Shape-related Features Research Articles

Stability of Radiomic Features against Variations in Lesion Segmentations Computed on Apparent Diffusion Coefficient Maps of Breast Lesions.

Diffusion-weighted imaging (DWI) combined with radiomics can aid in the differentiation of breast lesions. Segmentation characteristics, however, might influence radiomic features. To evaluate feature stability, we implemented a standardized pipeline featuring shifts and shape variations of the underlying segmentations. A total of 103 patients were retrospectively included in this IRB-approved study after multiparametric diagnostic breast 3T MRI with a spin-echo diffusion-weighted sequence with echoplanar readout (b-values: 50, 750 and 1500 s/mm2). Lesion segmentations underwent shifts and shape variations, with >100 radiomic features extracted from apparent diffusion coefficient (ADC) maps for each variation. These features were then compared and ranked based on their stability, measured by the Overall Concordance Correlation Coefficient (OCCC) and Dynamic Range (DR). Results showed variation in feature robustness to segmentation changes. The most stable features, excluding shape-related features, were FO (Mean, Median, RootMeanSquared), GLDM (DependenceNonUniformity), GLRLM (RunLengthNonUniformity), and GLSZM (SizeZoneNonUniformity), which all had OCCC and DR > 0.95 for both shifting and resizing the segmentation. Perimeter, MajorAxisLength, MaximumDiameter, PixelSurface, MeshSurface, and MinorAxisLength were the most stable features in the Shape category with OCCC and DR > 0.95 for resizing. Considering the variability in radiomic feature stability against segmentation variations is relevant when interpreting radiomic analysis of breast DWI data.

Gearbox faults severity classification using Poincaré plots of acoustic emission signals

Classification of fault severity in gearboxes using Acoustic Emission (AE) signals is challenging because such signals represent a highly non-linear and possibly chaotic system. Due to the common assumption of linearity, the statistical features extracted from these systems are suboptimal for the classification of fault severity. Hence, this paper uses the Poincaré plot (PP) of Acoustic Emission (AE) signals to extract useful features to classify fault type and severity in gearboxes. For this development, four fault types were applied over different gears and then tested on an experimental condition monitoring bench: broken tooth, pitting, scuffing, and cracks, each with nine severity levels. Then, the feature set was extracted from the conventional 2-D PP, composed of shape-related features and a set of features known as complex correlation measurements (CCM). The fault type and severity classification was performed using four frequency bands. Low and band-pass filtered signals obtained the highest classification accuracy with Random Forest (RF): the fault type was classified with an accuracy of 99.69%, the severity was classified with an accuracy depending on the fault type corresponding to pitting 98.76%, cracks 98.71%, broken tooth 98.96%, and scuffing 98.51%. The PP features set has a low computational cost even for large datasets representing AE signals, which can benefit the practical possibility of the implementation with high classification accuracy for different types of fault and severity levels in a gearbox.

Clinical value of dual-energy CT for predicting occult metastasis in central neck lymph nodes of papillary thyroid carcinoma.

To predict the probability of occult lymph node metastasis (OLNM) in the central cervical by analyzing the dual-energy computed tomography (DECT) parameters derived from papillary thyroid carcinoma (PTC). Data were retrospectively collected from patients with pathologically confirmed PTC who underwent arterial and venous phases of enhanced DECT with concurrent central neck lymph node dissection (CLND). Three clinical features, three shape-related features, and twenty-six DECT-derived parameters were measured. The univariate and multivariate analyses were applied to select the relevant parameters and develop the nomogram. A total 140 cases with negative diagnosis of cervical central lymph node metastases by preoperative evaluation were included, among which 88 patients with metastasis (OLNM +) and 52 patients without metastasis (OLNM -) were finally confirmed by pathology.(1) Anteroposterior/transverse diameter ratio (A/T) derived from the PTC focus had significant difference between the OLNM + and OLNM - groups (p < 0.05). (2) In the arterial phase, iodine concentration (ICarterial), normalized iodine concentration (NICarterial), effective atomic number (Zeff-arterial), electron density (EDarterial), and slope of energy curve (karterial) from PTC focus showed significant difference (all p < 0.05) between the two groups. In the venous phase, only the CT value under the 40keV (HU40keVvenous) had differences (p < 0.05). (3) The nomogram was produced to predict the probability of OLNM, and the AUC, sensitivity, and specificity in the training and test cohort were 0.830, 75.0%, 76.9%, and 0.829, 65.9%, 84.6%, respectively. DECT parameters combined with shape-related feature derived from PTC might be used as predictors of OLNM in the central neck. Preoperative imaging evaluation combining shape-related features and dual-energy CT parameters could serve as a reference to discern occult lymph node metastasis in central neck during the surgically planning of papillary thyroid carcinoma. • Papillary thyroid carcinoma (PTC) patients may have occult lymph node metastasis (OLNM) in the central neck, which is extremely difficult to find by preoperative imaging examination. • Dual-energy CT quantitative evaluation has higher accuracy than conventional CT and can predicting OLNM in the central neck of PTC. • Dual-energy CT quantitative parameters and morphology of PTC can serve as a useful tool in predicting OLNM in the central neck, and as a guide for personalized treatment.

A low-cost edge AI-chip-based system for real-time algae species classification and HAB prediction

Harmful Algal Blooms (HAB) are damaging to ecosystem functions and pose challenges to environmental and fisheries management. The key to HAB management and understanding the complex algal growth dynamics is the development of robust systems for real-time monitoring of algae populations and species. Previous algae classification studies mainly rely on the combination of an in-situ imaging flow cytometer and an off-site lab-based algae classification model such as Random Forest (RF) for the analysis of high-throughput images. An on-site AI algae monitoring system on top of an edge AI chip embedded with the proposed Algal Morphology Deep Neural Network (AMDNN) model is developed to achieve real-time algae species classification and HAB prediction. Based on a detailed examination of real-world algae images, dataset augmentation is first performed: consisting of orientation, flipping, blurring, and Resizing with Aspect ratio Preserved (RAP). The dataset augmentation is shown to significantly improve classification performance which is superior to that of the competitive RF model. And the attention heatmaps show that for relatively regular-shaped algal species (e.g., Vicicitus), the model weights the color and texture information heavily; while the shape-related features are more important for complex-shaped algae (e.g., Chaetoceros). The AMDNN is tested on a dataset of 11,250 algae images containing the 25 most common HAB classes in Hong Kong subtropical waters with 99.87% test accuracy. Based on the fast and accurate algae classification, the AI-chip-based on-site system is applied to a one-month dataset in February 2020; the predicted trends of total cell counts and targeted HAB species counts are in good agreement with observations. The proposed edge AI algae monitoring system provides a platform for the development of practical HAB early warning systems that can effectively support environmental risk and fisheries management.

Shape and texture analyses based on conventional MRI for the preoperative prediction of the aggressiveness of pituitary adenomas.

Pituitary adenomas can exhibit aggressive behavior, characterized by rapid growth, resistance to conventional treatment, and early recurrence. This study aims to evaluate the clinical value of shape-related features combined with textural features based on conventional MRI in evaluating the aggressiveness of pituitary adenomas and develop the best diagnostic model. Two hundred forty-six pituitary adenoma patients (84 aggressive, 162 non-aggressive) who underwent preoperative MRI were retrospectively reviewed. The patients were divided into training (n = 193) and testing (n = 53) sets. Clinical information, shape-related, and textural features extracted from the tumor volume on contrast-enhanced T1-weighted images (CE-T1WI), were compared between aggressive and non-aggressive groups. Variables with significant differences were enrolled into Pearson's correlation analysis to weaken multicollinearity. Logistic regression models based on the selected features were constructed to predict tumor aggressiveness under fivefold cross-validation. Sixty-five imaging features, including five shape-related and sixty textural features, were extracted from volumetric CE-T1WI. Forty-seven features were significantly different between aggressive and non-aggressive groups (all p values < 0.05). After feature selection, four features (SHAPE_Sphericity, SHAPE_Compacity, DISCRETIZED_Q3, and DISCRETIZED_Kurtosis) were put into logistic regression analysis. Based on the combination of these features and Knosp grade, the model yielded an area under the curve value of 0.935, with a sensitivity of 94.4% and a specificity of 82.9%, to discriminate between aggressive and non-aggressive pituitary adenomas in the testing set. The radiomic model based on tumor shape and textural features study from CE-T1WI might potentially assist in the preoperative aggressiveness diagnosis of pituitary adenomas. • Pituitary adenomas with aggressive behavior exhibit rapid growth, resistance to conventional treatment, and early recurrence despite gross resection and may require multiline treatments. • Shape-related features and texture features based on CE-T1WI were significantly correlated with the Ki-67 labeling index, mitotic count, and p53 expression, and the proposed model achieved a favorable prediction of the aggressiveness of PAs with an AUC value of 0.935. • The prediction model might provide valuable guidance for individualized treatment in patients with PAs.

Gray and white matter structural examination for diagnosis of major depressive disorder and subthreshold depression in adolescents and young adults: a preliminary radiomics analysis

BackgroundRadiomics is an emerging image analysis framework that provides more details than conventional methods. In present study, we aimed to identify structural radiomics features of gray matter (GM) and white matter (WM), and to develop and validate the classification model for major depressive disorder (MDD) and subthreshold depression (StD) diagnosis using radiomics analysis.MethodsA consecutive cohort of 142 adolescents and young adults, including 43 cases with MDD, 49 cases with StD and 50 healthy controls (HC), were recruited and underwent the three-dimensional T1 weighted imaging (3D-T1WI) and diffusion tensor imaging (DTI). We extracted radiomics features representing the shape and diffusion properties of GM and WM from all participants. Then, an all-relevant feature selection process embedded in a 10-fold cross-validation framework was used to identify features with significant power for discrimination. Random forest classifiers (RFC) were established and evaluated successively using identified features.ResultsThe results showed that a total of 3030 features were extracted after preprocessing, including 2262 shape-related features from each T1-weighted image representing GM morphometry and 768 features from each DTI representing the diffusion properties of WM. 25 features were selected ultimately, including ten features for MDD versus HC, eight features for StD versus HC, and seven features for MDD versus StD. The accuracies and area under curve (AUC) the RFC achieved were 86.75%, 0.93 for distinguishing MDD from HC with significant radiomics features located in the left medial orbitofrontal cortex, right superior and middle temporal regions, right anterior cingulate, left cuneus and hippocampus, 70.51%, 0.69 for discriminating StD from HC within left cuneus, medial orbitofrontal cortex, cerebellar vermis, hippocampus, anterior cingulate and amygdala, right superior and middle temporal regions, and 59.15%, 0.66 for differentiating MDD from StD within left medial orbitofrontal cortex, middle temporal and cuneus, right superior frontal, superior temporal regions and hippocampus, anterior cingulate, respectively.ConclusionThese findings provide preliminary evidence that radiomics features of brain structure are valid for discriminating MDD and StD subjects from healthy controls. The MRI-based radiomics approach, with further improvement and validation, might be a potential facilitating method to clinical diagnosis of MDD or StD.

Sex determination of Japanese rhinoceros beetles, Trypoxylus dichotomus (Coleoptera: Scarabaeidae), based on their dropping shape

The Mahalanobis-Taguchi system (MTS) is one of the multi-variate analyses which can classify by correlations among multi-variables. It has a significant advantage of applying a cause analysis which provides effective variable combinations to upgrade the accuracy of the classification. In this study, droppings, which were extruded from Japanese rhinoceros beetle larva (called Kabutomushi in Japanese) were classified into male/female based on their shape-related features using the MTS. Their droppings have a spheroid shape of approximately 10 mm in their long axis. Seven features (i.e., variables) were obtained from digital micrographic images using image analysis software, such as height/width (H/M), major/minor (Ma/Mi), perimeter/Feret diameter (P/F), projected area/Feret diameter (A/F), roundness, circularity, and solidity. Although an abnormality rate, which shows how the correlation pattern of one larval dropping is far from any standard ones, has a boundary in order to classify into male/female from 18 larval droppings, 3 larva were judged as the opposite sex. Based on the cause analysis, the A/F and solidity were the best variable combination which all the larval droppings were completely classified into male/female. Why these variables were affected by the sex most seemed to be caused by the gut components, as determined by time-domain nuclear magnetic resonance (TD-NMR). MTS has the great ability to classify from the powders’ minor difference and will be an effective tool for particle design in the near future.

The impact of phantom design and material-dependence on repeatability and reproducibility of CT-based radiomics features.

To understand the design of radiomics phantom and material-dependence on repeatability and reproducibility of computed tomography (CT) radiomics features. A radiomics phantom consisting of various materials with uniformity, textural, and biological components, was constructed. The phantom was scanned with different manufacturer CT scanners and the scans were repeated multiple times on the same scanner with different acquisition settings as kVp, mAs, orientation, field of view (FOV), slice thickness, pitch, reconstruction kernels, and acquisition mode. A total of 72 phantom scans were included. For each scan, 18 different regions of interest (ROI) were contoured and 708 radiomics features were extracted from each ROI via an open source radiomics tool, IBEX. To relate the phantom data to patient data, the radiomics features from different phantom materials were compared with those extracted from 50 patients' images of five disease sites as brain, head-and-neck, breast, liver, and lung cases using box-plots comparison and principal component analysis (PCA). The temporal stability of imaging features was then evaluated with respect to a controlled scenario (test-retest) via the intra-class correlation coefficient (ICC). The reproducibility of radiomics features with respect to different scanners or acquisition settings were further evaluated with concordance correlation coefficients (CCC). Among all phantom materials, the biological component had feature values closest to human tissues, especially for tumors in brain and liver. The textural component showed similar ranges of variation to lung lesions, particularly for cartridges of rice, cereal, and the 3D-printed textural phantom with fine and rough grid. It also showed that certain materials, such as polystyrene foam, plaster, and peanuts, did not have comparable values to human tissue and could be excluded for future phantom design. High repeatability was observed in the test-retest study as indicated by an ICC value of 0.998±0.020. All materials were used for feature stability analysis. For the inter-scanner study, shape-related features were the most-reliable category with 94% of features having CCC≥0.9, while gradient orientation histogram (GOH) were the least-reliable with only 14.6% meeting the criteria. For the intra-scanner study, the reproducibility of CT-based radiomics features showed material-dependence. In general, the instability of radiomics features introduced by kVp, mAs, pitch, acquisition mode, and orientation were relatively mild. However, the homogeneous materials were more vulnerable to those changes compared to materials with textural patterns. Regardless of material compositions, resolution parameters like FOV and slice thickness, could have large impact on feature stability. Switching between standard and bone reconstruction kernels could also result significant changes to feature reproducibility. We have built a radiomics phantom using materials that cover a wide span of tumor textures seen in oncological CT images. The designed phantom presents a preliminary opportunity for investigating reproducibility of radiomics features and the reproducibility can be material dependent. Thus, in the radiomics quality assurance design, it is important to choose appropriate materials that can provide a close range of radiomics features to patients with specific disease sites dependency taken into consideration.

Review on Natural, Incidental, Bioinspired, and Engineered Nanomaterials: History, Definitions, Classifications, Synthesis, Properties, Market, Toxicities, Risks, and Regulations.

Nanomaterials are becoming important materials in several fields and industries thanks to their very reduced size and shape-related features. Scientists think that nanoparticles and nanostructured materials originated during the Big Bang process from meteorites leading to the formation of the universe and Earth. Since 1990, the term nanotechnology became very popular due to advances in imaging technologies that paved the way to specific industrial applications. Currently, nanoparticles and nanostructured materials are synthesized on a large scale and are indispensable for many industries. This fact fosters and supports research in biochemistry, biophysics, and biochemical engineering applications. Recently, nanotechnology has been combined with other sciences to fabricate new forms of nanomaterials that could be used, for instance, for diagnostic tools, drug delivery systems, energy generation/storage, environmental remediation as well as agriculture and food processing. In contrast with traditional materials, specific features can be integrated into nanoparticles, nanostructures, and nanosystems by simply modifying their scale, shape, and composition. This article first summarizes the history of nanomaterials and nanotechnology. Followed by the progress that led to improved synthesis processes to produce different nanoparticles and nanostructures characterized by specific features. The content finally presents various origins and sources of nanomaterials, synthesis strategies, their toxicity, risks, regulations, and self-aggregation.

Noncontrast Computed Tomography Markers of Cerebral Hemorrhage Expansion: Diagnostic Accuracy Meta-Analysis.

Assess the diagnostic accuracy of noncontrast computed tomography (NCCT) markers of hematoma expansion in patients with primary intracerebral hemorrhage. We performed a meta-analysis of observational studies and randomized controlled trials with available data for calculation of sensitivity and specificity of NCCT markers for hematoma expansion (absolute growth >6 or 12.5 mL and/or relative growth >33%). The following NCCT markers were analyzed: irregular shape, island sign (shape-related features); hypodensity, heterogeneous density, blend sign, black hole sign, and swirl sign (density-related features). Pooled accuracy values for each marker were derived from hierarchical logistic regression models. A total of 10,363 subjects from 23 eligible studies were included. Significant risk of bias of included studies was noted. Hematoma expansion frequency ranged from 7% to 40%, mean intracerebral hemorrhage volume from 9 to 27.8 ml, presence of NCCT markers from 9% (island sign) to 82% (irregular shape). Among shape features, sensitivity ranged from 0.32 (95%CI = 0.20-0.47) for island sign to 0.68 (95%CI = 0.57-0.77) for irregular shape, specificity ranged from 0.47 (95%CI = 0.36-0.59) for irregular shape to 0.92 (95%CI = 0.85-0.96) for island sign; among density features sensitivity ranged from 0.28 (95%CI = 0.21-0.35) for black hole sign to 0.63 (95%CI = 0.44-0.78) for hypodensity, specificity ranged from 0.65 (95%CI = 0.56-0.73) for heterogeneous density to 0.89 (95%CI = 0.85-0.92) for blend sign. Diagnostic accuracy of NCCT markers remains suboptimal for implementation in clinical trials although density features performed better than shape-related features. This analysis may help in better tailoring patients' selection for hematoma expansion targeted trials.

Feature extraction for chart pattern classification in financial time series

Extracting shape-related features from a given query subsequence is a crucial preprocessing step for chart pattern matching in rule-based, template-based and hybrid pattern classification methods. The extracted features can significantly influence the accuracy of pattern recognition tasks during the data mining process. Although shape-related features are widely used for chart pattern matching in financial time series, the intrinsic properties of these features and their relationships to the patterns are rarely investigated in research community. This paper aims to formally identify shape-related features used in chart patterns and investigates their impact on chart pattern classifications in financial time series. In this paper, we describe a comprehensive analysis of 14 shape-related features which can be used to classify 41 known chart patterns in technical analysis domain. In order to evaluate their effectiveness, shape-related features are then translated into rules for chart pattern classification. We perform extensive experiments on real datasets containing historical price data of 24 stocks/indices to analyze the effectiveness of the rules. Experimental results reveal that the features put forward in this paper can be effectively used for recognizing chart patterns in financial time series. Our analysis also reveals that high-level features can be hierarchically composed from low-level features. Hierarchical composition allows construction of complex chart patterns from features identified in this paper. We hope that the features identified in this paper can be used as a reference model for the future research in chart pattern analysis.

Dialect Identification using Chroma-Spectral Shape Features with Ensemble Technique

The present work proposes a text-independent dialect identification system. Generally, dialects of a language exhibit varying pronunciation styles followed in a specific geographical region. In this paper, chroma features familiar with music-related systems are employed for identification of dialects. In addition, eight significant spectral shape related features from short term spectra are computed and combined along with chroma features and named as chroma-spectral shape features. Chroma features try to aggregate spectral information and attempt to encapsulate the evidential variations, concerning timbre, correlated melody, rhythmic, and intonation patterns found prominently among dialects of few languages. The effectiveness of the proposed features and approach is evaluated on five prominent Kannada dialects spoken in Karnataka, India and internationally known standard Intonation Variation in English (IViE) dataset with nine British English dialects. Discriminative models such as, single classifier based Support Vector Machine (SVM) and ensemble based support vector machines (ESVM) are employed for classification. The proposed features have shown better performance over state-of-the-art i-vector features on both datasets. The highest recognition performance of 95.6% and 97.52% are achieved in the cases of Kannada and IViE dialect datasets respectively using ESVM. Proposed features have also demonstrated robust performance with small sized (limited data) audio clips even in noisy conditions.

Shape related features of intracranial aneurysm are associated with rupture status in a large Chinese cohort

BackgroundTo investigate the prevalence of small ruptured saccular intracranial aneurysms (sIA) in a Chinese cohort and to identify factors associated with rupture status of sIAs.MethodsConsecutive patients with confirmed sIAs by...

Comparative analysis of machine learning algorithms for Lip print based person identification

Human identification is centered on the theory that every individual is unique and has distinct characteristics. Various metrics like Fingerprints, DNA and Retina can be used for this purpose. Nonetheless, there is still a need for reliable alternatives in order to establish the identity of an individual on occasions where the above techniques are unavailable. Cheiloscopy is a technique of identifying an individual based on lip prints. It finds applications in medical fields predominantly in the forensic odontology. The patterns formed on the human lips and it’s shape is found to be unique for every individual. Patterns found on the human lips are perpetual unless subjected to major trauma or alterations. Analogous to the existing bio metrics, Lip prints can serve the purpose of confirming an individual’s identity. The main objective of this work is to design a robust computer-aided system that would identify an individual solely based on the lip-prints and work across diverse datasets. Local Binary Patterns are used to extract the texture based features from the segmented upper and lower lip. Shape related features are also extracted as a part of the feature extraction process. Finally, the extracted features are classified using various classifiers like Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Ensemble classifiers and Neural Networks. Performance of each and every classifier is analyzed. The classification results showed that the features extracted from the upper and the lower lip regions can be satisfactorily used to identify a person uniquely.

Integrating segmentation information into CNN for breast cancer diagnosis of mammographic masses

Background and ObjectivesSegmentation of mammographic lesions has been proven to be a valuable source of information, as it can assist in both extracting shape-related features and providing accurate localization of the lesion. In this work, a methodology is proposed for integrating mammographic mass segmentation information into a convolutional neural network (CNN), aiming to improve the diagnosis of breast cancer in mammograms. MethodsThe proposed methodology involves modification of each convolutional layer of a CNN, so that information of not only the input image but also the corresponding segmentation map is considered. Furthermore, a new loss function is introduced, which adds an extra term to the standard cross-entropy, aiming to steer the attention of the network to the mass region, penalizing strong feature activations based on their location. The segmentation maps are acquired either from the provided ground-truth or from an automatic segmentation stage. ResultsPerformance evaluation in diagnosis is conducted on two mammographic mass datasets, namely DDSM-400 and CBIS-DDSM, with differences in quality of the corresponding ground-truth segmentation maps. The proposed method achieves diagnosis performance of 0.898 and 0.862 in terms AUC when using ground-truth segmentation maps and a maximum of 0.880 and 0.860 when a U-Net-based automatic segmentation stage is employed, for DDSM-400 and CBIS-DDSM, respectively. ConclusionsThe experimental results demonstrate that integrating segmentation information into a CNN leads to improved performance in breast cancer diagnosis of mammographic masses.

An Efficient Hemorrhage Detection System using Decision Tree Classifier

the visual representations of the inner constituents of body along with the functions of either organs or tissues comprising its physiology are developed in medical imaging. These images can be obtained by various techniques such as computed tomography (CT), magnetic resonant imaging (MRI), and x-ray. The objective of the system mentioned in this paper is to detect the presence of hemorrhage and to classify the type of it when detected. CT images are considered here to find the hemorrhage. Pre-processing techniques such as grayscale conversion, image resizing, edge detection and sharpening are done to make the input image suitable for further processing. After preprocessing the images go through morphological operations to help identify the shape related features in correspondence to the hemorrhage. Sobel and markers are used in the processed ct image to highlight the interested region. Then watershed algorithm is employed for the purpose of segmentation. The presence of hemorrhage can be detected as a result of segmentation. Once hemorrhage is detected feature extraction is done to classify its type. Active contours are drawn and features extracted are fed to the decision tree. The classifier helps in finding the type of hemorrhage with the detected features. The classifier result can be viewed, interpreted and evaluated by medical assistance. The aim of this research is to increase the chance of predicting hemorrhage in the image and then to classify its type. The proposed system classifies three types of hemorrhages. The average accuracy of the system in classifying the three types of hemorrhage is found as 98%

A Multi-Sensor System for Silkworm Cocoon Gender Classification via Image Processing and Support Vector Machine.

Sericulture is traditionally a labor-intensive rural-based industry. In modern contexts, the development of process automation faces new challenges related to quality and efficiency. During the silkworm farming life cycle, a common issue is represented by the gender classification of the cocoons. Improper cocoon separation negatively affects quantity and quality of the yield resulting in disruptive bottlenecks for the productivity. To tackle this issue, this paper proposes a multi sensor system for silkworm cocoons gender classification and separation. Utilizing a load sensor and a digital camera, the system acquires weight and digital images from individual silkworm cocoons. An image processing procedure is then applied to extract significant shape-related features from each image instance, which, combined with the weight data, are provided as inputs to train a Support Vector Machine-based pattern classifier for gender classification. Subsequently, an air blower mechanism and a conveyor system sort the cocoons into their respective bins. The developed system was trained and tested on two different types of silkworm cocoons breeds, respectively CSR2 and Pure Mysore. The system performances are finally discussed in terms of accuracy, robustness and computation time.

Examining lag time using the landscape, pedoscape and lithoscape metrics of catchments

• Results indicate that lag time can be explicitly explained by the structure of the landscape. • Not only LULC but also can HSGs and GPCs effect on measures of lag time. • Degree of regularity, irregularity, and elongation of LULC, HSGs, and GPCs affect lag time. In order to explain total variations of lag time as a type of hydrological response affected by landscape-related features of catchments, the present study addresses relationships between lag time and the landscape structure-related metrics (perimeter-area ratio, contiguity index, fractal dimension index, shape index, and related circumscribing circle) of land use/land cover, hydrologic soil groups, and geological permeability classes. To explain a given catchment’s lag time, a regionalization approach was adopted, applying spatial data from 39 catchments located in the southern basin of the Caspian Sea, with areas varying from 33 to 4800 km 2 and mean discharge ranging from 0.47 to 21 m 3 s −1 . Forest cover (57.4%) accounts for the dominant land cover, while rangeland, farmland, and urban areas comprise the remaining 25.9%, 11.7%, and 1.6%, respectively. Category-level landscape structure metrics were estimated for the catchments’ land use/land cover, hydrologic soil groups, and geological permeability classes. These metrics were then applied as independent variables to stepwise multiple linear regression analysis in an attempt to explain the catchment lag time. The regression-based models (0.68 ≤ r 2 ≤ 0.80) indicated that the catchment lag time could be explicitly predicted by applying the average values of the related circumscribing circle, fractal dimension, perimeter-area ratio, and shape indices for the landscape categories, hydrologic soil groups, and geologic permeability classes of the catchments. The findings also indicated that shape-related features, implying regularity, irregularity, and elongation of the patches of landscape classes, hydrologic soil groups, and geological permeability classes, can be used to explain total variations in lag time of the catchments. Based on the results of the inter-model comparison, the most appropriate model is the regression model developed using the fractal dimension index, which has a high level of reliability (based on the results of the uncertainty analysis).

Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow.

We propose a method to classify cardiac pathology based on a novel approach to extract image derived features to characterize the shape and motion of the heart. An original semi-supervised learning procedure, which makes efficient use of a large amount of non-segmented images and a small amount of images segmented manually by experts, is developed to generate pixel-wise apparent flow between two time points of a 2D+t cine MRI image sequence. Combining the apparent flow maps and cardiac segmentation masks, we obtain a local apparent flow corresponding to the 2D motion of myocardium and ventricular cavities. This leads to the generation of time series of the radius and thickness of myocardial segments to represent cardiac motion. These time series of motion features are reliable and explainable characteristics of pathological cardiac motion. Furthermore, they are combined with shape-related features to classify cardiac pathologies. Using only nine feature values as input, we propose an explainable, simple and flexible model for pathology classification. On ACDC training set and testing set, the model achieves 95% and 94% respectively as classification accuracy. Its performance is hence comparable to that of the state-of-the-art. Comparison with various other models is performed to outline some advantages of our model.

An unsupervised metaheuristic search approach for segmentation and volume measurement of pulmonary nodules in lung CT scans

This paper proposes a new methodology to automatically segment and measure the volume of pulmonary nodules in lung computed tomography (CT) scans. Estimating the malignancy likelihood of a pulmonary nodule based on lesion characteristics motivated the development of an unsupervised pulmonary nodule segmentation and volume measurement as a preliminary stage for pulmonary nodule characterization. The idea is to optimally cluster a set of feature vectors composed by intensity and shape-related features in a given feature data space extracted from a pre-detected nodule. For that purpose, a metaheuristic search based on evolutionary computation is used for clustering the corresponding feature vectors. The proposed method is simple, unsupervised and is able to segment different types of nodules in terms of location and texture without the need for any manual annotation. We validate the proposed segmentation and volume measurement on the Lung Image Database Consortium and Image Database Resource Initiative – LIDC-IDRI dataset. The first dataset is a group of 705 solid and sub-solid (assessed as part-solid and non-solid) nodules located in different regions of the lungs, and the second, more challenging, is a group of 59 sub-solid nodules. The average Dice scores of 82.35% and 71.05% for the two datasets show the good performance of the segmentation proposal. Comparisons with previous state-of-the-art techniques also show acceptable and comparable segmentation results. The volumes of the segmented nodules are measured via ellipsoid approximation. The correlation and statistical significance between the measured volumes of the segmented nodules and the ground-truth are obtained by Pearson correlation coefficient value, obtaining an R-value ≥ 92.16% with a significance level of 5%.