Moti Freiman

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.

Image-guided system with miniature robot for precise positioning and targeting in keyhole neurosurgery.

This paper describes a novel image-guided system for precise automatic targeting in minimally invasive keyhole neurosurgery. The system consists of the MARS miniature robot fitted with a mechanical guide for needle, probe or catheter insertion. Intraoperatively, the robot is directly affixed to a head clamp or to the patients skull. It automatically positions itself with respect to predefined targets in a preoperative CT/MRI image following an anatomical registration with an intraoperative 3D surface scan of the patients facial features and registration jig. We present the system architecture, surgical protocol, custom hardware (targeting and registration jig), and software modules (preoperative planning, intraoperative execution, 3D surface scan processing, and three-way registration). We also describe a prototype implementation of the system and in vitro registration experiments. Our results indicate a system-wide target registration error of 1.7 mm (standard deviation = 0.7 mm), which is close to the required 1.0–1.5 mm clinical accuracy in many keyhole neurosurgical procedures.

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.

In vivo assessment of optimal b‐value range for perfusion‐insensitive apparent diffusion coefficient imaging

PURPOSE To assess the optimal b-values range for perfusion-insensitive apparent diffusion coefficient (ADC) imaging of abdominal organs using short-duration DW-MRI acquisitions with currently available ADC estimation methods. METHODS DW-MRI data of 15 subjects were acquired with eight b-values in the range of 5-800 s∕mm(2). The reference-standard, a perfusion insensitive, ADC value (ADC(IVIM)), was computed using an intravoxel incoherent motion (IVIM) model with all acquired diffusion-weighted images. Simulated DW-MRI data was generated using an IVIM model with b-values in the range of 0-1200 s∕mm(2). Monoexponential ADC estimates were calculated using: (1) Two-point estimator (ADC(2)); (2) least squares three-point (ADC(3)) estimator and; (3) Rician noise model estimator (ADC(R)). The authors found the optimal b-values for perfusion-insensitive ADC calculations by minimizing the relative root mean square error (RRMS) between the ADC(IVIM) and the monoexponential ADC values for each estimation method and organ. RESULTS Low b-value = 300 s∕mm(2) and high b-value = 1200 s∕mm(2) minimized the RRMS between the estimated ADC and the reference-standard ADC(IVIM) to less than 5% using the ADC(3) estimator. By considering only the in vivo DW-MRI data, the combination of low b-value = 270 s∕mm(2) and high b-value of 800 s∕mm(2) minimized the RRMS between the estimated ADC and the reference-standard ADC(IVIM) to <7% using the ADC(3) estimator. For all estimators, the RRMS between the estimated ADC and the reference standard ADC correlated strongly with the perfusion-fraction parameter of the IVIM model (r = [0.78-0.83], p ≤ 0.003). CONCLUSIONS The perfusion compartment in DW-MRI signal decay correlates strongly with the RRMS in ADC estimates from short-duration DW-MRI. The impact of the perfusion compartment on ADC estimations depends, however, on the choice of b-values and estimation method utilized. Likewise, perfusion-related errors can be reduced to <7% by carefully selecting the b-values used for ADC calculations and method of estimation.

AN ITERATIVE BAYESIAN APPROACH FOR NEARLY AUTOMATIC LIVER SEGMENTATION: ALGORITHM AND VALIDATION

PurposeWe present a new algorithm for nearly automatic liver segmentation and volume estimation from abdominal Computed Tomography Angiography (CTA) images and its validation.Materials and methodsOur hybrid algorithm uses a multiresolution iterative scheme. It starts from a single user-defined pixel seed inside the liver, and repeatedly applies smoothed Bayesian classification to identify the liver and other organs, followed by adaptive morphological operations and active contours refinement. We evaluate the algorithm with two retrospective studies on 56 validated CTA images. The first study compares it to ground-truth manual segmentation and semi-automatic and automatic commercial methods. The second study uses the public data-set SLIVER07 and its comparison methodology.ResultsWe achieved for both studies, correlations of 0.98 and 0.99 for liver volume estimation, with mean volume differences of 5.36 and 2.68% with respect to manual ground-truth estimation, and mean volume variability for different initial seeds of 0.54 and 0.004%, respectively. For the second study, our algorithm scored 71.8 and 67.87 for the training and test datasets, which compares very favorably with other semi-automatic methods.ConclusionsOur algorithm requires minimal interaction by a non-expert user, is accurate, efficient, and robust to initial seed selection. It can be effective for hepatic volume estimation and liver modeling in a clinical setup.

Characterization of fast and slow diffusion from diffusion-weighted MRI of pediatric Crohn's disease.

To characterize fast and slow diffusion components in diffusion‐weighted magnetic resonance imaging (DW‐MRI) of pediatric Crohns disease (CD). Overall diffusivity reduction as measured by the apparent diffusion coefficient (ADC) in patients with CD has been previously demonstrated. However, the ADC reduction may be due to changes in either fast or slow diffusion components. In this study we distinguished between the fast and slow diffusion components in the DW‐MRI signal decay of pediatric CD.

Robot-assisted image-guided targeting for minimally invasive neurosurgery: planning, registration, and in-vitro experiment

This paper present a novel image-guided system for precise automatic targeting in keyhole minimally invasive neurosurgery. The system consists of a miniature robot fitted with a mechanical guide for needle/probe insertion. Intraoperatively, the robot is directly affixed to a head clamp or to the patient skull. It automatically positions itself with respect to predefined targets in a preoperative CT/MRI image following an anatomical registration with a intraoperative 3D surface scan of the patient facial features. We describe the preoperative planning and registration modules, and an in-vitro registration experiment of the entire system which yields a target registration error of 1.7 mm (std = 0.7 mm).

fMRI-Based Hierarchical SVM Model for the Classification and Grading of Liver Fibrosis

We present a novel method for the automatic classification and grading of liver fibrosis based on hepatic hemodynamic changes measured noninvasively from functional MRI (fMRI) scans combined with hypercapnia and hyperoxia. The supervised learning method automatically creates a classification and grading model for liver fibrosis grade from training datasets. It constructs a statistical model of liver fibrosis by evaluating the signal intensity time course and local variance in T2*-W fMRI scans acquired during the breathing of air, air-carbon dioxide, and carbogen with a hierarchical multiclass binary-based support vector machine (SVM) classifier. Two experimental studies on 162 slices from 34 mice with the hierarchical multiclass binary-based SVM classifier yield 96.9% separation accuracy between healthy and histological-based fibrosis graded subjects, and an overall accuracy of 75.3% for healthy, fibrotic, and cirrhotic subjects. These results outperform existing image-based methods that can discriminate between healthy and mild-grade fibrosis subjects.

A Bayesian Approach for Liver Analysis: Algorithm and Validation Study

We present a new method for the simultaneous, nearly automatic segmentation of liver contours, vessels, and metastatic lesions from abdominal CTA scans. The method repeatedly applies multi-resolution, multi-class smoothed Bayesian classification followed by morphological adjustment and active contours refinement. It uses multi-class and voxel neighborhood information to compute an accurate intensity distribution function for each class. The method requires only one or two user-defined voxel seeds, with no manual adjustment of internal parameters. A retrospective study on two validated clinical datasets totaling 56 CTAs was performed. We obtained correlations of 0.98 and 0.99 with a manual ground truth liver volume estimation for the first and second databases, and a total score of 67.87 for the second database. These results suggest that our method is accurate, efficient, and robust to seed selection compared to manually generated ground truth segmentation and to other semi-automatic segmentation methods.

AN iterative model-constrained graph-cut algorithm for Abdominal Aortic Aneurysm thrombus segmentation

We present an iterative model-constrained graph-cut algorithm for the segmentation of Abdominal Aortic Aneurysm (AAA) thrombus. Given an initial segmentation of the aortic lumen, our method automatically segments the thrombus by iteratively coupling intensity-based graph min-cut segmentation and geometric parametric model fitting. The geometric model effectively constrains the graph min-cut segmentation from “leaking” to nearby veins and organs. Experimental results on 8 AAA CTA datasets yield robust segmentations of the AAA thrombus in 2 mins computer time with a mean absolute volume difference of 8.0% and mean volumetric overlap error of 12.9%, which is comparable to the interobserver error.