A supervised learning framework of statistical shape and probability priors for automatic prostate segmentation in ultrasound images

Prostate segmentation aids in prostate volume estimation, multi-modal image registration, and to create patient specific anatomical models for surgical planning and image guided biopsies. However, manual segmentation is time consuming and suffers from inter-and intra-observer variabilities. Low contrast images of trans rectal ultrasound and presence of imaging artifacts like speckle, micro-calcifications, and shadow regions hinder computer aided automatic or semi-automatic prostate segmentation. In this paper, we propose a prostate segmentation approach based on building multiple mean parametric models derived from principal component analysis of shape and posterior probabilities in a multi-resolution framework. The model parameters are then modified with the prior knowledge of the optimization space to achieve optimal prostate segmentation. In contrast to traditional statistical models of shape and intensity priors, we use posterior probabilities of the prostate region determined from random forest classification to build our appearance model, initialize and propagate our model. Furthermore, multiple mean models derived from spectral clustering of combined shape and appearance parameters are applied in parallel to improve segmentation accuracies. The proposed method achieves mean Dice similarity coefficient value of 0.91 ± 0.09 for 126 images containing 40 images from the apex, 40 images from the base and 46 images from central regions in a leave-one-patient-out validation framework. The mean segmentation time of the procedure is 0.67 ± 0.02 s.     

Semi-automatic liver tumor segmentation with hidden Markov measure field model and non-parametric distribution estimation

A novel liver tumor segmentation method for CT images is presented. The aim of this work was to reduce the manual labor and time required in the treatment planning of radiofrequency ablation (RFA), by providing accurate and automated tumor segmentations reliably. The developed method is semi-automatic, requiring only minimal user interaction. The segmentation is based on non-parametric intensity distribution estimation and a hidden Markov measure field model, with application of a spherical shape prior. A post-processing operation is also presented to remove the overflow to adjacent tissue. In addition to the conventional approach of using a single image as input data, an approach using images from multiple contrast phases was developed. The accuracy of the method was validated with two sets of patient data, and artificially generated samples. The patient data included preoperative RFA images and a public data set from “3D Liver Tumor Segmentation Challenge 2008”. The method achieved very high accuracy with the RFA data, and outperformed other methods evaluated with the public data set, receiving an average overlap error of 30.3% which represents an improvement of 2.3% points to the previously best performing semi-automatic method. The average volume difference was 23.5%, and the average, the RMS, and the maximum surface distance errors were 1.87, 2.43, and 8.09 mm, respectively. The method produced good results even for tumors with very low contrast and ambiguous borders, and the performance remained high with noisy image data.     

Automated model-based vertebra detection,identification, and segmentation in CT images

For many orthopaedic, neurological, and oncological applications, an exact segmentation of the vertebral column including an identification of each vertebra is essential. However, although bony structures show high contrast in CT images, the segmentation and labelling of individual vertebrae is challenging.In this paper, we present a comprehensive solution for automatically detecting, identifying, and segmenting vertebrae in CT images. A framework has been designed that takes an arbitrary CT image, e.g., head-neck, thorax, lumbar, or whole spine, as input and provides a segmentation in form of labelled triangulated vertebra surface models. In order to obtain a robust processing chain, profound prior knowledge is applied through the use of various kinds of models covering shape, gradient, and appearance information. The framework has been tested on 64 CT images even including pathologies. In 56 cases, it was successfully applied resulting in a final mean point-to-surface segmentation error of 1.12 ± 1.04 mm.One key issue is a reliable identification of vertebrae. For a single vertebra, we achieve an identification success of more than 70%. Increasing the number of available vertebrae leads to an increase in the identification rate reaching 100% if 16 or more vertebrae are shown in the image.     

Spine detection in CT and MR using iterated marginal space learning

Examinations of the spinal column with both, Magnetic Resonance (MR) imaging and Computed Tomography (CT), often require a precise three-dimensional positioning, angulation and labeling of the spinal disks and the vertebrae. A fully automatic and robust approach is a prerequisite for an automated scan alignment as well as for the segmentation and analysis of spinal disks and vertebral bodies in Computer Aided Diagnosis (CAD) applications. In this article, we present a novel method that combines Marginal Space Learning (MSL), a recently introduced concept for efficient discriminative object detection, with a generative anatomical network that incorporates relative pose information for the detection of multiple objects. It is used to simultaneously detect and label the spinal disks. While a novel iterative version of MSL is used to quickly generate candidate detections comprising position, orientation, and scale of the disks with high sensitivity, the anatomical network selects the most likely candidates using a learned prior on the individual nine dimensional transformation spaces. Finally, we propose an optional case-adaptive segmentation approach that allows to segment the spinal disks and vertebrae in MR and CT respectively. Since the proposed approaches are learning-based, they can be trained for MR or CT alike. Experimental results based on 42 MR and 30 CT volumes show that our system not only achieves superior accuracy but also is among the fastest systems of its kind in the literature. On the MR data set the spinal disks of a whole spine are detected in 11.5 s on average with 98.6% sensitivity and 0.073 false positive detections per volume. On the CT data a comparable sensitivity of 98.0% with 0.267 false positives is achieved. Detected disks are localized with an average position error of 2.4 mm/3.2 mm and angular error of 3.9°/4.5° in MR/CT, which is close to the employed hypothesis resolution of 2.1 mm and 3.3°.     

Adaptive local window for level set segmentation of CT and MRI liver lesions

We propose a novel method, the adaptive local window, for improving level set segmentation technique. The window is estimated separately for each contour point, over iterations of the segmentation process, and for each individual object. Our method considers the object scale, the spatial texture, and the changes of the energy functional over iterations. Global and local statistics are considered by calculating several gray level co-occurrence matrices. We demonstrate the capabilities of the method in the domain of medical imaging for segmenting 233 images with liver lesions. To illustrate the strength of our method, those lesions were screened by either Computed Tomography or Magnetic Resonance Imaging. Moreover, we analyzed images using three different energy models. We compared our method to a global level set segmentation, to a local framework that uses predefined fixed-size square windows and to a local region-scalable fitting model. The results indicate that our proposed method outperforms the other methods in terms of agreement with the manual marking and dependence on contour initialization or the energy model used. In case of complex lesions, such as low contrast lesions, heterogeneous lesions, or lesions with a noisy background, our method shows significantly better segmentation with an improvement of 0.25 ± 0.13 in Dice similarity coefficient, compared with state of the art fixed-size local windows (Wilcoxon, p  < 0.001).     

Endoluminal surface registration for CT colonography using haustral fold matching

Computed Tomographic (CT) colonography is a technique used for the detection of bowel cancer or potentially precancerous polyps. The procedure is performed routinely with the patient both prone and supine to differentiate fixed colonic pathology from mobile faecal residue. Matching corresponding locations is difficult and time consuming for radiologists due to colonic deformations that occur during patient repositioning.We propose a novel method to establish correspondence between the two acquisitions automatically. The problem is first simplified by detecting haustral folds using a graph cut method applied to a curvature-based metric applied to a surface mesh generated from segmentation of the colonic lumen. A virtual camera is used to create a set of images that provide a metric for matching pairs of folds between the prone and supine acquisitions. Image patches are generated at the fold positions using depth map renderings of the endoluminal surface and optimised by performing a virtual camera registration over a restricted set of degrees of freedom. The intensity difference between image pairs, along with additional neighbourhood information to enforce geometric constraints over a 2D parameterisation of the 3D space, are used as unary and pair-wise costs respectively, and included in a Markov Random Field (MRF) model to estimate the maximum a posteriori fold labelling assignment.The method achieved fold matching accuracy of 96.0% and 96.1% in patient cases with and without local colonic collapse. Moreover, it improved upon an existing surface-based registration algorithm by providing an initialisation. The set of landmark correspondences is used to non-rigidly transform a 2D source image derived from a conformal mapping process on the 3D endoluminal surface mesh. This achieves full surface correspondence between prone and supine views and can be further refined with an intensity based registration showing a statistically significant improvement (p < 0.001), and decreasing mean error from 11.9 mm to 6.0 mm measured at 1743 reference points from 17 CTC datasets.     

Hippocampal volumetry for lateralization of temporal lobe epilepsy: Automated versus manual methods

The hippocampus has been the primary region of interest in the preoperative imaging investigations of mesial temporal lobe epilepsy (mTLE). Hippocampal imaging and electroencephalographic features may be sufficient in several cases to declare the epileptogenic focus. In particular, hippocampal atrophy, as appreciated on T1-weighted (T1W) magnetic resonance (MR) images, may suggest a mesial temporal sclerosis. Qualitative visual assessment of hippocampal volume, however, is influenced by head position in the magnet and the amount of atrophy in different parts of the hippocampus. An entropy-based segmentation algorithm for subcortical brain structures (LocalInfo) was developed and supplemented by both a new multiple atlas strategy and a free-form deformation step to capture structural variability. Manually segmented T1-weighted magnetic resonance (MR) images of 10 non-epileptic subjects were used as atlases for the proposed automatic segmentation protocol which was applied to a cohort of 46 mTLE patients. The segmentation and lateralization accuracies of the proposed technique were compared with those of two other available programs, HAMMER and FreeSurfer, in addition to the manual method. The Dice coefficient for the proposed method was 11% (p < 10^?5) and 14% (p < 10^?4) higher in comparison with the HAMMER and FreeSurfer, respectively. Mean and Hausdorff distances in the proposed method were also 14% (p < 0.2) and 26% (p < 10^?3) lower in comparison with HAMMER and 8% (p < 0.8) and 48% (p < 10^?5) lower in comparison with FreeSurfer, respectively. LocalInfo proved to have higher concordance (87%) with the manual segmentation method than either HAMMER (85%) or FreeSurfer (83%). The accuracy of lateralization by volumetry in this study with LocalInfo was 74% compared to 78% with the manual segmentation method. LocalInfo yields a closer approximation to that of manual segmentation and may therefore prove to be more reliable than currently published automatic segmentation algorithms.     

Chest wall segmentation in automated 3D breast ultrasound scans

In this paper, we present an automatic method to segment the chest wall in automated 3D breast ultrasound images. Determining the location of the chest wall in automated 3D breast ultrasound images is necessary in computer-aided detection systems to remove automatically detected cancer candidates beyond the chest wall and it can be of great help for inter- and intra-modal image registration. We show that the visible part of the chest wall in an automated 3D breast ultrasound image can be accurately modeled by a cylinder. We fit the surface of our cylinder model to a set of automatically detected rib-surface points. The detection of the rib-surface points is done by a classifier using features representing local image intensity patterns and presence of rib shadows. Due to attenuation of the ultrasound signal, a clear shadow is visible behind the ribs. Evaluation of our segmentation method is done by computing the distance of manually annotated rib points to the surface of the automatically detected chest wall. We examined the performance on images obtained with the two most common 3D breast ultrasound devices in the market. In a dataset of 142 images, the average mean distance of the annotated points to the segmented chest wall was 5.59 ± 3.08 mm.     

Optimizing boundary detection via Simulated Search with applications to multi-modal heart segmentation

Segmentation of medical images can be achieved with the help of model-based algorithms. Reliable boundary detection is a crucial component to obtain robust and accurate segmentation results and to enable full automation. This is especially important if the anatomy being segmented is too variable to initialize a mean shape model such that all surface regions are close to the desired contours. Several boundary detection algorithms are widely used in the literature. Most use some trained image appearance model to characterize and detect the desired boundaries. Although parameters of the boundary detection can vary over the model surface and are trained on images, their performance (i.e., accuracy and reliability of boundary detection) can only be assessed as an integral part of the entire segmentation algorithm. In particular, assessment of boundary detection cannot be done locally and independently on model parameterization and internal energies controlling geometric model properties.In this paper, we propose a new method for the local assessment of boundary detection called Simulated Search. This method takes any boundary detection function and evaluates its performance for a single model landmark in terms of an estimated geometric boundary detection error. In consequence, boundary detection can be optimized per landmark during model training. We demonstrate the success of the method for cardiac image segmentation. In particular we show that the Simulated Search improves the capture range and the accuracy of the boundary detection compared to a traditional training scheme. We also illustrate how the Simulated Search can be used to identify suitable classes of features when addressing a new segmentation task. Finally, we show that the Simulated Search enables multi-modal heart segmentation using a single algorithmic framework. On computed tomography and magnetic resonance images, average segmentation errors (surface-to-surface distances) for the four chambers and the trunks of the large vessels are in the order of 0.8 mm. For 3D rotational X-ray angiography images of the left atrium and pulmonary veins, the average error is 1.3 mm. In all modalities, the locally optimized boundary detection enables fully automatic segmentation.     

Patient specific tumor growth prediction using multimodal images

Personalized tumor growth model is valuable in tumor staging and therapy planning. In this paper, we present a patient specific tumor growth model based on longitudinal multimodal imaging data including dual-phase CT and FDG-PET. The proposed Reaction–Advection–Diffusion model is capable of integrating cancerous cell proliferation, infiltration, metabolic rate and extracellular matrix biomechanical response. To bridge the model with multimodal imaging data, we introduce Intracellular Volume Fraction (ICVF) measured from dual-phase CT and Standardized Uptake Value (SUV) measured from FDG-PET into the model. The patient specific model parameters are estimated by fitting the model to the observation, which leads to an inverse problem formalized as a coupled Partial Differential Equations (PDE)-constrained optimization problem. The optimality system is derived and solved by the Finite Difference Method. The model was evaluated by comparing the predicted tumors with the observed tumors in terms of average surface distance (ASD), root mean square difference (RMSD) of the ICVF map, average ICVF difference (AICVFD) of tumor surface and tumor relative volume difference (RVD) on six patients with pathologically confirmed pancreatic neuroendocrine tumors. The ASD between the predicted tumor and the reference tumor was 2.4 ± 0.5 mm, the RMSD was 4.3 ± 0.4%, the AICVFD was 2.6 ± 0.6%, and the RVD was 7.7 ± 1.3%.     

A method of 2D/3D registration of a statistical mouse atlas with a planar X-ray projection and an optical photo

The development of sophisticated and high throughput whole body small animal imaging technologies has created a need for improved image analysis and increased automation. The registration of a digital mouse atlas to individual images is a prerequisite for automated organ segmentation and uptake quantification. This paper presents a fully-automatic method for registering a statistical mouse atlas with individual subjects based on an anterior–posterior X-ray projection and a lateral optical photo of the mouse silhouette. The mouse atlas was trained as a statistical shape model based on 83 organ-segmented micro-CT images. For registration, a hierarchical approach is applied which first registers high contrast organs, and then estimates low contrast organs based on the registered high contrast organs. To register the high contrast organs, a 2D-registration-back-projection strategy is used that deforms the 3D atlas based on the 2D registrations of the atlas projections. For validation, this method was evaluated using 55 subjects of preclinical mouse studies. The results showed that this method can compensate for moderate variations of animal postures and organ anatomy. Two different metrics, the Dice coefficient and the average surface distance, were used to assess the registration accuracy of major organs. The Dice coefficients vary from 0.31 ± 0.16 for the spleen to 0.88 ± 0.03 for the whole body, and the average surface distance varies from 0.54 ± 0.06 mm for the lungs to 0.85 ± 0.10 mm for the skin. The method was compared with a direct 3D deformation optimization (without 2D-registration-back-projection) and a single-subject atlas registration (instead of using the statistical atlas). The comparison revealed that the 2D-registration-back-projection strategy significantly improved the registration accuracy, and the use of the statistical mouse atlas led to more plausible organ shapes than the single-subject atlas. This method was also tested with shoulder xenograft tumor-bearing mice, and the results showed that the registration accuracy of most organs was not significantly affected by the presence of shoulder tumors, except for the lungs and the spleen.     

Segmentation by retrieval with guided random walks: Application to left ventricle segmentation in MRI

In this paper, a new segmentation framework with prior knowledge is proposed and applied to the left ventricles in cardiac Cine MRI sequences. We introduce a new formulation of the random walks method, coined as guided random walks, in which prior knowledge is integrated seamlessly. In comparison with existing approaches that incorporate statistical shape models, our method does not extract any principal model of the shape or appearance of the left ventricle. Instead, segmentation is accompanied by retrieving the closest subject in the database that guides the segmentation the best. Using this techniques, rare cases can also effectively exploit prior knowledge from few samples in training set. These cases are usually disregarded in statistical shape models as they are outnumbered by frequent cases (effect of class population). In the worst-case scenario, if there is no matching case in the database to guide the segmentation, performance of the proposed method reaches to the conventional random walks, which is shown to be accurate if sufficient number of seeds is provided. There is a fast solution to the proposed guided random walks by using sparse linear matrix operations and the whole framework can be seamlessly implemented in a parallel architecture. The method has been validated on a comprehensive clinical dataset of 3D+t short axis MR images of 104 subjects from 5 categories (normal, dilated left ventricle, ventricular hypertrophy, recent myocardial infarction, and heart failure). The average segmentation errors were found to be 1.54 mm for the endocardium and 1.48 mm for the epicardium. The method was validated by measuring different algorithmic and physiologic indices and quantified with manual segmentation ground truths, provided by a cardiologist.     

Tongue contour tracking in dynamic ultrasound via higher-order MRFs and efficient fusion moves

Analyses of the human tongue motion as captured from 2D dynamic ultrasound data often requires segmentation of the mid-sagittal tongue contours. However, semi-automatic extraction of the tongue shape presents practical challenges. We approach this segmentation problem by proposing a novel higher-order Markov random field energy minimization framework. For efficient energy minimization, we propose two novel schemes to sample the solution space efficiently. To cope with the unpredictable tongue motion dynamics, we also propose to temporally adapt regularization based on contextual information. Unlike previous methods, we employ the latest optimization techniques to solve the tracking problem under one unified framework. Our method was validated on a set of 63 clinical data sequences, which allowed for comparative analyses with three other competing methods. Experimental results demonstrate that our method can segment sequences containing over 500 frames with mean accuracy of 3 mm, approaching the accuracy of manual segmentations created by trained clinical observers.     

Comparison of atlas-based techniques for whole-body bone segmentation

We evaluate the accuracy of whole-body bone extraction from whole-body MR images using a number of atlas-based segmentation methods. The motivation behind this work is to find the most promising approach for the purpose of MRI-guided derivation of PET attenuation maps in whole-body PET/MRI. To this end, a variety of atlas-based segmentation strategies commonly used in medical image segmentation and pseudo-CT generation were implemented and evaluated in terms of whole-body bone segmentation accuracy. Bone segmentation was performed on 23 whole-body CT/MR image pairs via leave-one-out cross validation procedure. The evaluated segmentation techniques include: (i) intensity averaging (IA), (ii) majority voting (MV), (iii) global and (iv) local (voxel-wise) weighting atlas fusion frameworks implemented utilizing normalized mutual information (NMI), normalized cross-correlation (NCC) and mean square distance (MSD) as image similarity measures for calculating the weighting factors, along with other atlas-dependent algorithms, such as (v) shape-based averaging (SBA) and (vi) Hofmann's pseudo-CT generation method. The performance evaluation of the different segmentation techniques was carried out in terms of estimating bone extraction accuracy from whole-body MRI using standard metrics, such as Dice similarity (DSC) and relative volume difference (RVD) considering bony structures obtained from intensity thresholding of the reference CT images as the ground truth. Considering the Dice criterion, global weighting atlas fusion methods provided moderate improvement of whole-body bone segmentation (DSC = 0.65 ± 0.05) compared to non-weighted IA (DSC = 0.60 ± 0.02). The local weighed atlas fusion approach using the MSD similarity measure outperformed the other strategies by achieving a DSC of 0.81 ± 0.03 while using the NCC and NMI measures resulted in a DSC of 0.78 ± 0.05 and 0.75 ± 0.04, respectively. Despite very long computation time, the extracted bone obtained from both SBA (DSC = 0.56 ± 0.05) and Hofmann's methods (DSC = 0.60 ± 0.02) exhibited no improvement compared to non-weighted IA. Finding the optimum parameters for implementation of the atlas fusion approach, such as weighting factors and image similarity patch size, have great impact on the performance of atlas-based segmentation approaches. The voxel-wise atlas fusion approach exhibited excellent performance in terms of cancelling out the non-systematic registration errors leading to accurate and reliable segmentation results. Denoising and normalization of MR images together with optimization of the involved parameters play a key role in improving bone extraction accuracy.     

Organ-focused mutual information for nonrigid multimodal registration of liver CT and Gd–EOB–DTPA-enhanced MRI

Accurate detection of liver lesions is of great importance in hepatic surgery planning. Recent studies have shown that the detection rate of liver lesions is significantly higher in gadoxetic acid-enhanced magnetic resonance imaging (Gd–EOB–DTPA-enhanced MRI) than in contrast-enhanced portal-phase computed tomography (CT); however, the latter remains essential because of its high specificity, good performance in estimating liver volumes and better vessel visibility. To characterize liver lesions using both the above image modalities, we propose a multimodal nonrigid registration framework using organ-focused mutual information (OF-MI). This proposal tries to improve mutual information (MI) based registration by adding spatial information, benefiting from the availability of expert liver segmentation in clinical protocols. The incorporation of an additional information channel containing liver segmentation information was studied. A dataset of real clinical images and simulated images was used in the validation process. A Gd–EOB–DTPA-enhanced MRI simulation framework is presented. To evaluate results, warping index errors were calculated for the simulated data, and landmark-based and surface-based errors were calculated for the real data. An improvement of the registration accuracy for OF-MI as compared with MI was found for both simulated and real datasets. Statistical significance of the difference was tested and confirmed in the simulated dataset (p < 0.01).     

A new computationally efficient CAD system for pulmonary nodule detection in CT imagery

Early detection of lung nodules is extremely important for the diagnosis and clinical management of lung cancer. In this paper, a novel computer aided detection (CAD) system for the detection of pulmonary nodules in thoracic computed tomography (CT) imagery is presented. The paper describes the architecture of the CAD system and assesses its performance on a publicly available database to serve as a benchmark for future research efforts. Training and tuning of all modules in our CAD system is done using a separate and independent dataset provided courtesy of the University of Texas Medical Branch (UTMB). The publicly available testing dataset is that created by the Lung Image Database Consortium (LIDC). The LIDC data used here is comprised of 84 CT scans containing 143 nodules ranging from 3 to 30 mm in effective size that are manually segmented at least by one of the four radiologists. The CAD system uses a fully automated lung segmentation algorithm to define the boundaries of the lung regions. It combines intensity thresholding with morphological processing to detect and segment nodule candidates simultaneously. A set of 245 features is computed for each segmented nodule candidate. A sequential forward selection process is used to determine the optimum subset of features for two distinct classifiers, a Fisher Linear Discriminant (FLD) classifier and a quadratic classifier. A performance comparison between the two classifiers is presented, and based on this, the FLD classifier is selected for the CAD system. With an average of 517.5 nodule candidates per case/scan (517.5 ± 72.9), the proposed front-end detector/segmentor is able to detect 92.8% of all the nodules in the LIDC/testing dataset (based on merged ground truth). The mean overlap between the nodule regions delineated by three or more radiologists and the ones segmented by the proposed segmentation algorithm is approximately 63%. Overall, with a specificity of 3 false positives (FPs) per case/patient on average, the CAD system is able to correctly identify 80.4% of the nodules (115/143) using 40 selected features. A 7-fold cross-validation performance analysis using the LIDC database only shows CAD sensitivity of 82.66% with an average of 3 FPs per CT scan/case.     

Computerized identification of airway wall in CT examinations using a 3D active surface evolution approach

Airway diseases (e.g., asthma, emphysema, and chronic bronchitis) are extremely common worldwide. Any morphological variations (abnormalities) of airways may physically change airflow and ultimately affect the ability of the lungs in gas exchange. In this study, we describe a novel algorithm aimed to automatically identify airway walls depicted on CT images. The underlying idea is to place a three-dimensional (3D) surface model within airway regions and thereafter allow this model to evolve (deform) under predefined external and internal forces automatically to the location where these forces reach a state of balance. By taking advantage of the geometric and the density characteristics of airway walls, the evolution procedure is performed in a distance gradient field and ultimately stops at regions with the highest contrast. The performance of this scheme was quantitatively evaluated from several perspectives. First, we assessed the accuracy of the developed scheme using a dedicated lung phantom in airway wall estimation and compared it with the traditional full-width at half maximum (FWHM) method. The phantom study shows that the developed scheme has an error ranging from 0.04 mm to 0.36 mm, which is much smaller than the FWHM method with an error ranging from 0.16 mm to 0.84 mm. Second, we compared the results obtained by the developed scheme with those manually delineated by an experienced (>30 years) radiologist on clinical chest CT examinations, showing a mean difference of 0.084 mm. In particular, the sensitivity of the scheme to different reconstruction kernels was evaluated on real chest CT examinations. For the ‘lung’, ‘bone’ and ‘standard’ kernels, the average airway wall thicknesses computed by the developed scheme were 1.302 mm, 1.333 mm and 1.339 mm, respectively. Our preliminary experiments showed that the scheme had a reasonable accuracy in airway wall estimation. For a clinical chest CT examination, it took around 4 min for this scheme to identify the inner and outer airway walls on a modern PC.     

Head and neck tumor segmentation in PET/CT: The HECKTOR challenge

This paper relates the post-analysis of the first edition of the HEad and neCK TumOR (HECKTOR) challenge. This challenge was held as a satellite event of the 23rd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2020, and was the first of its kind focusing on lesion segmentation in combined FDG-PET and CT image modalities. The challenge’s task is the automatic segmentation of the Gross Tumor Volume (GTV) of Head and Neck (H&N) oropharyngeal primary tumors in FDG-PET/CT images. To this end, the participants were given a training set of 201 cases from four different centers and their methods were tested on a held-out set of 53 cases from a fifth center. The methods were ranked according to the Dice Score Coefficient (DSC) averaged across all test cases. An additional inter-observer agreement study was organized to assess the difficulty of the task from a human perspective. 64 teams registered to the challenge, among which 10 provided a paper detailing their approach. The best method obtained an average DSC of 0.7591, showing a large improvement over our proposed baseline method and the inter-observer agreement, associated with DSCs of 0.6610 and 0.61, respectively. The automatic methods proved to successfully leverage the wealth of metabolic and structural properties of combined PET and CT modalities, significantly outperforming human inter-observer agreement level, semi-automatic thresholding based on PET images as well as other single modality-based methods. This promising performance is one step forward towards large-scale radiomics studies in H&N cancer, obviating the need for error-prone and time-consuming manual delineation of GTVs.     

Individual nodule tracking in micro-CT images of a longitudinal lung cancer mouse model

We present and evaluate an automatic and quantitative method for the complex task of characterizing individual nodule volumetric progression in a longitudinal mouse model of lung cancer. Fourteen A/J mice received an intraperitoneal injection of urethane. Respiratory-gated micro-CT images of the lungs were acquired at 8, 22, and 37 weeks after injection. A radiologist identified a total of 196, 585 and 636 nodules, respectively. The three micro-CT image volumes from every animal were then registered and the nodules automatically matched with an average accuracy of 99.5%. All nodules detected at week 8 were tracked all the way to week 37, and volumetrically segmented to measure their growth and doubling rates. 92.5% of all nodules were correctly segmented, ranging from the earliest stage to advanced stage, where nodule segmentation becomes more challenging due to complex anatomy and nodule overlap. Volume segmentation was validated using a foam lung phantom with embedded polyethylene microspheres. We also correlated growth rates with nodule phenotypes based on histology, to conclude that the growth rate of malignant tumors is significantly higher than that of benign lesions. In conclusion, we present a turnkey solution that combines longitudinal imaging with nodule matching and volumetric nodule segmentation resulting in a powerful tool for preclinical research.     

Fast and robust multi-atlas segmentation of brain magnetic resonance images

We introduce an optimised pipeline for multi-atlas brain MRI segmentation. Both accuracy and speed of segmentation are considered. We study different similarity measures used in non-rigid registration. We show that intensity differences for intensity normalised images can be used instead of standard normalised mutual information in registration without compromising the accuracy but leading to threefold decrease in the computation time. We study and validate also different methods for atlas selection. Finally, we propose two new approaches for combining multi-atlas segmentation and intensity modelling based on segmentation using expectation maximisation (EM) and optimisation via graph cuts. The segmentation pipeline is evaluated with two data cohorts: IBSR data (N = 18, six subcortial structures: thalamus, caudate, putamen, pallidum, hippocampus, amygdala) and ADNI data (N =   60, hippocampus). The average similarity index between automatically and manually generated volumes was 0.849 (IBSR, six subcortical structures) and 0.880 (ADNI, hippocampus). The correlation coefficient for hippocampal volumes was 0.95 with the ADNI data. The computation time using a standard multicore PC computer was about 3–4 min. Our results compare favourably with other recently published results.