Breast cancer is one of the major causes of death in women. Computer Aided Diagnosis (CAD) systems are being developed to assist radiologists in early diagnosis. Micro-calcifications can be an early symptom of breast cancer. Besides detection, classification of micro-calcification as benign or malignant is essential in a complete CAD system. We have developed a novel method for the classification of benign and malignant micro-calcification using an improved Fisher Linear Discriminant Analysis (LDA) approach for the linear transformation of segmented micro-calcification data in combination with a Support Vector Machine (SVM) variant to classify between the two classes. The results indicate an average accuracy equal to 96% which is comparable to state-of-the art methods in the literature.
To improve the compression rates for lossless compression of medical images, an efficient algorithm, based on irregular segmentation and region-based prediction, is proposed in this paper. Considering that the first step of a region-based compression algorithm is segmentation, this paper proposes a hybrid method by combining geometry-adaptive partitioning and quadtree partitioning to achieve adaptive irregular segmentation for medical images. Then, least square (LS)-based predictors are adaptively designed for each region (regular subblock or irregular subregion). The proposed adaptive algorithm not only exploits spatial correlation between pixels but it utilizes local structure similarity, resulting in efficient compression performance. Experimental results show that the average compression performance of the proposed algorithm is 10.48, 4.86, 3.58, and 0.10% better than that of JPEG 2000, CALIC, EDP, and JPEG-LS, respectively.
Reconstructing magnetic resonance images from undersampled k-space data is a challenging problem. This paper introduces a novel method of image reconstruction from undersampled k-space data based on the concept of singularizing operators and a novel singular k-space model. Exploring the sparsity of an image in the k-space, the singular k-space model (SKM) is proposed in terms of the k-space functions of a singularizing operator. The singularizing operator is constructed by combining basic difference operators. An algorithm is developed to reliably estimate the model parameters from undersampled k-space data. The estimated parameters are then used to recover the missing k-space data through the model, subsequently achieving high-quality reconstruction of the image using inverse Fourier transform. Experiments on physical phantom and real brain MR images have shown that the proposed SKM method constantly outperforms the popular total variation (TV) and the classical zero-filling (ZF) methods regardless of the undersampling rates, the noise levels, and the image structures. For the same objective quality of the reconstructed images, the proposed method requires much less k-space data than the TV method. The SKM method is an effective method for fast MRI reconstruction from the undersampled k-space data.
An atlas-based multimodal registration method for 2-dimension images with discrepancy structures was proposed in this paper. Atlas was utilized for complementing the discrepancy structure information in multimodal medical images. The scheme includes three steps: floating image to atlas registration, atlas to reference image registration, and field-based deformation. To evaluate the performance, a frame model, a brain model, and clinical images were employed in registration experiments. We measured the registration performance by the squared sum of intensity differences. Results indicate that this method is robust and performs better than the direct registration for multimodal images with discrepancy structures. We conclude that the proposed method is suitable for multimodal images with discrepancy structures.
In this paper, we develop and validate an open source, fully automatic algorithm to localize the left ventricular (LV) blood pool centroid in short axis cardiac cine MR images, enabling follow-on automated LV segmentation algorithms. The algorithm comprises four steps: (i) quantify motion to determine an initial region of interest surrounding the heart, (ii) identify potential 2D objects of interest using an intensity-based segmentation, (iii) assess contraction/expansion, circularity, and proximity to lung tissue to score all objects of interest in terms of their likelihood of constituting part of the LV, and (iv) aggregate the objects into connected groups and construct the final LV blood pool volume and centroid. This algorithm was tested against 1140 datasets from the Kaggle Second Annual Data Science Bowl, as well as 45 datasets from the STACOM 2009 Cardiac MR Left Ventricle Segmentation Challenge. Correct LV localization was confirmed in 97.3% of the datasets. The mean absolute error between the gold standard and localization centroids was 2.8 to 4.7 mm, or 12 to 22% of the average endocardial radius.
Respiratory inductance plethysmography (RIP) sensor is an inexpensive, non-invasive, easy-to-use transducer for collecting respiratory movement data. Studies have reported that the RIP signal’s amplitude and frequency can be used to discriminate respiratory diseases. However, with the conventional approach of RIP data analysis, respiratory muscle effort cannot be estimated. In this paper, the estimation of the respiratory muscle effort through RIP signal was proposed. A complementary ensemble empirical mode decomposition method was used, to extract hidden signals from the RIP signals based on the frequency bands of the activities of different respiratory muscles. To validate the proposed method, an experiment to collect subjects’ RIP signal under thoracic breathing (TB) and abdominal breathing (AB) was conducted. The experimental results for both the TB and AB indicate that the proposed method can be used to loosely estimate the activities of thoracic muscles, abdominal muscles, and diaphragm.
The aim of this study was to investigate the plantar blood flow response to the same accumulated pressure stimulus in diabetic patients with different peak plantar pressure (PPP), which is important for assessing the risk of diabetic foot ulcer. Eleven diabetic subjects with high PPP (PPP ≥?207 kPa) and 8 diabetic subjects with low PPP (PPP <?207 kPa) were asked to walk naturally on a treadmill so as to induce an accumulated stimulus of 73,000 kPa·s on their first metatarsal head, which was monitored with a sensorized insole. Blood perfusion (BP) in the first metatarsal head was measured before and after walking. Results showed that blood flow after applying the same walking stimulus was significantly decreased in comparison to the basal BP before walking in both high PPP and low PPP groups (p?<?0.05), but no significant differences were found between the two groups in terms of BP parameters and its percentage change (p?>?0.05). Moreover, BP parameters were not significantly correlated to PPP and the pressure-time integral (PTI) of the subjects’ gait (p?>?0.05). This indicated that, besides PPP and PTI, the accumulated mechanical stimulus should be taken into consideration when assessing the risk of diabetic patients developing foot ulcers.
This paper presents the design and simulation of a handheld device for people with hand tremor, such as Parkinson’s and essential tremor patients. This device can be used as a pen for smartphones or as a spoon. The designed system includes two links, which are connected to two servomotors, which are mounted in orthogonal directions. To attenuate the effect of hand tremor on the tip of device, PID and computed torque methods are used to actively control the system. These controllers are used to control the rotation of the motors for moving the links in opposite directions of the hand tremor. Performance of the device with mentioned controllers is studied for different applications and finally, the results of both controllers are discussed and compared. Based on the presented results in this study, the designed device is able to suppress the hand tremor up to 75% during eating and 65% during following a spiral pattern.
Impedance cardiography is a low-cost noninvasive technique, based on monitoring of the thoracic impedance, for estimation of stroke volume (SV). Impedance cardiogram (ICG) is the negative of the first derivative of the impedance signal. A technique for beat-to-beat SV estimation using impedance cardiography and artificial neural network (ANN) is proposed. A three-layer feed-forward ANN with error back-propagation algorithm is optimized by examining the effects of number of neurons in the hidden layer, activation function, training algorithm, and set of input parameters. The input parameters are obtained by automatic detection of the ICG characteristic points, and the target values are obtained by beat-to-beat SV measurements from time-aligned Doppler echocardiogram. The technique is evaluated using an ICG-echocardiography database with recordings from subjects with normal health in the under-rest and post-exercise conditions and from subjects with cardiovascular disorders in the under-rest condition. The proposed technique performed much better than the earlier established equation-based estimations, and it resulted in correlation coefficient of 0.93 for recordings from subjects with cardiovascular disorders. It may be helpful in improving the acceptability of impedance cardiography in clinical practice.
For capacitive biopotential measurement, a novel high input impedance front-end is proposed. The input impedance of the front-end can achieve more than 100 GΩ by matching the peripheral parameters. The front-end’s noise model is provided, and noise optimization is given further. The analysis shows the proposed front-end can achieve at least two orders of input impedance more than the non-inverting amplifier circuit with the same peripheral parameters at the cost of only increasing twice input-referred noise. The final experimental results verify the analysis and show the front-end’s feasibility of capacitive sensing electrocardiogram signal.
Graphical abstract A novel high input impedance front-end is proposed, which impedance can achieve more than 100 GΩ by matching the peripheral parameters. The analysis and noise optimization results show the proposed front-end can achieve at least two orders of input impedance more than the non-inverting amplifier circuit with the same peripheral parameters at the cost of only increasing twice input-referred noise. The final experimental results verify the analysis and show its feasibility of capacitive sensing electrocardiogram signal.
Chronic scapholunate ligament (SL) injuries are difficult to treat and can lead to wrist dysfunction. Whilst several tendon reconstruction techniques have been employed in the management of SL instability, SL gap reappearance after surgery has been reported. Using a finite element model and cadaveric study data, we investigated the performance of the Corella, scapholunate axis (SLAM) and modified Brunelli tenodesis (MBT) techniques. Scapholunate dorsal and volar gap and angle were obtained following virtual surgery undertaken using each of the three reconstruction methods with the wrist positioned in flexion, extension, ulnar deviation and radial deviation, in addition to the ulnar-deviated clenched fist and neutral positions. From the study, it was found that, following simulated scapholunate interosseous ligament rupture, the Corella technique was better able to restore the SL gap and angle close to the intact ligament for all wrist positions investigated, followed by SLAM and MBT. The results suggest that for the tendon reconstruction techniques, the use of multiple junction points between scaphoid and lunate may be of benefit.
The present paper aims at presenting the methodology and first results of a detection system of risk of diabetic macular edema (DME) in fundus images. The system is based on the detection of retinal exudates (Ex), whose presence in the image is clinically used for an early diagnosis of the disease. To do so, the system applies digital image processing algorithms to the retinal image in order to obtain a set of candidate regions to be Ex, which are validated by means of feature extraction and supervised classification techniques. The diagnoses provided by the system on 1058 retinographies of 529 diabetic patients at risk of having DME show that the system can operate at a level of sensitivity comparable to that of ophthalmological specialists: it achieved 0.9000 sensitivity per patient against 0.7733, 0.9133 and 0.9000 of several specialists, where the false negatives were mild clinical cases of the disease. In addition, the level of specificity reached by the system was 0.6939, high enough to screen about 70% of the patients with no evidence of DME. These values show that the system fulfils the requirements for its possible integration into a complete diabetic retinopathy pre-screening tool for the automated management of patients within a screening programme.
Atherosclerosis is a type of cardiovascular disease which may cause stroke. It is due to the deposition of fatty plaque in the artery walls resulting in the reduction of elasticity gradually and hence restricting the blood flow to the heart. Hence, an early prediction of carotid plaque deposition is important, as it can save lives. This paper proposes a novel data mining framework for the assessment of atherosclerosis in its early stage using ultrasound images. In this work, we are using 1353 symptomatic and 420 asymptomatic carotid plaque ultrasound images. Our proposed method classifies the symptomatic and asymptomatic carotid plaques using bidimensional empirical mode decomposition (BEMD) and entropy features. The unbalanced data samples are compensated using adaptive synthetic sampling (ADASYN), and the developed method yielded a promising accuracy of 91.43%, sensitivity of 97.26%, and specificity of 83.22% using fourteen features. Hence, the proposed method can be used as an assisting tool during the regular screening of carotid arteries in hospitals.
The purpose of this document is to describe a methodology to select the most adequate time-frequency distribution (TFD) kernel for the characterization of impedance cardiography signals (ICG). The predominant ICG beat was extracted from a patient and was synthetized using time-frequency variant Fourier approximations. These synthetized signals were used to optimize several TFD kernels according to a performance maximization. The optimized kernels were tested for noise resistance on a clinical database. The resulting optimized TFD kernels are presented with their performance calculated using newly proposed methods. The procedure explained in this work showcases a new method to select an appropriate kernel for ICG signals and compares the performance of different time-frequency kernels found in the literature for the case of ICG signals. We conclude that, for ICG signals, the performance (P) of the spectrogram with either Hanning or Hamming windows (P?=?0.780) and the extended modified beta distribution (P?=?0.765) provided similar results, higher than the rest of analyzed kernels.
Electrical impedance tomography (EIT) attempts to reveal the conductivity distribution of a domain based on the electrical boundary condition. This is an ill-posed inverse problem; its solution is very unstable. Total variation (TV) regularization is one of the techniques commonly employed to stabilize reconstructions. However, it is well known that TV regularization induces staircase effects, which are not realistic in clinical applications. To reduce such artifacts, modified TV regularization terms considering a higher order differential operator were developed in several previous studies. One of them is called total generalized variation (TGV) regularization. TGV regularization has been successively applied in image processing in a regular grid context. In this study, we adapted TGV regularization to the finite element model (FEM) framework for EIT reconstruction. Reconstructions using simulation and clinical data were performed. First results indicate that, in comparison to TV regularization, TGV regularization promotes more realistic images.
Graphical abstract Reconstructed conductivity changes located on selected vertical lines. For each of the reconstructed images as well as the ground truth image, conductivity changes located along the selected left and right vertical lines are plotted. In these plots, the notation GT in the legend stands for ground truth, TV stands for total variation method, and TGV stands for total generalized variation method. Reconstructed conductivity distributions from the GREIT algorithm are also demonstrated.
With the rapid development of DNA microarray technology, large amount of genomic data has been generated. Classification of these microarray data is a challenge task since gene expression data are often with thousands of genes but a small number of samples. In this paper, an effective gene selection method is proposed to select the best subset of genes for microarray data with the irrelevant and redundant genes removed. Compared with original data, the selected gene subset can benefit the classification task. We formulate the gene selection task as a manifold regularized subspace learning problem. In detail, a projection matrix is used to project the original high dimensional microarray data into a lower dimensional subspace, with the constraint that the original genes can be well represented by the selected genes. Meanwhile, the local manifold structure of original data is preserved by a Laplacian graph regularization term on the low-dimensional data space. The projection matrix can serve as an importance indicator of different genes. An iterative update algorithm is developed for solving the problem. Experimental results on six publicly available microarray datasets and one clinical dataset demonstrate that the proposed method performs better when compared with other state-of-the-art methods in terms of microarray data classification.
Prediction of sudden cardiac death continues to gain universal attention as a promising approach to saving millions of lives threatened by sudden cardiac death (SCD). This study attempts to promote the literature from mere feature extraction analysis to developing strategies for manipulating the extracted features to target improvement of classification accuracy. To this end, a novel approach to local feature subset selection is applied using meticulous methodologies developed in previous studies of this team for extracting features from non-linear, time-frequency, and classical processes. We are therefore enabled to select features that differ from one another in each 1-min interval before the incident. Using the proposed algorithm, SCD can be predicted 12 min before the onset; thus, more propitious results are achieved. Additionally, through defining a utility function and employing statistical analysis, the alarm threshold has effectively been determined as 83%. Having selected the best combination of features, the two classes are classified using the multilayer perceptron (MLP) classifier. The most effective features would subsequently be discussed considering their prevalence in the rank-based selection. The results indicate the significant capacity of the proposed method for predicting SCD as well as selecting the appropriate processing method at any time before the incident.
Acute limp is a common presenting condition in the paediatric emergency department. There are a number of causes of acute limp that include traumatic injury, infection and malignancy. These causes in young children are not easily distinguished. In this pilot study, an infrared thermographic imaging technique to diagnose acute undifferentiated limp in young children was developed. Following required ethics approval, 30 children (mean age =?5.2 years, standard deviation =?3.3 years) were recruited. The exposed lower limbs of participants were imaged using a high-resolution thermal camera. Using predefined regions of interest (ROI), any skin surface temperature difference between the healthy and affected legs was statistically analysed, with the aim of identifying limp. In all examined ROIs, the median skin surface temperature for the affected limb was higher than that of the healthy limb. The small sample size recruited for each group, however, meant that the statistical tests of significant difference need to be interpreted in this context. Thermal imaging showed potential in helping with the diagnosis of acute limp in children. Repeating a similar study with a larger sample size will be beneficial to establish reproducibility of the results.
Graphical abstract A young child with an acute undifferentiated limp undergoes thermal imaging and the follow on image analysis assists the limp diagnosis.
A 3D convolution neural network (CNN) of deep learning architecture is supplied with essential visual features to accurately classify and segment granulation, necrotic eschar, and slough tissues in pressure ulcer color images. After finding a region of interest (ROI), the features are extracted from both the original and convolved with a pre-selected Gaussian kernel 3D HSI images, combined with first-order models of current and prior visual appearance. The models approximate empirical marginal probability distributions of voxel-wise signals with linear combinations of discrete Gaussians (LCDG). The framework was trained and tested on 193 color pressure ulcer images. The classification accuracy and robustness were evaluated using the Dice similarity coefficient (DSC), the percentage area distance (PAD), and the area under the ROC curve (AUC). The obtained preliminary DSC of 92%, PAD of 13%, and AUC of 95% are promising.
People with transtibial amputation often experience skin breakdown due to the pressures and shear stresses that occur at the limb-socket interface. The purpose of this research was to create a transtibial finite element model (FEM) of a contemporary prosthesis that included complete socket geometry, two frictional interactions (limb-liner and liner-socket), and an elastomeric liner. Magnetic resonance imaging scans from three people with characteristic transtibial limb shapes (i.e., short-conical, long-conical, and cylindrical) were acquired and used to develop the models. Each model was evaluated with two loading profiles to identify locations of focused stresses during stance phase. The models identified five locations on the participants’ residual limbs where peak stresses matched locations of mechanically induced skin issues they experienced in the 9 months prior to being scanned. The peak contact pressure across all simulations was 98 kPa and the maximum resultant shear stress was 50 kPa, showing reasonable agreement with interface stress measurements reported in the literature. Future research could take advantage of the developed FEM to assess the influence of changes in limb volume or liner material properties on interface stress distributions.
