Geometrical methods for level set based abdominal aortic aneurysm thrombus and outer wall 2D image segmentation

A semi-automatic segmentation method for meningioma developed using a variational approach model

BACKGROUND

Meningioma is the commonest primary brain tumour. Volumetric post-contrast magnetic resonance imaging (MRI) is recognised as gold standard for delineation of meningioma volume but is hindered by manual processing times. We aimed to investigate the utility of a model-based variational approach in segmenting meningioma.

METHODS

A database of patients with a meningioma (2007-2015) was queried for patients with a contrast-enhanced volumetric MRI, who had consented to a research tissue biobank. Manual segmentation by a neuroradiologist was performed and results were compared to the mathematical model, using a battery of tests including the Sørensen-Dice coefficient (DICE) and JACCARD index. A publicly available meningioma dataset (708 segmented T1 contrast-enhanced slices) was also used to test the reliability of the model.

RESULTS

49 meningioma cases were included. The most common meningioma location was convexity (n = 15, 30.6%). The mathematical model segmented all but one incidental meningioma, which failed due to the lack of contrast uptake. The median meningioma volume by manual segmentation was 19.0 cm3 (IQR 4.9-31.2). The median meningioma volume using the mathematical model was 16.9 cm3 (IQR 4.6-28.34). The mean DICE score was 0.90 (SD = 0.04). The mean JACCARD index was 0.82 (SD = 0.07). For the publicly available dataset, the mean DICE and JACCARD scores were 0.90 (SD = 0.06) and 0.82 (SD = 0.10), respectively.

CONCLUSIONS

Segmentation of meningioma volume using the proposed mathematical model was possible with accurate results. Application of this model on contrast-enhanced volumetric imaging may help reduce work burden on neuroradiologists with the increasing number in meningioma diagnoses.

Deep-learning-based image segmentation for image-based computational hemodynamic analysis of abdominal aortic aneurysms: a comparison study

Computational hemodynamics is increasingly being used to quantify hemodynamic characteristics in and around abdominal aortic aneurysms (AAA) in a patient-specific fashion. However, the time-consuming manual annotation hinders the clinical translation of computational hemodynamic analysis. Thus, we investigate the feasibility of using deep-learning-based image segmentation methods to reduce the time required for manual segmentation. Two of the latest deep-learning-based image segmentation methods, ARU-Net and CACU-Net, were used to test the feasibility of automated computer model creation for computational hemodynamic analysis. Morphological features and hemodynamic metrics of 30 computed tomography angiography (CTA) scans were compared between pre-dictions and manual models. The DICE score for both networks was 0.916, and the correlation value was above 0.95, indicating their ability to generate models comparable to human segmentation. The Bland-Altman analysis shows a good agreement between deep learning and manual segmentation results. Compared with manual (computational hemodynamics) model recreation, the time for automated computer model generation was significantly reduced (from ∼2 h to ∼10 min). Automated image segmentation can significantly reduce time expenses on the recreation of patient-specific AAA models. Moreover, our study showed that both CACU-Net and ARU-Net could accomplish AAA segmentation, and CACU-Net outperformed ARU-Net in terms of accuracy and time-saving.

Automated Intracranial Clot Detection: A Promising Tool for Vascular Occlusion Detection in Non-Enhanced CT

(1) Background: to test the diagnostic performance of a fully convolutional neural network-based software prototype for clot detection in intracranial arteries using non-enhanced computed tomography (NECT) imaging data. (2) Methods: we retrospectively identified 85 patients with stroke imaging and one intracranial vessel occlusion. An automated clot detection prototype computed clot location, clot length, and clot volume in NECT scans. Clot detection rates were compared to the visual assessment of the hyperdense artery sign by two neuroradiologists. CT angiography (CTA) was used as the ground truth. Additionally, NIHSS, ASPECTS, type of therapy, and TOAST were registered to assess the relationship between clinical parameters, image results, and chosen therapy. (3) Results: the overall detection rate of the software was 66%, while the human readers had lower rates of 46% and 24%, respectively. Clot detection rates of the automated software were best in the proximal middle cerebral artery (MCA) and the intracranial carotid artery (ICA) with 88-92% followed by the more distal MCA and basilar artery with 67-69%. There was a high correlation between greater clot length and interventional thrombectomy and between smaller clot length and rather conservative treatment. (4) Conclusions: the automated clot detection prototype has the potential to detect intracranial arterial thromboembolism in NECT images, particularly in the ICA and MCA. Thus, it could support radiologists in emergency settings to speed up the diagnosis of acute ischemic stroke, especially in settings where CTA is not available.

Machine learning and image analysis in vascular surgery

Deep learning, a subset of machine learning within artificial intelligence, has been successful in medical image analysis in vascular surgery. Unlike traditional computer-based segmentation methods that manually extract features from input images, deep learning methods learn image features and classify data without making prior assumptions. Convolutional neural networks, the main type of deep learning for computer vision processing, are neural networks with multilevel architecture and weighted connections between nodes that can "auto-learn" through repeated exposure to training data without manual input or supervision. These networks have numerous applications in vascular surgery imaging analysis, particularly in disease classification, object identification, semantic segmentation, and instance segmentation. The purpose of this review article was to review the relevant concepts of machine learning image analysis and its application to the field of vascular surgery.

Deep-learning method for fully automatic segmentation of the abdominal aortic aneurysm from computed tomography imaging

Abdominal aortic aneurysm (AAA) is one of the leading causes of death worldwide. AAAs often remain asymptomatic until they are either close to rupturing or they cause pressure to the spine and/or other organs. Fast progression has been linked to future clinical outcomes. Therefore, a reliable and efficient system to quantify geometric properties and growth will enable better clinical prognoses for aneurysms. Different imaging systems can be used to locate and characterize an aneurysm; computed tomography (CT) is the modality of choice in many clinical centers to monitor later stages of the disease and plan surgical treatment. The lack of accurate and automated techniques to segment the outer wall and lumen of the aneurysm results in either simplified measurements that focus on few salient features or time-consuming segmentation affected by high inter- and intra-operator variability. To overcome these limitations, we propose a model for segmenting AAA tissues automatically by using a trained deep learning-based approach. The model is composed of three different steps starting with the extraction of the aorta and iliac arteries followed by the detection of the lumen and other AAA tissues. The results of the automated segmentation demonstrate very good agreement when compared to manual segmentation performed by an expert.

Evaluation of a hybrid pipeline for automated segmentation of solid lesions based on mathematical algorithms and deep learning

We evaluate the accuracy of an original hybrid segmentation pipeline, combining variational and deep learning methods, in the segmentation of CT scans of stented aortic aneurysms, abdominal organs and brain lesions. The hybrid pipeline is trained on 50 aortic CT scans and tested on 10. Additionally, we trained and tested the hybrid pipeline on publicly available datasets of CT scans of abdominal organs and MR scans of brain tumours. We tested the accuracy of the hybrid pipeline against a gold standard (manual segmentation) and compared its performance to that of a standard automated segmentation method with commonly used metrics, including the DICE and JACCARD and volumetric similarity (VS) coefficients, and the Hausdorff Distance (HD). Results. The hybrid pipeline produced very accurate segmentations of the aorta, with mean DICE, JACCARD and VS coefficients of: 0.909, 0.837 and 0.972 in thrombus segmentation and 0.937, 0.884 and 0.970 for stent and lumen segmentation. It consistently outperformed the standard automated method. Similar results were observed when the hybrid pipeline was trained and tested on publicly available datasets, with mean DICE scores of: 0.832 on brain tumour segmentation, and 0.894/0.841/0.853/0.847/0.941 on left kidney/right kidney/spleen/aorta/liver organ segmentation.

Automatic Detection and Segmentation of Thrombi in Abdominal Aortic Aneurysms Using a Mask Region-Based Convolutional Neural Network with Optimized Loss Functions

The detection and segmentation of thrombi are essential for monitoring the disease progression of abdominal aortic aneurysms (AAAs) and for patient care and management. As they have inherent capabilities to learn complex features, deep convolutional neural networks (CNNs) have been recently introduced to improve thrombus detection and segmentation. However, investigations into the use of CNN methods is in the early stages and most of the existing methods are heavily concerned with the segmentation of thrombi, which only works after they have been detected. In this work, we propose a fully automated method for the whole process of the detection and segmentation of thrombi, which is based on a well-established mask region-based convolutional neural network (Mask R-CNN) framework that we improve with optimized loss functions. The combined use of complete intersection over union (CIoU) and smooth L1 loss was designed for accurate thrombus detection and then thrombus segmentation was improved with a modified focal loss. We evaluated our method against 60 clinically approved patient studies (i.e., computed tomography angiography (CTA) image volume data) by conducting 4-fold cross-validation. The results of comparisons to multiple other state-of-the-art methods suggested the superior performance of our method, which achieved the highest F1 score for thrombus detection (0.9197) and outperformed most metrics for thrombus segmentation.

Development and Comparison of Multimodal Models for Preoperative Prediction of Outcomes After Endovascular Aneurysm Repair

Objective

The aim of this study was to develop and compare multimodal models for predicting outcomes after endovascular abdominal aortic aneurysm repair (EVAR) based on morphological, deep learning (DL), and radiomic features.

Methods

We retrospectively reviewed 979 patients (January 2010—December 2019) with infrarenal abdominal aortic aneurysms (AAAs) who underwent elective EVAR procedures. A total of 486 patients (January 2010–December 2015) were used for morphological feature model development and optimization. Univariable and multivariable analyses were conducted to determine significant morphological features of EVAR-related severe adverse events (SAEs) and to build a morphological feature model based on different machine learning algorithms. Subsequently, to develop the morphological feature model more easily and better compare with other modal models, 340 patients of AAA with intraluminal thrombosis (ILT) were used for automatic segmentation of ILT based on deep convolutional neural networks (DCNNs). Notably, 493 patients (January 2016–December 2019) were used for the development and comparison of multimodal models (optimized morphological feature, DL, and radiomic models). Of note, 80% of patients were classified as the training set and 20% of patients were classified as the test set. The area under the curve (AUC) was used to evaluate the predictive abilities of different modal models.

Results

The mean age of the patients was 69.9 years, the mean follow-up was 54 months, and 307 (31.4%) patients experienced SAEs. Statistical analysis revealed that short neck, angulated neck, conical neck, ILT, ILT percentage ≥51.6%, luminal calcification, double iliac sign, and common iliac artery index ≥1.255 were associated with SAEs. The morphological feature model based on the support vector machine had a better predictive performance with an AUC of 0.76, an accuracy of 0.76, and an F1 score of 0.82. Our DCNN model achieved a mean intersection over union score of more than 90.78% for the segmentation of ILT and AAA aortic lumen. The multimodal model result showed that the radiomic model based on logistics regression had better predictive performance (AUC 0.93, accuracy 0.86, and F1 score 0.91) than the optimized morphological feature model (AUC 0.62, accuracy 0.69, and F1 score 0.81) and the DL model (AUC 0.82, accuracy 0.85, and F1 score 0.89).

Conclusion

The radiomic model has better predictive performance for patient status after EVAR. The morphological feature model and DL model have their own advantages and could also be used to predict outcomes after EVAR.

Fully automatic segmentation of abdominal aortic thrombus in pre-operative CTA images using deep convolutional neural networks

BACKGROUND

Endovascular aortic aneurysm repair (EVAR) is currently established as the first-line treatment for anatomically suitable abdominal aortic aneurysm (AAA).

OBJECTIVE

To establish a deep convolutional neural networks (DCNN) model for fully automatic segmentation intraluminal thrombosis (ILT) of abdominal aortic aneurysm (AAA) in pre-operative computed tomography angiography (CTA) images.

METHODS

We retrospectively reviewed 340 patients of AAA with ILT at our single center. The software ITKSNAP was used to draw AAA and ILT region of interests (ROIs), respectively. Image preprocessing and DCNN model build using MATLAB. Randomly divided, 80% of patients was classified as training set, 20% of patients was classified as test set. Accuracy, intersection over union (IOU), Boundary F1 (BF) Score were used to evaluate the predictive effect of the model.

RESULTS

By training in 34760-35652 CTA images (n= 204) and validation in 6968-7860 CTA images (n=68), the DCNN model achieved encouraging predictive performance in test set (n= 68, 6898 slices): Global accuracy 0.9988 ± 5.7735E-05, mean accuracy 0.9546 ± 0.0054, ILT IOU 0.8650 ± 0.0033, aortic lumen IOU 0.8595 ± 0.0085, ILT weighted IOU 0.9976 ± 0.0001, mean IOU 0.9078 ± 0.0029, mean BF Score 0.9829 ± 0.0011. Our DCNN model achieved a mean IOU of more than 90.78% for segmentation of ILT and aortic lumen. It provides a mean relative volume difference between automatic segmentation and ground truth (P> 0.05).

CONCLUSION

An end-to-end DCNN model could be used as an efficient and adjunctive tool for fully automatic segmentation of abdominal aortic thrombus in pre-operative CTA image.

Automated Segmentation of the Human Abdominal Vascular System Using a Hybrid Approach Combining Expert System and Supervised Deep Learning

Background: Computed tomography angiography (CTA) is one of the most commonly used imaging technique for the management of vascular diseases. Here, we aimed to develop a hybrid method combining a feature-based expert system with a supervised deep learning (DL) algorithm to enable a fully automatic segmentation of the abdominal vascular tree. Methods: We proposed an algorithm based on the hybridization of a data-driven convolutional neural network and a knowledge-based model dedicated to vascular system segmentation. By using two distinct datasets of CTA from patients to evaluate independence to training dataset, the accuracy of the hybrid method for lumen and thrombus segmentation was evaluated compared to the feature-based expert system alone and to the ground truth provided by a human expert. Results: The hybrid approach demonstrated a better accuracy for lumen segmentation compared to the expert system alone (volume similarity: 0.8128 vs. 0.7912, p = 0.0006 and Dice similarity coefficient: 0.8266 vs. 0.7942, p < 0.0001). The accuracy for thrombus segmentation was also enhanced using the hybrid approach (volume similarity: 0.9404 vs. 0.9185, p = 0.0027 and Dice similarity coefficient: 0.8918 vs. 0.8654, p < 0.0001). Conclusions: By enabling a robust and fully automatic segmentation, the method could be used to develop real-time decision support to help in the management of vascular diseases.

Artificial intelligence in abdominal aortic aneurysm

OBJECTIVE

Abdominal aortic aneurysm (AAA) is a life-threatening disease, and the only curative treatment relies on open or endovascular repair. The decision to treat relies on the evaluation of the risk of AAA growth and rupture, which can be difficult to assess in practice. Artificial intelligence (AI) has revealed new insights into the management of cardiovascular diseases, but its application in AAA has so far been poorly described. The aim of this review was to summarize the current knowledge on the potential applications of AI in patients with AAA.

METHODS

A comprehensive literature review was performed. The MEDLINE database was searched according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The search strategy used a combination of keywords and included studies using AI in patients with AAA published between May 2019 and January 2000. Two authors independently screened titles and abstracts and performed data extraction. The search of published literature identified 34 studies with distinct methodologies, aims, and study designs.

RESULTS

AI was used in patients with AAA to improve image segmentation and for quantitative analysis and characterization of AAA morphology, geometry, and fluid dynamics. AI allowed computation of large data sets to identify patterns that may be predictive of AAA growth and rupture. Several predictive and prognostic programs were also developed to assess patients' postoperative outcomes, including mortality and complications after endovascular aneurysm repair.

CONCLUSIONS

AI represents a useful tool in the interpretation and analysis of AAA imaging by enabling automatic quantitative measurements and morphologic characterization. It could be used to help surgeons in preoperative planning. AI-driven data management may lead to the development of computational programs for the prediction of AAA evolution and risk of rupture as well as postoperative outcomes. AI could also be used to better evaluate the indications and types of surgical treatment and to plan the postoperative follow-up. AI represents an attractive tool for decision-making and may facilitate development of personalized therapeutic approaches for patients with AAA.

Abdominal Aortic Aneurysm Segmentation Using Convolutional Neural Networks Trained with Images Generated with a Synthetic Shape Model

An abdominal aortic aneurysm (AAA) is a ballooning of the abdominal aorta, that if not treated tends to grow and rupture. Computed Tomography Angiography (CTA) is the main imaging modality for the management of AAAs, and segmenting them is essential for AAA rupture risk and disease progression assessment. Previous works have shown that Convolutional Neural Networks (CNNs) can accurately segment AAAs, but have the limitation of requiring large amounts of annotated data to train the networks. Thus, in this work we propose a methodology to train a CNN only with images generated with a synthetic shape model, and test its generalization and ability to segment AAAs from new original CTA scans. The synthetic images are created from realistic deformations generated by applying principal component analysis to the deformation fields obtained from the registration of few datasets. The results show that the performance of a CNN trained with synthetic data to segment AAAs from new scans is comparable to the one of a network trained with real images. This suggests that the proposed methodology may be applied to generate images and train a CNN to segment other types of aneurysms, reducing the burden of obtaining large annotated image databases.

3D segmentation of exterior wall surface of abdominal aortic aneurysm from CT images using variable neighborhood search

A 3D model of abdominal aortic aneurysm (AAA) can provide useful anatomical information for clinical management and simulation. Thin-slice contiguous computed tomographic (CT) angiography is the best source of medical images for construction of 3D models, which requires segmentation of AAA in the images. Existing methods for segmentation of AAA rely on either manual process or 2D segmentation in each 2D CT slide. However, a traditional manual segmentation is a time consuming process which is not practical for routine use. The construction of a 3D model from 2D segmentation of each CT slice is not a fully satisfactory solution due to rough contours that can occur because of lack of constraints among segmented slices, as well as missed segmentation slices. To overcome such challenges, this paper proposes the 3D segmentation of AAA using the concept of variable neighborhood search by iteratively alternating between two different segmentation techniques in the two different 3D search spaces of voxel intensity and voxel gradient. The segmentation output of each method is used as the initial contour to the other method in each iteration. By alternating between search spaces, the technique can escape local minima that naturally occur in each search space. Also, the 3D search spaces provide more constraints across CT slices, when compared with the 2D search spaces in individual CT slices. The proposed method is evaluated with 10 easy and 10 difficult cases of AAA. The results show that the proposed 3D segmentation technique achieves the outstanding segmentation accuracy with an average dice similarity value (DSC) of 91.88%, when compared to the other methods using the same dataset, which are the 2D proposed method, classical graph cut, distance regularized level set evolution, and registration based geometric active contour with the DSCs of 87.57 ± 4.52%, 72.47 ± 8.11%, 58.50 ± 8.86% and 76.21 ± 10.49%, respectively.

Generic thrombus segmentation from pre- and post-operative CTA

PURPOSE

Abdominal aortic aneurysm (AAA) is a localized, permanent and irreversible enlargement of the artery, with the formation of thrombus into the inner wall of the aneurysm. A precise patient-specific segmentation of the thrombus is useful for both the pre-operative planning to estimate the rupture risk, and for post-operative assessment to monitor the disease evolution. This paper presents a generic approach for 3D segmentation of thrombus from patients suffering from AAA using computed tomography angiography (CTA) scans.

METHODS

A fast and versatile thrombus segmentation approach has been developed. It is composed of initial centerline detection and aorta lumen segmentation, an optimized pre-processing stage and the use of a 3D deformable model. The approach has been designed to be very generic and requires minimal user interaction. The proposed method was tested on different datasets with 145 patients overall, including pre- and post-operative CTAs, abdominal aorta and iliac artery sections, different calcification degrees, aneurysm sizes and contrast enhancement qualities.

RESULTS

The thrombus segmentation approach showed very accurate results with respect to manual delineations for all datasets ([Formula: see text] and [Formula: see text] for abdominal aorta sections on pre-operative CTA, iliac artery sections on pre-operative CTAs and aorta sections on post-operative CTA, respectively). Experiments on the different patient and image conditions showed that the method was highly versatile, with no significant differences in term of precision. Comparison with the level-set algorithm also demonstrated the superiority of the 3D deformable model. Average processing time was [Formula: see text].

CONCLUSION

We presented a near-automatic and generic thrombus segmentation algorithm applicable to a large variability of patient and imaging conditions. When integrated in an endovascular planning system, our segmentation algorithm shows its compatibility with clinical routine and could be used for pre-operative planning and post-operative assessment of endovascular procedures.

Quantitative Aortic Distensibility Measurement Using CT in Patients with Abdominal Aortic Aneurysm: Reproducibility and Clinical Relevance

Purpose. To investigate the reproducibility of aortic distensibility (D) measurement using CT and assess its clinical relevance in patients with infrarenal abdominal aortic aneurysm (AAA). Methods. 54 patients with infrarenal abdominal aortic aneurysm were studied to determine their distensibility by using 64-MDCT. Aortic cross-sectional area changes were determined at two positions of the aorta, immediately below the lowest renal artery (level 1.) and at the level of its maximal diameter (level 2.) by semiautomatic segmentation. Measurement reproducibility was assessed using intraclass correlation coefficient (ICC) and Bland-Altman analyses. Stepwise multiple regression analysis was performed to assess linear associations between aortic D and anthropometric and biochemical parameters. Results. A mean distensibility of D_{level  1.} = (1.05 ± 0.22) × 10⁻⁵  Pa⁻¹ and D_{level  2.} = (0.49 ± 0.18) × 10⁻⁵  Pa⁻¹ was found. ICC proved excellent consistency between readers over two locations: 0.92 for intraobserver and 0.89 for interobserver difference in level 1. and 0.85 and 0.79 in level 2. Multivariate analysis of all these variables showed sac distensibility to be independently related (R² = 0.68) to BMI, diastolic blood pressure, and AAA diameter. Conclusions. Aortic distensibility measurement in patients with AAA demonstrated high inter- and intraobserver agreement and may be valuable when choosing the optimal dimensions graft for AAA before endovascular aneurysm repair.

Biomechanical Indices for Rupture Risk Estimation in Abdominal Aortic Aneurysms

PURPOSE

To review the use of biomechanical indices for the estimation of abdominal aortic aneurysm (AAA) rupture risk, emphasizing their potential use in a clinical setting.

METHODS

A search of the PubMed, Embase, Scopus, and Compendex databases was made up to June 2015 to identify articles involving biomechanical analysis of AAA rupture risk. Outcome variables [aneurysm diameter, peak wall stress (PWS), peak wall shear stress (PWSS), wall strain, peak wall rupture index (PWRI), and wall stiffness] were compared for asymptomatic intact AAAs vs symptomatic or ruptured AAAs. For quantitative analysis of the pooled data, a random effects model was used to calculate the standard mean differences (SMDs) with the 95% confidence interval (CI) for the biomechanical indices.

RESULTS

The initial database searches yielded 1894 independent articles of which 19 were included in the analysis. The PWS was significantly higher in the symptomatic/ruptured group, with a SMD of 1.11 (95% CI 0.93 to 1.26, p<0.001). Likewise, the PWRI was significantly higher in the ruptured or symptomatic group, with a SMD of 1.15 (95% CI 0.30 to 2.01, p=0.008). After adjustment for the aneurysm diameter, the PWS remained higher in the ruptured or symptomatic group, with a SMD of 0.85 (95% CI 0.46 to 1.23, p<0.001). Less is known of the wall shear stress and wall strain indices, as too few studies were available for analysis.

CONCLUSION

Biomechanical indices are a promising tool in the assessment of AAA rupture risk as they incorporate several factors, including geometry, tissue properties, and patient-specific risk factors. However, clinical implementation of biomechanical AAA assessment remains a challenge owing to a lack of standardization.

Alveolar bone-loss area localization in periodontitis radiographs based on threshold segmentation with a hybrid feature fused of intensity and the H-value of fractional Brownian motion model

BACKGROUND AND OBJECTIVE

Periodontitis involves progressive loss of alveolar bone around the teeth. Hence, automatic alveolar bone-loss (ABL) measurement in periapical radiographs can assist dentists in diagnosing such disease. In this paper, we propose an effective method for ABL area localization and denote it as ABLIfBm.

METHOD

ABLIfBm is a threshold segmentation method that uses a hybrid feature fused of both intensity and texture measured by the H-value of fractional Brownian motion (fBm) model, where the H-value is the Hurst coefficient in the expectation function of a fBm curve (intensity change) and is directly related to the value of fractal dimension. Adopting leave-one-out cross validation training and testing mechanism, ABLIfBm trains weights for both features using Bayesian classifier and transforms the radiograph image into a feature image obtained from a weighted average of both features. Finally, by Otsu's thresholding, it segments the feature image into normal and bone-loss regions.

RESULTS

Experimental results on 31 periodontitis radiograph images in terms of mean true positive fraction and false positive fraction are about 92.5% and 14.0%, respectively, where the ground truth is provided by a dentist. The results also demonstrate that ABLIfBm outperforms (a) the threshold segmentation method using either feature alone or a weighted average of the same two features but with weights trained differently; (b) a level set segmentation method presented earlier in literature; and (c) segmentation methods based on Bayesian, K-NN, or SVM classifier using the same two features.

CONCLUSION

Our results suggest that the proposed method can effectively localize alveolar bone-loss areas in periodontitis radiograph images and hence would be useful for dentists in evaluating degree of bone-loss for periodontitis patients.

Automated Delineation of Vessel Wall and Thrombus Boundaries of Abdominal Aortic Aneurysms Using Multispectral MR Images

A correct patient-specific identification of the abdominal aortic aneurysm is useful for both diagnosis and treatment stages, as it locates the disease and represents its geometry. The actual thickness and shape of the arterial wall and the intraluminal thrombus are of great importance when predicting the rupture of the abdominal aortic aneurysms. The authors describe a novel method for delineating both the internal and external contours of the aortic wall, which allows distinguishing between vessel wall and intraluminal thrombus. The method is based on active shape model and texture statistical information. The method was validated with eight MR patient studies. There was high correspondence between automatic and manual measurements for the vessel wall area. Resulting segmented images presented a mean Dice coefficient with respect to manual segmentations of 0.88 and a mean modified Hausdorff distance of 1.14 mm for the internal face and 0.86 and 1.33 mm for the external face of the arterial wall. Preliminary results of the segmentation show high correspondence between automatic and manual measurements for the vessel wall and thrombus areas. However, since the dataset is small the conclusions cannot be generalized.

Automatic classification of left ventricular wall segments in small animal ultrasound imaging

Multiple statistics show that heart diseases are one of the main causes of mortality in our highly developed societies today. These diseases lead to a change of the physiology of the heart, which gives useful information about characteristic and severity of the defect. A fast and reliable diagnosis is the base for successful therapy. As a first step towards recognition of such heart remodeling processes, this work proposes a fully automatic processing pipeline for regional classification of the left ventricular wall in ultrasound images of small animals. The pipeline is based on state-of-the-art methods from computer vision and pattern classification. The myocardial wall is segmented and its motion is estimated. A feature extraction using the segmented data is realized to automatically classify the image regions into normal and abnormal myocardial tissue. The performance of the proposed pipeline is evaluated and a comparison of common classification algorithms on ultrasound data of living mice before and after artificially induced myocardial infarction is given. It is shown that the results of this work, reaching a maximum accuracy of 91.46%, are an encouraging base for further investigation.

A novel method for pulmonary embolism detection in CTA images

In this paper, we propose a new computer-aided detection (CAD) - based method to detect pulmonary embolism (PE) in computed tomography angiography images (CTAI). Since lung vessel segmentation is the main objective to provide high sensitivity in PE detection, this method performs accurate lung vessel segmentation. To concatenate clogged vessels due to PEs, the starting region of PEs and some reference points (RPs) are determined. These RPs are detected according to the fixed anatomical structures. After lung vessel tree is segmented, the region, intensity, and size of PEs are used to distinguish them. We used the data sets that have heart disease or abnormal tissues because of lung disease except PE in this work. According to the results, 428 of 450 PEs, labeled by the radiologists from 33 patients, have been detected. The sensitivity of the developed system is 95.1% at 14.4 false positive per data set (FP/ds). With this performance, the proposed CAD system is found quite useful to use as a second reader by the radiologists.

A marker-based watershed method for X-ray image segmentation

Digital X-ray images are the most frequent modality for both screening and diagnosis in hospitals. To facilitate subsequent analysis such as quantification and computer aided diagnosis (CAD), it is desirable to exclude image background. A marker-based watershed segmentation method was proposed to segment background of X-ray images. The method consisted of six modules: image preprocessing, gradient computation, marker extraction, watershed segmentation from markers, region merging and background extraction. One hundred clinical direct radiograph X-ray images were used to validate the method. Manual thresholding and multiscale gradient based watershed method were implemented for comparison. The proposed method yielded a dice coefficient of 0.964±0.069, which was better than that of the manual thresholding (0.937±0.119) and that of multiscale gradient based watershed method (0.942±0.098). Special means were adopted to decrease the computational cost, including getting rid of few pixels with highest grayscale via percentile, calculation of gradient magnitude through simple operations, decreasing the number of markers by appropriate thresholding, and merging regions based on simple grayscale statistics. As a result, the processing time was at most 6s even for a 3072×3072 image on a Pentium 4 PC with 2.4GHz CPU (4 cores) and 2G RAM, which was more than one time faster than that of the multiscale gradient based watershed method. The proposed method could be a potential tool for diagnosis and quantification of X-ray images.

A hybrid semi-automatic method for liver segmentation based on level-set methods using multiple seed points

The present study developed a hybrid semi-automatic method to extract the liver from abdominal computerized tomography (CT) images. The proposed hybrid method consists of a customized fast-marching level-set method for detection of an optimal initial liver region from multiple seed points selected by the user and a threshold-based level-set method for extraction of the actual liver region based on the initial liver region. The performance of the hybrid method was compared with those of the 2D region growing method implemented in OsiriX using abdominal CT datasets of 15 patients. The hybrid method showed a significantly higher accuracy in liver extraction (similarity index, SI=97.6 ± 0.5%; false positive error, FPE = 2.2 ± 0.7%; false negative error, FNE=2.5 ± 0.8%; average symmetric surface distance, ASD=1.4 ± 0.5mm) than the 2D (SI=94.0 ± 1.9%; FPE = 5.3 ± 1.1%; FNE=6.5 ± 3.7%; ASD=6.7 ± 3.8mm) region growing method. The total liver extraction time per CT dataset of the hybrid method (77 ± 10 s) is significantly less than the 2D region growing method (575 ± 136 s). The interaction time per CT dataset between the user and a computer of the hybrid method (28 ± 4 s) is significantly shorter than the 2D region growing method (484 ± 126 s). The proposed hybrid method was found preferred for liver segmentation in preoperative virtual liver surgery planning.