Navigating the nuances: comparative analysis and hyperparameter optimisation of neural architectures on contrast-enhanced MRI for liver and liver tumour segmentation.

In medical imaging, accurate segmentation is crucial to improving diagnosis, treatment, or both. However, navigating the multitude of available architectures for automatic segmentation can be overwhelming, making it challenging to determine the appropriate type of architecture and tune the most crucial parameters during dataset optimisation. To address this problem, we examined and refined seven distinct architectures for segmenting the liver, as well as liver tumours, with a restricted training collection of 60 3D contrast-enhanced magnetic resonance images (CE-MRI) from the ATLAS dataset. Included in these architectures are convolutional neural networks (CNNs), transformers, and hybrid CNN/transformer architectures. Bayesian search techniques were used for hyperparameter tuning to hasten convergence to the optimal parameter mixes while also minimising the number of trained models. It was unexpected that hybrid models, which typically exhibit superior performance on larger datasets, would exhibit comparable performance to CNNs. The optimisation of parameters contributed to better segmentations, resulting in an average increase of 1.7% and 5.0% in liver and tumour segmentation Dice coefficients, respectively. In conclusion, the findings of this study indicate that hybrid CNN/transformer architectures may serve as a practical substitute for CNNs even in small datasets. This underscores the significance of hyperparameter optimisation.

Validation of a discovery MI 4-ring model according to the NEMA NU 2-2018 standards: from Monte Carlo simulations to clinical-like reconstructions.

BACKGROUND: We propose a comprehensive evaluation of a Discovery MI 4-ring (DMI) model, using a Monte Carlo simulator (GATE) and a clinical reconstruction software package (PET toolbox). The following performance characteristics were compared with actual measurements according to NEMA NU 2-2018 guidelines: system sensitivity, count losses and scatter fraction (SF), coincidence time resolution (CTR), spatial resolution (SR), and image quality (IQ). For SR and IQ tests, reconstruction of time-of-flight (TOF) simulated data was performed using the manufacturer's reconstruction software. RESULTS: Simulated prompt, random, true, scatter and noise equivalent count rates closely matched the experimental rates with maximum relative differences of 1.6%, 5.3%, 7.8%, 6.6%, and 16.5%, respectively, in a clinical range of less than 10 kBq/mL. A 3.6% maximum relative difference was found between experimental and simulated sensitivities. The simulated spatial resolution was better than the experimental one. Simulated image quality metrics were relatively close to the experimental results. CONCLUSIONS: The current model is able to reproduce the behaviour of the DMI count rates in the clinical range and generate clinical-like images with a reasonable match in terms of contrast and noise.

Pre-treatment dosimetry in90Y-SIRT: Is it possible to optimise SPECT reconstruction parameters and calculation methods for accurate dosimetry?

PURPOSE: The aim of this study was (a) to optimise the99mTc-SPECT reconstruction parameters for the pre-treatment dosimetry of90Y-selective internal radiation therapy (SIRT) and (b) to compare the accuracy of clinical dosimetry methods with full Monte-Carlo dosimetry (fMCD) performed with Gate. METHODS: To optimise the reconstruction parameters, two hundred reconstructions with different parameters were performed on a NEMA phantom, varying the number of iterations, subsets, and post-filtering. The accuracy of the dosimetric methods was then investigated using an anthropomorphic phantom. Absorbed dose maps were generated using (1) the Partition Model (PM), (2) the Dose Voxel Kernel (DVK) convolution, and (3) the Local Deposition Method (LDM) with known activity restricted to the whole phantom (WP) or to the liver and lungs (LL). The dose to the lungs was calculated using the "multiple DVK" and "multiple LDM" methods. RESULTS: Optimal OSEM reconstruction parameters were found to depend on object size and dosimetric criterion chosen (Dmean or DVH-derived metric). The Dmean of all three dosimetric methods was close (≤ 10%) to the Dmean of fMCD simulations when considering large segmented volumes (whole liver, normal liver). In contrast, the Dmean to the small volume (∅=31) was systemically underestimated (12%-25%). For lungs, the "multiple DVK" and "multiple LDM" methods yielded a Dmean within 20% for the WP method and within 10% for the LL method. CONCLUSIONS: All three methods showed a substantial degradation of the dose-volume histograms (DVHs) compared to fMCD simulations. The DVK and LDM methods performed almost equally well, with the "multiple DVK" method being more accurate in the lungs.

Biomechanical properties of 3D printable material usable for synthetic personalized healthy human aorta.

With the development of three-dimensional (3D) printing, 3D-printed products have been widely used in medical fields, such as plastic surgery, orthopedics, dentistry, etc. In cardiovascular research, 3D-printed models are becoming more realistic in shape. However, from a biomechanical point of view, only a few studies have explored printable materials that can represent the properties of the human aorta. This study focuses on 3D-printed materials that might simulate the stiffness of human aortic tissue. First, the biomechanical properties of a healthy human aorta were defined and used as reference. The main objective of this study was to identify 3D printable materials that possess similar properties to the human aorta. Three synthetic materials, NinjaFlex (Fenner Inc., Manheim, USA), FilasticTM (Filastic Inc., Jardim Paulistano, Brazil), and RGD450+TangoPlus (Stratasys Ltd.©, Rehovot, Israel), were printed in different thicknesses. Uniaxial and biaxial tensile tests were performed to compute several biomechanical properties, such as thickness, stress, strain, and stiffness. We found that with the mixed material RGD450+TangoPlus, it was possible to achieve a similar stiffness to healthy human aorta. Moreover, the 50-shore-hardness RGD450+TangoPlus had similar thickness and stiffness to the human aorta.

Segmentation of 4D Flow MRI: Comparison between 3D Deep Learning and Velocity-Based Level Sets.

A thoracic aortic aneurysm is an abnormal dilatation of the aorta that can progress and lead to rupture. The decision to conduct surgery is made by considering the maximum diameter, but it is now well known that this metric alone is not completely reliable. The advent of 4D flow magnetic resonance imaging has allowed for the calculation of new biomarkers for the study of aortic diseases, such as wall shear stress. However, the calculation of these biomarkers requires the precise segmentation of the aorta during all phases of the cardiac cycle. The objective of this work was to compare two different methods for automatically segmenting the thoracic aorta in the systolic phase using 4D flow MRI. The first method is based on a level set framework and uses the velocity field in addition to 3D phase contrast magnetic resonance imaging. The second method is a U-Net-like approach that is only applied to magnitude images from 4D flow MRI. The used dataset was composed of 36 exams from different patients, with ground truth data for the systolic phase of the cardiac cycle. The comparison was performed based on selected metrics, such as the Dice similarity coefficient (DSC) and Hausdorf distance (HD), for the whole aorta and also three aortic regions. Wall shear stress was also assessed and the maximum wall shear stress values were used for comparison. The U-Net-based approach provided statistically better results for the 3D segmentation of the aorta, with a DSC of 0.92 ± 0.02 vs. 0.86 ± 0.5 and an HD of 21.49 ± 24.8 mm vs. 35.79 ± 31.33 mm for the whole aorta. The absolute difference between the wall shear stress and ground truth slightly favored the level set method, but not significantly (0.754 ± 1.07 Pa vs. 0.737 ± 0.79 Pa). The results showed that the deep learning-based method should be considered for the segmentation of all time steps in order to evaluate biomarkers based on 4D flow MRI.

Segmentation of the aorta in systolic phase from 4D flow MRI: multi-atlas vs. deep learning.

OBJECTIVE: In the management of the aortic aneurysm, 4D flow magnetic resonance Imaging provides valuable information for the computation of new biomarkers using computational fluid dynamics (CFD). However, accurate segmentation of the aorta is required. Thus, our objective is to evaluate the performance of two automatic segmentation methods on the calculation of aortic wall pressure. METHODS: Automatic segmentation of the aorta was performed with methods based on deep learning and multi-atlas using the systolic phase in the 4D flow MRI magnitude image of 36 patients. Using mesh morphing, isotopological meshes were generated, and CFD was performed to calculate the aortic wall pressure. Node-to-node comparisons of the pressure results were made to identify the most robust automatic method respect to the pressures obtained with a manually segmented model. RESULTS: Deep learning approach presented the best segmentation performance with a mean Dice similarity coefficient and a mean Hausdorff distance (HD) equal to 0.92+/- 0.02 and 21.02+/- 24.20 mm, respectively. At the global level HD is affected by the performance in the abdominal aorta. Locally, this distance decreases to 9.41+/- 3.45 and 5.82+/- 6.23 for the ascending and descending thoracic aorta, respectively. Moreover, with respect to the pressures from the manual segmentations, the differences in the pressures computed from deep learning were lower than those computed from multi-atlas method. CONCLUSION: To reduce biases in the calculation of aortic wall pressure, accurate segmentation is needed, particularly in regions with high blood flow velocities. Thus, the deep learning segmen-tation method should be preferred.

Comparison of In-Vivo and Ex-Vivo Ascending Aorta Elastic Properties through Automatic Deep Learning Segmentation of Cine-MRI and Biomechanical Testing.

Ascending aortic aneurysm is a pathology that is important to be supervised and treated. During the years the aorta dilates, it becomes stiff, and its elastic properties decrease. In some cases, the aortic wall can rupture leading to aortic dissection with a high mortality rate. The main reference standard to measure when the patient needs to undertake surgery is the aortic diameter. However, the aortic diameter was shown not to be sufficient to predict aortic dissection, implying other characteristics should be considered. Therefore, the main objective of this work is to assess in-vivo the elastic properties of four different quadrants of the ascending aorta and compare the results with equivalent properties obtained ex-vivo. The database consists of 73 cine-MRI sequences of thoracic aorta acquired in axial orientation at the level of the pulmonary trunk. All the patients have dilated aorta and surgery is required. The exams were acquired just prior to surgery, each consisting of 30 slices on average across the cardiac cycle. Multiple deep learning architectures have been explored with different hyperparameters and settings to automatically segment the contour of the aorta on each image and then automatically calculate the aortic compliance. A semantic segmentation U-Net network outperforms the rest explored networks with a Dice score of 98.09% (±0.96%) and a Hausdorff distance of 4.88 mm (±1.70 mm). Local aortic compliance and local aortic wall strain were calculated from the segmented surfaces for each quadrant and then compared with elastic properties obtained ex-vivo. Good agreement was observed between Young's modulus and in-vivo strain. Our results suggest that the lateral and posterior quadrants are the stiffest. In contrast, the medial and anterior quadrants have the lowest aortic stiffness. The in-vivo stiffness tendency agrees with the values obtained ex-vivo. We can conclude that our automatic segmentation method is robust and compatible with clinical practice (thanks to a graphical user interface), while the in-vivo elastic properties are reliable and compatible with the ex-vivo ones.

4D segmentation of the thoracic aorta from 4D flow MRI using deep learning.

BACKGROUND: 4D flow MRI allows the analysis of hemodynamic changes in the aorta caused by pathologies such as thoracic aortic aneurysms (TAA). For personalized management of TAA, new biomarkers are required to analyze the effect of fluid structure iteration which can be obtained from 4D flow MRI. However, the generation of these biomarkers requires prior 4D segmentation of the aorta. OBJECTIVE: To develop an automatic deep learning model to segment the aorta in 4D from 4D flow MRI. METHODS: Segmentation is addressed with a U-Net based segmentation model that treats each 4D flow MRI frame as an independent sample. Performance is measured with respect to Dice score (DS) and Hausdorff distance (HD). In addition, the maximum and minimum surface areas at the level of the ascending aorta are measured and compared with those obtained from cine-MRI. RESULTS: The segmentation performance was 0.90 ± 0.02 for the DS and the mean HD was 9.58 ± 4.36 mm. A correlation coefficient of r = 0.85 was obtained for the maximum surface and r = 0.86 for the minimum surface between the 4D flow MRI and cine-MRI. CONCLUSION: The proposed automatic approach of 4D aortic segmentation from 4D flow MRI seems to be accurate enough to contribute to the wider use of this imaging technique in the analysis of pathologies such as TAA.

A Practical Quality Assurance Procedure for Data Acquisitions in Preclinical Simultaneous PET/MR Systems.

The availability of preclinical simultaneous PET/MR imaging systems has been increasing in recent years. Therefore, this technique is progressively moving from the hands of pure physicists towards those of scientists more involved in pharmacology and biology. Unfortunately, these combined scanners can be prone to artefacts and deviation of their characteristics under the influence of external factors or mutual interference between subsystems. This may compromise the image quality as well as the quantitative aspects of PET and MR data. Hence, quality assurance is crucial to avoid loss of animals and experiments. A possible risk to the acceptance of quality control by preclinical teams is that the complexity and duration of this quality control are increased by the addition of MR and PET tests. To avoid this issue, we have selected over the past 5 years, simple tests that can be easily and quickly performed each day before starting an animal PET/MR acquisition. These tests can be performed by the person in charge of the experiment even if this person has a limited expertise in instrumentation and performance evaluation. In addition to these daily tests, other tests are suggested for an advanced system follow-up at a lower frequency. In the present paper, the proposed tests are sorted by periodicity from daily to annual. Besides, we have selected test materials that are available at moderate cost either commercially or through 3D printing.

Critical analysis of the effect of various methodologies to compute breast cancer tumour blood flow-based texture features using first-pass 18F-FDG PET.

PURPOSE: Assessment of tumour blood flow (BF) heterogeneity using first-pass FDG PET/CT and textural feature (TF) analysis is an innovative concept. We aim to explore the relationship between BF heterogeneity measured with different TFs calculation methods and the response to neoadjuvant chemotherapy (NAC) in patients with newly diagnosed breast cancer (BC). METHODS: One hundred and twenty-five patients were enrolled. Dynamic first-pass and delayed FDG PET/CT scans were performed before NAC. Nine TFs were calculated from perfusion and metabolic PET images using relative (RR) or absolute (AR) rescaling strategies with two textural matrix calculation methods. Patients were classified according to presence or absence of a pathologic complete response (pCR) after NAC. The relationship between BF texture features and conventional features were analysed using spearman correlations. The TFs' differences between pCR and non-pCR groups were evaluated using Mann-Whitney tests and descriptive factorial discriminant analysis (FDA). RESULTS: Relation between tumour BF-based TFs and global BF parameters were globally similar to those observed for tumour metabolism. None of the TFs was significantly different between pCR and non-pCR groups in the Mann-Whitney analysis, after Benjamini-Hochberg correction. Using a RR led to better discriminations between responders and non-responders in the FDA analysis. The best results were obtained by combining all the PET features, including BF ones. CONCLUSION: A better differentiation of patients reaching a pCR was observed using a RR. Moreover, BF heterogeneity might bring a useful information when combined with metabolic PET parameters to predict the pCR after neoadjuvant chemotherapy.

What Are the Biomechanical Properties of an Aortic Aneurysm Associated with Quadricuspid Aortic Valve?

Association of quadricuspid aortic valve (QAV) with ascending aortic aneurysms (AsAA) is rare. A 63-year-old female with hypertension was found (on MRI) to have an ascending aortic aneurysm (52 mm in maximum diameter) and dilatation at the level of the sinotubular junction (38 mm in diameter) associated with quadricuspid aortic valve. An ascending aortic wall replacement surgery was performed. In this study, we focus on the behavior of the aorta associated with QAV considering the in vitro biomechanical characteristics and histology. The properties of QAV are closer to bicuspid aortic valve than tricuspid aortic valve, but with higher wall thickness.

Aortic local biomechanical properties in ascending aortic aneurysms.

Ascending aortic aneurysm (AsAA) is a high-risk cardiovascular disease with an increased incidence over years. In this study, we compared different risk factors based on the pre-failure behavior (from a biomechanical point of view) obtained ex-vivo from an equi-biaxial tensile test. A total of 100 patients (63 ± 12 years, 72 males) with AsAA replacement, were recruited. Equi-biaxial tensile tests of AsAA walls were performed on freshly sampled aortic wall tissue after ascending aortic replacement. The aneurysmal aortic walls were divided into four quadrants (medial, anterior, lateral, and posterior) and two directions (longitudinal and circumferential) were considered. The stiffness was represented by the maximum Young modulus (MYM). Based on patient information, the following subgroups were considered: age, gender, hypertension, obesity, dyslipidemia, diabetes, smoking history, aortic insufficiency, aortic stenosis, coronary artery disease, aortic diameter and aortic valve type. In general, when the aortic diameter increased, the aortic wall became thicker. In terms of the MYM, the longitudinal direction was significantly higher than that in the circumferential direction. In the multivariant analysis, the impact factors of age (p = 0.07), smoking (p = 0.05), diabetes (p = 0.03), aortic stenosis (p = 0.02), coronary artery disease (p < 10-3), and aortic diameters (p = 0.02) were significantly influencing the MYM. There was no significant MYM difference when the patients presented arterial hypertension, dyslipidemia, obesity, or bicuspid aortic valve. To conclude, the pre-failure aortic stiffness is multi-factorial, according to our population of 100 patients with AsAA. STATEMENT OF SIGNIFICANCE: Our research on the topic of "Aortic local biomechanical properties in case of ascending aortic aneurysms" is about the biomechanical properties on one hundred aortic samples according to the aortic wall quadrants and the direction. More than ten factors and risks which may impact ascending aortic aneurysms have been studied. According to our knowledge, so far, this article involved the largest population on this topic. It will be our pleasure to share this information with all the readers.

Impact of contouring methods on pre-treatment and post-treatment dosimetry for the prediction of tumor control and survival in HCC patients treated with selective internal radiation therapy.

INTRODUCTION: The aim of this study was to evaluate the impact of the contouring methods on dose metrics and their predictive value on tumor control and survival, in both situations of pre-treatment and post-treatment dosimetry, for patients with advanced HCC treated with SIRT. METHODS: Forty-eight patients who underwent SIRT between 2012 and 2020 were retrospectively included in this study. Target volumes were delineated using two methods: MRI-based contours manually drawn by a radiologist and then registered on SPECT/CT and PET/CT via deformable registration (Pre-CMRI and Post-CMRI), 99mTc-MAA-SPECT and 90Y-microspheres-PET 10% threshold contouring (Pre-CSPECT and Post-CPET). The mean absorbed dose (Dm) and the minimal absorbed dose delivered to 70% of the tumor volume (D70) were evaluated with both contouring methods; the tumor-to-normal liver uptake ratio (TNR) was evaluated with MRI-based contours only. Tumor response was assessed using the mRECIST criteria on the follow-up MRIs. RESULTS: No significant differences were found for Dm and TNR between pre- and post-treatment. TNR evaluated with radiologic contours (Pre-CMRI and Post-CMRI) were predictive of tumor control at 6 months on pre- and post-treatment dosimetry (OR 5.9 and 7.1, respectively; p = 0.02 and 0.01). All dose metrics determined with both methods were predictive of overall survival (OS) on pre-treatment dosimetry, but only Dm with MRI-based contours was predictive of OS on post-treatment images with a median of 23 months for patients with a supramedian Dm versus 14 months for the others (p = 0.04). CONCLUSION: In advanced HCC treated with SIRT, Dm and TNR determined with radiologic contours were predictive of tumor control and OS. This study shows that a rigorous clinical workflow (radiologic contours + registration on scintigraphic images) is feasible and should be prospectively considered for improving therapeutic strategy.

Biological correlates of tumor perfusion and its heterogeneity in newly diagnosed breast cancer using dynamic first-pass 18F-FDG PET/CT.

PURPOSE: The aim of this prospective study is to analyze the global tumor blood flow (BF) and its heterogeneity in newly diagnosed breast cancer (BC) according to tumor biological characteristics and molecular subtypes. These perfusion parameters were compared to those classically derived from metabolic studies to investigate links between perfusion and metabolism. METHODS: Two hundred seventeen newly diagnosed BC patients underwent a 18F-FDG PET/CT exam before any treatment. A 2-min dynamic acquisition, centered on the chest, was performed immediately after intravenous injection of 3 MBq/kg of 18F-FDG, followed by a two-step static acquisition 90 min later. Tumor BF was calculated (in ml/min/g) using a single compartment kinetic model. In addition to standard PET parameters, texture features (TF) describing the heterogeneity of tumor perfusion and metabolism were extracted. Patients were divided into three groups: Luminal (HR+/HER2-), HER2 (HER2+), and TN (HR-/HER2-). Global and TF parameters of BF and metabolism were compared in different groups of patients according to tumor biological characteristics. RESULTS: Tumors with lymph node involvement showed a higher perfusion, whereas no significant differences in SUV_max or SUV_mean were reported. TN tumors had a higher metabolic activity than HER2 and luminal tumors but no significant differences in global BF values were noted. HER2 tumors exhibited a larger tumor heterogeneity of both perfusion and metabolism compared to luminal and TN tumors. Heterogeneity of perfusion appeared well correlated to that of metabolism. CONCLUSIONS: The study of breast cancer perfusion shows a higher BF in large tumors and in tumors with lymph node involvement, not paralleled by similar modifications in tumor global metabolism. In addition, the observed correlation between the perfusion heterogeneity and the metabolism heterogeneity suggests that tumor perfusion and consequently the process of tumor angiogenesis might be involved in the metabolism heterogeneity previously shown in BC.

GAS: A genetic atlas selection strategy in multi-atlas segmentation framework.

Multi-Atlas based Segmentation (MAS) algorithms have been successfully applied to many medical image segmentation tasks, but their success relies on a large number of atlases and good image registration performance. Choosing well-registered atlases for label fusion is vital for an accurate segmentation. This choice becomes even more crucial when the segmentation involves organs characterized by a high anatomical and pathological variability. In this paper, we propose a new genetic atlas selection strategy (GAS) that automatically chooses the best subset of atlases to be used for segmenting the target image, on the basis of both image similarity and segmentation overlap. More precisely, the key idea of GAS is that if two images are similar, the performances of an atlas for segmenting each image are similar. Since the ground truth of each atlas is known, GAS first selects a predefined number of similar images to the target, then, for each one of them, finds a near-optimal subset of atlases by means of a genetic algorithm. All these near-optimal subsets are then combined and used to segment the target image. GAS was tested on single-label and multi-label segmentation problems. In the first case, we considered the segmentation of both the whole prostate and of the left ventricle of the heart from magnetic resonance images. Regarding multi-label problems, the zonal segmentation of the prostate into peripheral and transition zone was considered. The results showed that the performance of MAS algorithms statistically improved when GAS is used.

Iterative framework for the joint segmentation and CT synthesis of MR images: application to MRI-only radiotherapy treatment planning.

To tackle the problem of magnetic resonance imaging (MRI)-only radiotherapy treatment planning (RTP), we propose a multi-atlas information propagation scheme that jointly segments organs and generates pseudo x-ray computed tomography (CT) data from structural MR images (T1-weighted and T2-weighted). As the performance of the method strongly depends on the quality of the atlas database composed of multiple sets of aligned MR, CT and segmented images, we also propose a robust way of registering atlas MR and CT images, which combines structure-guided registration, and CT and MR image synthesis. We first evaluated the proposed framework in terms of segmentation and CT synthesis accuracy on 15 subjects with prostate cancer. The segmentations obtained with the proposed method were compared using the Dice score coefficient (DSC) to the manual segmentations. Mean DSCs of 0.73, 0.90, 0.77 and 0.90 were obtained for the prostate, bladder, rectum and femur heads, respectively. The mean absolute error (MAE) and the mean error (ME) were computed between the reference CTs (non-rigidly aligned to the MRs) and the pseudo CTs generated with the proposed method. The MAE was on average [Formula: see text] HU and the ME [Formula: see text] HU. We then performed a dosimetric evaluation by re-calculating plans on the pseudo CTs and comparing them to the plans optimised on the reference CTs. We compared the cumulative dose volume histograms (DVH) obtained for the pseudo CTs to the DVH obtained for the reference CTs in the planning target volume (PTV) located in the prostate, and in the organs at risk at different DVH points. We obtained average differences of [Formula: see text] in the PTV for [Formula: see text], and between [Formula: see text] and 0.05% in the PTV, bladder, rectum and femur heads for D mean and [Formula: see text]. Overall, we demonstrate that the proposed framework is able to automatically generate accurate pseudo CT images and segmentations in the pelvic region, potentially bypassing the need for CT scan for accurate RTP.

Evaluation of a new transperineal ultrasound probe for inter-fraction image-guidance for definitive and post-operative prostate cancer radiotherapy.

PURPOSE: The aim of this study was to evaluate a new system based on transperineal ultrasound (TP-US) acquisitions for prostate and post-prostatectomy pre-treatment positioning by comparing this device to cone-beam computed tomography (CBCT). METHODS: The differences between CBCT/CT and TP-US/TP-US registrations were analyzed on 427 and 453 sessions for 13 prostate and 14 post-prostatectomy patients, respectively. The inter-operator variability (IOV) of the registration process, and the impact and variability of the probe pressure were also evaluated. RESULTS: CBCT and TP-US shift agreements at ± 5 mm were 76.6%, 95.1%, 96.3% and 90.3%, 85.0%, 97.6% in anterior-posterior, superior-inferior and left-right directions, for prostate and post-prostatectomy patients, respectively. IOV values were similar between the 2 modalities. Displacements above 5 mm due to strong pressures were observed on both localizations, but such pressures were rarely reproduced during treatment courses. CONCLUSIONS: High concordance between CBCT/CT and TP-US/TP-US localization of prostates or prostatic beds was found in this study. TP-US based prepositioning is a feasible method to ensure accurate treatment delivery, and represents an attractive alternative to invasive and/or irradiating imaging modalities.

Ultrasound versus Cone-beam CT image-guided radiotherapy for prostate and post-prostatectomy pretreatment localization.

PURPOSE: To evaluate the accuracy of an intra-modality trans-abdominal ultrasound (TA-US) device against soft-tissue based Cone-Beam Computed tomography (CBCT) registration for prostate and post-prostatectomy pre-treatment positioning. METHODS: The differences between CBCT and US shifts were calculated on 25 prostate cancer patients (cohort A) and 11 post-prostatectomy patients (cohort B), resulting in 284 and 106 paired shifts for cohorts A and B, respectively. As a second step, a corrective method was applied to the US registration results to decrease the systematic shifts observed between TA-US and CBCT results. This method consisted of subtracting the mean difference obtained between US and CBCT registration results during the first 3 sessions from the US registration results of the subsequent sessions. Inter-operator registration variability (IOV) was also investigated for both modalities. RESULTS: After initial review, about 20% of the US images were excluded because of insufficient quality. The average differences between US and CBCT were: 2.8 ± 4.1 mm, -0.9 ± 4.2 mm, 0.4 ± 3.4 mm for cohort A and 1.3 ± 5.0 mm, -2.3 ± 4.6 mm, 0.5 ± 2.9 mm for cohort B, in the anterior-posterior (AP), superior-inferior (SI) and lateral (LR) directions, respectively. After applying the corrective method, only the differences in the AP direction remained significant (p < 0.05). The IOV values were between 0.6-2.0 mm and 2.1-3.5 mm for the CBCT and TA-US modalities, respectively. CONCLUSIONS: Based on the obtained results and on the image quality, the TA-US imaging modality is not safely interchangeable with CBCT for pre-treatment repositioning. Treatment margins adaptation based on the correction of the systematic shifts should be considered.

Development of 2D+T tracking algorithm in ultrasound images for radiotherapy.

The aim of this study is to develop and validate a deformable tracking algorithm for monitoring the motion of the target volume on 2D ultrasound (US) images during a radiotherapy fraction. The proposed method is applied on images acquired with a transperineal ultrasound (TP-US) probe on 31 treatment patient's sessions, treated with a prostate or after a surgery, called a prostatectomy. The developed algorithm is based on Speeded-Up Robust Features (SURF) to find and match the corresponding salient points in the reference and moving images, and Thin Plate Spline (TPS) to warp the image. The results are promising and show that the proposed algorithm performs well with either artificial transforms, or in comparison with a rigid intensity based algorithm used in clinic.

Semiautomatic registration of 3D transabdominal ultrasound images for patient repositioning during postprostatectomy radiotherapy.

PURPOSE: The aim of the present work is to propose and evaluate registration algorithms of three-dimensional (3D) transabdominal (TA) ultrasound (US) images to setup postprostatectomy patients during radiation therapy. METHODS: Three registration methods have been developed and evaluated to register a reference 3D-TA-US image acquired during the planning CT session and a 3D-TA-US image acquired before each treatment session. The first method (method A) uses only gray value information, whereas the second one (method B) uses only gradient information. The third one (method C) combines both sets of information. All methods restrict the comparison to a region of interest computed from the dilated reference positioning volume drawn on the reference image and use mutual information as a similarity measure. The considered geometric transformations are translations and have been optimized by using the adaptive stochastic gradient descent algorithm. Validation has been carried out using manual registration by three operators of the same set of image pairs as the algorithms. Sixty-two treatment US images of seven patients irradiated after a prostatectomy have been registered to their corresponding reference US image. The reference registration has been defined as the average of the manual registration values. Registration error has been calculated by subtracting the reference registration from the algorithm result. For each session, the method has been considered a failure if the registration error was above both the interoperator variability of the session and a global threshold of 3.0 mm. RESULTS: All proposed registration algorithms have no systematic bias. Method B leads to the best results with mean errors of -0.6, 0.7, and -0.2 mm in left-right (LR), superior-inferior (SI), and anterior-posterior (AP) directions, respectively. With this method, the standard deviations of the mean error are of 1.7, 2.4, and 2.6 mm in LR, SI, and AP directions, respectively. The latter are inferior to the interoperator registration variabilities which are of 2.5, 2.5, and 3.5 mm in LR, SI, and AP directions, respectively. Failures occur in 5%, 18%, and 10% of cases in LR, SI, and AP directions, respectively. 69% of the sessions have no failure. CONCLUSIONS: Results of the best proposed registration algorithm of 3D-TA-US images for postprostatectomy treatment have no bias and are in the same variability range as manual registration. As the algorithm requires a short computation time, it could be used in clinical practice provided that a visual review is performed.