Mass Segmentation Research Articles

Efficient segmentation method using quantised and non‐linear CeNN for breast tumour classification

A new segmentation method for mammography imaging system is proposed. Segmentation of masses is always a difficult problem in radiological image interpretation. Conventional methods such as region growing suffer from their computational complexity and hence can hardly be used for segmentation of high-resolution images. In order to achieve efficiency in both computational complexity and accuracy, a novel digital cellular neural network (CeNN) based approach is presented for segmentation. The approach is featured with quantisation to significantly reduce the computational complexity and non-linear template for robustness. After segmentation, a multilayer perceptron classifier is used for feature extraction and classification. Compared with other prior works, the proposed work is able to reduce resource overhead up to 63% and energy consumption up to 41% on FPGA while maintaining only up to 1.5 and 0.6% accuracy deviations for mediolateral-oblique and cranial-caudal views, respectively.

The Correlation between Activities of Daily Living and Physical Composition for Healthy Science Research: A Randomized Controlled Pilot Trial in Stroke

The purpose of this study was to establish a correlation between the physical compositions of stroke patients and their activities of daily living. The participants in this study included 33 hemiplegic stroke patients. The physical composition measurements included fat-free mass, body fat mass, percentage of body fat, and the segmental muscle mass of the participants. The difference in muscle mass between the paralyzed and non-paralyzed sides of the body was calculated through the analysis in stroke. The activities of daily living were evaluated by scoring the respondents’ basic activities of daily living using the modified Barthel index (MBI) scale. The correlation between the MBI score and the muscle mass of both limbs was not significant. Although not statistically significant, the MBI score and body fat percentage showed a slight negative correlation. The conclusion of this study is that the relationship between the physical composition of stroke patients and activities of daily living cannot be clearly defined.

Evaluating Controls on Nutrient Retention and Export in Wide and Narrow Valley Segments of a Mountain River Corridor

AbstractOver the past few decades, nitrate‐nitrogen (NO3‐N) concentrations have increased within streams of the central Rockies, a pattern linked to regional N deposition trends. As NO3‐N concentrations increase, in‐stream biological demand may become saturated and stream N export may increase. In mountain landscapes, streams generally flow through steep, narrow valleys with limited riparian area and strong stream‐hillslope connectivity. Interspersed between the narrow valleys are wide segments where substantial floodplain riparian areas can develop. Here, we coupled measures of stream reach NO3‐N flux balances with nutrient enrichment experiments along two stream reaches of contrasting valley morphology in Rocky Mountain National Park. The stream reaches were (1) a narrow valley segment with limited floodplain riparian area and (2) a longitudinally adjacent (directly downstream) wide valley segment with extensive floodplain riparian area. We found that in‐stream biological uptake of added NO3‐N was limited in both segments, presumably as a consequence of saturating conditions. Assessment of mass flux indicated that the narrow valley segment was a consistent source of water and NO3‐N across flow states, while the wide segment was a sink at high flow and a source at low flow. Due to low in‐stream biological retention, gross gains and losses of water and NO3‐N to and from the stream exerted primary constraint on segment mass balances. Our results suggest that the exchange of water and nutrients between the stream and adjacent landscape can exert strong control on reach‐scale nutrient export, particularly in streams experiencing or approaching N saturation.

Unbalance-induced rub between rotor and compliant-segmented stator

Today, turbomachinery designers are trying to attain zero clearances for optimizing performance and efficiency of machine by designing advanced compliant-segmented seals. This trend involves secondary issues such as rotor-to-stator contact interaction which is to be treated with more technical knowledge in rotordynamic design and condition monitoring programs. The aim of this paper is to gain insight into dynamic interaction between a flexible rotor and a set of compliant arc-shaped segments as stator system. Specifically, the unbalanced-induced forward rubbing response is investigated in tight clearance condition during resonance-passing situations. A Jeffcott rotor modeling is used for representing the flexible rotor. A set of linear elastically-mounted rigid bodies with arc-shaped inner surfaces, which are arranged circumferentially around the rotor, are assumed as the model of the stator. The effects of mass, rotary inertia, translational and tilting stiffnesses are taken into account in the segment modeling. To compute the contact dynamic response, the equations of motion are coupled via Lagrange multiplier technique. The constrained equation of motion is solved by an implicit predictor-corrector time-marching numerical algorithm. Investigations reveal that the steady-state coupled rubbing solutions exist for the rotor interacting with the segmented stator. The solutions are classified with respect to stator properties, e.g. the number of segments and the stator stiffness. The synchronous rubbing solution covers various feature including shift in resonance speed, lower amplitude of rotor's vibration, smooth rise and fall in case of soft segments, jump phenomena in case of stiff segments, chaotic orbiting motion under effects of segment mass, etc. as are discussed in detail.

Automated and real-time segmentation of suspicious breast masses using convolutional neural network.

In this work, a computer-aided tool for detection was developed to segment breast masses from clinical ultrasound (US) scans. The underlying Multi U-net algorithm is based on convolutional neural networks. Under the Mayo Clinic Institutional Review Board protocol, a prospective study of the automatic segmentation of suspicious breast masses was performed. The cohort consisted of 258 female patients who were clinically identified with suspicious breast masses and underwent clinical US scan and breast biopsy. The computer-aided detection tool effectively segmented the breast masses, achieving a mean Dice coefficient of 0.82, a true positive fraction (TPF) of 0.84, and a false positive fraction (FPF) of 0.01. By avoiding positioning of an initial seed, the algorithm is able to segment images in real time (13–55 ms per image), and can have potential clinical applications. The algorithm is at par with a conventional seeded algorithm, which had a mean Dice coefficient of 0.84 and performs significantly better (P< 0.0001) than the original U-net algorithm.

Classification of Breast Masses Using a Computer-Aided Diagnosis Scheme of Contrast Enhanced Digital Mammograms.

Contrast-enhanced digital mammography (CEDM) is a promising imaging modality in breast cancer diagnosis. This study aims to investigate how to optimally develop a computer-aided diagnosis (CAD) scheme of CEDM images to classify breast masses. A CEDM dataset of 111 patients was assembled, which includes 33 benign and 78 malignant cases. Each CEDM includes two types of images namely, low energy (LE) and dual-energy subtracted (DES) images. A CAD scheme was applied to segment mass regions depicting on LE and DES images separately. Optimal segmentation results generated from DES images were also mapped to LE images or vice versa. After computing image features, multilayer perceptron based machine learning classifiers that integrate with a correlation-based feature subset evaluator and leave-one-case-out cross-validation method were built to classify mass regions. When applying CAD to DES and LE images with original segmentation, areas under ROC curves (AUC) were 0.759 ± 0.053 and 0.753 ± 0.047, respectively. After mapping the mass regions optimally segmented on DES images to LE images, AUC significantly increased to 0.848 ± 0.038 (p < 0.01). Study demonstrated that DES images eliminated overlapping effect of dense breast tissue, which helps improve mass segmentation accuracy. The study demonstrated that applying a novel approach to optimally map mass region segmented from DES images to LE images enabled CAD to yield significantly improved performance.

Induction, Growth Kinetics and Morpho-histological Characterization of Neem Callus

Azadirachta indica A. Juss, popularly known as neem, is a species native to India, belonging to family Meliaceae, considered the most important plant species with insecticidal action. The aim of this study was to evaluate the influence of growth regulators on induction and growth of neem callus and to observe their viability for embryogenesis through morpho-histological characteristics. In vitro germinated plants were used for excision of nodal explants. These segments were inoculated in Murashige and Skoog culture medium containing 1.0 mg/l 2,4-D (2,4-dichlorophenoxyacetic) combined with BAP (6-benzylaminopurine) at the following concentrations: 0.0, 0.5, 1.0 and 2.0 mg/l (T1, T2, T3 and T4 respectively), for callus induction. At 0 (mass of nodal segments without callus), 20, 40 and 60 days of culture, the percentage of callus formation was observed and the callus weight was measured for each treatment and at the end of the 60 days, consistency, color, and cell histology were evaluated. There was callus formation in all treatments tested. The highest induction of Azadirachta indica A. Juss callus is observed in the presence of 1.0 mg/l 2,4-D + 2.0 mg/l BAP, with callus showing light brown color, friable consistency and rounded cells with intense cell division, typical of cells with potential embryogenic capacity.

Evaluation of a pictorial method to obtain subject-specific inertial properties in equine limb segments.

Data describing segmental masses and moments of inertia (MOI) of limb segments are required for inverse dynamic calculations. In horses, these values are usually calculated using regression equations that have been developed from a limited number of horses representing a small number of breeds. The objective of the present study was to evaluate the performance of a scaling method and a pictorial method for estimating of the values of segmental masses, lengths, and MOI in the equine limb segments by comparing their output with the standard technique involving direct measurements. Limbs of 30 horses of various breeds and sizes were disarticulated post mortem. Segmental masses, lengths, and MOI were determined using a standard method based on weighing the segments, measuring their length with calipers, and estimating the MOI from the rotational frequency of a trifilar pendulum. The scaling method used a jack-knifing procedure to avoid the need for two data sets. The pictorial method was based on digitization of two orthogonal photographs to determine segmental volumes, which were combined with published values for average segment densities to determine the inertial parameters. Scaling method and pictorial method provided comparable estimation of segmental messes and lengths, but the scaling method performed better in estimating segmental MOI. The scaling method worked well enough in the majority of horses but there were a few horses in which it was less effective. The pictorial method sometimes showed a bias correctable by regression equations but it may not warrant the additional effort unless for specific cases.

Differences In Lean Mass And Strength In Adolescent ACLR Female Athletes

PURPOSE: To compare differences in total and segmental lean mass (LM), muscle strength and lower leg force production between adolescent female athletes with and without anterior cruciate ligament repair (ACLR). METHODS: Twenty-four females, 12 ACLR and 12 healthy controls (CON), were matched by age (16.4±0.9 vs 16.4±1.0 yrs), body mass index (23.2±2.1 vs 23.2±2.7 kg/m2), and sport. Total, segmental, and regional body composition were measured by 3 DXA scans (1 total body, 2 lateral leg). Muscle peak torque for knee extension/flexion (60, 120°/sec) was measured using isokinetic dynamometry. Lower limb force, power and jump height were measured using a squat jump on dual force plates. Paired t-tests assessed total, regional and segmental lean mass, peak torque and lower limb force production differences within (Involved/Non-involved) and between groups (ACLR/CON). Linear regression assessed the total-leg LM vs peak force relation of each leg and of ACLR vs CON. RESULTS: No body composition differences were observed between ACLR and CON groups (p=0.07-0.90). However, ACLR INV legs had significantly lower total LM (7.1±0.8 vs 7.4±1.0 kg, p=0.004), anterior upper leg LM (1.5±0.3 vs 1.62±0.2 kg, p=0.007), and posterior upper leg LM (1.9±0.2 vs 2.0±0.2 kg, p=0.036). Peak torque was significantly lower in ACLR INV vs NINV legs (p<0.003) and vs CON (p=0.010-0.019) for extension at 60 and 120°/sec and flexion at 60°/sec (p=0.011), with no differences between ACLR NINV vs CON (p=0.23-0.90). Peak force was significantly lower in ACLR INV vs NINV legs (296±45 vs 375±55 N, p<0.001) and between ACLR INV legs vs CON (296±45 vs 372±88 N, p<0.015), but no significant (p=0.736) difference between ACLR NINV leg vs CON. The slope between total LM and peak force was smaller for ACLR participants (INV: m=0.02 r=0.36, p=0.25; NINV: m=0.03, r=0.50, p=0.10) compared to CON (INV: m=0.06, r=0.63, p=0.03; NINV: m=0.06, r=0.62, p=0.03). CONCLUSION: One year post-ACLR female athletes have significant differences in the quantity and quality of leg muscle, compared to matched CON athletes, for both involved and non-involved legs. Importantly, muscle function (strength and force production) is limited in both ACLR legs relative to the amount of lean mass, which may provide evidence for increased risk of ACL tear in the involved and non-involved legs.

Association between Segmental Lean Body Mass and Muscular Strength

Association between Segmental Lean Body Mass and Muscular Strength

Comfort Level Refinement of Military Tracked Vehicle Crew through Optimal Control Study

Military tracked vehicle and crew are modelled together in this paper as integrated man-machine lumped parameter model, by integrating the simplified 5 degrees of freedom (DoF) tracked vehicle model, including seat and 4 DoF human bio-dynamic model, thus resulting in a 9 DoF simplified vehicle-occupant model. Then the natural frequency of major mass segment namely the chassis mass is obtained through simulation study, for a known road input. The value obtained is compared with that of an earlier research work, for validation of said man-machine model. Then focusing our study locally at crew seat location, parameters of crew seat suspension for ride comfort are optimised using the optimal digital state space controller designed for this purpose by implementing it in a 2 DoF occupant - seat suspension model and its Simulink model constructed. Simulation results illustrate the attainment of the goal by meeting the controller design requirements.

Agreement between single-frequency bioimpedance analysis and dual energy x-ray absorptiometry varies based on sex and segmental mass

Bioimpedance analysis (BIA) and dual energy X-ray absorptiometry (DXA) are commonly utilized for total and segmental body composition assessment, but the agreement between these methods varies. Group (i.e., constant error [CE]) and individual error (i.e., standard error of estimate [SEE] and 95% limits of agreement [LOAs]) of single-frequency BIA were determined in apparently healthy men and women (n = 28 and 45, respectively) when using DXA as a reference method. It was hypothesized that single-frequency BIA would provide lower error for the estimation of total and segmental FFM than FM and BF%. The CE for many of the total and segmental body composition comparisons revealed statistically significant (all P < .05) mean differences (FMTOTAL, FMLEGS, FFMTOTAL, FFMARMS, FFMLEGS, FFMTRUNK, BF%TOTAL and BF%ARMS for both sexes as well as FMTRUNK and BF%TRUNK for women and FMARMS and FMLEGS for men). Although there were significant CEs for many comparisons, the individual error (i.e., SEEs and 95% LOAs) for total and segmental FFM were small whereas FM and BF% were large. Furthermore, the individual error tended to be larger for men than women when estimating FM and BF%, which is likely attributed to the larger segmental mass of men. This finding indicates the agreement between single-frequency BIA and DXA varies based on sex and segmental mass. Consequently, single-frequency BIA can be used for total and segmental FFM, but is not recommended for FM and BF%.

Mass Segmentation in Automated 3-D Breast Ultrasound Using Adaptive Region Growing and Supervised Edge-Based Deformable Model.

Automated 3-D breast ultrasound has been proposed as a complementary modality to mammography for early detection of breast cancers. To facilitate the interpretation of these images, computer aided detection systems are being developed in which mass segmentation is an essential component for feature extraction and temporal comparisons. However, automated segmentation of masses is challenging because of the large variety in shape, size, and texture of these 3-D objects. In this paper, the authors aim to develop a computerized segmentation system, which uses a seed position as the only priori of the problem. A two-stage segmentation approach has been proposed incorporating shape information of training masses. At the first stage, a new adaptive region growing algorithm is used to give a rough estimation of the mass boundary. The similarity threshold of the proposed algorithm is determined using a Gaussian mixture model based on the volume and circularity of the training masses. In the second stage, a novel geometric edge-based deformable model is introduced using the result of the first stage as the initial contour. In a data set of 50 masses, including 38 malignant and 12 benign lesions, the proposed segmentation method achieved a mean Dice of 0.74 ± 0.19 which outperformed the adaptive region growing with a mean Dice of 0.65 ± 0.2 (p-value < 0.02). Moreover, the resulting mean Dice was significantly (p-value < 0.001) better than that of the distance regularized level set evolution method (0.52 ± 0.27). The supervised method presented in this paper achieved accurate mass segmentation results in terms of Dice measure. The suggested segmentation method can be utilized in two aspects: 1) to automatically measure the change in volume of breast lesions over time and 2) to extract features for a computer aided detection or diagnosis system.

Breast Mass Segmentation Using a Semi-automatic Procedure Based on Fuzzy C-means Clustering

Breast Mass Segmentation Using a Semi-automatic Procedure Based on Fuzzy C-means Clustering

Breast Mass Segmentation Using a Semi-automatic Procedure Based on Fuzzy C-means Clustering

Mammography is the primary modality that helped in the early detection and diagnosis of women breast diseases. Further, the process of extracting the masses in mammogram represents a challenging task facing the radiologists, due to problems such as fuzzy or speculated borders, low contrast and the presence of intensity inhomogeneities. Aims to help the radiologists in the diagnosis of breast cancer, many approaches have been conducted to automatically segment the masses in mammograms. Towards this aim, in this paper, we present a new approach for extraction of tumors from region-of-interest (ROI) using the algorithm of Fuzzy C-Means (FCM) setting two clusters for semi-automated segmentation. The proposed method meant to select as input data the set of pixels that enable to get the meaningful information required to segment the masses with high accuracy. This could be accomplished through eliminating unnecessary pixels, which influence on this process through separating it outside of the input data using an optimal threshold given by monitoring the change of clusters rate during the process of threshold decrementing. The proposed methodology has successfully segmented the masses, with an average sensitivity of 82.02% and specificity of 98.23%.

Elders’ fall detection based on biomechanical features using depth camera

An accidental fall poses a serious threat to the health of the elderly. With the advances of technology, an increased number of surveillance systems have been installed in the elderly home to help medical staffs find the elderly at risk. Based on the study of human biomechanical equilibrium, we proposed a fall detection method based on 3D skeleton data obtained from the Microsoft Kinect. This method leverages the accelerated velocity of Center of Mass (COM) of different body segments and the skeleton data as main biomechanical features, and adopts Long Short-Term Memory networks (LSTM) for fall detection. Compared with other fall detection methods, it does not require older people to wear any other sensors and can protect the privacy of the elderly. According to the experiment to validate our method using the existing database, we found that it could efficiently detect the fall behaviors. Our method provides a feasible solution for the fall detection that can be applied at homes of the elderly.

SCM-motivated enhanced CV model for mass segmentation from coarse-to-fine in digital mammography

A novel approach for mass segmentation from coarse-to-fine in digital mammography, termed as SCM-motivated enhanced CV algorithm, is presented in this paper. As well known, it is difficult to robustly achieve mammogram mass segmentation due to low contrast between normal and lesion tissues, as well as high density tissue interference in mammograms. Therefore, Spiking Cortical Model with biology background is introduced to achieve mammary-specific and mass edge detection, and this mass candidate is regarded as the initial contour of improved CV model followed by, effectively overcoming the drawback that CV method is sensitive to the initial contour; especially, the enhanced CV model innovatively combines the techniques of physical imaging principle, and local region-scalable force, harvesting the coarse-to-fine mass boundary accurately. The proposed method is tested totally on 400 mammograms from two well-known digitized datasets (digital database for screening mammography and mammography image analysis society database), achieving the average detection rate of 93.25%. By comparing with the region-based model with bias field (Method 1) and typical CV model (Method 2), we can reach the conclusion that proposed method is outperform other methods, yielding the average sensitivity of 95.83%, specificity of 99.13%, dice similarity co-efficient of 92.21% and AUC of 98.02%. In addition, this method is verified on the mammograms from Gansu Provincial Cancer Hospital, the detection results reveal that our method can accurately detect the abnormal in clinical application.

A comparison of methods to determine center of mass during pregnancy

Balance changes during pregnancy likely occur because of mass gains and mass distribution changes. However, to date there is no way of tracking balance through center of mass motion because no method is available to identify of the body center of mass throughout pregnancy. We compared methods for determining segment masses and torso center of mass location. The availability of a method for tracking these changes during pregnancy will make determining balance changes through center of mass motion an option for future pregnancy balance research. Thirty pregnant women from eight weeks gestation until birth were recruited for monthly anthropometric measurements, motion capture analysis of body segment locations, and force plate analysis of center of pressure during quiet standing and supine laying. From these measurements, we were able to compare regression, volume measurement, and weighted sum methods to calculate body center of mass throughout pregnancy. We found that mass changes around the trunk were most prevalent as expected, but mass changes throughout the body (especially the thighs) were also seen. Our findings also suggest that a series of anthropometric measurements first suggested by Pavol et al. (2002), in combination with quiet standing on a force plate, can be used to identify the needed components (segment masses and torso center of mass location in three dimensions) to calculate body center of mass changes during pregnancy. The results of this study will make tracking of center of mass motion a possibility for future pregnancy balance research.

Multi-period media planning for multi-products incorporating segment specific and mass media

Efficient budget allocation between different communication channels is one of the fundamental activities of any media planner. In this paper, we attempt to develop a multi-objective integer linear programming model to determine the optimal schedule of advertisements for a set of multiple products of a firm in a segmented market (influenced by both mass and segment-specific media) over a planning horizon. The objectives are to maximize the gross impressions of advertisements and simultaneously minimize the advertising expenditure. To incorporate continuous changes that occur in the market, the total planning horizon is divided into shorter time periods and decisions for each of the subsequent time periods are taken, bearing in mind the changes that have occurred in the preceding time periods. Based on the gap that exists in the extant literature, we also jointly consider, in our model, the notions of (a) carry-over effect of gross impressions, (b) spectrum effect of mass media on segments, and (c) cross-product effect. The model is solved through a goal programming approach to achieve the best trade-off between the conflicting objectives. Further, the model could be adapted to provide solutions in a wide variety of real-life situations. This is substantiated via a numerical analysis for a firm that advertises products in the Indian market through mass and segment-specific media.

Morphological operation and scaled Réyni entropy based approach for masses detection in mammograms

Detection of suspicious masses in mammograms play a vital role in early diagnosis of breast cancer, to reduce the death rate among women. The presence of masses and calcification’s in mammograms is distinguishing signs for breast cancer diagnosis. But in some cases, due to contrast variation, fuzzy boundaries and presence of noise in mammograms, segmentation and detection of masses is challenging assignment. This paper presents a new segmentation approach to detect masses in mammographic images. The proposed approach consist of artifacts elimination and pectoral region extraction, suspicious mass enhancement using dual morphological operation technique and finally, extraction of Regions of Interest (ROIs) from background using scaled Reyni entropy. The proposed system has been tested on two data-sets i.e. mini- Mammographic Image Analysis Society (mini-MIAS) and Digital Database for Screening Mammography (DDSM), over 50 and 90 mammograms respectively. Performance achieved with proposed system in terms of True Positive Fraction (TPF) yields 93.2% and 93.9% respectively, at the rate of 1.48 and 0.74 average False Positive per Image (FP/I), tested on both Cranio-Caudal (CC) and Medio-Lateral Oblique (MLO) views. The obtained experimental results demonstrates that proposed method gives improved results for mass detection and can be useful for radiologists in diagnosis of breast cancer at early stage.