine transformation in the list mode data prior to reconstruction can produce significant improvements in accounting for respiratory motion artefacts in the lungs and heart. However, the application of a common set of transformation parameters across the imaging field of view does not significantly correct the respiratory effects on organs such as the stomach, liver or spleen.

Fuzzy hidden Markov chains segmentation for volume determination and quantitation in PET.

Accurate volume of interest (VOI) estimation in PET is crucial in different oncology applications such as response to therapy evaluation and radiotherapy treatment planning. The objective of our study was to evaluate the performance of the proposed algorithm for automatic lesion volume delineation; namely the fuzzy hidden Markov chains (FHMC), with that of current state of the art in clinical practice threshold based techniques. As the classical hidden Markov chain (HMC) algorithm, FHMC takes into account noise, voxel intensity and spatial correlation, in order to classify a voxel as background or functional VOI. However the novelty of the fuzzy model consists of the inclusion of an estimation of imprecision, which should subsequently lead to a better modelling of the 'fuzzy' nature of the object of interest boundaries in emission tomography data. The performance of the algorithms has been assessed on both simulated and acquired datasets of the IEC phantom, covering a large range of spherical lesion sizes (from 10 to 37 mm), contrast ratios (4:1 and 8:1) and image noise levels. Both lesion activity recovery and VOI determination tasks were assessed in reconstructed images using two different voxel sizes (8 mm3 and 64 mm3). In order to account for both the functional volume location and its size, the concept of % classification errors was introduced in the evaluation of volume segmentation using the simulated datasets. Results reveal that FHMC performs substantially better than the threshold based methodology for functional volume determination or activity concentration recovery considering a contrast ratio of 4:1 and lesion sizes of <28 mm. Furthermore differences between classification and volume estimation errors evaluated were smaller for the segmented volumes provided by the FHMC algorithm. Finally, the performance of the automatic algorithms was less susceptible to image noise levels in comparison to the threshold based techniques. The analysis of both simulated and acquired datasets led to similar results and conclusions as far as the performance of segmentation algorithms under evaluation is concerned.