Search

With recent advances in the field of deep learning, the use of convolutional neural networks (CNNs) in medical imaging has become very encouraging. The aim of our paper is to propose a patch-based CNN method for automated mass detection in full-field digital mammograms (FFDM). In addition to evaluating CNNs pretrained with the ImageNet dataset, we investigate the use of transfer learning for a particular domain adaptation. First, the CNN is trained using a large public database of digitized mammograms (CBIS-DDSM dataset), and then the model is transferred and tested onto the smaller database of digital mammograms (INbreast dataset). We evaluate three widely used CNNs (VGG16, ResNet50, InceptionV3) and show that the InceptionV3 obtains the best performance for classifying the mass and nonmass breast region for CBIS-DDSM. We further show the benefit of domain adaptation between the CBIS-DDSM (digitized) and INbreast (digital) datasets using the InceptionV3 CNN. Mass detection evaluation follows a fivefold cross-validation strategy using free-response operating characteristic curves. Results show that the transfer learning from CBIS-DDSM obtains a substantially higher performance with the best true positive rate (TPR) of 0.98 ± 0.02 at 1.67 false positives per image (FPI), compared with transfer learning from ImageNet with TPR of 0.91 ± 0.07 at 2.1 FPI. In addition, the proposed framework improves upon mass detection results described in the literature on the INbreast database, in terms of both TPR and FPI This work is partially supported by SMARTER project funded by Ministry of Economy and Competitiveness of Spain, under project reference DPI2015-68442-R.A. is funded by the support of the Secretariat of Universities and Research, Ministry of Economy and Knowledge, Government of Catalonia Ref. ECO/1794/2015 FIDGR-2016

Current practice for diabetic foot ulcers (DFU) screening involves detection and localization by podiatrists. Existing automated solutions either focus on segmentation or classification. In this work, we design deep learning methods for real-time DFU localization. To produce a robust deep learning model, we collected an extensive database of 1775 images of DFU. Two medical experts produced the ground truths of this data set by outlining the region of interest of DFU with an annotator software. Using five-fold cross-validation, overall, faster R-CNN with InceptionV2 model using two-tier transfer learning achieved a mean average precision of 91.8%, the speed of 48 ms for inferencing a single image and with a model size of 57.2 MB. To demonstrate the robustness and practicality of our solution to real-time prediction, we evaluated the performance of the models on a NVIDIA Jetson TX2 and a smartphone app. This work demonstrates the capability of deep learning in real-time localization of DFU, which can be further improved with a more extensive data set.

The proposed research methodology aims to design a generally implementable framework for providing a house owner/member with the immediate notification of an on-going theft (unauthorized access to their premises). For this purpose, a rigorous analysis of existing systems was undertaken to identify research gaps. The problems found with existing systems were that they can only identify the intruder after the theft, or cannot distinguish between human and non-human objects. Wireless Sensors Networks (WSNs) combined with the use of Internet of Things (IoT), Cognitive Internet of Things, Internet of Medical Things, and Cloud Computing are expanding smart home concepts and solutions, and their applications. The primary objective of the present research work was to design and develop IoT and cloud computing based smart home solutions. In addition, we also propose a novel smart home anti-theft system that can detect an intruder, even if they have partially/fully hidden their face using clothing, leather, fiber, or plastic materials. The proposed system can also detect an intruder in the dark using a CCTV camera without night vision facility. The fundamental idea was to design a cost-effective and efficient system for an individual to be able to detect any kind of theft in real-time and provide instant notification of the theft to the house owner. The system also promises to implement home security with large video data handling in real-time.

Breast ultrasound images have a complicated structure, which is difficult to be segmented due to the fact that it has low signal and affected by noise ratio. Recent research concentrated on the Region of Interest (ROI) labeling and ROI segmentation. In order to reduce chances of human error, stages of processing in breast ultrasound images might be different from one another. This research proposes a new image filtering method for breast ultrasound, namely Altered Phase Preserving Dynamic Range Compression (APPDRC). In addition, this paper compares the performance of filtering algorithms, in combination with standard thresholding segmentation. Focusing on the filtering stage, a comparison between the proposed method APPDRC Filter and previous approaches is validated on a dataset of 306 images, namely Inverted Median filter, Multifractal Filter, Hybrid Filter, SRAD filter, and PPDRC. Further, a summary of the work to date on the effect of filtering on lesion segmentation in ultrasound breast images is reported. Jaccard Similarity Index (JSI) is used for evaluation, in which the automated segmentation result is compared with the experienced radiologist's manual delineation. Our results revealed that making the choice of filtering algorithm affects the final segmentation results. Considering Mean JSI, Dice and MCC metrics, the proposed APPDRC Filter achieved the best performance, and outperformed the five evaluated filtering methods. Keywords: Ultrasound images, Jaccard similarity index, Filtering, Region-of-interest (ROI), Breast lesion, 2017 MSC: 00-01, 99-00

This paper outlines the procedure for automated segmentation of human thigh magnetic resonance images. Datasets that included sequential transverse-plane images (approximately 20 sequential images) were used to develop the framework and the images of mid-thigh were selected to establish the segmentation algorithm because these images contain essential parametric and geometric information that represents the subsequent images of the same dataset. Hence, if the mid-thigh can be decomposed accurately, it would significantly improve the prospects of decomposing all remaining transverse images within the dataset. The segmentation framework was designed based on the integration of statistical signal processing and medical imaging algorithms. The results showed good segmentation accuracy and fast processing time.

Existing methods for automated breast ultrasound lesions detection and recognition tend to be based on multi-stage processing, such as preprocessing, filtering/denoising, segmentation and classification. The performance of these processes is dependent on the prior stages. To improve the current state of the art, we have proposed an end-to-end breast ultrasound lesions detection and recognition using a deep learning approach. We implemented a popular semantic segmentation framework, i.e. Fully Convolutional Network (FCN-AlexNet) for our experiment. To overcome data deficiency, we used a pre-trained model based on ImageNet and transfer learning. We validated our results on two datasets, which consist of a total of 113 malignant and 356 benign lesions. We assessed the performance of the model using the following split: 70p for training data, 10p for validation data, and 20p testing data. The results show that our proposed method performed better on benign lesions, with a Dice score of 0.6879, when compared to the malignant lesions with a Dice score of 0.5525. When considering the number of images with Dice score > 0.5, 79p of the benign lesions were successfully segmented and correctly recognised, while 65p of the malignant lesions were successfully segmented and correctly recognised. This paper provides the first end-to-end solution for breast ultrasound lesion recognition. The future challenges for the proposed approaches are to obtain additional datasets and customize the deep learning framework to improve the accuracy of this method.

Manual identification of capillaries in transverse muscle sections is laborious and time consuming. Although the process of classifying a structure as a capillary is facilitated by (immuno)histochemical staining methods, human judgement is still required in a significant number of cases. This is mainly due to the fact that not all capillaries stain as strongly: they may have an elongated appearance and/or there may be staining artefacts that would lead to a false identification of a capillary. Here we propose two automated methods of capillary detection: a novel image processing approach and an existing machine learning approach that has been previously used to detect nuclei-shaped objects. The robustness of the proposed methods was tested on two sets of differently stained muscle sections. On average, the image processing approach scored a True Positive Rate of 0.817 and a harmonic mean (F1 measure) of 0.804 whilst the machine learning approach scored a True Positive Rate 0.843 and F1 measure of 0.846. Both proposed methods are thus able to mimic most of the manual capillary detection, but further improvements are required for practical applications.

The aim of this study was to compare the performance between young adults (n = 15), healthy old people (n = 10), and masters athletes (n = 15) using a depth sensor and automated digital assessment framework. Participants were asked to complete a clinically validated assessment of the sit-to-stand technique (five repetitions), which was recorded using a depth sensor. A feature encoding and evaluation framework to assess balance, core, and limb performance using time- and speed-related measurements was applied to markerless motion capture data. The associations between the measurements and participant groups were examined and used to evaluate the assessment framework suitability. The proposed framework could identify phases of sit-to-stand, stability, transition style, and performance between participant groups with a high degree of accuracy. In summary, we found that a depth sensor coupled with the proposed framework could identify performance subtleties between groups.

The contributions of fiber atrophy, fiber loss, in situ specific force, and voluntary activation to weakness in sarcopenia remain unclear. To investigate, 40 older (20 women; age 72 ± 4 years) and 31 younger adults (15 women, age 22 ± 3 years) completed measurements. The knee extensor maximal voluntary torque (MVC) was measured as well as voluntary activation, patella tendon moment arm length, muscle volume, and fascicle architecture to estimate in situ specific force. Fiber cross-sectional area (FCSA), fiber numbers, and connective tissue contents were also estimated from vastus lateralis biopsies. The MVC, quadriceps volume, and specific force were 39%, 28%, and 17% lower, respectively, in old compared with young, but voluntary activation was not different. The difference in muscle size was due in almost equal proportions to lower type II FCSA and fewer fibers. Five years later (n = 23) the MVC, muscle volume and voluntary activation in old decreased an additional 12%, 6%, and 4%, respectively, but there was no further change in specific force. In situ specific force declines relatively early in older age and reduced voluntary activation occurs later, but the overall weakness in sarcopenia is mainly related to loss of both type I and II fibers and type II fiber atrophy.

Digital image processing systems are complex, being usually composed of different computer vision libraries. Algorithm implementations cannot be directly used in conjunction with algorithms developed using other computer vision libraries. This paper formulates a software solution by proposing a processor with the capability of handling different types of image processing algorithms, which allow the end users to install new image processing algorithms from any library. This approach has other functionalities like capability to process one or more images, manage multiple processing jobs simultaneously and maintain the manner in which an image was processed for later use. It is a computational efficient and promising technique to handle variety of image processing algorithms. To promote the reusability and adaptation of the package for new types of analysis, a feature of sustainability is established. The framework is integrated and tested on a medical imaging application, and the software is made freely available for the reader. Future work involves introducing the capability to connect to another instance of processing service with better performance. Copyright © 2015 John Wiley & Sons, Ltd.

Wrinkles can be embedded in several image-based applications as a descriptor for human skin. However, wrinkle-based age estimation research has not been widely addressed. In this paper, we introduce a Multi-scale Wrinkle Patterns (MWP) representation, investigate the effect of wrinkles on face age estimation and propose Hybrid Ageing Patterns (HAP) for face age estimation. To define the wrinkle regions more precisely, a template consisting of 10 regions constructed relatively to a set of automatically located facial landmarks is used. We extract the multi-scale wrinkles in each region and encode them into MWP. We use Support Vector Regression to estimate age from the combination of such patterns. The performance of the algorithms is assessed by using Mean Absolute Error (MAE) on three state-of-the-art datasets - FG-NET, FERET and MORPH. We observe that MWP produces a comparable MAE of 4.16 on FERET to the state of the art. Finally we propose HAP, which combines the features from MWP and the facial appearance model (FAM), and demonstrate improved performance on FERET and MORPH with MAE of 3.02 (±2.92) and 3.68 (±2.98), respectively. Therefore, we conclude that MWP is an important complementary feature for face age estimation.

We propose the Component Bio-Inspired Feature (CBIF) with a moving segmentation scheme for age estimation. The CBIF defines a superset for the commonly used Bio-Inspired Feature (BIF) with more parameters and flexibility in settings, resulting in features with abundant characteristics. An in-depth study is performed for the determination of the parameters good for capturing age-related traits. The moving segmentation is proposed to better determine the age boundaries good for age grouping, and improve the overall performance. The proposed approach is evaluated on two common benchmarks, FG-NET and MORPH databases, and compared with contemporary approaches to demonstrate its efficacy.

The aim of this study was to compare postural sway during a series of static balancing tasks and during five chair rises between healthy young (mean [SEM], age 26 [1] years), healthy old (age 67 [1] years) and master athlete runners (age 67 [1] years; competing and training for the previous 51 [5] years) using the Microsoft Kinect One. The healthy old had more sway than the healthy young in all balance tasks. The master athletes had similar sway to young athletes during two-leg balancing and one-leg standing with eyes open. When balancing on one leg with eyes closed, both the healthy old and the master athletes had around 17-fold more sway than the young athletes. The healthy old and master athletes also had less anterio-posterior movement during chair rising compared with young athletes. These results suggest that masters runners are not spared from the age-associated decline in postural stability and may benefit from specific balance training.

Evaluating the execution style of human motion can give insight into the performance and behaviour exhibited by the participant. This could enable support in developing personalised rehabilitation programmes by providing better understanding of motion mechanics and contextual behaviour. However, performing analyses, generating statistical representations and models which are free from external bins, repeatable and robust is a difficult task. In this work, we propose a framework which evaluates clinically valid motions to identify unstable behaviour during performance using Deep Convolutional Neural Networks. The framework is composed of two parts; 1) Instead of using the whole skeleton as input, we divide the human skeleton into five joint groups. For each group, feature encoding is used to represent spatial and temporal domains to permit high-level abstraction and to remove noise these are then represented using distance matrices. 2) The encoded representations are labelled using an automatic labelling method and evaluated using deep learning. Experimental results demonstrates the ability to correctly classify data compared to classical approaches.

Face features convey many personal information that promote and regulate our social linkages. Age prediction using single layer estimation such as aging subspace or a hybrid pattern is limited due to the complexity of human faces. In this work, we propose Multilayer Age Regression (MAR) where the face age is predicted based on a coarse-to-fine estimation using global and local features. In the first layer, Support Vector Regression (SVR) performs a between group prediction by the parameters of Facial Appearance Model (FAM). In the second layer, a within group estimation is performed using FAM, Bio-Inspired Features (BIF), Kernel-based Local Binary Patterns (KLBP) and Multi-scale Wrinkle Patterns (MWP). The performance of MAR is assessed on four benchmark datasets: FGNET, MORPH, FERET and PAL. Results showed that MAR outperforms the state of the art on FERET with a Mean Absolute Error (MAE) of 3.00 (±4.14).

Background Generating quantitative metrics of rodent locomotion and general behaviours from video footage is important in behavioural neuroscience studies. However, there is not yet a free software system that can process large amounts of video data with minimal user interventions. New method Here we propose a new, automated rodent tracker (ART) that uses a simple rule-based system to quickly and robustly track rodent nose and body points, with minimal user input. Tracked points can then be used to identify behaviours, approximate body size and provide locomotion metrics, such as speed and distance. Results ART was demonstrated here on video recordings of a SOD1 mouse model, of amyotrophic lateral sclerosis, aged 30, 60, 90 and 120 days. Results showed a robust decline in locomotion speeds, as well as a reduction in object exploration and forward movement, with an increase in the time spent still. Body size approximations (centroid width), showed a significant decrease from P30. Comparison with existing method(s) ART performed to a very similar accuracy as manual tracking and Ethovision (a commercially available alternative), with average differences in coordinate points of 0.6 and 0.8 mm, respectively. However, it required much less user intervention than Ethovision (6 as opposed to 30 mouse clicks) and worked robustly over more videos. Conclusions ART provides an open-source option for behavioural analysis of rodents, performing to the same standards as commercially available software. It can be considered a validated, and accessible, alternative for researchers for whom non-invasive quantification of natural rodent behaviour is desirable.

Facial skin assessment is crucial for a number of fields including the make-up industry, dermatology and plastic surgery. This paper addresses skin classification techniques which use conventional machine learning and state-of-the-art Convolutional Neural Networks to classify three types of facial skin patches, namely normal, spots and wrinkles. This study aims to accomplish the pivotal work on the basis of these three classes to provide the collective facial skin quality score. In this work, we collected high quality face images of people from different ethnicities to create a derma dataset. Then, we outlined the skin patches of 100 \(\times \) 100 resolution in the three pre-decided classes. With extensive parameter tuning, we ran a number of computer vision experiments using both traditional machine learning and deep learning techniques for this 3-class classification. Despite the limited dataset, GoogLeNet outperforms the Support Vector Machine approach with Accuracy of 0.899, F-Measure of 0.852 and Matthews Correlation Coefficient of 0.779. The result shows the potential use of deep learning for non-clinical skin images classification, which will be more promising with a larger dataset.

Globally, in 2016, one out of eleven adults suffered from Diabetes Mellitus. Diabetic Foot Ulcers (DFU) are a major complication of this disease, which if not managed properly can lead to amputation. Current clinical approaches to DFU treatment rely on patient and clinician vigilance, which has significant limitations such as the high cost involved in the diagnosis, treatment and lengthy care of the DFU. We collected an extensive dataset of foot images, which contain DFU from different patients. In this paper, we have proposed the use of traditional computer vision features for detecting foot ulcers among diabetic patients, which represent a cost-effective, remote and convenient healthcare solution. Furthermore, we used Convolutional Neural Networks (CNNs) for the first time in DFU classification. We have proposed a novel convolutional neural network architecture, DFUNet, with better feature extraction to identify the feature differences between healthy skin and the DFU. Using 10-fold cross-validation, DFUNet achieved an AUC score of 0.962. This outperformed both the machine learning and deep learning classifiers we have tested. Here we present the development of a novel and highly sensitive DFUNet for objectively detecting the presence of DFUs. This novel approach has the potential to deliver a paradigm shift in diabetic foot care., Comment: Submitted to IEEE Access Journal

Aims: To establish a rich Facial Action Coding System (FACS) coded database and to investigate the use of the facial visual cues for deception detection. Study Design: A within-participants design experime nt was conducted, using immigration as a scenario for asking questions of participants in controlled experimental conditions.The study design required participants to answer questions on two topics, one as themselves and one based on a learned scenario.Data regarding visible images of facial movement were collected and analyzed against cues identified as indicative of deceit.

Wireless Communication is an inevitable part of Smart Home domain. A Mobile Ad-Hoc Network (MANET) is defined as an arrangement of wireless mobile nodes which creates a temporary network for the communication. MANET suffers from both kinds of attacks, active and passive attacks at all the layers of the network model. The lacks of security measures of routing protocols allow attackers to intrude the network. Wormhole, the attack is generated by tunnels creation and it results in complete disruption of routing paths on MANET. The proposed security approach is to detect and mitigate wormhole attack. It is secured Ad hoc on demand distance vector (AODV) approach which efficiently finds wormhole attack present in a MANET and Digital signature is used to prevent it. This approach is based on a calculation of tunneling time taken by tunnel to analyze the behavior of wormhole. Afterward, it decides some static threshold value. Based upon this tunneling time and threshold value, it decides whether given node is wormhole node or trustworthy node. A digital signature and hash chain algorithm is applied to mitigate the wormhole node.

In recent years, E-commerce had made a tremendous impact on the world. However before the emergence of E-commerce, individuals can't skim the information about the products within short time of the period, so therefore recommendation system was introduced. The principle point of the recommendation system is to prescribe the most appropriate items to the user. Many of the recommendation systems mainly use content based method, collaborative filtering method, demographic based method and hybrid method. In this paper, the major challenges such as “data sparsity” and “cold start problem” are addressed. To overcome these challenges, we propose a new methodology by combining the clustering algorithm with Eclat Algorithm for better rules generation. Firstly we cluster the rating matrix based on the user similarity. Then we convert the clustered data into Boolean data and applying Eclat Algorithm on Boolean data efficient rules generation takes place. At last based on rules generation recommendation takes place. Our experiments shows that approach not only decrease the sparsity level but also increase the accuracy of a system.

The effectiveness of whey protein plus potassium bicarbonate-enriched diet (WP+KHCO3) in mitigating disuse-induced changes in muscle fiber oxidative capacity and capillarization was investigated in a 21-day crossover design bed rest study. Ten healthy men (31 ± 6 yr) once received WP+KHCO3 and once received a standardized isocaloric diet. Muscle biopsies were taken 2 days before and during the 19th day of bed rest (BR) from the soleus (SOL) and vastus lateralis (VL) muscle. Whole-body aerobic power (V̇o2 max), muscle fatigue, and isometric strength of knee extensor and plantar flexor muscles were monitored. Muscle fiber types and capillaries were identified by immunohistochemistry. Fiber oxidative capacity was determined as the optical density (OD) at 660 nm of succinate dehydrogenase (SDH)-stained sections. The product of fiber cross-sectional area and SDH-OD (integrated SDH) indicated the maximal oxygen consumption of that fiber. The maximal oxygen consumption supported by a capillary was calculated as the integrated SDH in its supply area. BR reduced isometric strength of knee extensor muscles ( P < 0.05), and the fiber oxidative capacity ( P < 0.001) and V̇o2 max ( P = 0.042), but had no significant impact on muscle capillarization or fatigue resistance of thigh muscles. The maximal oxygen consumption supported by a capillary was reduced by 24% in SOL and 16% in VL ( P < 0.001). WP+KHCO3 attenuated the disuse-induced reduction in fiber oxidative capacity in both muscles ( P < 0.01). In conclusion, following 19 days of bed rest, the decrement in fiber oxidative capacity is proportionally larger than the loss of capillaries. WP+KHCO3 appears to attenuate disuse-induced reductions in fiber oxidative capacity.

Micro-expressions are brief spontaneous facial expressions that appear on a face when a person conceals an emotion, making them different to normal facial expressions in subtlety and duration. Currently, emotion classes within the CASME II dataset are based on Action Units and self-reports, creating conflicts during machine learning training. We will show that classifying expressions using Action Units, instead of predicted emotion, removes the potential bias of human reporting. The proposed classes are tested using LBP-TOP, HOOF and HOG 3D feature descriptors. The experiments are evaluated on two benchmark FACS coded datasets: CASME II and SAMM. The best result achieves 86.35\% accuracy when classifying the proposed 5 classes on CASME II using HOG 3D, outperforming the result of the state-of-the-art 5-class emotional-based classification in CASME II. Results indicate that classification based on Action Units provides an objective method to improve micro-expression recognition., Comment: 11 pages, 4 figures and 5 tables. This paper will be submitted for journal review

Micro-facial expressions are spontaneous, involuntary movements of the face when a person experiences an emotion but attempts to hide their facial expression, most likely in a high-stakes environment. Recently, research in this field has grown in popularity, however publicly available datasets of micro-expressions have limitations due to the difficulty of naturally inducing spontaneous micro-expressions. Other issues include lighting, low resolution and low participant diversity. We present a newly developed spontaneous micro-facial movement dataset with diverse participants and coded using the Facial Action Coding System. The experimental protocol addresses the limitations of previous datasets, including eliciting emotional responses from stimuli tailored to each participant. Dataset evaluation was completed by running preliminary experiments to classify micro-movements from non-movements. Results were obtained using a selection of spatio-temporal descriptors and machine learning. We further evaluate the dataset on emerging methods of feature difference analysis and propose an Adaptive Baseline Threshold that uses individualised neutral expression to improve the performance of micro-movement detection. In contrast to machine learning approaches, we outperform the state of the art with a recall of 0.91. The outcomes show the dataset can become a new standard for micro-movement data, with future work expanding on data representation and analysis.

Analysis and quantification of human motion to support clinicians in the decision-making process is the desired outcome for many clinical-based approaches. However, generating statistical models that are free from human interpretation and yet representative is a difficult task. In this paper, we propose a framework that automatically recognizes and evaluates human mobility impairments using the Microsoft Kinect One depth sensor. The framework is composed of two parts. First, it recognizes motions, such as sit-to-stand or walking 4 m, using abstract feature representation techniques and machine learning. Second, evaluation of the motion sequence in the temporal domain by comparing the test participant with a statistical mobility model, generated from tracking movements of healthy people. To complement the framework, we propose an automatic method to enable a fairer, unbiased approach to label motion capture data. Finally, we demonstrate the ability of the framework to recognize and provide clinically relevant feedback to highlight mobility concerns, hence providing a route toward stratified rehabilitation pathways and clinician-led interventions.

Micro-facial expressions are regarded as an important human behavioural event that can highlight emotional deception. Spotting these movements is difficult for humans and machines, however research into using computer vision to detect subtle facial expressions is growing in popularity. This paper proposes an individualised baseline micro-movement detection method using 3D Histogram of Oriented Gradients (3D HOG) temporal difference method. We define a face template consisting of 26 regions based on the Facial Action Coding System (FACS). We extract the temporal features of each region using 3D HOG. Then, we use Chi-square distance to find subtle facial motion in the local regions. Finally, an automatic peak detector is used to detect micro-movements above the newly proposed adaptive baseline threshold. The performance is validated on two FACS coded datasets: SAMM and CASME II. This objective method focuses on the movement of the 26 face regions. When comparing with the ground truth, the best result was an AUC of 0.7512 and 0.7261 on SAMM and CASME II, respectively. The results show that 3D HOG outperformed for micro-movement detection, compared to state-of-the-art feature representations: Local Binary Patterns in Three Orthogonal Planes and Histograms of Oriented Optical Flow.

The method of capillary domains has often been used to study capillarization of skeletal and heart muscle. However, the conventional data processing method using a digitizing tablet is an arduous and time-consuming task. Here we compare a new semi-automated capillary domain data collection and analysis in muscle tissue with the standard capillary domain method. The capillary density (1481 ± 59 vs. 1447 ± 54 caps mm−2; R2:0.99; P < 0.01) and heterogeneity of capillary spacing (0.085 ± 0.002 vs. 0.085 ± 0.002; R2:0.95; P < 0.01) were similar in both methods. The fiber cross-sectional area correlated well between the methods (R2:0.84; P < 0.01) and did not differ significantly (~8 % larger in the old than new method at P = 0.08). The latter was likely due to differences in outlining the contours between the two methods. In conclusion, the semi-automated method gives quantitatively and qualitatively similar data as the conventional method and saves a considerable amount of time.

The purpose of this study is to enhance the algorithms towards the development of an efficient three dimensional face recognition system in the presence of expressions. The overall aim is to analyse patterns of expressions based on techniques relating to feature distances compare to the benchmarks. To investigate how the use of distances can help the recognition process, a feature set of diagonal distance patterns, were determined and extracted to distinguish face models. The significant finding is that, to solve the problem arising from data with facial expressions, the feature sets of the expression-invariant and expression-variant regions were determined and described by geodesic distances and Euclidean distances. By using regression models, the correlations between expressions and neutral feature sets were identified. The results of the study have indicated that our proposed analysis methods of facial expressions, was capable of undertaking face recognition using a minimum set of features improving efficiency and computation.

There is a clear advantage to developing automated systems to detect human motion in the field of computer vision for applications associated with healthcare. We have compiled a diverse dataset of clinically-relevant motions using the Microsoft Kinect One sensor and release the dataset to the community as an open source solution for benchmarking detection, quantification and recognition algorithms. The dataset, namely Kinect 3D Active (K3Da), includes motions collected from young and older men and women ranging in age from 18–81 years. Participants performed standardised tests, including the Short Physical Performance Battery, Timed-Up-And-Go, vertical jump and other balance assessments which were recorded using depth sensor technology and extracted to generate motion capture data, sampled at 30 frames-per-second. Preliminary evaluations using Support Vector Machines, Random Forests, Artificial Neural Networks and Boltzmann Machines show age-related differences in many of the movements. These results demonstrate the relevance of the dataset to support benchmarking of algorithms associated and/or intended for use in a healthcare setting.

The majority of current facial age estimation methods are based on appearance based features. However, wrinkle based research has not been widely addressed. In this paper, we propose a novel method based on multi-scale aging patterns (MAP). These directly extract the features from local patches without extensive geometric modelling. First, we locate facial landmarks by using the Face++ detector and then normalize the face by using a linear transformation. We define a face template which consists of ten predefined wrinkle regions. Then, for each region, we detect wrinkles and construct aging patterns by using the MAP. Finally, the age is estimated by implementing the sequential minimal optimization (SMO). The performance of the algorithms is assessed by using mean absolute error (MAE) on the benchmark database - FERET. We observe that MAP produces a lower MAE of 4.87 on FERET compared to the benchmark algorithms. Therefore, we conclude that wrinkle could be used as a feature on face age estimation. Future work would involve improvements of the algorithm by combining other descriptors such as non-wrinkle descriptor and appearance parameters.

Detecting micro-facial movements in a video sequence is the first step in realising a system that can pick out rapid movements automatically as a person is being recorded. This paper proposes a new method of micro-movement detection by applying Histogram of Oriented Gradients as a feature descriptor on our in-house high-speed video dataset of spontaneous micro facial movements. Firstly the algorithm aligns and crops faces for each video using automatic facial point detection and affine transformation. Then a de-noising algorithm is applied to each video before splitting them into blocks where the Histogram of Oriented Gradient features are calculated for each frame in every video block. The Chi-Squared distance measure is then used to calculate dissimilarity in the spatial appearance between frames at a set interval. The final feature vector is calculated after normalisation of the raw distance values and peak detection is applied to 'spot' micro-facial movements. An individualised baseline threshold is used to determine the value a peak must exceed to be classed as a movement. The result is compared with a benchmark algorithm - feature difference analysis techniques for micro-facial movements using Local Binary Patterns. Results indicate the proposed method achieves higher Recall of 0.8429 and F1-measure of 0.7672.

Modern facial motion capture systems employ a two-pronged approach for capturing and rendering facial motion. Visual data (2D) is used for tracking the facial features and predicting facial expression, whereas Depth (3D) data is used to build a series of expressions on 3D face models. An issue with modern research approaches is the use of a single data stream that provides little indication of the 3D facial structure. We compare and analyse the performance of Convolutional Neural Networks (CNN) using visual, Depth and merged data to identify facial features in real-time using a Depth sensor. First, we review the facial landmarking algorithms and its datasets for Depth data. We address the limitation of the current datasets by introducing the Kinect One Expression Dataset (KOED). Then, we propose the use of CNNs for the single data stream and merged data streams for facial landmark detection. We contribute to existing work by performing a full evaluation on which streams are the most effective for the field of facial landmarking. Furthermore, we improve upon the existing work by extending neural networks to predict into 3D landmarks in real-time with additional observations on the impact of using 2D landmarks as auxiliary information. We evaluate the performance by using Mean Square Error (MSE) and Mean Average Error (MAE). We observe that the single data stream predicts accurate facial landmarks on Depth data when auxiliary information is used to train the network. The codes and dataset used in this paper will be made available.

The authors extend their previous work on Ultrasound (US) image lesion detection and segmentation, to classification, proposing a complete end-to-end solution for automatic Ultrasound Computer Aided Detection (US CAD). Carried out is a comprehensive analysis to determine the best classifier-feature set combination that works optimally in US imaging. In particular the use of nineteen features categorised into three groups (shape, texture and edge), ten classifiers and 22 feature selection approaches are used in the analysis. From the overall performance, the classifier RBFNetworks defined by the WEKA pattern recognition tool set, with a feature set comprising of the area to perimeter ratio, solidity, elongation, roundness, standard deviation, two Fourier related and a fractal related texture measures out-performed other combinations of feature-classifiers, with an achievement of predicted Az value of 0.948. Next analyzed is the use of a number of different metrics in performance analysis and provide an insight to future improvements and extension. DOI: 10.4018/jcmam.2010040104 54 International Journal of Computational Models and Algorithms in Medicine, 1(2), 53-81, April-June 2010 Copyright © 2010, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. (CAD) systems with high sensitivity, specificity and consistency. Despite these efforts CAD of ultrasound images still remains an area with many open research problems that needs solutions. In this article we identify a key open research problem in ultrasound imaging which is thoroughly investigated in order to develop a new method of ultrasound image processing for extracting relevant tissue structure information that will help differentiate between normal and malignant tissues. The ultimate goal is to provide fast and reliable tools for the early detection of malignant tissues in ultrasound images. The current practical use of a typical US CAD system can be illustrated as in figure 1. The input of a CAD system consists of a rectangular region of interests, manually selected by a radiologist. The output provides a statistical analysis that can aid the radiologist in the final decision making, i.e., the malignancy and/or type of cancer. The above approach (Figure 1) to CAD of breast ultrasound images has a limitation in that no aid is provided to the radiologist who selects the Region of Interest (ROI) of the lesions. Modern computer vision approaches can be used for fully automatic initial lesion detection, which can then be used as an aid to the decision making process of the radiologist, thus improving the accuracy of their performance. Further at this initial stage the need of a radiologist can be completely eliminated by allowing for a higher degree of false positives which can later be removed by further CAD or the presence of a radiologist at the final decision making stage. Thus in this article we aim to use our previous work in initial lesion detection and segmentation to remove the need of a radiologist at the initial lesion detection stage and then propose a novel approach for the selection of lesion features and feature based lesion classification to automatically determine the lesion type. In particular within the research context of this article we aim to develop a framework for the selection of best feature-classifier combinations in US breast imaging. To the authors knowledge such an attempt has previously not been published in relevant literature. The aims of our research are: (i) to automate the Region of Interest (ROI) selection and (ii) to improve the segmentation and classification algorithms. Figure 2 illustrates the above aims. It is important to note that both above automations will improve the information provided to the radiologist to aid in decision making (at the ROI cropping and final decision making stages, refer to Figure 1), improving the overall accuracy of the CAD system and reducing human error. For clarity of presentation this article has been divided into 5 sub-sections. Apart from this section which provides the reader an introduction to the problem domain and setting out the objectives of the proposed research, State-ofthe-art US CAD Systems section introduces a detailed review of the state-if-the-art in US CAD system research. Method section proposes the proposed end-to-end solution to US CAD, with particular emphasis given to the recognition stage. Experimental results and analysis section Figure 1. Existing US CAD approach 27 more pages are available in the full version of this document, which may be purchased using the "Add to Cart" button on the publisher's webpage: www.igi-global.com/article/computer-aided-detectionrecognition-lesions/43021

This paper proposes a novel approach to initial lesion detection in ultrasound breast images. The objective is to automate the manual process of region of interest (ROI) labeling in computer‐aided diagnosis (CAD). We propose the use of hybrid filtering, multifractal processing, and thresholding segmentation in initial lesion detection and automated ROI labeling. We used 360 ultrasound breast images to evaluate the performance of the proposed approach. Images were preprocessed using histogram equalization before hybrid filtering and multifractal analysis were conducted. Subsequently, thresholding segmentation was applied on the image. Finally, the initial lesions are detected using a rule‐based approach. The accuracy of the automated ROI labeling was measured as an overlap of 0.4 with the lesion outline as compared with lesions labeled by an expert radiologist. We compared the performance of the proposed method with that of three state‐of‐the‐art methods, namely, the radial gradient index filtering technique, the local mean technique, and the fractal dimension technique. We conclude that the proposed method is more accurate and performs more effectively than do the benchmark algorithms considered. PACS numbers: 87.57.Nk

This paper aims to investigate whether micro-facial movement sequences can be distinguished from neutral face sequences. As a micro-facial movement tends to be very quick and subtle, classifying when a movement occurs compared to the face without movement can be a challenging computer vision problem. Using local binary patterns on three orthogonal planes and Gaussian derivatives, local features, when interpreted by machine learning algorithms, can accurately describe when a movement and non-movement occurs. This method can then be applied to help aid humans in detecting when the small movements occur. This also differs from current literature as most only concentrate in emotional expression recognition. Using the CASME II dataset, the results from the investigation of different descriptors have shown a higher accuracy compared to state-of-the-art methods.

Aging as a natural phenomenon affects different parts of the human body under the influence of various biological and environmental factors. The most pronounced changes that occur on the face is the appearance of wrinkles, which are the focus of this research. Accurate wrinkle detection is an important task in face analysis. Some have been proposed in the literature, but the poor localization limits the performance of wrinkle detection. It will lead to false wrinkle detection and consequently affect the processes such as age estimation and clinician score assessment. Therefore, we propose a hybrid Hessian filter (HHF) to cope with the identified problem. HHF is composed of the directional gradient and Hessian matrix. The proposed filter is conceptually simple, however, it significantly increases the true wrinkle localization when compared with the conventional methods. In the experimental setup, three coders have been instructed to annotate the wrinkle of 2D forehead image manually. The inter-reliability among three coders is 93 % of Jaccard similarity index (JSI). In comparison to the state-of-the-art Cula method (CLM) and Frangi filter, HHF yielded the best result with a mean JSI of 75.67 %. We noticed that the proposed method is capable of detecting the medium to coarse wrinkle but not the fine wrinkle. Although there is a gap between human annotation and automated detection, this work demonstrates that HHF is a remarkably strong filter for wrinkle detection. From the experimental results, we believe that our findings are notable in terms of the JSI.

Image segmentation of anatomic structures is often an essential step in medical image analysis. A variety of segmentation methods have been proposed, but none provides automatic segmentation of the thigh. In magnetic resonance images of the thigh, the segmentation is complicated by factors, such as artifacts (e.g. intensity inhomogeneity and echo) and inconsistency of soft and hard tissue compositions, especially in muscle from older people, where accumulation of intermuscular fat is greater than in young muscles. In this paper, the combination framework that leads to a segmentation enhancement method for region of interest segmentation are demonstrated. Appropriate methods of image pre-processing, thresholding, manual interaction of muscle border, template conversion and deformable contours in combination with image filters are applied. Prior geometrical information in an initial template image is used to automatically derive the muscle outlines by application of snake active contours, in serial images within a single MRI dataset. Our approach has an average segmented output accuracy of 93.34% by Jaccard Similarity Index, and reduced the processing time by 97.73% per image compared to manual segmentation.

Diabetic foot ulcers (DFUs) and other foot pathologies are highly prevalent in people with diabetes, especially in patients with the secondary complications of peripheral neuropathy and/or peripheral vascular disease.1 The development of DFUs involves changes in the appearance of the foot over time, however, many subtle changes in foot shape, texture, and color will likely be undetectable by human vision until a DFU is established. Advanced computer vision algorithms have been applied in the medical field to detect subtle signs to differentiate the type of tumours2 subtle changes in facial features—such as fine wrinkles on the face3 and micro facial movements4—where some of these features are not detectable by human vision. We see the opportunity to apply computer vision algorithms to help in the early detection of key pathological changes in the diabetic foot leading to the development of a DFU.

This research proposes a mobile framework for two types of cognitive tests - Trail Making and Reaction Time, and conducts an investigation of its performance. The proposed methodology uses a cross platform framework which enables the deployment of apps to multiple platforms using a single Java code base. The functionality and usability of the mobile application were tested. Exploratory validation to compare existing testing methods and the new mobile implementation was conducted on a small sample of participants using a within-subjects design, with the intention to complete a full validation on a larger sample in future work. Benefits of the app over existing methods such as simplification of administration and increased data capture are discussed. It is the intention of the authors to release the app as an open source project, to encourage other developers and researchers to use it as the basis of a general purpose cognitive testing system. Such a system could have the potential to increase the number of manual cognitive testing methods being computerised. The app is currently a prototype, therefore a number of suggestions for future work are proposed.

Automatic segmentation of anatomic structures of magnetic resonance thigh scans can be a challenging task due to the potential lack of precisely defined muscle boundaries and issues related to intensity inhomogeneity or bias field across an image. In this paper, we demonstrate a combination framework of atlas construction and image registration methods to propagate the desired region of interest (ROI) between atlas image and the targeted MRI thigh scans for quadriceps muscles, femur cortical layer and bone marrow segmentations. The proposed system employs a semi-automatic segmentation method on an initial image in one dataset (from a series of images). The segmented initial image is then used as an atlas image to automate the segmentation of other images in the MRI scans (3-D space). The processes include: ROI labeling, atlas construction and registration, and morphological transform correspondence pixels (in terms of feature and intensity value) between the atlas (template) image and the targeted image based on the prior atlas information and non-rigid image registration methods.

Recent works on human action recognition have focused on representing and classifying articulated body motion. These methods require a detailed knowledge of the action composition both in the spatial and temporal domains, which is a difficult task, most notably under real-time conditions. As such, there has been a recent shift towards the exemplar paradigm as an efficient low-level and invariant modelling approach. Motivated by recent success, we believe a real-time solution to the problem of human action recognition can be achieved. In this work, we present an exemplar-based approach where only a single action sequence is used to model an action class. Notably, rotations for each pose are parameterised in Exponential Map form. Delegate exemplars are selected using k-means clustering, where the cluster criteria is selected automatically. For each cluster, a delegate is identified and denoted as the exemplar by means of a similarity function. The number of exemplars is adaptive based on the complexity of the action sequence. For recognition, Dynamic Time Warping and template matching is employed to compare the similarity between a streamed observation and the action model. Experimental results using motion capture demonstrate our approach is superior to current state-of-the-art, with the additional ability to handle large and varied action sequences.

The recognition of human activity is a challenging topic for machine learning. We present an analysis of Support Vector Machines (SVM) and Random Forests (RF) in their ability to accurately classify Kinect kinematic activities. Twenty participants were captured using the Microsoft Kinect performing ten physical rehabilitation activities. We extracted the kinematic location, velocity and energy of the skeletal joints at each frame of the activity to form a feature vector. Principle Component Analysis (PCA) was applied as a pre-processing step to reduce dimensionality and identify significant features amongst activity classes. SVM and RF are then trained on the PCA feature space to assess classification performance, we undertook an incremental increase in the dataset size. We analyse the classification accuracy, model training and classification time quantitatively at each incremental increase. The experimental results demonstrate that RF outperformed SVM in classification rate for six out of the ten activities. Although SVM has performance advantages in training time, RF would be more suited to real-time activity classification due to its low classification time and high classification accuracy when using eight to ten participants in the training set.

The application of computer vision in face processing remains an important research field. The aim of this chapter is to provide an up-to-date review of research efforts of computer vision scientist in facial image processing, especially in the areas of entertainment industry, surveillance, and other human computer interaction applications. To be more specific, this chapter reviews and demonstrates the techniques of visible facial analysis, regardless of specific application areas. First, the chapter makes a thorough survey and comparison of face detection techniques. It provides some demonstrations on the effect of computer vision algorithms and colour segmentation on face images. Then, it reviews the facial expression recognition from the psychological aspect (Facial Action Coding System, FACS) and from the computer animation aspect (MPEG-4 Standard). The chapter also discusses two popular existing facial feature detection techniques: Gabor feature based boosted classifiers and Active Appearance Models, and demonstrate the performance on our in-house dataset. Finally, the chapter concludes with the future challenges and future research direction of facial image processing.

This paper proposes a method to detect the facial Action Units (AUs) and introduce an automatic measurement in predicting the intensity scores of each AU in near-to-frontal face image sequences. To our knowledge, this is the first attempt in computer vision to automate the intensity scores of facial expression research. First, the facial feature points are detected by using Gabor feature based boosted classifiers and the movement of each point is tracked by optical flow. Then, we introduce a set of distance measurement for the feature points and analyze the distances by using Sequence Analysis. Further, we exploit the sequence partition to predict the possible temporal segments in the sequence. We found there is a relationship between the intensity scores and the partition threshold, which we automated the process of threshold selection in our work. We tested the proposed prototype with our in-house dataset and MMI database. Finally, we discuss the result, the possibilities of further research, and the next challenges for computer vision scientist in facial actions detection.