Manual Segmentation Approach Research Articles

Training and assessing convolutional neural network performance in automatic vascular segmentation using Ga-68 DOTATATE PET/CT

To evaluate a convolutional neural network’s performance (nnU-Net) in the assessment of vascular contours, calcification and PET tracer activity using Ga-68 DOTATATE PET/CT. Patients who underwent Ga-68 DOTATATE PET/CT imaging over a 12-month period for neuroendocrine investigation were included. Manual cardiac and aortic segmentations were performed by an experienced observer. Scans were randomly allocated in ratio 64:16:20 for training, validation and testing of the nnU-Net model. PET tracer uptake and calcium scoring were compared between segmentation methods and different observers. 116 patients (53.5% female) with a median age of 64.5 years (range 23–79) were included. There were strong, positive correlations between all segmentations (mostly r > 0.98). There were no significant differences between manual and AI segmentation of SUVmean for global cardiac (mean ± SD 0.71 ± 0.22 vs. 0.71 ± 0.22; mean diff 0.001 ± 0.008, p > 0.05), ascending aorta (mean ± SD 0.44 ± 0.14 vs. 0.44 ± 0.14; mean diff 0.002 ± 0.01, p > 0.05), aortic arch (mean ± SD 0.44 ± 0.10 vs. 0.43 ± 0.10; mean diff 0.008 ± 0.16, p > 0.05) and descending aorta (mean ± SD < 0.001; 0.58 ± 0.12 vs. 0.57 ± 0.12; mean diff 0.01 ± 0.03, p > 0.05) contours. There was excellent agreement between the majority of manual and AI segmentation measures (r ≥ 0.80) and in all vascular contour calcium scores. Compared with the manual segmentation approach, the CNN required a significantly lower workflow time. AI segmentation of vascular contours using nnU-Net resulted in very similar measures of PET tracer uptake and vascular calcification when compared to an experienced observer and significantly reduced workflow time.

Volumetric evaluation of osteotomy gap following mandibular bilateral sagittal split osteotomy using a novel semi-automated approach: a pilot study

ObjectivesTo establish an analysis pipeline for the volumetric evaluation of the osteotomy site after bilateral sagittal split osteotomy (BSSO).Patients and methodsCone-beam computed tomography (CBCT) was performed before, directly after BSSO, and 6–12 months after surgery. Image segmentations of each osteotomy gap data set were performed manually by four physicians and were compared to a semi-automatic segmentation approach.ResultsFive patients with a total of ten osteotomy gaps were included. The mean interclass correlation coefficient (ICC) of individual patients was 0.782 and the standard deviation 0.080 when using the manual segmentation approach. However, the mean ICC of the evaluation of anatomical sites and time points separately was 0.214, suggesting a large range of deviation within the manual segmentation of each rater. The standard deviation was 0.355, further highlighting the extent of the variation. In contrast, the semi-automatic approach had a mean ICC of 0.491 and a standard deviation of 0.365, which suggests a relatively higher agreement among the operators compared to the manual segmentation approach. Furthermore, the volume of the osteotomy gap in the semi-automatic approach showed the same tendency in every site as the manual segmentation approach, but with less deviation.ConclusionThe semi-automatic approach developed in the present study proved to be valid as a standardised method with high repeatability. Such image analysis methods could help to quantify the progression of bone healing after BSSO and beyond, eventually facilitating the earlier identification of patients with retarded healing.

Perspectives on lung visualization: Three-dimensional anatomical modeling of computed and micro-computed tomographic data in comparative evolutionary morphology and medicine with applications for COVID-19.

The vertebrate respiratory system is challenging to study. The complex relationship between the lungs and adjacent tissues, the vast structural diversity of the respiratory system both within individuals and between taxa, its mobility (or immobility) and distensibility, and the difficulty of quantifying and visualizing functionally important internal negative spaces have all impeded descriptive, functional, and comparative research. As a result, there is a relative paucity of three-dimensional anatomical information on this organ system in all vertebrate groups (including humans) relative to other regions of the body. We present some of the challenges associated with evaluating and visualizing the vertebrate respiratory system using computed and micro-computed tomography and its subsequent digital segmentation. We discuss common mistakes to avoid when imaging deceased and live specimens and various methods for merging manual and threshold-based segmentation approaches to visualize pulmonary tissues across a broad range of vertebrate taxa, with a particular focus on sauropsids (reptiles and birds). We also address some of the recent work in comparative evolutionary morphology and medicine that have used these techniques to visualize respiratory tissues. Finally, we provide a clinical study on COVID-19 in humans in which we apply modeling methods to visualize and quantify pulmonary infection in the lungs of human patients.

An aseptic approach towards skin lesion localization and grading using deep learning and harris hawks optimization

Skin cancer is the most common form of cancer. It is predicted that the total number of cases of cancer will double in the next fifty years. It is an expensive procedure to discover skin cancer types in the early stages. Additionally, the survival rate reduces as cancer progresses. The current study proposes an aseptic approach toward skin lesion detection, classification, and segmentation using deep learning and Harris Hawks Optimization Algorithm (HHO). The current study utilizes the manual and automatic segmentation approaches. The manual segmentation is used when the dataset has no masks to use while the automatic segmentation approach is used, using U-Net models, to build an adaptive segmentation model. Additionally, the meta-heuristic HHO optimizer is utilized to achieve the optimization of the hyperparameters of 5 pre-trained CNN models, namely VGG16, VGG19, DenseNet169, DenseNet201, and MobileNet. Two datasets are used, namely "Melanoma Skin Cancer Dataset of 10000 Images" and "Skin Cancer ISIC" dataset from two publicly available sources for variety purpose. For the segmentation, the best-reported scores are 0.15908, 91.95%, 0.08864, 0.04313, 0.02072, 0.20767 in terms of loss, accuracy, Mean Absolute Error, Mean Squared Error, Mean Squared Logarithmic Error, and Root Mean Squared Error, respectively. For the "Melanoma Skin Cancer Dataset of 10000 Images" dataset, from the applied experiments, the best reported scores are 97.08%, 98.50%, 95.38%, 98.65%, 96.92% in terms of overall accuracy, precision, sensitivity, specificity, and F1-score, respectively by the DenseNet169 pre-trained model. For the "Skin Cancer ISIC" dataset, the best reported scores are 96.06%, 83.05%, 81.05%, 97.93%, 82.03% in terms of overall accuracy, precision, sensitivity, specificity, and F1-score, respectively by the MobileNet pre-trained model. After computing the results, the suggested approach is compared with 9 related studies. The results of comparison proves the efficiency of the proposed framework.

Semi-automated micro-computed tomography lung segmentation and analysis in mouse models

Computed Tomography (CT) is a standard clinical tool utilized to diagnose known lung pathologies based on established grading methods. However, for preclinical trials and toxicity investigations in animal models, more comprehensive datasets are typically needed to determine discriminative features between experimental treatments, which oftentimes require analysis of multiple images and their associated differential quantification using manual segmentation methods. Furthermore, for manual segmentation of image data, three or more readers is the gold standard of analysis, but this requirement can be time-consuming and inefficient, depending on variability due to reader bias. In previous papers, microCT image manual segmentation was a valuable tool for assessment of lung pathology in several animal models; however, the manual segmentation approach and the commercial software used was typically a major rate-limiting step. To improve the efficiency, the semi-manual segmentation method was streamlined, and a semi-automated segmentation process was developed to produce:•Quantifiable segmentations: using manual and semi-automated analysis methods for assessing experimental injury and toxicity models,•Deterministic results and efficiency through automation in an unbiased and parameter free process, thereby reducing reader variance, user time, and increases throughput in data analysis,•Cost-Effectiveness: portable with low computational resource demand, based on a cross-platform open-source ImageJ program.

Anatomically curated segmentation of human subcortical structures in high resolution magnetic resonance imaging: An open science approach.

Magnetic resonance imaging (MRI)-based brain segmentation has recently been revolutionized by deep learning methods. These methods use large numbers of annotated segmentations to train algorithms that have the potential to perform brain segmentations reliably and quickly. However, training data for these algorithms are frequently obtained from automated brain segmentation systems, which may contain inaccurate neuroanatomy. Thus, the neuroimaging community would benefit from an open source database of high quality, neuroanatomically curated and manually edited MRI brain images, as well as the publicly available tools and detailed procedures for generating these curated data. Manual segmentation approaches are regarded as the gold standard for brain segmentation and parcellation. These approaches underpin the construction of neuroanatomically accurate human brain atlases. In addition, neuroanatomically precise definitions of MRI-based regions of interest (ROIs) derived from manual brain segmentation are essential for accuracy in structural connectivity studies and in surgical planning for procedures such as deep brain stimulation. However, manual segmentation procedures are time and labor intensive, and not practical in studies utilizing very large datasets, large cohorts, or multimodal imaging. Automated segmentation methods were developed to overcome these issues, and provide high data throughput, increased reliability, and multimodal imaging capability. These methods utilize manually labeled brain atlases to automatically parcellate the brain into different ROIs, but do not have the anatomical accuracy of skilled manual segmentation approaches. In the present study, we developed a custom software module for manual editing of brain structures in the freely available 3D Slicer software platform that employs principles and tools based on pioneering work from the Center for Morphometric Analysis (CMA) at Massachusetts General Hospital. We used these novel 3D Slicer segmentation tools and techniques in conjunction with well-established neuroanatomical definitions of subcortical brain structures to manually segment 50 high resolution T1w MRI brains from the Human Connectome Project (HCP) Young Adult database. The structural definitions used herein are associated with specific neuroanatomical ontologies to systematically interrelate histological and MRI-based morphometric definitions. The resulting brain datasets are publicly available and will provide the basis for a larger database of anatomically curated brains as an open science resource.

Region Convolutional Neural Network for Brain Tumor Segmentation.

Gliomas are often difficult to find and distinguish using typical manual segmentation approaches because of their vast range of changes in size, shape, and appearance. Furthermore, the manual annotation of cancer tissue segmentation under the close supervision of a human professional is both time-consuming and exhausting to perform. It will be easier and faster in the future to get accurate and quick diagnoses and treatments thanks to automated segmentation and survival rate prediction models that can be used now. In this article, a segmentation model is designed using RCNN that enables automatic prognosis on brain tumors using MRI. The study adopts a U-Net encoder for capturing the features during the training of the model. The feature extraction extracts geometric features for the estimation of tumor size. It is seen that the shape, location, and size of a tumor are significant factors in the estimation of prognosis. The experimental methods are conducted to test the efficacy of the model, and the results of the simulation show that the proposed method achieves a reduced error rate with increased accuracy than other methods.

Thalamic volumetric abnormalities in type 1 diabetes mellitus and ‘peripheral’ neuropathy

We hypothesized that thalamic volumes of patients with type 1 diabetes mellitus (DM) and nonpainful diabetic peripheral neuropathy (DPN) would be reduced relative to thalamic volumes of patients with type 1 DM and painful DPN. We calculated the standardized thalamic volumetric difference between these groups in a pilot sample to obtain a statistical power of 80% at a 5% significance level. Hence, we measured thalamic volumes from 15 patients with nonpainful DPN (10 women, mean age = 49 years, standard deviation [SD] = 11.5) and from 13 patients with painful DPN (8 women, mean age = 43 years, SD = 12.5) by using a manual segmentation approach. A volumetric difference of approximately 15% was found between the nonpainful (mean = 5072 mm3, SD = 528.1) and painful (mean = 5976 mm3, SD = 643.1) DPN groups (P < 0.001). Curiously, a volumetric difference between the left (mean = 5198 mm3, SD = 495.0) and the right (mean = 4946 mm3, SD = 590.6) thalamus was also found in patients with nonpainful DPN (P < 0.01), but not in patients with painful DPN (P = 0.97). Patients with nonpainful DPN have lower thalamic volumes than those with painful DPN, especially in the right thalamus.

Prediction of multiple pH compartments by deep learning in magnetic resonance spectroscopy with hyperpolarized 13C-labelled zymonic acid

BackgroundHyperpolarization enhances the sensitivity of nuclear magnetic resonance experiments by between four and five orders of magnitude. Several hyperpolarized sensor molecules have been introduced that enable high sensitivity detection of metabolism and physiological parameters. However, hyperpolarized magnetic resonance spectroscopy imaging (MRSI) often suffers from poor signal-to-noise ratio and spectral analysis is complicated by peak overlap. Here, we study measurements of extracellular pH (pHe) by hyperpolarized zymonic acid, where multiple pHe compartments, such as those observed in healthy kidney or other heterogeneous tissue, result in a cluster of spectrally overlapping peaks, which is hard to resolve with conventional spectroscopy analysis routines.MethodsWe investigate whether deep learning methods can yield improved pHe prediction in hyperpolarized zymonic acid spectra of multiple pHe compartments compared to conventional line fitting. As hyperpolarized 13C-MRSI data sets are often small, a convolutional neural network (CNN) and a multilayer perceptron (MLP) were trained with either a synthetic or a mixed (synthetic and augmented) data set of acquisitions from the kidneys of healthy mice.ResultsComparing the networks’ performances compartment-wise on a synthetic test data set and eight real kidney data shows superior performance of CNN compared to MLP and equal or superior performance compared to conventional line fitting. For correct prediction of real kidney pHe values, training with a mixed data set containing only 0.5% real data shows a large improvement compared to training with synthetic data only. Using a manual segmentation approach, pH maps of kidney compartments can be improved by neural network predictions for voxels including three pH compartments.ConclusionThe results of this study indicate that CNNs offer a reliable, accurate, fast and non-interactive method for analysis of hyperpolarized 13C MRS and MRSI data, where low amounts of acquired data can be complemented to achieve suitable network training.

Automatic quantification of white matter hyperintensities on T2-weighted fluid attenuated inversion recovery magnetic resonance imaging

White matter hyperintensities (WMH) are areas of increased signal visualized on T2-weighted fluid attenuated inversion recovery (FLAIR) brain magnetic resonance imaging (MRI) sequences. They are typically attributed to small vessel cerebrovascular disease in the context of aging. Among older adults, WMH are associated with risk of cognitive decline and dementia, stroke, and various other health outcomes. There has been increasing interest in incorporating quantitative WMH measurement as outcomes in clinical trials, observational research, and clinical settings. Here, we present a novel, fully automated, unsupervised detection algorithm for WMH segmentation and quantification. The algorithm uses a robust preprocessing pipeline, including brain extraction and a sample-specific mask that incorporates spatial information for automatic false positive reduction, and a half Gaussian mixture model (HGMM). The method was evaluated in 24 participants with varying degrees of WMH (4.9–78.6 cm3) from a community-based study of aging and dementia with dice coefficient, sensitivity, specificity, correlation, and bias relative to the ground truth manual segmentation approach performed by two expert raters. Results were compared with those derived from commonly used available WMH segmentation packages, including SPM lesion probability algorithm (LPA), SPM lesion growing algorithm (LGA), and Brain Intensity AbNormality Classification Algorithm (BIANCA). The HGMM algorithm derived WMH values that had a dice score of 0.87, sensitivity of 0.89, and specificity of 0.99 compared to ground truth. White matter hyperintensity volumes derived with HGMM were strongly correlated with ground truth values (r = 0.97, p = 3.9e-16), with no observable bias (−1.1 [−2.6, 0.44], p-value = 0.16). Our novel algorithm uniquely uses a robust preprocessing pipeline and a half-Gaussian mixture model to segment WMH with high agreement with ground truth for large scale studies of brain aging.

Deep architectures for the segmentation of frontal sinuses in X-ray images: Towards an automatic forensic identification system in comparative radiography

Comparative radiography (CR) is the forensic anthropology technique in which ante-mortem (AM) and post-mortem (PM) radiographic materials (e.g., X-ray images or CTs) are compared in order to determine the identity of a human being (either by providing a positive identification or by reducing the number of candidates). One of the most commonly used anatomical structures in CR are the frontal sinuses, which are used in forensic human identification tasks due to their singularity and high identification power. In order to automate the comparison of frontal sinuses in AM and PM materials, we need to perform their segmentation and registration. However, these tasks are time-consuming, subjective, and complex. This paper presents the first CR-based identification system for the comparison of frontal sinuses and supporting the forensic expert’s decision. The proposed system comprises two building blocks. First, a frontal sinus segmentation method in X-ray images using deep convolutional neural networks. Different convolutional architectures are compared in solving the segmentation problem, obtaining an average Dice Similarity Coefficient of the frontal sinuses of 0.823 on a dataset composed of 234 skull radiographs. Second, an evolutionary-based 2D-3D IR method, that searches for the best alignment of segmented AM and PM images using a real-coded evolutionary algorithm. The proposed system is evaluated on a real multiple-comparison identification scenario including 10 X-ray images and 10 CTs, where manual and automatic segmentation approaches are compared. The global results shows that the proposed system is able to filter 50% of the sample. These preliminary results suggest that our system can reliably keep the true positive identity in the first half of the sample, allowing for a significant reduction of forensic experts’ workload and shortening identification times.

Comparative analysis of active contour and convolutional neural network in rapid left-ventricle volume quantification using echocardiographic imaging

In cardiology, ultrasound is often used to diagnose heart disease associated with myocardial infarction. This study aims to develop robust segmentation techniques for segmenting the left ventricle (LV) in ultrasound images to check myocardium movement during heartbeat. The proposed technique utilizes machine learning (ML) techniques such as the active contour (AC) and convolutional neural networks (CNNs) for segmentation. Medical experts determine the consistency between the proposed ML approach, which is a state-of-the-art deep learning method, and the manual segmentation approach. These methods are compared in terms of performance indicators such as the ventricular area (VA), ventricular maximum diameter (VMXD), ventricular minimum diameter (VMID), and ventricular long axis angle (AVLA) measurements. Furthermore, the Dice similarity coefficient, Jaccard index, and Hausdorff distance are measured to estimate the agreement of the LV segmented results between the automatic and visual approaches. The obtained results indicate that the proposed techniques for LV segmentation are useful and practical. There is no significant difference between the use of AC and CNN in image segmentation; however, the AC method could obtain comparable accuracy as the CNN method using less training data and less run-time.

One Step before 3D Printing-Evaluation of Imaging Software Accuracy for 3-Dimensional Analysis of the Mandible: A Comparative Study Using a Surface-to-Surface Matching Technique.

The accuracy of 3D reconstructions of the craniomaxillofacial region using cone beam computed tomography (CBCT) is important for the morphological evaluation of specific anatomical structures. Moreover, an accurate segmentation process is fundamental for the physical reconstruction of the anatomy (3D printing) when a preliminary simulation of the therapy is required. In this regard, the objective of this study is to evaluate the accuracy of four different types of software for the semiautomatic segmentation of the mandibular jaw compared to manual segmentation, used as a gold standard. Twenty cone beam computed tomography (CBCT) with a manual approach (Mimics) and a semi-automatic approach (Invesalius, ITK-Snap, Dolphin 3D, Slicer 3D) were selected for the segmentation of the mandible in the present study. The accuracy of semi-automatic segmentation was evaluated: (1) by comparing the mandibular volumes obtained with semi-automatic 3D rendering and manual segmentation and (2) by deviation analysis between the two mandibular models. An analysis of variance (ANOVA) was used to evaluate differences in mandibular volumetric recordings and for a deviation analysis among the different software types used. Linear regression was also performed between manual and semi-automatic methods. No significant differences were found in the total volumes among the obtained 3D mandibular models (Mimics = 40.85 cm3, ITK-Snap = 40.81 cm3, Invesalius = 40.04 cm3, Dolphin 3D = 42.03 cm3, Slicer 3D = 40.58 cm3). High correlations were found between the semi-automatic segmentation and manual segmentation approach, with R coefficients ranging from 0,960 to 0,992. According to the deviation analysis, the mandibular models obtained with ITK-Snap showed the highest matching percentage (Tolerance A = 88.44%, Tolerance B = 97.30%), while those obtained with Dolphin 3D showed the lowest matching percentage (Tolerance A = 60.01%, Tolerance B = 87.76%) (p < 0.05). Colour-coded maps showed that the area of greatest mismatch between semi-automatic and manual segmentation was the condylar region and the region proximate to the dental roots. Despite the fact that the semi-automatic segmentation of the mandible showed, in general, high reliability and high correlation with the manual segmentation, caution should be taken when evaluating the morphological and dimensional characteristics of the condyles either on CBCT-derived digital models or physical models (3D printing).

Machine Learning Applications in Orthopaedic Imaging.

Machine Learning Applications in Orthopaedic Imaging.

IMPACT OF OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY REVIEW STRATEGY ON DETECTION OF CHOROIDAL NEOVASCULARIZATION.

To compare optical coherence tomography angiography (OCTA) review strategies for optimizing choroidal neovascularization (CNV) detection. Eyes with CNV in the differential diagnosis were imaged with the Avanti RTVue XR HD (Optovue, Fremont, CA). Three modalities of review for CNV presence were used in each case: a single report generated using automated segmentation within Avanti software; a continuous slab descent video OCTA export; and a manual segmentation approach using cross-sectional OCT with decorrelation signal overlay. Scans were reviewed by two masked expert reviewers; a third reviewer was used for discrepancies. The study included 421 eyes, and 350 eyes had reports deemed sufficient quality for interpretation. Choroidal neovascularization was in the differential diagnosis in 107 of 350 patients. Overall CNV was identified in 55% (59/107) eyes. In those eyes with CNV, the automated segmentation identified CNV in 56% (33/59) of cases, continuous slab descent method identified CNV in 53% (31/59) of cases, and the manual segmentation group identified CNV in 92% (54/59) of cases. Review strategies for detection of CNV on OCTA were highest using the manual segmentation method as compared to both the automated report and continuous slab descent methods. Although the manual segmentation method had a higher rate of detection, the practical aspects of the time required for segmentation make this method challenging in routine clinical practice.

Semi-automated Root Image Analysis (saRIA)

Quantitative characterization of root system architecture and its development is important for the assessment of a complete plant phenotype. To enable high-throughput phenotyping of plant roots efficient solutions for automated image analysis are required. Since plants naturally grow in an opaque soil environment, automated analysis of optically heterogeneous and noisy soil-root images represents a challenging task. Here, we present a user-friendly GUI-based tool for semi-automated analysis of soil-root images which allows to perform an efficient image segmentation using a combination of adaptive thresholding and morphological filtering and to derive various quantitative descriptors of the root system architecture including total length, local width, projection area, volume, spatial distribution and orientation. The results of our semi-automated root image segmentation are in good conformity with the reference ground-truth data (mean dice coefficient = 0.82) compared to IJ_Rhizo and GiAroots. Root biomass values calculated with our tool within a few seconds show a high correlation (Pearson coefficient = 0.8) with the results obtained using conventional, pure manual segmentation approaches. Equipped with a number of adjustable parameters and optional correction tools our software is capable of significantly accelerating quantitative analysis and phenotyping of soil-, agar- and washed root images.

Ultrasound image-based thyroid nodule automatic segmentation using convolutional neural networks.

Delineation of thyroid nodule boundaries from ultrasound images plays an important role in calculation of clinical indices and diagnosis of thyroid diseases. However, it is challenging for accurate and automatic segmentation of thyroid nodules because of their heterogeneous appearance and components similar to the background. In this study, we employ a deep convolutional neural network (CNN) to automatically segment thyroid nodules from ultrasound images. Our CNN-based method formulates a thyroid nodule segmentation problem as a patch classification task, where the relationship among patches is ignored. Specifically, the CNN used image patches from images of normal thyroids and thyroid nodules as inputs and then generated the segmentation probability maps as outputs. A multi-view strategy is used to improve the performance of the CNN-based model. Additionally, we compared the performance of our approach with that of the commonly used segmentation methods on the same dataset. The experimental results suggest that our proposed method outperforms prior methods on thyroid nodule segmentation. Moreover, the results show that the CNN-based model is able to delineate multiple nodules in thyroid ultrasound images accurately and effectively. In detail, our CNN-based model can achieve an average of the overlap metric, dice ratio, true positive rate, false positive rate, and modified Hausdorff distance as [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text] on overall folds, respectively. Our proposed method is fully automatic without any user interaction. Quantitative results also indicate that our method is so efficient and accurate that it can be good enough to replace the time-consuming and tedious manual segmentation approach, demonstrating the potential clinical applications.

MAVEN: An Algorithm for Multi-Parametric Automated Segmentation of Brain Veins From Gradient Echo Acquisitions.

Cerebral vein analysis provides a chance to study, from an unusual viewpoint, an entire class of brain diseases, including neurodegenerative disorders and traumatic brain injuries. Manual segmentation approaches can be used to assess vascular anatomy, but they are observer-dependent and time-consuming; therefore, automated approaches are desirable, as they also improve reproducibility. In this paper, a new, fully automated algorithm, based on structural, morphological, and relaxometric information, is proposed to segment the entire cerebral venous system from MR images. The algorithm for multi-parametric automated segmentation of brain VEiNs (MAVEN) is based on a combined investigation of multi-parametric information that allows for rejection of false positives and detection of thin vessels. The method is tested on gradient echo brain data sets acquired at 1.5, 3, and 7 T. It is compared to previous methods against manual segmentation, and its inter-scan reproducibility is assessed. The achieved accuracy and reproducibility are good, meaning that MAVEN outperforms previous methods on both quantitative and qualitative analyses. It is usable at all the field strengths explored, showing comparable accuracy scores, with no need for algorithm parameter adjustments, and thus, it is a promising candidate for the characterization of the venous tree topology.

Semiautomated segmentation of head and neck cancers in 18F-FDG PET scans: A just-enough-interaction approach.

Purpose:The purpose of this work was to develop, validate, and compare a highly computer-aided method for the segmentation of hot lesions in head and neck 18F-FDG PET scans.Methods:A semiautomated segmentation method was developed, which transforms the segmentation problem into a graph-based optimization problem. For this purpose, a graph structure around a user-provided approximate lesion centerpoint is constructed and a suitable cost function is derived based on local image statistics. To handle frequently occurring situations that are ambiguous (e.g., lesions adjacent to each other versus lesion with inhomogeneous uptake), several segmentation modes are introduced that adapt the behavior of the base algorithm accordingly. In addition, the authors present approaches for the efficient interactive local and global refinement of initial segmentations that are based on the “just-enough-interaction” principle. For method validation, 60 PET/CT scans from 59 different subjects with 230 head and neck lesions were utilized. All patients had squamous cell carcinoma of the head and neck. A detailed comparison with the current clinically relevant standard manual segmentation approach was performed based on 2760 segmentations produced by three experts.Results:Segmentation accuracy measured by the Dice coefficient of the proposed semiautomated and standard manual segmentation approach was 0.766 and 0.764, respectively. This difference was not statistically significant (p = 0.2145). However, the intra- and interoperator standard deviations were significantly lower for the semiautomated method. In addition, the proposed method was found to be significantly faster and resulted in significantly higher intra- and interoperator segmentation agreement when compared to the manual segmentation approach.Conclusions:Lack of consistency in tumor definition is a critical barrier for radiation treatment targeting as well as for response assessment in clinical trials and in clinical oncology decision-making. The properties of the authors approach make it well suited for applications in image-guided radiation oncology, response assessment, or treatment outcome prediction.

Shape-intensity prior level set combining probabilistic atlas and probability map constrains for automatic liver segmentation from abdominal CT images.

Propose a fully automatic 3D segmentation framework to segment liver on challenging cases that contain the low contrast of adjacent organs and the presence of pathologies from abdominal CT images. First, all of the atlases are weighted in the selected training datasets by calculating the similarities between the atlases and the test image to dynamically generate a subject-specific probabilistic atlas for the test image. The most likely liver region of the test image is further determined based on the generated atlas. A rough segmentation is obtained by a maximum a posteriori classification of probability map, and the final liver segmentation is produced by a shape-intensity prior level set in the most likely liver region. Our method is evaluated and demonstrated on 25 test CT datasets from our partner site, and its results are compared with two state-of-the-art liver segmentation methods. Moreover, our performance results on 10 MICCAI test datasets are submitted to the organizers for comparison with the other automatic algorithms. Using the 25 test CT datasets, average symmetric surface distance is [Formula: see text]mm (range 0.62-2.12mm), root mean square symmetric surface distance error is [Formula: see text]mm (range 0.97-3.01mm), and maximum symmetric surface distance error is [Formula: see text]mm (range 12.73-26.67mm) by our method. Our method on 10 MICCAI test data sets ranks 10th in all the 47 automatic algorithms on the site as of July 2015. Quantitative results, as well as qualitative comparisons of segmentations, indicate that our method is a promising tool to improve the efficiency of both techniques. The applicability of the proposed method to some challenging clinical problems and the segmentation of the liver are demonstrated with good results on both quantitative and qualitative experimentations. This study suggests that the proposed framework can be good enough to replace the time-consuming and tedious slice-by-slice manual segmentation approach.