Synthesis of 68Ga-radiopharmaceuticals using both generator-derived and cyclotron-produced 68Ga as exemplified by [68Ga]Ga-PSMA-11 for prostate cancer PET imaging.

[68Ga]Ga-PSMA-11, a urea-based peptidomimetic, is a diagnostic radiopharmaceutical for positron emission tomography (PET) imaging that targets the prostate-specific membrane antigen (PSMA). The recent Food and Drug Administration approval of [68Ga]Ga-PSMA-11 for PET imaging of patients with prostate cancer, expected follow-up approval of companion radiotherapeutics (e.g., [177Lu]Lu-PSMA-617, [225Ac]Ac-PSMA-617) and large prostate cancer patient volumes requiring access are poised to create an unprecedented demand for [68Ga]Ga-PSMA-11 in nuclear medicine clinics around the world. Meeting this global demand is going to require a variety of synthesis methods compatible with 68Ga eluted from a generator or produced on a cyclotron. To address this urgent need in the PET radiochemistry community, herein we report detailed protocols for the synthesis of [68Ga]Ga-PSMA-11, (also known as HBED-CC, Glu-urea-Lys(Ahx)-HBED-CC and PSMA-HBED-CC) using both generator-eluted and cyclotron-produced 68Ga and contrast the pros and cons of each method. The radiosyntheses are automated and have been validated for human use at two sites (University of Michigan (UM), United States; Royal Prince Alfred Hospital (RPA), Australia) and used to produce [68Ga]Ga-PSMA-11 for patient use in good activity yields (single generator, 0.52 GBq (14 mCi); dual generators, 1.04-1.57 GBq (28-42 mCi); cyclotron method (single target), 1.47-1.89 GBq (40-51 mCi); cyclotron method (dual target), 3.63 GBq (98 mCi)) and high radiochemical purity (99%) (UM, n = 645; RPA, n > 600). Both methods are appropriate for clinical production but, in the long term, the method employing cyclotron-produced 68Ga is the most promising for meeting high patient volumes. Quality control testing (visual inspection, pH, radiochemical purity and identity, radionuclidic purity and identity, sterile filter integrity, bacterial endotoxin content, sterility, stability) confirmed doses are suitable for clinical use, and there is no difference in clinical prostate cancer PET imaging using [68Ga]Ga-PSMA-11 prepared using the two production methods.

Cyclotron-based production of 68Ga, [68Ga]GaCl3, and [68Ga]Ga-PSMA-11 from a liquid target.

PURPOSE: To optimize the direct production of 68Ga on a cyclotron, via the 68Zn(p,n)68Ga reaction using a liquid cyclotron target. We Investigated the yield of cyclotron-produced 68Ga, extraction of [68Ga]GaCl3 and subsequent [68Ga]Ga-PSMA-11 labeling using an automated synthesis module. METHODS: Irradiations of a 1.0 M solution of [68Zn]Zn(NO3)2 in dilute (0.2-0.3 M) HNO3 were conducted using GE PETtrace cyclotrons and GE 68Ga liquid targets. The proton beam energy was degraded to a nominal 14.3 MeV to minimize the co-production of 67Ga through the 68Zn(p,2n)67Ga reaction without unduly compromising 68Ga yields. We also evaluated the effects of varying beam times (50-75 min) and beam currents (27-40 µA). Crude 68Ga production was measured. The extraction of [68Ga]GaCl3 was performed using a 2 column solid phase method on the GE FASTlab Developer platform. Extracted [68Ga]GaCl3 was used to label [68Ga]Ga-PSMA-11 that was intended for clinical use. RESULTS: The decay corrected yield of 68Ga at EOB was typically > 3.7 GBq (100 mCi) for a 60 min beam, with irradiations of [68Zn]Zn(NO3)2 at 0.3 M HNO3. Target/chemistry performance was more consistent when compared with 0.2 M HNO3. Radionuclidic purity of 68Ga was typically > 99.8% at EOB and met the requirements specified in the European Pharmacopoeia (< 2% combined 66/67Ga) for a practical clinical product shelf-life. The activity yield of [68Ga]GaCl3 was typically > 50% (~ 1.85 GBq, 50 mCi); yields improved as processes were optimized. Labeling yields for [68Ga]Ga-PSMA-11 were near quantitative (~ 1.67 GBq, 45 mCi) at EOS. Cyclotron produced [68Ga]Ga-PSMA-11 underwent full quality control, stability and sterility testing, and was implemented for human use at the University of Michigan as an Investigational New Drug through the US FDA and also at the Royal Prince Alfred Hospital (RPA). CONCLUSION: Direct cyclotron irradiation of a liquid target provides clinically relevant quantities of [68Ga]Ga-PSMA-11 and is a viable alternative to traditional 68Ge/68Ga generators.

Side lying during nebulisation can significantly improve apical deposition in healthy adults and adults with mild cystic fibrosis lung disease: a randomised crossover trial.

BACKGROUND: In people with and without Cystic Fibrosis (CF), does side lying during nebulisation change: the proportion of the dose loaded in the nebuliser that is deposited in the lungs; the uniformity of deposition throughout the lungs; or the apical drug density as a percentage of the drug density in the remaining lung? Do these effects differ depending on the degree of lung disease present? METHODS: A randomised crossover trial with concealed allocation, intention-to-treat analysis and blinded assessors, involving 39 adults: 13 healthy, 13 with mild CF lung disease (FEV1 > 80%pred), and 13 with more advanced CF lung disease (FEV1 < 80%pred). In random order, 4 mL of nebulised radioaerosol was inhaled in upright sitting and in alternate right and left side lying at 2-min intervals, for 20 min. RESULTS: Compared to sitting upright, lung deposition and the uniformity of deposition were not significantly altered by side lying in any of the three groups. In sitting, the density of the deposition was significantly less in the apical regions than in the rest of the lung in all participants. Side lying significantly improved apical deposition in healthy adults (MD, 13%; 95% CI, 7 to 19), and in minimal CF lung disease (MD, 4%; 95% CI, 1 to 7) but not in advanced disease (MD, 4%; 95% CI, - 2 to 9). CONCLUSION: Alternating between right and left side lying during nebulisation significantly improves apical deposition in healthy adults and in adults with mild CF lung disease, without substantial detriment to overall deposition. TRIAL REGISTRATION: ACTRN12611000674932 (Healthy), ACTRN12611000672954 (CF) Retrospectively registered 4/7/2011.

Effects of exercise and airway clearance (positive expiratory pressure) on mucus clearance in cystic fibrosis: a randomised crossover trial.

Exercise improves mucus clearance in people without lung disease and those with chronic bronchitis. No study has investigated exercise alone for mucus clearance in cystic fibrosis (CF). The aim of this study was to compare the effects of treadmill exercise to resting breathing and airway clearance with positive expiratory pressure (PEP) therapy on mucus clearance in adults with CF.This 3-day randomised, controlled, crossover trial included 14 adults with mild to severe CF lung disease (forced expiratory volume in 1 s % predicted 31-113%). Interventions were 20 min of resting breathing (control), treadmill exercise at 60% of the participant's peak oxygen consumption or PEP therapy (including huffing and coughing). Mucus clearance was measured using the radioaerosol technique and gamma camera imaging.Treadmill exercise improved whole lung mucus clearance compared to resting breathing (mean difference 3%, 95% CI 2-4); however, exercise alone was less effective than PEP therapy (mean difference -7%, 95% CI -6- -8). When comparing treadmill exercise to PEP therapy, there were no significant differences in mucus clearance from the intermediate and peripheral lung regions, but significantly less clearance from the central lung region (likely reflecting the huffing and coughing that was only in PEP therapy).It is recommended that huffing and coughing are included to maximise mucus clearance with exercise.

A topo-graph model for indistinct target boundary definition from anatomical images.

BACKGROUND AND OBJECTIVE: It can be challenging to delineate the target object in anatomical imaging when the object boundaries are difficult to discern due to the low contrast or overlapping intensity distributions from adjacent tissues. METHODS: We propose a topo-graph model to address this issue. The first step is to extract a topographic representation that reflects multiple levels of topographic information in an input image. We then define two types of node connections - nesting branches (NBs) and geodesic edges (GEs). NBs connect nodes corresponding to initial topographic regions and GEs link the nodes at a detailed level. The weights for NBs are defined to measure the similarity of regional appearance, and weights for GEs are defined with geodesic and local constraints. NBs contribute to the separation of topographic regions and the GEs assist the delineation of uncertain boundaries. Final segmentation is achieved by calculating the relevance of the unlabeled nodes to the labels by the optimization of a graph-based energy function. We test our model on 47 low contrast CT studies of patients with non-small cell lung cancer (NSCLC), 10 contrast-enhanced CT liver cases and 50 breast and abdominal ultrasound images. The validation criteria are the Dice's similarity coefficient and the Hausdorff distance. RESULTS: Student's t-test show that our model outperformed the graph models with pixel-only, pixel and regional, neighboring and radial connections (p-values <0.05). CONCLUSIONS: Our findings show that the topographic representation and topo-graph model provides improved delineation and separation of objects from adjacent tissues compared to the tested models.

The effect of device resistance and inhalation flow rate on the lung deposition of orally inhaled mannitol dry powder.

The present study investigates the effect of DPI resistance and inhalation flow rates on the lung deposition of orally inhaled mannitol dry powder. Mannitol powder radiolabeled with 99mTc-DTPA was inhaled from an Osmohaler™ by healthy human volunteers at 50-70L/min peak inhalation flow rate (PIFR) using both a low and high resistance Osmohaler™, and 110-130L/min PIFR using the low resistance Osmohaler™ (n=9). At 50-70L/min PIFR, the resistance of the Osmohaler™ did not significantly affect the total and peripheral lung deposition of inhaled mannitol [for low resistance Osmohaler™, 20% total lung deposition (TLD), 0.3 penetration index (PI); for high resistance Osmohaler™, 17% TLD, 0.23 PI]. Increasing the PIFR 50-70L/min to 110-130L/min (low resistance Osmohaler™) significantly reduced the total lung deposition (10% TLD) and the peripheral lung deposition (PI 0.21). The total lung deposition showed dependency on the in vitro FPF (R2=1.0). On the other hand, the PI had a stronger association with the MMAD (R2=1.0) than the FPF (R2=0.7). In conclusion the resistance of Osmohaler™ did not significantly affect the total and regional lung deposition at 50-70L/min PIFR. Instead, the total and regional lung depositions are dependent on the particle size of the aerosol and inhalation flow rate, the latter itself affecting the particle size distribution.

A combinatorial Bayesian and Dirichlet model for prostate MR image segmentation using probabilistic image features.

Blurred boundaries and heterogeneous intensities make accurate prostate MR image segmentation problematic. To improve prostate MR image segmentation we suggest an approach that includes: (a) an image patch division method to partition the prostate into homogeneous segments for feature extraction; (b) an image feature formulation and classification method, using the relevance vector machine, to provide probabilistic prior knowledge for graph energy construction; (c) a graph energy formulation scheme with Bayesian priors and Dirichlet graph energy and (d) a non-iterative graph energy minimization scheme, based on matrix differentiation, to perform the probabilistic pixel membership optimization. The segmentation output was obtained by assigning pixels with foreground and background labels based on derived membership probabilities. We evaluated our approach on the PROMISE-12 dataset with 50 prostate MR image volumes. Our approach achieved a mean dice similarity coefficient (DSC) of 0.90 ± 0.02, which surpassed the five best prior-based methods in the PROMISE-12 segmentation challenge.

Primary lung tumor segmentation from PET-CT volumes with spatial-topological constraint.

PURPOSE: Accurate lung tumor segmentation is a prerequisite for effective radiation therapy and surgical planning. However, tumor delineation is challenging when the tumor boundaries are indistinct on PET or CT. To address this problem, we developed a segmentation method to improve the delineation of primary lung tumors from PET-CT images. METHODS: We formulated the segmentation problem as a label information propagation process in an iterative manner. Our model incorporates spatial-topological information from PET and local intensity changes from CT. The topological information of the regions was extracted based on the metabolic activity of different tissues. The spatial-topological information moderates the amount of label information that a pixel receives: The label information attenuates as the spatial distance increases and when crossing different topological regions. Thus, the spatial-topological constraint assists accurate tumor delineation and separation. The label information propagation and transition model are solved under a random walk framework. RESULTS: Our method achieved an average DSC of 0.848 ± 0.036 and HD (mm) of 8.652 ± 4.532 on 40 patients with lung cancer. The t test showed a significant improvement (p value < 0.05) in segmentation accuracy when compared to eight other methods. Our method was better able to delineate tumors that had heterogeneous FDG uptake and which abutted adjacent structures that had similar densities. CONCLUSIONS: Our method, using a spatial-topological constraint, provided better lung tumor delineation, in particular, when the tumor involved or abutted the chest wall and the mediastinum.

Topology polymorphism graph for lung tumor segmentation in PET-CT images.

Accurate lung tumor segmentation is problematic when the tumor boundary or edge, which reflects the advancing edge of the tumor, is difficult to discern on chest CT or PET. We propose a 'topo-poly' graph model to improve identification of the tumor extent. Our model incorporates an intensity graph and a topology graph. The intensity graph provides the joint PET-CT foreground similarity to differentiate the tumor from surrounding tissues. The topology graph is defined on the basis of contour tree to reflect the inclusion and exclusion relationship of regions. By taking into account different topology relations, the edges in our model exhibit topological polymorphism. These polymorphic edges in turn affect the energy cost when crossing different topology regions under a random walk framework, and hence contribute to appropriate tumor delineation. We validated our method on 40 patients with non-small cell lung cancer where the tumors were manually delineated by a clinical expert. The studies were separated into an 'isolated' group (n = 20) where the lung tumor was located in the lung parenchyma and away from associated structures / tissues in the thorax and a 'complex' group (n = 20) where the tumor abutted / involved a variety of adjacent structures and had heterogeneous FDG uptake. The methods were validated using Dice's similarity coefficient (DSC) to measure the spatial volume overlap and Hausdorff distance (HD) to compare shape similarity calculated as the maximum surface distance between the segmentation results and the manual delineations. Our method achieved an average DSC of 0.881 ± 0.046 and HD of 5.311 ± 3.022 mm for the isolated cases and DSC of 0.870 ± 0.038 and HD of 9.370 ± 3.169 mm for the complex cases. Student's t-test showed that our model outperformed the other methods (p-values <0.05).

The relationship between neuropsychological functioning and FDG-PET hypometabolism in intractable mesial temporal lobe epilepsy.

We examined the relationship between baseline neuropsychological functioning and 18-fluorodeoxyglucose positron emission tomography (FDG-PET) in intractable mesial temporal lobe epilepsy (MTLE). We hypothesized relationships between dominant temporal lobe hypometabolism and verbal memory and between nondominant temporal lobe hypometabolism and nonverbal memory in line with the lateralized material-specific model of memory deficits in MTLE. We also hypothesized an association between performance on frontal lobe neuropsychological tests and prefrontal hypometabolism. Thirty-two patients who had undergone temporal lobectomy for treatment of MTLE and who completed both presurgical FDG-PET and comprehensive neuropsychological investigations with widely used standardized measures were included. Age-adjusted composite measures were calculated for verbal memory, nonverbal memory, relative material-specific memory, IQ, executive function, attention/working memory, and psychomotor speed. Fluorodeoxyglucose positron emission tomography was analyzed with statistical parametric mapping (SPM) to identify hypometabolism relative to healthy controls. Pearson's correlation was used to determine the relationship between regions of hypometabolism and neuropsychological functioning. Dominant temporal lobe hypometabolism was associated with relatively inferior verbal memory, while nondominant temporal lobe hypometabolism was associated with inferior nonverbal memory. No relationship was found between performance on any frontal lobe measures and prefrontal hypometabolism. Statistical parametric mapping-quantified lateralized temporal lobe hypometabolism correlates with material-specific episodic memory impairment in MTLE. In contrast, prefrontal hypometabolism is not associated with performance on frontal lobe measures. We suggest that this is because frontal lobe neuropsychology tests may not be good measures of isolated frontal lobe functioning.

Supervised variational model with statistical inference and its application in medical image segmentation.

Automated and general medical image segmentation can be challenging because the foreground and the background may have complicated and overlapping density distributions in medical imaging. Conventional region-based level set algorithms often assume piecewise constant or piecewise smooth for segments, which are implausible for general medical image segmentation. Furthermore, low contrast and noise make identification of the boundaries between foreground and background difficult for edge-based level set algorithms. Thus, to address these problems, we suggest a supervised variational level set segmentation model to harness the statistical region energy functional with a weighted probability approximation. Our approach models the region density distributions by using the mixture-of-mixtures Gaussian model to better approximate real intensity distributions and distinguish statistical intensity differences between foreground and background. The region-based statistical model in our algorithm can intuitively provide better performance on noisy images. We constructed a weighted probability map on graphs to incorporate spatial indications from user input with a contextual constraint based on the minimization of contextual graphs energy functional. We measured the performance of our approach on ten noisy synthetic images and 58 medical datasets with heterogeneous intensities and ill-defined boundaries and compared our technique to the Chan-Vese region-based level set model, the geodesic active contour model with distance regularization, and the random walker model. Our method consistently achieved the highest Dice similarity coefficient when compared to the other methods.

Metabolic changes in occipital lobe epilepsy with automatisms.

PURPOSE: Some studies suggest that the pattern of glucose hypometabolism relates not only to the ictal-onset zone but also reflects seizure propagation. We investigated metabolic changes in patients with occipital lobe epilepsy (OLE) that may reflect propagation of ictal discharge during seizures with automatisms. METHODS: Fifteen patients who had undergone epilepsy surgery for intractable OLE and had undergone interictal Fluorine-18-fluorodeoxyglucose positron-emission tomography ((18)F-FDG-PET) between 1994 and 2004 were divided into two groups (with and without automatisms during seizure). Significant regions of hypometabolism were identified by comparing (18)F-FDG-PET results from each group with 16 healthy controls by using statistical parametric mapping. KEY FINDINGS: Significant hypometabolism was confined largely to the epileptogenic occipital lobe in the patient group without automatisms. In patients with automatisms, glucose hypometabolism extended from the epileptogenic occipital lobe into the ipsilateral temporal lobe. SIGNIFICANCE: We identified a distinctive hypometabolic pattern that was specific for OLE patients with automatisms during a seizure. This finding supports the postulate that seizure propagation is a cause of glucose hypometabolism beyond the region of seizure onset.

Multi-Channel neurodegenerative pattern analysis and its application in Alzheimer's disease characterization.

Neuroimaging has played an important role in non-invasive diagnosis and differentiation of neurodegenerative disorders, such as Alzheimer's disease and Mild Cognitive Impairment. Various features have been extracted from the neuroimaging data to characterize the disorders, and these features can be roughly divided into global and local features. Recent studies show a tendency of using local features in disease characterization, since they are capable of identifying the subtle disease-specific patterns associated with the effects of the disease on human brain. However, problems arise if the neuroimaging database involved multiple disorders or progressive disorders, as disorders of different types or at different progressive stages might exhibit different degenerative patterns. It is difficult for the researchers to reach consensus on what brain regions could effectively distinguish multiple disorders or multiple progression stages. In this study we proposed a Multi-Channel pattern analysis approach to identify the most discriminative local brain metabolism features for neurodegenerative disorder characterization. We compared our method to global methods and other pattern analysis methods based on clinical expertise or statistics tests. The preliminary results suggested that the proposed Multi-Channel pattern analysis method outperformed other approaches in Alzheimer's disease characterization, and meanwhile provided important insights into the underlying pathology of Alzheimer's disease and Mild Cognitive Impairment.

The cognitive profile of occipital lobe epilepsy and the selective association of left temporal lobe hypometabolism with verbal memory impairment.

We investigated the cognitive profile of structural occipital lobe epilepsy (OLE) and whether verbal memory impairment is selectively associated with left temporal lobe hypometabolism on [18F]-fluorodeoxyglucose positron emission tomography (FDG-PET). Nine patients with OLE, ages 8-29 years, completed presurgical neuropsychological assessment. Composite measures were calculated for intelligence quotient (IQ), speed, attention, verbal memory, nonverbal memory, and executive functioning. In addition, the Wisconsin Card Sorting Test (WCST) was used as a specific measure of frontal lobe functioning. Presurgical FDG-PET was analyzed with statistical parametric mapping in 8 patients relative to 16 healthy volunteers. Mild impairments were evident for IQ, speed, attention, and executive functioning. Four patients demonstrated moderate or severe verbal memory impairment. Temporal lobe hypometabolism was found in seven of eight patients. Poorer verbal memory was associated with left temporal lobe hypometabolism (p = 0.002), which was stronger (p = 0.03 and p = 0.005, respectively) than the association of left temporal lobe hypometabolism with executive functioning or with performance on the WCST. OLE is associated with widespread cognitive comorbidity, suggesting cortical dysfunction beyond the occipital lobe. Verbal memory impairment is selectively associated with left temporal lobe hypometabolism in OLE, supporting a link between neuropsychological dysfunction and remote hypometabolism in focal epilepsy.

Automated identification of dementia using FDG-PET imaging.

Parametric FDG-PET images offer the potential for automated identification of the different dementia syndromes. However, various existing image features and classifiers have their limitations in characterizing and differentiating the patterns of this disease. We reported a hybrid feature extraction, selection, and classification approach, namely, the GA-MKL algorithm, for separating patients with suspected Alzheimer's disease and frontotemporal dementia from normal controls. In this approach, we extracted three groups of features to describe the average level, spatial variation, and asymmetry of glucose metabolic rates in 116 cortical volumes. An optimal combination of features, that is, capable of classifying dementia cases was identified by a genetic algorithm- (GA-) based method. The condition of each FDG-PET study was predicted by applying the selected features to a multikernel learning (MKL) machine, in which the weighting parameter of each kernel function can be automatically estimated. We compared our approach to two state-of-the-art dementia identification algorithms on a set of 129 clinical cases and improved the performance in separating the dementia types, achieving accuracy of 94.62%. There is a very good agreement between the proposed automated technique and the diagnosis made by clinicians.

A likelihood and local constraint level set model for liver tumor segmentation from CT volumes.

In computed tomography of liver tumors there is often heterogeneous density, weak boundaries, and the liver tumors are surrounded by other abdominal structures with similar densities. These pose limitations to accurate the hepatic tumor segmentation. We propose a level set model incorporating likelihood energy with the edge energy. The minimization of the likelihood energy approximates the density distribution of the target and the multimodal density distribution of the background that can have multiple regions. In the edge energy formulation, our edge detector preserves the ramp associated with the edges for weak boundaries. We compared our approach to the Chan-Vese and the geodesic level set models and the manual segmentation performed by clinical experts. The Chan-Vese model was not successful in segmenting hepatic tumors and our model outperformed the geodesic level set model. Our results on 18 clinical datasets showed that our algorithm had a Jaccard distance error of 14.4 ± 5.3%, relative volume difference of -8.1 ± 2.1%, average surface distance of 2.4 ± 0.8 mm, RMS surface distance of 2.9 ± 0.7 mm, and the maximum surface distance of 7.2 ± 3.1 mm.

Robust model for segmenting images with/without intensity inhomogeneities.

Intensity inhomogeneities and different types/levels of image noise are the two major obstacles to accurate image segmentation by region-based level set models. To provide a more general solution to these challenges, we propose a novel segmentation model that considers global and local image statistics to eliminate the influence of image noise and to compensate for intensity inhomogeneities. In our model, the global energy derived from a Gaussian model estimates the intensity distribution of the target object and background; the local energy derived from the mutual influences of neighboring pixels can eliminate the impact of image noise and intensity inhomogeneities. The robustness of our method is validated on segmenting synthetic images with/without intensity inhomogeneities, and with different types/levels of noise, including Gaussian noise, speckle noise, and salt and pepper noise, as well as images from different medical imaging modalities. Quantitative experimental comparisons demonstrate that our method is more robust and more accurate in segmenting the images with intensity inhomogeneities than the local binary fitting technique and its more recent systematic model. Our technique also outperformed the region-based Chan­Vese model when dealing with images without intensity inhomogeneities and produce better segmentation results than the graph-based algorithms including graph-cuts and random walker when segmenting noisy images.

A new energy framework with distribution descriptors for image segmentation.

Segmentation of the target object(s) from images that have multiple complicated regions, mixture intensity distributions or are corrupted by noise poses a challenge for the level set models. In addition, the conventional piecewise smooth level set models normally require prior knowledge about the number of image segments. To address these problems, we propose a novel segmentation energy function with two distribution descriptors to model the background and the target. The single background descriptor models the heterogeneous background with multiple regions. Then, the target descriptor takes into account the intensity distribution and incorporates local spatial constraint. Our descriptors, which have more complete distribution information, construct the unique energy function to differentiate the target from the background and are more tolerant of image noise. We compare our approach to three other level set models: 1) the Chan-Vese; 2) the multiphase level set; and 3) the geodesic level set. This comparison using 260 synthetic images with varying levels and types of image noise and medical images with more complicated backgrounds showed that our method outperforms these models for accuracy and immunity to noise. On an additional set of 300 synthetic images, our model is also less sensitive to the contour initialization as well as to different types and levels of noise.

Similarity guided feature labeling for lesion detection.

The performance of automatic lesion detection is often affected by the intra- and inter-subject feature variations of lesions and normal anatomical structures. In this work, we propose a similarity-guided sparse representation method for image patch labeling, with three aspects of similarity information modeling, to reduce the chance that the best reconstruction of a feature vector does not provide the correct classification. Based on this classification model, we then design a new approach for detecting lesions in positron emission tomography computed tomography (PET-CT) images. The approach works well with simple image features, and the proposed sparse representation model is effectively applied for both detection of all lesions and characterization of lung tumors and abnormal lymph nodes. The experiments show promising performance improvement over the state-of-the-art.

Lung tumor segmentation in PET images using graph cuts.

The aim of segmentation of tumor regions in positron emission tomography (PET) is to provide more accurate measurements of tumor size and extension into adjacent structures, than is possible with visual assessment alone and hence improve patient management decisions. We propose a segmentation energy function for the graph cuts technique to improve lung tumor segmentation with PET. Our segmentation energy is based on an analysis of the tumor voxels in PET images combined with a standardized uptake value (SUV) cost function and a monotonic downhill SUV feature. The monotonic downhill feature avoids segmentation leakage into surrounding tissues with similar or higher PET tracer uptake than the tumor and the SUV cost function improves the boundary definition and also addresses situations where the lung tumor is heterogeneous. We evaluated the method in 42 clinical PET volumes from patients with non-small cell lung cancer (NSCLC). Our method improves segmentation and performs better than region growing approaches, the watershed technique, fuzzy-c-means, region-based active contour and tumor customized downhill.