Clinical impact of allergy and pre-medication in CT studies with low-osmolality intravenous iodinated contrast media.

AIM: To evaluate the occurrence and severity of allergic reactions to iodinated contrast media (ICM), including associated risk factors and the impact of pre-medication. MATERIALS AND METHODS: Data on patients who had experienced allergic reactions during outpatient computed tomography (CT) examinations between January 2014 and September 2018 were analysed retrospectively. Response severity was assessed according to validated criteria. A control group was selected among individuals who underwent CT during the study period and did not experience allergic reactions. RESULTS: Screening of 36,920 CT studies revealed 74 (0.2%) individuals with systemic reactions to ICM. No significant differences in patient characteristics were found among patients who experienced mild (n=54), moderate (n=17), or severe (n=4) reactions. Previous ICM allergy was reported in 10 patients (13.3%). Patients with a history of ICM allergy had mild (9/10) or moderate (1/10) reactions, with one individual showing decreased intensity of the allergic response compared to a previous event. Within the control group, four patients (4%) had previous ICM allergy. In these individuals, lack of allergic reactions could not be attributed to pre-medication. All patients with severe reactions did not have a prior history of ICM allergy. CONCLUSION: Severe allergic reactions to ICM are rare, lack significant risk factors, and do not appear to be impacted by pre-medication. The findings presented herein highlight the need for prospective work that will re-evaluate the yield of pre-medication protocols.

Inter-observer variability of manual contour delineation of structures in CT.

PURPOSE: To quantify the inter-observer variability of manual delineation of lesions and organ contours in CT to establish a reference standard for volumetric measurements for clinical decision making and for the evaluation of automatic segmentation algorithms. MATERIALS AND METHODS: Eleven radiologists manually delineated 3193 contours of liver tumours (896), lung tumours (1085), kidney contours (434) and brain hematomas (497) on 490 slices of clinical CT scans. A comparative analysis of the delineations was then performed to quantify the inter-observer delineation variability with standard volume metrics and with new group-wise metrics for delineations produced by groups of observers. RESULTS: The mean volume overlap variability values and ranges (in %) between the delineations of two observers were: liver tumours 17.8 [-5.8,+7.2]%, lung tumours 20.8 [-8.8,+10.2]%, kidney contours 8.8 [-0.8,+1.2]% and brain hematomas 18 [-6.0,+6.0] %. For any two randomly selected observers, the mean delineation volume overlap variability was 5-57%. The mean variability captured by groups of two, three and five observers was 37%, 53% and 72%; eight observers accounted for 75-94% of the total variability. For all cases, 38.5% of the delineation non-agreement was due to parts of the delineation of a single observer disagreeing with the others. No statistical difference was found for the delineation variability between the observers based on their expertise. CONCLUSION: The variability in manual delineations for different structures and observers is large and spans a wide range across a variety of structures and pathologies. Two and even three observers may not be sufficient to establish the full range of inter-observer variability. KEY POINTS: • This study quantifies the inter-observer variability of manual delineation of lesions and organ contours in CT. • The variability of manual delineations between two observers can be significant. Two and even three observers capture only a fraction of the full range of inter-observer variability observed in common practice. • Inter-observer manual delineation variability is necessary to establish a reference standard for radiologist training and evaluation and for the evaluation of automatic segmentation algorithms.

Quantitative biomarkers for liver metastases: comparison of MRI diffusion-weighted imaging heterogeneity index and fluorine-18-fluoro-deoxyglucose standardised uptake value in hybrid PET/MR.

AIM: To investigate the ability of apparent diffusion coefficient (ADC) heterogeneity index to discriminate liver metastases (LM) from normal-appearing liver (NAL) tissue as compared to common magnetic resonance imaging (MRI) metrics, and to investigate its correlation with 2-[18F]-fluoro-2-deoxy-d-glucose (18F-FDG) positron-emission tomography (PET) standardised uptake value (SUV). MATERIALS AND METHODS: Thirty-nine liver metastases in 24 oncology patients (13 women, 11 men; mean age 56±13 years) with proven LM from heterogeneous sources were evaluated on a PET/MRI system. Abdominal sequences included Dixon and diffusion-weighted imaging (DWI) protocols with simultaneous PET. Tissue heterogeneity was calculated using the coefficient of variance (CV) of the ADC, and compared in LM and in NAL tissue of the same volume in an adjacent portion of the liver. The correlations between various ADC measures and PET SUV in distinguishing LM from NAL were evaluated. RESULTS: A good correlation was found between ADCcv and SUVpeak (r=0.712). Moderate inverse correlation was found between ADCmin and SUVpeak (r=-0.536), and a weak inverse correlation between ADCmean and SUVpeak (r=-0.273). There was a significant difference between LM and NAL when ADCcv (p<0.0001) and ADCmin (p=0.001) were used. Receiver operating characteristic (ROC) analysis of SUV, ADCcv, ADCmin, and ADCmean produced an AUC of 0.989, 0.900, 0.742, and 0.623 respectively. CONCLUSIONS: The ADCcv index is a potential biomarker of LM with better correlation to 18F-FDG PET SUVpeak than conventional MRI metrics, and may serve to quantitatively discriminate between LM and NAL.

Early 68GA-PSMA PET/MRI acquisition: assessment of lesion detectability and PET metrics in patients with prostate cancer undergoing same-day late PET/CT.

AIM: To compare lesion detectability and positron-emission tomography (PET) metric measurements between early-PET/magnetic resonance imaging (MRI) acquisition and same-day PET/computed tomography (CT). MATERIALS AND METHODS: The study was approved by the institutional review board and written informed consent was obtained from all patients. Twenty-one patients underwent non-time-of-flight (TOF) PET/MRI immediately following 68GA-prostate-specific membrane antigen (PSMA) tracer injection in two steps: firstly, early prostate PET/MRI (pPET/MRI) and early whole-body (WB) PET/MRI (wbPET/MR) followed by WB TOF PET/CT (wbPET/CT). Lesion detectability was compared between wbPET/MRI and wbPET/CT while PET metric measurements were compared between pPET/MR, wbPET/MRI, and wbPET/CT. RESULTS: Sixty-one and 63 lesions were found on wbPET/MRI and wbPET/CT, respectively (K=0.95, 95% confidence interval (CI)=0.89-1.0) with very good correlation between PET metric measurements (r=0.91; p=0.001). Bland-Altman plots demonstrated a mean percentage difference between wbPET/CT with wbPET/MRI of 34.4% with 95% limits of agreement (LOA) between -39% to 107.9% for metabolic tumour volume (MTV) and a mean difference of 30% with LOA between -13.4% to 73.4% for peak standardised uptake value (SUVpeak). CONCLUSION: Early PET/MRI demonstrates very good lesion detectability agreement and correlation with PET metrics compared to same-day PET/CT. Nevertheless, LOA are far beyond the clinically acceptable range, and therefore, PET/CT and early PET/MRI metrics cannot be used interchangeably.

Comparison of 80 and 120 kVp contrast-enhanced CT for attenuation correction in PET/CT, using quantitative analysis and reporter assessment of PET image quality.

AIM: To determine the effect of low tube voltage on positron-emission tomography (PET) image quality, quantitative analysis, and radiation dose in a combined PET/computed tomography (CT) study in patients with normal body mass index (BMI). MATERIALS AND METHODS: One hundred and twenty-nine examinations performed in 46 patients (mean age 57 years), who had at least two separate studies were retrospectively evaluated; at least one with 120 kVp and one with 80 kVp. Three independent readers reviewed all PET images and graded the image quality. PET signal and noise were recorded on the liver, spleen, fat, bone marrow, and aorta. CT dose index (CTDI) and the dose-length product (DLP) were used for CT radiation dose estimation. A mixed-effects model analysis was used for comparison of estimated radiation dose and PET data. RESULTS: There was a significant decrease of 15% in the radiation dose estimates between 80 and 120 kVp (DLP 946.2 ± 189 versus 1157.0 ± 236, respectively; p < 0.001). There was an increase of 12% in PET signal in the normal liver with 80 kVp. The average score of PET image quality obtained between 80 and 120 kVp was 4.85 ± 0.42 versus 4.90 ± 0.27, respectively (p = 0.47). CONCLUSION: PET/80 kVp CT has no statistically significant difference in the PET image quality and quantitative analysis compared to PET/120 kVp and may be used in selected patients to reduce the radiation dose.

Automatic segmentation variability estimation with segmentation priors.

PURPOSE: Segmentations produced manually by experts or by algorithms are subject to variability, as they depend on many factors, e.g., the structure of interest, the resolution, contrast and quality of the images, and the expert experience or the algorithmic method. To properly assess the quality of these segmentations, it is thus essential to quantify their variability. However, obtaining reference variability ground truth requires several observers to manually delineate structures, which is time-consuming and impractical. METHODS: We describe a new comprehensive formal framework for segmentation evaluation and variability estimation without ground truth and a generic method for automatic segmentation variability estimation based on segmentation priors and multivariate sensitivity analysis. The method inputs the image scan and a user-validated segmentation of the structure of interest and uses predefined segmentation priors to compute a variability estimation around the given segmentation. The segmentation priors are combined with an integrator function whose sensitivity around the given segmentation is the segmentation variability. RESULTS: We validate our methods with two studies. The first study establishes the reference manual delineation variability. Eleven radiologists with varying levels of expertise manually delineated the contours of liver tumors, lung tumors, kidneys, and brain hematomas on 2,835 delineations from 18 CT scans. The relative delineation volume variability ranges are 51 [-24,+27]% for liver tumors, 56 [-25,+31]% for lung tumors, 25 [-12,+13]% for kidney contours, and 53 [-24,+29]% brain hematomas. The second study compares the estimated segmentation variability results to this reference data. The mean volume variability difference of the delineation is <6%, with a Dice similarity coefficient of >70% with respect to the mean manual delineation variability data. CONCLUSIONS: Reliable segmentation variability estimation with no ground truth enables the establishment of a proper observer variability reference. The segmentation variability should be taken into account when setting reference standards for clinical decisions based on volumetric measurements and when evaluating segmentation algorithms.

A fully automatic end-to-end method for content-based image retrieval of CT scans with similar liver lesion annotations.

PURPOSE: The goal of medical content-based image retrieval (M-CBIR) is to assist radiologists in the decision-making process by retrieving medical cases similar to a given image. One of the key interests of radiologists is lesions and their annotations, since the patient treatment depends on the lesion diagnosis. Therefore, a key feature of M-CBIR systems is the retrieval of scans with the most similar lesion annotations. To be of value, M-CBIR systems should be fully automatic to handle large case databases. METHODS: We present a fully automatic end-to-end method for the retrieval of CT scans with similar liver lesion annotations. The input is a database of abdominal CT scans labeled with liver lesions, a query CT scan, and optionally one radiologist-specified lesion annotation of interest. The output is an ordered list of the database CT scans with the most similar liver lesion annotations. The method starts by automatically segmenting the liver in the scan. It then extracts a histogram-based features vector from the segmented region, learns the features' relative importance, and ranks the database scans according to the relative importance measure. The main advantages of our method are that it fully automates the end-to-end querying process, that it uses simple and efficient techniques that are scalable to large datasets, and that it produces quality retrieval results using an unannotated CT scan. RESULTS: Our experimental results on 9 CT queries on a dataset of 41 volumetric CT scans from the 2014 Image CLEF Liver Annotation Task yield an average retrieval accuracy (Normalized Discounted Cumulative Gain index) of 0.77 and 0.84 without/with annotation, respectively. CONCLUSIONS: Fully automatic end-to-end retrieval of similar cases based on image information alone, rather that on disease diagnosis, may help radiologists to better diagnose liver lesions.

Automatic detection of new tumors and tumor burden evaluation in longitudinal liver CT scan studies.

PURPOSE: Radiological longitudinal follow-up of liver tumors in CT scans is the standard of care for disease progression assessment and for liver tumor therapy. Finding new tumors in the follow-up scan is essential to determine malignancy, to evaluate the total tumor burden, and to determine treatment efficacy. Since new tumors are typically small, they may be missed by examining radiologists. METHODS: We describe a new method for the automatic detection and segmentation of new tumors in longitudinal liver CT studies and for liver tumors burden quantification. Its inputs are the baseline and follow-up CT scans, the baseline tumors delineation, and a tumor appearance prior model. Its outputs are the new tumors segmentations in the follow-up scan, the tumor burden quantification in both scans, and the tumor burden change. Our method is the first comprehensive method that is explicitly designed to find new liver tumors. It integrates information from the scans, the baseline known tumors delineations, and a tumor appearance prior model in the form of a global convolutional neural network classifier. Unlike other deep learning-based methods, it does not require large tagged training sets. RESULTS: Our experimental results on 246 tumors, of which 97 were new tumors, from 37 longitudinal liver CT studies with radiologist approved ground-truth segmentations, yields a true positive new tumors detection rate of 86 versus 72% with stand-alone detection, and a tumor burden volume overlap error of 16%. CONCLUSIONS: New tumors detection and tumor burden volumetry are important for diagnosis and treatment. Our new method enables a simplified radiologist-friendly workflow that is potentially more accurate and reliable than the existing one by automatically and accurately following known tumors and detecting new tumors in the follow-up scan.

Automatic lung tumor segmentation with leaks removal in follow-up CT studies.

PURPOSE: In modern oncology, disease progression and response to treatment are routinely evaluated with a series of volumetric scans. The number of tumors and their volume (mass) over time provides a quantitative measure for the evaluation. Thus, many of the scans are follow-up scans. We present a new, fully automatic algorithm for lung tumors segmentation in follow-up CT studies that takes advantage of the baseline delineation. METHODS: The inputs are a baseline CT scan and a delineation of the tumors in it and a follow-up scan; the output is the tumor delineations in the follow-up CT scan; the output is the tumor delineations in the follow-up CT scan. The algorithm consists of four steps: (1) deformable registration of the baseline scan and tumor's delineations to the follow-up CT scan; (2) segmentation of these tumors in the follow-up CT scan with the baseline CT and the tumor's delineations as priors; (3) detection and correction of follow-up tumors segmentation leaks based on the geometry of both the foreground and the background; and (4) tumor boundary regularization to account for the partial volume effects. RESULTS: Our experimental results on 80 pairs of CT scans from 40 patients with ground-truth segmentations by a radiologist yield an average DICE overlap error of 14.5 % ([Formula: see text]), a significant improvement from the 30 % ([Formula: see text]) result of stand-alone level-set segmentation. CONCLUSION: The key advantage of our method is that it automatically builds a patient-specific prior to the tumor. Using this prior in the segmentation process, we developed an algorithm that increases segmentation accuracy and robustness and reduces observer variability.

Sequential myeloablative autologous stem cell transplantation and reduced intensity allogeneic hematopoietic cell transplantation is safe and feasible in children, adolescents and young adults with poor-risk refractory or recurrent Hodgkin and non-Hodgkin lymphoma.

The outcome of children, adolescents and young adults (CAYA) with poor-risk recurrent/refractory lymphoma is dismal (⩽30%). To overcome this poor prognosis, we designed an approach to maximize an allogeneic graft vs lymphoma effect in the setting of low disease burden. We conducted a multi-center prospective study of myeloablative conditioning (MAC) and autologous stem cell transplantation (AutoSCT), followed by a reduced intensity conditioning (RIC) and allogeneic hematopoietic cell transplantation (AlloHCT) in CAYA, with poor-risk refractory or recurrent lymphoma. Conditioning for MAC AutoSCT consisted of carmustine/etoposide/cyclophosphamide, RIC consisted of busulfan/fludarabine. Thirty patients, 16 Hodgkin lymphoma (HL) and 14 non-Hodgkin lymphoma (NHL), with a median age of 16 years and median follow-up of 5years, were enrolled. Twenty-three patients completed both MAC AutoSCT and RIC AlloHCT. Allogeneic donor sources included unrelated cord blood (n=9), unrelated donor (n=8) and matched siblings (n=6). The incidence of transplant-related mortality following RIC AlloHCT was only 12%. In patients with HL and NHL, 10 year EFS was 59.8% and 70% (P=0.613), respectively. In summary, this approach is safe, and long-term EFS with this approach is encouraging considering the poor-risk patient characteristics and the use of unrelated donors for RIC AlloHCT in the majority of cases.

The occurrence, recrudescence, and worsening of asthma in a population of young adults: impact of varying types of occupation.

OBJECTIVE: To describe the rates of exacerbation of existing asthma and incidence of new disease in Israeli men during military service. DESIGN: All 17-year-old Israeli nationals are obliged by law to appear at the Israel Defense Forces (IDF) recruiting office for medical examination. The medical history of army recruits was noted during the 30-month period after their induction into the IDF, and medical examinations were performed by pulmonary specialists in all suspected cases of asthma. The duty status of the soldiers in combat units (CUs), maintenance units (MUs), and clerical tasks was related to their asthma status. RESULTS: Of a total of 59,058 recruits, 1.0% developed asthma during the 30 months of this study; of those in CUs, 1.2% developed asthma; of those in MUs, 0.8% developed asthma; and of those performing clerical tasks, 0.6% developed asthma. The relative risk for developing or worsening of asthma was related to both the preexisting asthma status of the recruit and the environment in which he carried out his military service. The annual incidence of occupational-related asthma in MUs was found to be 800/million: five to six times the rates reported elsewhere. CONCLUSIONS: Service in CUs was associated with an increased frequency of exacerbation of asthma among recruits with previous disease and with the appearance of disease de novo. "Normal" conscripts with a history of childhood asthma are at a higher risk of developing overt asthma when compared to subjects with no such history. We found a 25% relative excess of incident cases of asthma in soldiers posted in MUs compared to those performing clerical tasks [(0.8 to 0.6%)/0.8%]. This difference is probably attributed to the difference in occupational hazards in these categories. Further studies are needed to determine if this represents the elicitation of underlying preexisting airway lability by new work demands or other environmental conditions, or if this represents a new development of airway lability because of specific immune or nonimmune factors.

Drug-resistant pulmonary tuberculosis in Israel, a society of immigrants: 1985-1994.

SETTING AND OBJECTIVES: Drug-resistant tuberculosis was uncommon in Israel until 1985, when the waves of immigration began. We studied the incidence and clinical course of resistant pulmonary tuberculosis nationwide. DESIGN: Isolates of Mycobacterium tuberculosis between 1985 and 1994 were surveyed. Data on 150 patients with resistance and 110 patients with drug-sensitive disease were reviewed. Ethnic origin, type of resistance, radiological findings and outcome were analysed. RESULTS: In total, 16.7% of the isolates showed resistance to at least one drug; 58% had resistance to multiple drugs. In 67% of the patients the resistance was primary. Most patients were immigrants from the former USSR and from Ethiopia; none were Israeli-born Jews. Mortality with resistance was 10%, and was highest (14%) with multiple drug resistance. Mortality among drug-resistant cases was lowest (3%) among Ethiopian Jews. Cavities and extensive disease were more common with drug resistance. CONCLUSION: Drug resistance has become relatively common in Israel due to immigration from the former USSR and Ethiopia. It is more extensive radiologically and carries a poorer outcome.

The distribution of heat in bone during radiofrequency ablation of an ex vivo bovine model of osteoid osteoma.

Osteoid osteoma is treated primarily by radiofrequency (RF) ablation. However, there is little information about the distribution of heat in bone during the procedure and its safety. We constructed a model of osteoid osteoma to assess the distribution of heat in bone and to define the margins of safety for ablation. Cavities were drilled in cadaver bovine bones and filled with a liver homogenate to simulate the tumour matrix. Temperature-sensing probes were placed in the bone in a radial fashion away from the cavities. RF ablation was performed 107 times in tumours < 10 mm in diameter (72 of which were in cortical bone, 35 in cancellous bone), and 41 times in cortical bone with models > 10 mm in diameter. Significantly higher temperatures were found in cancellous bone than in cortical bone (p < 0.05). For lesions up to 10 mm in diameter, in both bone types, the temperature varied directly with the size of the tumour (p < 0.05), and inversely with the distance from it. Tumours of > 10 mm in diameter showed a trend similar to those of smaller lesions. No temperature rise was seen beyond 12 mm from the edge of a cortical tumour of any size. Formulae were developed to predict the expected temperature in the bone during ablation.

Direct enzyme-substrate affinity determination by real-time hyperpolarized (13)C-MRS.

A specialized kinetic analysis of real-time hyperpolarized [1,1,2,2-D4, 1-(13)C]choline (13)C-magnetic resonance spectroscopy enabled the determination of initial rates of metabolic enzyme activity (choline oxidase), enzyme-substrate affinity (Km), and inhibition. In a clinical MRI scanner, metabolite levels lower than 16 µM were detected at a temporal resolution of 1 s.

Anatomical structures segmentation by spherical 3D ray casting and gradient domain editing.

Fuzzy boundaries of anatomical structures in medical images make segmentation a challenging task. We present a new segmentation method that addresses the fuzzy boundaries problem. Our method maps the lengths of 3D rays cast from a seed point to the unit sphere, estimates the fuzzy boundaries location by thresholding the gradient magnitude of the rays lengths, and derives the true boundaries by Laplacian interpolation on the sphere. Its advantages are that it does not require a global shape prior or curvature based constraints, that it has an automatic stopping criteria, and that it is robust to anatomical variability, noise, and parameters values settings. Our experimental evaluation on 23 segmentations of kidneys and on 16 segmentations of abdominal aortic aneurysms (AAA) from CT scans yielded an average volume overlap error of 12.6% with respect to the ground-truth. These results are comparable to those of other segmentation methods without their underlying assumptions.

Carotid vasculature modeling from patient CT angiography studies for interventional procedures simulation.

OBJECTIVE: A practical method for patient-specific modeling of the aortic arch and the entire carotid vasculature from computed tomography angiography (CTA) scans for morphologic analysis and for interventional procedure simulation. MATERIALS AND METHODS: The method starts with the automatic watershed-based segmentation of the aorta and the construction of an a-priori intensity probability distribution function for arteries. The carotid arteries are then segmented with a graph min-cut method based on a new edge weighting function that adaptively couples voxel intensity, intensity prior, and local vesselness shape prior. Finally, the same graph-cut optimization framework is used to interactively remove a few unwanted veins segments and to fill in minor vessel discontinuities caused by intensity variations. RESULTS: We validate our modeling method with two experimental studies on 71 multicenter clinical CTA datasets, including carotid bifurcation lumen segmentation on 56 CTAs from the MICCAI'2009 3D Segmentation Challenge. Segmentation results show that our method is comparable to the best existing methods and was successful in modeling the entire carotid vasculature with a Dice similarity measure of 84.5% (SD = 3.3%) and MSSD 0.48 mm (SD = 0.12 mm.) Simulation study shows that patient-specific simulations with four patient-specific models generated by our segmentation method on the ANGIO Mentor™ simulator platform are robust, realistic, and greatly improve the simulation. CONCLUSION: This constitutes a proof-of-concept that patient-specific CTA-based modeling and simulation of carotid interventional procedures are practical in a clinical environment.

The association between the embolic load and atrial size in acute pulmonary embolism.

BACKGROUND: Early identification by computed tomography pulmonary angiography (CTPA) of patients with acute pulmonary embolism (PE) who have signs associated with a high embolic burden would be highly desirable. OBJECTIVES: To investigate whether an increased obstruction of the pulmonary vasculature is associated with reduced left atrial (LA) and increased right atrial (RA) areas. METHODS: We retrospectively analyzed a consecutive series of CTPA studies of 137 patients with acute PE and 38 controls without PE between October 2004 and March 2006. Left and right atrial areas and longitudinal and short axis diameters were measured and correlated with the pulmonary arterial obstruction index (PAOI) divided into tertiles (obstruction of < 12.5%, 12.5%-42.5% and ≥ 42.5%). RESULTS: There was a significant negative age- and gender-adjusted correlation between the PAOI and LA measurements, particularly the LA area (r = -0.259) and the LA short axis diameter (r = -0.331). All RA measurements had positive correlations (RA area, r = 0.279; RA short axis diameter, r = 0.313). The LA/RA area ratio correlated negatively with the PAOI (r = -0.447). All above-mentioned correlations had P < 0.002. All the LA measurements were the largest in the controls and gradually decreased with higher PAOIs. A receiver operating characteristic curve analysis demonstrated that the RV/LV diameter, LA/RA area and LA/RA short axis diameter ratios had comparable discriminative ability for higher PAOI tertiles. CONCLUSIONS: The higher the clot load in the pulmonary arteries, the smaller the LA area and the larger the RA area. Atrial area measurements by CTPA may serve as a real-time parameter in assessing the severity of PE upon diagnosis.

Evaluation framework for carotid bifurcation lumen segmentation and stenosis grading.

This paper describes an evaluation framework that allows a standardized and objective quantitative comparison of carotid artery lumen segmentation and stenosis grading algorithms. We describe the data repository comprising 56 multi-center, multi-vendor CTA datasets, their acquisition, the creation of the reference standard and the evaluation measures. This framework has been introduced at the MICCAI 2009 workshop 3D Segmentation in the Clinic: A Grand Challenge III, and we compare the results of eight teams that participated. These results show that automated segmentation of the vessel lumen is possible with a precision that is comparable to manual annotation. The framework is open for new submissions through the website http://cls2009.bigr.nl.

Non-parametric iterative model constraint graph min-cut for automatic kidney segmentation.

We present a new non-parametric model constraint graph min-cut algorithm for automatic kidney segmentation in CT images. The segmentation is formulated as a maximum a-posteriori estimation of a model-driven Markov random field. A non-parametric hybrid shape and intensity model is treated as a latent variable in the energy functional. The latent model and labeling map that minimize the energy functional are then simultaneously computed with an expectation maximization approach. The main advantages of our method are that it does not assume a fixed parametric prior model, which is subjective to inter-patient variability and registration errors, and that it combines both the model and the image information into a unified graph min-cut based segmentation framework. We evaluated our method on 20 kidneys from 10 CT datasets with and without contrast agent for which ground-truth segmentations were generated by averaging three manual segmentations. Our method yields an average volumetric overlap error of 10.95%, and average symmetric surface distance of 0.79 mm. These results indicate that our method is accurate and robust for kidney segmentation.