Volumetric Features Research Articles

Sequential and Iterative Auto-Segmentation of High-Risk Clinical Target Volume for Radiotherapy of Nasopharyngeal Carcinoma in Planning CT Images.

Background: Accurate segmentation of tumor targets is critical for maximizing tumor control and minimizing normal tissue toxicity. We proposed a sequential and iterative U-Net (SI-Net) deep learning method to auto-segment the high-risk primary tumor clinical target volume (CTVp1) for treatment planning of nasopharyngeal carcinoma (NPC) radiotherapy.Methods: The SI-Net is a variant of the U-Net architecture. The input of SI-Net includes one CT image, the CTVp1 contour on this image, and the next CT image. The output is the predicted CTVp1 contour on the next CT image. We designed the SI-Net, using the left side to learn the volumetric features and the right to localize the contour on the next image. Two prediction directions, one from inferior to superior (forward direction) and the other from superior to inferior (backward direction), were tested. The performance was compared between the SI-Net and the U-Net using Dice similarity coefficient (DSC), Jaccard index (JI), average surface distance (ASD), and Hausdorff distance (HD) metrics.Results: The DSC and JI values from the forward direction SI-Net model were 5 and 6% higher than those from the U-Net model (0.84 ± 0.04 vs. 0.80 ± 0.05 and 0.74 ± 0.05 vs. 0.69 ± 0.05, p < 0.001). The smaller ASD and HD values also indicated a better performance (2.8 ± 1.0 vs. 3.3 ± 1.0 mm and 8.7 ± 2.5 vs. 9.7 ± 2.7 mm, p < 0.01) for the SI-Net model. For the backward direction SI-Net model, the DSC and JI values were still better than those from the U-Net model (p < 0.01), although there were no significant differences in ASD and HD.Conclusions: The SI-Net model preserved the continuity between adjacent images and thus improved the segmentation accuracy compared with the conventional U-Net model. This model has potential of improving the efficiency and consistence of CTVp1 contouring for NPC patients.

Deep learning for glioblastoma segmentation using preoperative magnetic resonance imaging identifies volumetric features associated with survival

BackgroundMeasurement of volumetric features is challenging in glioblastoma. We investigate whether volumetric features derived from preoperative MRI using a convolutional neural network–assisted segmentation is correlated with survival.MethodsPreoperative MRI of 120 patients were scored using Visually Accessible Rembrandt Images (VASARI) features. We trained and tested a multilayer, multi-scale convolutional neural network on multimodal brain tumour segmentation challenge (BRATS) data, prior to testing on our dataset. The automated labels were manually edited to generate ground truth segmentations. Network performance for our data and BRATS data was compared. Multivariable Cox regression analysis corrected for multiple testing using the false discovery rate was performed to correlate clinical and imaging variables with overall survival.ResultsMedian Dice coefficients in our sample were (1) whole tumour 0.94 (IQR, 0.82–0.98) compared to 0.91 (IQR, 0.83–0.94 p = 0.012), (2) FLAIR region 0.84 (IQR, 0.63–0.95) compared to 0.81 (IQR, 0.69–0.8 p = 0.170), (3) contrast-enhancing region 0.91 (IQR, 0.74–0.98) compared to 0.83 (IQR, 0.78–0.89 p = 0.003) and (4) necrosis region were 0.82 (IQR, 0.47–0.97) compared to 0.67 (IQR, 0.42–0.81 p = 0.005). Contrast-enhancing region/tumour core ratio (HR 4.73 [95% CI, 1.67–13.40], corrected p = 0.017) and necrotic core/tumour core ratio (HR 8.13 [95% CI, 2.06–32.12], corrected p = 0.011) were independently associated with overall survival.ConclusionSemi-automated segmentation of glioblastoma using a convolutional neural network trained on independent data is robust when applied to routine clinical data. The segmented volumes have prognostic significance.

Identifying brain regions contributing to Alzheimer's disease using self regulating particle swarm optimization

AbstractIn this article, we developed an approach for detecting brain regions that contribute to Alzheimer's disease (AD) using support vector machine (SVM) classifiers and the recently developed self regulating particle swarm optimization (SRPSO) algorithm. SRPSO employs strategies inspired by the principles of learning in humans to achieve faster and better optimization results. The classifiers for distinguishing subjects into AD patients and cognitively normal (CN) individuals were built using grey matter (GM) and white matter (WM) volumetric features extracted from structural magnetic resonance (MR) images. It could be observed from results that the classifier built using both GM and WM features provided accuracy of 89.26% which is better than the performance of classifiers built using either GM or WM features only. Moreover, consideration of clinical features in addition to volumetric features improves the accuracy further to 94.63% which is better than the performance reported by recent works in literature. In order to identify the brain regions that are important for AD vs CN classification problem, we used SRPSO to extract GM and WM features that yield better classification performance. Using 50 features identified by SRPSO, an accuracy of 89.39% was obtained which is close to the accuracy based on all features. The features identified by SRPSO were mapped back to the brain to identify brain regions that exhibit degeneration in AD. In addition to identifying areas known to be involved in AD like cerebellum, hippocampus, this helped in finding newer areas that might contribute towards AD.

Prediction of Cognitive Decline in Temporal Lobe Epilepsy and Mild Cognitive Impairment by EEG, MRI, and Neuropsychology.

Cognitive decline is a severe concern of patients with mild cognitive impairment. Also, in patients with temporal lobe epilepsy, memory problems are a frequently encountered problem with potential progression. On the background of a unifying hypothesis for cognitive decline, we merged knowledge from dementia and epilepsy research in order to identify biomarkers with a high predictive value for cognitive decline across and beyond these groups that can be fed into intelligent systems. We prospectively assessed patients with temporal lobe epilepsy (N = 9), mild cognitive impairment (N = 19), and subjective cognitive complaints (N = 4) and healthy controls (N = 18). All had structural cerebral MRI, EEG at rest and during declarative verbal memory performance, and a neuropsychological assessment which was repeated after 18 months. Cognitive decline was defined as significant change on neuropsychological subscales. We extracted volumetric and shape features from MRI and brain network measures from EEG and fed these features alongside a baseline testing in neuropsychology into a machine learning framework with feature subset selection and 5-fold cross validation. Out of 50 patients, 27 had a decline over time in executive functions, 23 in visual-verbal memory, 23 in divided attention, and 7 patients had an increase in depression scores. The best sensitivity/specificity for decline was 72%/82% for executive functions based on a feature combination from MRI volumetry and EEG partial coherence during recall of memories; 95%/74% for visual-verbal memory by combination of MRI-wavelet features and neuropsychology; 84%/76% for divided attention by combination of MRI-wavelet features and neuropsychology; and 81%/90% for increase of depression by combination of EEG partial directed coherence factor at rest and neuropsychology. Combining information from EEG, MRI, and neuropsychology in order to predict neuropsychological changes in a heterogeneous population could create a more general model of cognitive performance decline.

Hybrid attention for automatic segmentation of whole fetal head in prenatal ultrasound volumes

Background and objective: Biometric measurements of fetal head are important indicators for maternal and fetal health monitoring during pregnancy. 3D ultrasound (US) has unique advantages over 2D scan in covering the whole fetal head and may promote the diagnoses. However, automatically segmenting the whole fetal head in US volumes still pends as an emerging and unsolved problem. The challenges that automated solutions need to tackle include the poor image quality, boundary ambiguity, long-span occlusion, and the appearance variability across different fetal poses and gestational ages. In this paper, we propose the first fully-automated solution to segment the whole fetal head in US volumes.Methods: The segmentation task is firstly formulated as an end-to-end volumetric mapping under an encoder-decoder deep architecture. We then combine the segmentor with a proposed hybrid attention scheme (HAS) to select discriminative features and suppress the non-informative volumetric features in a composite and hierarchical way. With little computation overhead, HAS proves to be effective in addressing boundary ambiguity and deficiency. To enhance the spatial consistency in segmentation, we further organize multiple segmentors in a cascaded fashion to refine the results by revisiting context in the prediction of predecessors.Results: Validated on a large dataset collected from 100 healthy volunteers, our method presents superior segmentation performance (DSC (Dice Similarity Coefficient), 96.05%), remarkable agreements with experts (−1.6±19.5 mL). With another 156 volumes collected from 52 volunteers, we ahieve high reproducibilities (mean standard deviation 11.524 mL) against scan variations.Conclusion: This is the first investigation about whole fetal head segmentation in 3D US. Our method is promising to be a feasible solution in assisting the volumetric US-based prenatal studies.

Features of the Design of a Valveless Spur Pump

A new engineering solution, a rotary valveless volumetric spur pump, is considered and features of the operation of the pump are considered. A technique for constructing the profile of the hollow in a pump closure is presented. With the use of the technique, dependences of the pump effective storage on the geometric parameters of the driven elements of the pump are determined.

Prediction of Molecular Mutations in Diffuse Low-Grade Gliomas using MR Imaging Features

Diffuse low-grade gliomas (LGG) have been reclassified based on molecular mutations, which require invasive tumor tissue sampling. Tissue sampling by biopsy may be limited by sampling error, whereas non-invasive imaging can evaluate the entirety of a tumor. This study presents a non-invasive analysis of low-grade gliomas using imaging features based on the updated classification. We introduce molecular (MGMT methylation, IDH mutation, 1p/19q co-deletion, ATRX mutation, and TERT mutations) prediction methods of low-grade gliomas with imaging. Imaging features are extracted from magnetic resonance imaging data and include texture features, fractal and multi-resolution fractal texture features, and volumetric features. Training models include nested leave-one-out cross-validation to select features, train the model, and estimate model performance. The prediction models of MGMT methylation, IDH mutations, 1p/19q co-deletion, ATRX mutation, and TERT mutations achieve a test performance AUC of 0.83 ± 0.04, 0.84 ± 0.03, 0.80 ± 0.04, 0.70 ± 0.09, and 0.82 ± 0.04, respectively. Furthermore, our analysis shows that the fractal features have a significant effect on the predictive performance of MGMT methylation IDH mutations, 1p/19q co-deletion, and ATRX mutations. The performance of our prediction methods indicates the potential of correlating computed imaging features with LGG molecular mutations types and identifies candidates that may be considered potential predictive biomarkers of LGG molecular classification.

Left Atrial Volumetric and Deformation Analysis in Adult Patients with Dextro-Transposition of the Great Arteries (Insights from the CSONGRAD Registry and MAGYAR-Path Study)

Background: In complete or dextro-transposition of the great arteries (dTGA), the aorta and the pulmonary artery are transposed. The present study was designed to examine dTGA-associated left atrial (LA) volumetric and functional abnormalities in adult patients late after repair and to compare their results to those of healthy controls. Methods: The present study consisted of 15 dTGA patients (30.3 ± 8.1 years, 9 males), the patients had Mustard (n = 8) or Senning (n = 7) procedure performed. Their results were compared to those of 36 age- and gender-matched healthy subjects (28.7 ± 1.5 years, 24 males). Results: Increased maximum LA volume and reduced LA emptying fractions respecting the cardiac cycle could be demonstrated in our dTGA patients. LA stroke volumes representing all LA functions were significantly reduced. Peak LA circumferential, longitudinal, and area strains and LA circumferential, longitudinal, and area strains measured at atrial contraction were reduced in our dTGA patients. Most LA strains were reduced in patients having Mustard surgery compared to controls and patients undergoing Senning operation. Conclusions: Significant LA volumetric and functional abnormalities could be demonstrated in adult patients with dTGA late after repair. Senning procedure seems to have more beneficial long-term effects on LA volumetric and functional features as compared to the Mustard procedure.

Retrieving 3D medical data along fitted curved slices and their display

BackgroundComputeros tomography and magnetic resonance imaging are usually offered to the clinician in the form of sequences of axial, sagittal and coronal planar cuts. Frequently this does not allow for the full inspection of the morphology of the area of interest, because it is limited by the planarity. Efforts have been made to extract information along curved slices but their planar display is prone to metric deformation.MethodsWe propose a new visualization alternative of 3D medical volumes using curved slices adapted to areas of interest. We use surfaces fitted to specific organs as visualization canvasses. We describe the differential geometry techniques used to build the surfaces that may be isometrically flattened. These are referred to as develpable surfaces.ResultsWe show concrete examples deemed useful for the development of clinical and educational tools. Our examples are centered in magnetic resonance data of the rotator cuff muscle complex and computed tomography data of maxillofacial and dental studies. We also look at the extraction and display of information from volumes of aortic aneurysms along transversal surfaces.DiscussionWe look at extensions of the technique and propose further possible clinical use of texturized surfaces in the context of volume navigation.ConclusionsWe presented a technique to extract information from computer tomography and magnetic resonance volumes, using two different texturization techniques. In the cases that the fitting surfaces are chosen to be developable, they may be flattened without distortion. We also discuss how tu use the technique in other visualization tasks such as volume navigation and detection of volumetric features.

A Novel Comprehensive Clinical Stratification Model to Refine Prognosis of Glioblastoma Patients Undergoing Surgical Resection.

Despite recent discoveries in genetics and molecular fields, glioblastoma (GBM) prognosis still remains unfavorable with less than 10% of patients alive 5 years after diagnosis. Numerous studies have focused on the research of biological biomarkers to stratify GBM patients. We addressed this issue in our study by using clinical/molecular and image data, which is generally available to Neurosurgical Departments in order to create a prognostic score that can be useful to stratify GBM patients undergoing surgical resection. By using the random forest approach [CART analysis (classification and regression tree)] on Survival time data of 465 cases, we developed a new prediction score resulting in 10 groups based on extent of resection (EOR), age, tumor volumetric features, intraoperative protocols and tumor molecular classes. The resulting tree was trimmed according to similarities in the relative hazard ratios amongst groups, giving rise to a 5-group classification tree. These 5 groups were different in terms of overall survival (OS) (p < 0.000). The score performance in predicting death was defined by a Harrell’s c-index of 0.79 (95% confidence interval [0.76–0.81]). The proposed score could be useful in a clinical setting to refine the prognosis of GBM patients after surgery and prior to postoperative treatment.

Glioblastoma: from volumetric analysis to molecular predictors.

Decades of therapeutic and molecular refinements, the prognosis of patients with glioblastoma (GBM) still remains unfavorable. Integrative clinical studies allow a better understanding of the natural evolution of GBM. To assess independent predictors of overall survival (OS) and progression free survival (PFS) clinical, surgical, molecular and radiological variables were evaluated. A novel preoperative volumetric magnetic resonance imaging (MRI) Index for tumor prognosis in GBM patients was investigated. A cohort of 195 cases of patients operated for newly GBM were analyzed. Extent of tumoral resection (EOR), tumor growth pattern, expressed by preoperative volumetric ΔT1-T2 MRI Index, molecular markers such as O6-methylguanine-DNA methyltransferase (MGMT) methylation and isocitrate dehydrogenase 1/2 (IDH1/2) mutation, were analyzed. Analysis of survival was done using Cox-proportional hazard models. The 1-, 2- years estimated OS and PFS rate for the whole population were 61% and 27%, 38% and 17%, respectively. A better survival rate, both in terms of survival and tumor progression, was observed in patient with higher EOR (P=0.000), younger age (P=0.000), MGMT methylation status (P=0.001) and lower preoperative ΔT1-T2 MRI Index (P=0.004). Regarding the tumor growth pattern a cut-off value of 0.75 was found to discriminate patient with different prognosis. Patients with a preoperative ΔT1-T2 MRI Index <0.75 had a 1-year estimated OS of 67%, otherwise patients with a preoperative ΔT1-T2 MRI Index >0.75 had a 1-year estimated OS of 34%. In this investigation longer survival is associated with younger age, EOR, promoter methylation of MGMT and preoperative tumor volumetric features expressed by ΔT1-T2 MRI Index The preoperative ΔT1-T2 MRI Index could be a promising prognostic factor potentially useful in GBM management. Future investigations based on multiparametric MRI data and next generation sequences analysis, may better clarify this result.

Large debris flows in Chosica, Lima, Peru: the application of hydraulic infrastructure for erosion control and disaster prevention

Large debris flows in steep-sloped ravines debouching to the Rimac River, in metropolitan Lima (Peruvian capital), have resulted in considerable loss of life and property adversely impacting communities in the region. Temporal, spatial and volumetric features of debris flows are difficult to predict, and it is of utmost importance that achievable management solutions are found to reduce the impact of these catastrophic events. The emotional and economic toll of these debris flows on this increasingly densely populated capital city in South America is devastating where communities must live in such inadequate and dangerous conditions. To address this problem, the application of advanced Japanese technology, Sustainable Actions Basin Orientation (SABO), has been investigated using a geomorphological modelling to develop an implementation plan. Rayos de Sol stream basin in Chosica, was selected as a pilot to develop the proposal, as it is considered high risk due to the presence of ancient debris flows and recent flows in 2012, 2015 and 2017. The recurrence of debris flows in this location has resulted in numerous deaths and catastrophic property losses. This study combines geologic and geomorphic mapping and hydraulic and landform evolution numerical modelling. The implementation of a SABO Master Plan based on the multidisciplinary assessment hazard scenarios, will allow the implementation of feasible mitigation actions. The SABO technology has been applied successfully in Japan and other countries in areas with steep short slopes, similar to the conditions surrounding the Peruvian capital. Results from this study will be presented to the Peruvian Government as part of an action plan to manage debris-flow impact.KEY POINTSHigh-risk mass slope failure is linked to poor urban planning in urban developing regions of Lima the capital of Peru.A multidisciplinary study including geotechnical and hydrological analysis, engineering design, and socio-economic research is required to implement a SABO Master Plan, and this basin is pilot study basin.At the present time, a maintenance programme for existing hydraulic structures should be implemented, and a flood risk management plan developed may propose the relocation of some communities and infrastructure.

Automated Cardiovascular Pathology Assessment Using Semantic Segmentation and Ensemble Learning.

Cardiac magnetic resonance imaging provides high spatial resolution, enabling improved extraction of important functional and morphological features for cardiovascular disease staging. Segmentation of ventricular cavities and myocardium in cardiac cine sequencing provides a basis to quantify cardiac measures such as ejection fraction. A method is presented that curtails the expense and observer bias of manual cardiac evaluation by combining semantic segmentation and disease classification into a fully automatic processing pipeline. The initial processing element consists of a robust dilated convolutional neural network architecture for voxel-wise segmentation of the myocardium and ventricular cavities. The resulting comprehensive volumetric feature matrix captures diagnostic clinical procedure data and is utilized by the final processing element to model a cardiac pathology classifier. Our approach evaluated anonymized cardiac images from a training data set of 100 patients (4 pathology groups, 1 healthy group, 20 patients per group) examined at the University Hospital of Dijon. The top average Dice index scores achieved were 0.940, 0.886, and 0.849 for structure segmentation of the left ventricle (LV), myocardium, and right ventricle (RV), respectively. A 5-ary pathology classification accuracy of 90% was recorded on an independent test set using the trained model. Performance results demonstrate the potential for advanced machine learning methods to deliver accurate, efficient, and reproducible cardiac pathological assessment.

The impact of quantitative CT-based tumor volumetric features on the outcomes of patients with limited stage small cell lung cancer

IntroductionLimited stage small cell lung cancer (LS-SCLC) has a poor prognosis. Additional prognostic markers are needed for risk-stratification and treatment intensification. This study compares quantitative CT-based volumetric tumor measurements versus International Association for the Study of Lung Cancer (IASLC) TNM staging to predict outcomes.Materials & methodsA cohort of 105 patients diagnosed with LS-SCLC and treated with chemoradiation (CRT) from 2000 to 2013 were analyzed retrospectively. Patients were staged by the Union for International Cancer Control (UICC) TNM Classification, 8th edition. Tumor volumes and diameters were extracted from radiation planning CT imaging. Univariable and multivariable models were used to analyze relationships between CT features and overall survival (OS), locoregional recurrence (LRR), in-field LRR, any progression, and distant metastasis (DM).ResultsMedian follow-up was 21.3 months. Two-year outcomes were as follows: 38% LRR, 31% in-field LRR, 52% DM, 62% any progression, and 47% OS (median survival 16.5 months).On univariable analysis, UICC T-stage and N-stage were not associated with any clinical outcome. UICC overall stage was only statistically associated with in-field LRR. One imaging feature (3D maximum tumor diameter) was found to be significantly associated with LRR (HR 1.10, p = 0.003), in-field LRR (HR 1.10, p = 0.007), DM (HR 1.10, p = 0.02), any progression (HR 1.10, p = 0.008), and OS (HR 1.10, p = 0.03). On multivariable analysis, this feature remained significantly associated with all outcomes.ConclusionFor LS-SCLC, quantitative CT-based volumetric tumor measurements were significantly associated with outcomes after CRT and may be better predictors of outcome than TNM stage.

Deep learning for lung Cancer detection and classification

Lung cancer is one of the main reasons for death in the world among both men and women, with an impressive rate of about five million deadly cases per year. Computed Tomography (CT) scan can provide valuable information in the diagnosis of lung diseases. The main objective of this work is to detect the cancerous lung nodules from the given input lung image and to classify the lung cancer and its severity. To detect the location of the cancerous lung nodules, this work uses novel Deep learning methods. This work uses best feature extraction techniques such as Histogram of oriented Gradients (HoG), wavelet transform-based features, Local Binary Pattern (LBP), Scale Invariant Feature Transform (SIFT) and Zernike Moment. After extracting texture, geometric, volumetric and intensity features, Fuzzy Particle Swarm Optimization (FPSO) algorithm is applied for selecting the best feature. Finally, these features are classified using Deep learning. A novel FPSOCNN reduces computational complexity of CNN. An additional valuation is performed on another dataset coming from Arthi Scan Hospital which is a real-time data set. From the experimental results, it is shown that novel FPSOCNN performs better than other techniques.

Intelligent systems for volumetric feature recognition from CAD mesh models

This paper presents an intelligent technique to recognise the volumetric features from CAD mesh models based on hybrid mesh segmentation. The hybrid approach is an intelligent blending of facet-based, vertex based, rule-based, and artificial neural network (ANN)-based techniques. Comparing with existing state-of-the-art approaches, the proposed approach does not depend on attributes like curvature, minimum feature dimension, number of clusters, number of cutting planes, the orientation of model and thickness of the slice to extract volumetric features. ANN-based intelligent threshold prediction makes hybrid mesh segmentation automatic. The proposed technique automatically extracts volumetric features like blends and intersecting holes along with their geometric parameters. The proposed approach has been extensively tested on various benchmark test cases. The proposed approach outperforms the existing techniques favourably and found to be robust and consistent with coverage of more than 95% in addressing volumetric features.

Representation of model for efficient collision detection in virtual reality environment

In conceptual design, virtual reality assurances to be a natural, cost-effective, and creative method. Representation of the model in the virtual reality environment is a significant step. In the virtual environment, while representing the model, it should behave realistically. Several techniques like implicit, tessellated, parametric representations are available for representing the models. In the present work, the model is created from data of point cloud using volumetric self-organising feature map algorithm. The virtual model generation from point cloud data helps in the secure exchange of database between commercially available computer-aided design (CAD) software. 3D B-splines have been selected to represent the virtual model. A three-dimensional virtual model has been generated from the data of point cloud. For efficient collision detection, surfaces have been also extracted from the three-dimensional model by considering the alternative values of u, v, w parameters as 0 and 1. Anyone of the six extracted surfaces can be used for collision detection. The results showed that the extraction of surfaces is beneficial for efficient collision detection.

ВОПРОСЫ РАЗВИТИЯ ЭТНОКУЛЬТУРНЫХ ТРАДИЦИЙ В СОВРЕМЕННОЙ ХУДОЖЕСТВЕННОЙ ПРАКТИКЕ

The article deals with insufficiently studied theoretical aspects of revealing and analyzing new elements and motives of artistic and compositional means of expression in folk art, as well as topical issues concerning determining principles and possible options for their creative development in modern decorative and applied art, design, and artistic practice in general. The most important structural features of shaping in traditional art in the ontologically interrelated system "nature — man — object" are analyzed. The main structurally stable elements and components in Kazakh folk ornament are distinguished and characterized, these are the circle, S-shaped element, cruciform and triangular components. The evolution of their ideological and figurative interpretation and symbolism is traced, and their role in the genesis of folk art traditions formed over thousands of years is revealed. The selected basic elements of folk ornament, as the main components of means of artistic expression, are proposed to be defined and developed in line with modern interpretations of artistic and aesthetic categories — dynamics, statics, harmony and their decorative variations in accordance with the volumetric and spatial features of form.

Intelligent systems for volumetric feature recognition from CAD mesh models

This paper presents an intelligent technique to recognise the volumetric features from CAD mesh models based on hybrid mesh segmentation. The hybrid approach is an intelligent blending of facet-based, vertex based, rule-based, and artificial neural network (ANN)-based techniques. Comparing with existing state-of-the-art approaches, the proposed approach does not depend on attributes like curvature, minimum feature dimension, number of clusters, number of cutting planes, the orientation of model and thickness of the slice to extract volumetric features. ANN-based intelligent threshold prediction makes hybrid mesh segmentation automatic. The proposed technique automatically extracts volumetric features like blends and intersecting holes along with their geometric parameters. The proposed approach has been extensively tested on various benchmark test cases. The proposed approach outperforms the existing techniques favourably and found to be robust and consistent with coverage of more than 95% in addressing volumetric features.

3D Object Classification Using a Volumetric Deep Neural Network: An Efficient Octree Guided Auxiliary Learning Approach

We consider the recent challenges of 3D shape analysis based on a volumetric CNN that requires a huge computational power. This high-cost approach forces to reduce the volume resolutions when applying 3D CNN on volumetric data. In this context, we propose a multiorientation volumetric deep neural network (MV-DNN) for 3D object classification with octree generating low-cost volumetric features. In comparison to conventional octree representations, we propose to limit the octree partition to a certain depth to reserve all leaf octants with sparsity features. This allows for improved learning of complex 3D features and increased prediction of object labels at both low and high resolutions. Our auxiliary learning approach predicts object classes based on the subvolume parts of a 3D object that improve the classification accuracy compared to other existing 3D volumetric CNN methods. In addition, the influence of views and depths of the 3D model on the classification performance is investigated through extensive experiments applied to the ModelNet40 database. Our deep learning framework runs significantly faster and consumes less memory than full voxel representations and demonstrate the effectiveness of our octree-based auxiliary learning approach for exploring high resolution 3D models. Experimental results reveal the superiority of our MV-DNN that achieves better classification accuracy compared to state-of-art methods on two public databases.