Search

This paper summarizes the panel discussion at the IEEE Engineering in Medicine and Biology Point-of-Care Healthcare Technology Conference (POCHT 2013) held in Bangalore India from Jan 16–18, 2013. Modern medicine has witnessed interdisciplinary technology innovations in healthcare with a continuous growth in life expectancy across the globe. However, there is also a growing global concern on the affordability of rapidly rising healthcare costs. To provide quality healthcare at reasonable costs, there has to be a convergence of preventive, personalized, and precision medicine with the help of technology innovations across the entire spectrum of point-of-care (POC) to critical care at hospitals. The first IEEE EMBS Special Topic POCHT conference held in Bangalore, India provided an international forum with clinicians, healthcare providers, industry experts, innovators, researchers, and students to define clinical needs and technology solutions toward commercialization and translation to clinical applications across different environments and infrastructures. This paper presents a summary of discussions that took place during the keynote presentations, panel discussions, and breakout sessions on needs, challenges, and technology innovations in POC technologies toward improving global healthcare. Also presented is an overview of challenges and trends in developing and developed economies with respect to priority clinical needs, technology innovations in medical devices, translational engineering, information and communication technologies, infrastructure support, and patient and clinician acceptance of POC healthcare technologies., This paper summarizes the panel discussion at the IEEE Engineering in Medicine and Biology Point of Care Healthcare Technology Conference (POCHT 2013) held in Bangalore India from Jan 16-18, 2013.

Patients undergoing nuclear medicine procedures for cancer therapy are administered radiopharmaceuticals that emit various types of radiation. Because radiation has differential delivery to and uptake by cells in tissue, radiation exposures are often highly nonuniform. Some cell populations in a tissue may contain widely different amounts of radioactivity, whereas other cell populations in the same tissue may contain no radioactivity, referred to as labeled and unlabeled cells, respectively. Furthermore, the toxicity of the radiations emitted can depend on the location of the radioactive decay within the cell (e.g., nucleus vs. cytoplasm). Therefore, the response of a given cell depends on the absorbed dose received from radiations emitted by decays within the cell (self-dose) and emitted by decays in neighboring cells (cross-dose), among other factors. Taken together, these variables make it difficult to predict the response of cell populations to radiopharmaceuticals. Accordingly, to assist in designing treatment plans for therapeutic radiopharmaceuticals, an applet software application called MIRDcell was developed. This applet models the distribution of radiopharmaceuticals in tissues, calculates the distribution of radiation dose, models responses on a cell-by-cell basis, and predicts the surviving fraction of the labeled and unlabeled cell populations. MIRDcell can be accessed at http://mirdcell.njms.rutgers.edu/.

Subsurface information about skin lesions, such as the blood volume beneath the lesion, is important for the analysis of lesion severity towards early detection of skin cancer such as malignant melanoma. Depth information can be obtained from diffuse reflectance based multispectral transillumination images of the skin. An inverse volume reconstruction method is presented which uses a genetic algorithm optimization procedure with a novel population initialization routine and nudge operator based on the multispectral images to reconstruct the melanin and blood layer volume components. Forward model evaluation for fitness calculation is performed using a parallel processing voxel-based Monte Carlo simulation of light in skin. Reconstruction results for simulated lesions show excellent volume accuracy. Preliminary validation is also done using a set of 14 clinical lesions, categorized into lesion severity by an expert dermatologist. Using two features, the average blood layer thickness and the ratio of blood volume to total lesion volume, the lesions can be classified into mild and moderate/severe classes with 100% accuracy. The method therefore has excellent potential for detection and analysis of pre- malignant lesions.

Detecting the early stages of melanoma can be greatly assisted by an accurate estimate of subsurface blood volume and blood oxygen saturation, indicative of angiogenesis. Visualization of this blood volume present beneath a skin lesion can be achieved through the transillumination of the skin. As the absorption of major chromophores in the skin is wavelength dependent, multispectral imaging can provide the needed information to separate out relative amounts of each chromophore. However, a critical challenge to this strategy is relating the pixel intensities observed in a given image to the wavelength-dependent total absorption existing at each spatial location. Consequently, in this paper, we develop an extension to Beer's law, estimated through a novel voxel-based, parallel processing Monte Carlo simulation of light propagation in skin which takes into account the specific geometry of our transillumination imaging apparatus. We then use this relation in a linear mixing model, solved using a multispectral image set, for chromophore separation and oxygen saturation estimation of an absorbing object located at a given depth within the medium. Validation is performed through the Monte Carlo simulation, as well as by imaging on a skin phantom. Results show that subsurface oxygen saturation can be reasonably estimated with good implications for the reconstruction of 3-D skin lesion volumes using transillumination toward early detection of malignancy.

This chapter contains sections titled: MRI Principles MR Instrumentation MRI Pulse Sequences Flow Imaging fMRI Diffusion Imaging Contrast, Spatial Resolution, and SNR Exercises References

This chapter contains sections titled: Propagation of Sound in a Medium Reflection and Refraction Transmission of Ultrasound Waves in a Multilayered Medium Attenuation Ultrasound Reflection Imaging Ultrasound Imaging Instrumentation Imaging with Ultrasound: A-Mode Imaging with Ultrasound: M-Mode Imaging with Ultrasound: B-Mode Doppler Ultrasound Imaging Contrast, Spatial Resolution, and SNR Exercises References

This chapter contains sections titled: Radioactivity SPECT PET Dual-Modality Spect-CT and PET-CT Scanners Exercises References

This chapter contains sections titled: Multiparameter Medical Imaging and Analysis Targeted Imaging Optical Imaging and Other Emerging Modalities Model-Based and Multiscale Analysis References ]]>

Multi-spectral optical imaging of skin and skin-lesions has been of significant interest for various biomedical applications. A multi-spectral optical imaging instrument called Nevoscope has been developed to acquire images of skin and skin-lesion through trans-illumination. Nevoscope based multi-spectral trans-illumination imaging is aimed at characterization of skin-lesions for early diagnosis of skin-cancers by reconstructing distributions of melanin and blood. Conventional approaches usually involve dividing the field of view into a number of voxels and assuming constant optical properties in each voxel. The optical properties are reconstructed in terms of measurements at multiple wavelengths and the distribution of melanin and blood are subsequently calculated. However, since the inverse problem is generally an ill-posed and under-determined one, it is hard to get quantitatively accurate reconstruction. In this paper, a shape-based multi-constrained reconstruction algorithm is presented, which uses a genetic algorithm based optimization methods to find the best possible reconstruction solution. A skin-lesion such as melanoma is modeled as melanin and blood parts, which are delineated by two cubic tensor-product B-spline surfaces. This reduces the number of unknowns to a few control parameters of the surfaces. The parameters are then coded into a genetic algorithm to find a solution through global optimization. Reasonable constraints are incorporated into the genetic algorithm to stabilize the solution. Results of reconstructions of melanin and blood parts are presented for simulated lesions using multi-spectral wavelengths at 580 nm and 800 nm.

Adaptive learning of specific patterns or events of interest has been an area of significant research for various applications in the last two decades. In developing diagnostic evaluation and safety monitoring applications of a propulsion system, it is critical to detect, characterize and model events of interest. It is a challenging task since the detection system should allow adaptive characterization of potential events of interest and correlate them to learn new models for future detection for online health monitoring and diagnostic evaluation. In this paper, a novel framework is established using a hierarchical adaptive clustering approach with fuzzy membership functions to characterize specific events of interest from the measured and processed features. Raw engine measurement data is first analyzed using the wavelet transform to provide features for localization of frequency information for use in the classification system. A method combining hierarchical and fuzzy k-means clustering is then applied to a set of selected measurements and computed features to determine the events of interest during engine operations. Experimental results have shown that the proposed approach is effective and computationally efficient to detect, characterize and model new events of interest from data collected through continuous operations.

Three-dimensional, voxel-based, and wavelength-dependent skin lesion models are developed and simulated using Monte Carlo techniques. The optical geometry of the Nevoscope with trans-illumination is used in the simulations for characterizing the lesion thickness. Based on the correlation analysis between the lesion thickness and the diffuse reflectance, optical wavelengths are selected for multispectral imaging of skin lesions using the Nevoscope. Tissue optical properties reported by various researchers are compiled together to form a voxel library. Tissue models used in the simulations are developed using the voxel library which offers flexibility in updating the optical properties and adding new media types into the models independent of the Monte Carlo simulation code.

The sensitivity and specificity of melanoma diagnosis can be improved by adding the lesion depth and structure information obtained from the multi-spectral, trans-illumination images to the surface characteristic information obtained from the epi-illumination images. Wavelet transform based bi-modal channel energy features obtained from the images are used in the analysis. Methods using both crisp and fuzzy membership based partitioning of the feature space are evaluated. For this purpose, the ADWAT classification method that uses crisp partitioning is extended to handle multi-spectral image data. Also, multi-dimensional fuzzy membership functions with Gaussian and Bell profiles are proposed for classification. Results show that the fuzzy membership functions with Bell profile are more effective than the extended ADWAT method in discriminating melanoma from dysplastic nevus.

This paper presents a wavelet transform based tree structure model developed and evaluated for the classification of skin lesion images into melanoma and dysplastic nevus. The tree structure model utilizes a semantic representation of the spatial-frequency information contained in the skin lesion images including textural information. Results show that the presented method is effective in discriminating melanoma from dysplastic nevus. The results are also compared with those obtained using another method of developing tree structures utilizing the maximum channel energy criteria with a fixed energy ratio threshold.

Real-time analysis of an airframe’s eutter boundaries during eight testing can help ensure safety and reduce costs. One method of identiecation is to performcorrelation elteringusing a set of singlet functions. The method is abletoidentifyaccuratelythefrequencyand dampingcoefe cientof thesystemtoexcitation, but the computational time required can be too signiecant to implement in real-time. An alternative method is presented for correlation e ltering that employs amultiple-level discretewavelet transform. The wavelet transform decomposes theresponse signal into a set of subsignals that correspond to different frequency bands. The same operation is applied to each entry in a dictionary of singlet functions. The transform results in a considerable reduction in the data and, thus, to a reduction in the computational time needed to calculate the correlation. We demonstrate that our approach is able to identify accurately frequency and damping characteristics of the impulse response of both a synthetically generated test signal and actual eight-test data. As a result, real-time identie cation of eutter boundaries during e ight testing may be possible with relatively low-cost computational resources.

There are many different criteria for the comparative analysis of pattern classifiers. They include generalization ability, computational complexity and understanding of the feature space. In some applications such as the medical diagnostic systems it is crucial to use reliable tools, whose behavior is always predictable, so that the risk of misdiagnosis is minimized. In such applications the use of the popular feedforward backpropagation (BP) neural network algorithm can be seen as questionable. This is because it is not inherent for the backpropagation method to analyze the problem's feature space during training, which can sometimes result in inadequate decision surfaces. A novel convex-set-based neuro-fuzzy algorithm for classification of difficult-to-diagnose instances of breast cancer is described in this paper. With its structural approach to feature space the new method offers rational advantages over the backpropagation algorithm. The classification performance, computational and structural efficiencies are analyzed and compared with that of the BP network. A 20-dimensional set of “difficult-to-diagnose” mammographic microcalcifications was used to evaluate the neuro-fuzzy pattern classifier (NFPC) and the BP methods. In order to evaluate the learning ability of both methods, the relative size of training sets was varied from 40 to 90%. The comparative results obtained using receiver operating characteristic (ROC) analysis show that the ability of the convex-set-based method to infer knowledge was better than that of backpropagation in all of the tests performed, making it more suitable for use in real diagnostic systems.

MR brain image segmentation into several tissue classes is of significant interest to visualize and quantify individual anatomical structures. Traditionally, the segmentation is performed manually in a clinical environment that is operator dependent and may be difficult to reproduce. Though several algorithms have been investigated in the literature for computerized automatic segmentation of MR brain images, they are usually targeted to classify image into a limited number of classes such as white matter, gray matter, cerebrospinal fluid and specific lesions. We present a novel model-based method for the automatic segmentation and classification of multi-parameter MR brain images into a larger number of tissue classes of interest. Our model employs 15 brain tissue classes instead of the commonly used set of four classes, which were of clinical interest to neuroradiologists for following-up with patients suffering from cerebrovascular deficiency (CVD) and/or stroke. The model approximates the spatial distribution of tissue classes by a Gauss Markov random field and uses the maximum likelihood method to estimate the class probabilities and transitional probabilities for each pixel of the image. Multi-parameter MR brain images with T 1 , T 2 , proton density, Gd+ T 1 , and perfusion imaging were used in segmentation and classification. In the development of the segmentation model, true class-membership of measured parameters was determined from manual segmentation of a set of normal and pathologic brain images by a team of neuroradiologists. The manual segmentation was performed using a human–computer interface specifically designed for pixel-by-pixel segmentation of brain images. The registration of corresponding images from different brains was accomplished using an elastic transformation. The presented segmentation method uses the multi-parameter model in adaptive segmentation of brain images on a pixel-by-pixel basis. The method was evaluated on a set of multi-parameter MR brain images of a twelve-year old patient 48h after suffering a stroke. The results of classification as compared to the manual segmentation of the same data show the efficacy and accuracy of the presented methods as well as its capability to create and learn new tissue classes.

A rapid time-series of T2*-weighted magnetic resonance (MR) images acquired during the first pass of a bolus injection of a paramagnetic MR contrast agent provides a basis for estimating cerebral perfusion. The concentration versus time of the contrast agent is calculated in a single image plane on a pixel-wise basis. A number of hemodynamic parameters can be extracted from the integral of the concentration-time curve, hence a method for obtaining an efficient and accurate estimate of the area under the curve is essential for the assessment of perfusion images. A new, automatic, multilevel processing method for calculating area under the concentration-time curve is proposed. In the first level of processing, the signal-to-noise ratio (SNR) is estimated for every pixel, and, if satisfactory, the limit points of integration are determined. An averaging filter is applied on the concentration-time curve, and the slope of the output of the filter Is calculated. The thresholds for initial and final integration points are determined next and are used to obtain limit points of integration. At this level, some pixels may be left without computed limits. These are determined at the next level of processing, using the median filter applied on the pixel neighborhood limit points. After determining limit points, the conventional method for integration is used to obtain the area under the curve. Tests of the proposed method are described for both simulated and real data. The simulated data are based on the gamma-variate function, with white noise added. The parameters used are obtained from fitting the gamma-variate function for regions within white matter, gray matter and cerebrospinal fluid in real perfusion images. The results obtained by the proposed estimator compare very favorably with the theoretical values for the particular cases studied. The performance of the proposed method for measuring cerebral hemodynamic parameters is also discussed when applied to perfusion studies in patients performed on a GE Signa 1.5 T, Advantage, whole body scanner. The results compare well with a previously used procedure based on slice-averaged time of arrival of the contrast bolus and manually determined limiting points. The new method automatizes the integration limit selection procedure efficiently, and is based on local, rather than global calculations. The procedure is simple and fast, and can perform numerical integration of 128*256 pMRI images in less than a second on a Sun SPARC 2 workstation.

The expectation maximization (EM) algorithm and its derivatives have been applied to the problem of image reconstruction in positron emission tomography (PET). The multigrid EM (MGEM) algorithm uses the EM algorithm on a set of reconstruction grids with different resolutions. This paper introduces a multiresolution EM (MREM) algorithm that extends the MGEM algorithm to both the image reconstruction and the detector space. The detectors comprising the ring are reorganized to form a multiresolution detector space. The algorithm begins iterating at the coarsest grid level using tube data that has been re-binned at the coarsest detector level. It switches both the grid and detector levels simultaneously until the finest detector resolution is reached. The algorithm iterates further for various multiresolution grid levels using the tube data at the finest detector resolution. This method provides faster convergence and better reconstruction than the conventional single-grid EM (SGEM) algorithm. The MREM algorithm uses a new transition criterion for switching the grid levels, which is developed using the high-frequency energy derived from the wavelet decomposition of the reconstructed image at each iteration. It also uses a wavelet spline interpolation method to project the intermediate reconstruction from a specific grid level to the next finer grid. The results of the MREM algorithm and the modified MGEM algorithm incorporating the wavelet decomposition-based transition criterion and wavelet interpolation method on simulated phantom data and actual PET camera data are presented.

The M-band wavelet decomposition, a direct generalization of the standard 2-band wavelet decomposition has been applied to the problem of discriminating natural textures of varying sizes. Regular, M-band filter banks were designed using a genetic algorithm search strategy over the Householder parameter space of M-band wavelets. An exhaustive M-band decomposition was performed on 20 natural textures and energy features were extracted for each decomposed sub-band. The discrimination ability of the extracted features was compared for values of M=2, 3 and 4. A nearest neighbor algorithm was used to classify a test set of 700 images to an accuracy of 99.5%. The performance was compared with a complete decomposition and decomposition using an irregular M-band filter bank. Statistical tests were used to evaluate the average performance of features extracted from the decomposed sub-bands.