Convolutional LSTM-LSTM model for predicting the daily number of influenza patients in South Korea using satellite images.

OBJECTIVES: Influenza affects a considerable proportion of the global population each year, and meteorological conditions may have a significant impact on its transmission. In this study, we aimed to develop a prediction model for the number of influenza patients at the national level using satellite images and provide a basis for predicting influenza through satellite image data. STUDY DESIGN: We developed an influenza incidence prediction model using satellite images and influenza patient data. METHODS: We collected satellite images and daily influenza patient data from July 2014 to June 2019 and developed a convolutional long short-term memory (LSTM)-LSTM neural network model. The model with the lowest average of mean absolute error (MAE) was selected. RESULTS: The final model showed a high correlation between the predicted and actual number of influenza patients, with an average MAE of 5.9010 per million population. The model performed best with a 2-week time sequence. CONCLUSIONS: We developed a national-level prediction model using satellite images to predict influenza incidence. The model offers the advantage of nationwide analysis. These results may reduce the burden of influenza by enabling timely public health interventions.

Anti-immunoglobulin E in the treatment of refractory atopic dermatitis.

Atopic dermatitis (AD) is a chronic and relapsing inflammatory skin disease affecting > 10% of children and 1-3% of adults, and can cause significant morbidity. The incidence of AD seems to be increasing. Omalizumab, a monoclonal antibody, has recently been suggested as a potential new systemic treatment for patients with recalcitrant AD with elevated IgE levels, based on its efficacy in treating asthma and allergic rhinitis. We report a study of 10 patients with AD (aged 19-35 years) who received anti-IgE treatment for persistent asthma. All patients, regardless of IgE value, were treated with a fixed schedule of eight cycles of omalizumab 300 mg administered subcutaneously at intervals of 2 weeks. Eczema symptoms were scored at baseline and after 2, 4 and 6 months of treatment. There was a steady improvement in the objective SCORAD (SCORing Atopic Dermatitis), with significantly lower scores observed at the 6-month evaluation. At 2 months after the end of treatment, two patients had a very good result (SCORAD reduction of > 50%), five patients had a satisfactory result (reduction of 25-50%), and three patients had no clinically relevant result (reduction of 25-50%). No patient had worsening of the AD (increase of > 25% in SCORAD), and once a clinical improvement occurred, none of the patients experienced worsening of their eczema symptoms while on omalizumab. With the caveats of the financial expense and unknown long-term risks of malignancy associated with omalizumab, this drug should be considered for treatment-resistant patients with AD, particularly patients with high IgE level whose symptoms are not controlled by routine therapies. Omalizumab has proven useful in treating asthma, but it may also prove valuable for other conditions, such as allergic rhinitis, food allergies, chronic urticaria, and AD, as shown by the present study.

Inhibitory effect of tianeptine on catagen induction in alopecia areata-like lesions induced by ultrasonic wave stress in mice.

BACKGROUND: Alopecia areata (AA) is characterized by rapid and complete hair loss in one or multiple areas of the scalp. Stress is an important triggering factor in AA. AIM: To identify the inhibitory effect of tianeptine on catagen induction in C57BL/6 mice with AA-like lesions induced by ultrasonic wave stress (UWS). METHODS: The mice were divided into four groups. Group 1 received oral tianeptine before and after UWS; group 2 received oral tianeptine only after UWS; group 3 was given UWS treatment only; and group 4 (negative control group) was not given any treatment. Phototrichigraphy and dermatoscopy were used for assessment. Histological analysis was performed using haematoxylin and eosin, toluidine blue, Masson trichrome and Verhoeff-van Gieson stains. Immunohistochemical analysis was also performed. The level of apoptosis and expression of neuropeptides in the skin were assessed by terminal deoxynucleotidyl transferase dUTP nick end labelling and immunofluorescence assays. RESULTS: Mice in group 1 had an increased rate of hair growth and greater hair-shaft thickness compared with mice in groups 2 and 3. In addition, mice in group 1 had a higher number of anagen hair follicles, increased synthesis of collagen and elastic fibres, decreased mast-cell degranulation, reduction in cell apoptosis in hair follicles, and recovery of vitamin D receptor expression. Expression of neuropeptides (substance P, calcitonin gene-related peptide) was not altered. CONCLUSIONS: Tianeptine might play a role in suppressing catagen induction in a stress-induced AA mouse model.

A pilot study of silver-loaded cellulose fabric with incorporated seaweed for the treatment of atopic dermatitis.

Because clothing has the longest and most direct contact with human skin, it is important to carefully choose suitable fabrics for atopic patients who have disrupted skin. To evaluate the clinical effectiveness and biophysical properties of a newly developed silver-loaded cellulose fabric with incorporated seaweed, we enrolled 12 subjects with mild to moderate atopic dermatitis into a clinical control study. The subjects wore a two-piece garment (top and leggings), each piece of which was divided into two parts: one side was made of SkinDoctor(®) fabric, and the other of 100% cotton. Treatment efficacy was measured with the modified SCORing Atopic Dermatitis (mSCORAD) index, transepidermal water loss (TEWL) and the patients' subjective impressions. All three of these measures had significantly better scores on the side covered with SkinDoctor. These results suggest that SkinDoctor is a beneficial fabric that can improve the comfort of patients with AD.

WS/PIDS: standard interoperable PIDS in web services environments.

An electronic health record depends on the consistent handling of people's identities within and outside healthcare organizations. Currently, the Person Identification Service (PIDS), a CORBA specification, is the only well-researched standard that meets these needs. In this paper, we introduce WS/PIDS, a PIDS specification for Web Services (WS) that closely matches the original PIDS and improves on it by providing explicit support for medical multimedia attributes. WS/PIDS is currently supported by a test implementation, layered on top of a PIDS back-end, with Java- and NET-based, and Web clients. WS/PIDS is interoperable among platforms; it preserves PIDS semantics to a large extent, and it is intended to be fully compliant with established and emerging WS standards. The specification is open source and immediately usable in dynamic clinical systems participating in grid environments. WS/PIDS has been tested successfully with a comprehensive set of use cases, and it is being used in a clinical research setting.

Critical appraisal of electronic structure of metmyoglobin. 14N and 57Fe hyperfine interactions.

The electronic structure of metmyoglobin is subjected to a critical examination by comparison of results of recent ENDOR measurements of nitrogen hyperfine interaction constants on the porphyrin ring and on the proximal histidine linking the heme to the protein with theoretical values for these properties from calculated electronic wavefunctions for this molecule. The observed interesting trends of the 14N hyperfine data as well as available 57Fe data are both successfully explained showing that theory has provided a satisfactory description of the electronic distribution in this important molecule.

Three-dimensional computer-simulated prostate models: lateral prostate biopsies increase the detection rate of prostate cancer.

OBJECTIVES: Urologists routinely use the systematic sextant needle biopsy technique to detect prostate cancer. However, recent evidence suggests that this technique has a significant sampling error. We developed a novel three-dimensional (3D) computer-assisted prostate biopsy simulator based on whole-mounted step-sectioned radical prostatectomy specimens to compare the diagnostic accuracy of various prostate needle biopsy protocols. METHODS: We obtained digital images of 201 step-sectioned whole-mounted radical prostatectomy specimens. 3D computer simulation software was developed to accurately depict the anatomy of the prostate and all individual tumor foci. Additional peripheral devices were incorporated into the system to perform interactive prostate biopsies. We obtained 18 biopsies of each prostate model to determine the detection rates of various biopsy protocols. RESULTS: The 10- and 12-pattern biopsy protocols had a 99.0% detection rate; the traditional sextant biopsy protocol rate was only 72.6%. The 5-region biopsy protocol had a 90.5% detection rate and the 14-pattern, which includes all the biopsies used in the patterns above, only added 1 additional positive case (99.5%). Transitional zone and seminal vesicle biopsies did not result in a significantly increased detection rate when added to the patterns above. Only one positive model was obtained when the transitional zone biopsies were added. The lateral sextant pattern had a detection rate of 95.5%, and the 4-pattern lateral biopsy protocol had a 93.5% detection rate. CONCLUSIONS: Our results suggest that all the biopsy protocols that use laterally placed biopsies based on the 5-region anatomic model are superior to the routinely used sextant prostate biopsy pattern. Lateral biopsies in the mid and apical zones of the gland are the most important.

A telemedicine consultative service for the evaluation of patients with urolithiasis.

OBJECTIVES: A 6-month pilot teleconsultative project linking Georgetown University Medical Center (GUMC) in Washington, DC, and City Hospital in Martinsburg, West Virginia, 90 miles away, was designed to assess the effectiveness of telemedicine on the clinical decision-making process for patients with urolithiasis. METHODS: The telemedicine system designed and tested for this project was based on a PC-based platform. Videoconferencing and review of the patient's imaging studies were performed over an Integrated Service Digital Network (ISDN) with 3 Basic Rate (BRI) ISDN lines providing a 336-kilobytes/s bandwidth through an Inverse Multiplexor (IMUX). Treatment options were recorded for the clinical trial group and a simulated study group by the consulting urologist after the initial telephone consultation, after the telemedicine consultation, and after examination of those patients transferred to GUMC. RESULTS: A total of 32 telemedicine consultations were performed: 14 in the clinical trial group and 18 in the simulated study group. The recommendation of the consulting urologist at the tertiary center was altered in 12 patients (37.5%) after the telemedicine consultation compared with the recommended treatment after the initial telephone consultation. CONCLUSIONS: In the evaluation of patients with urolithiasis, this telemedicine application enhanced the clinical decision-making process by allowing for improved quality of care through immediate access and effective transfer of information between the referring urologist, the patient, and the stone center specialist.

Automated segmentation of anatomic regions in chest radiographs using an adaptive-sized hybrid neural network.

The purposes of this research are to investigate the effectiveness of our novel image features for segmentation of anatomic regions such as the lungs and the mediastinum in chest radiographs and to develop an automatic computerized method for image processing. A total of 85 screening chest radiographs from Johns Hopkins University Hospital were digitized to 2 K by 2.5 K pixels with 12 bit gray scale. To reduce the amount of information, the images were smoothed and subsampled to 256 by 310 pixels with 8 bit. The determination approach consists of classifying each pixel into two anatomic classes (lung and others) on the basis of several image features: (1) relative pixel address (Rx, Ry) based on lung edges extracted through image processing using profile, (2) density normalized from lungs and mediastinum density, and (3) histogram equalized entropy. The combinations of image features were evaluated using an adaptive-sized hybrid neural network consisting of an input, a hidden, and an output layer. Fourteen images were used for the training of the neural network and the remaining 71 images for testing. Using four features of relative address (Rx, Ry), normalized density, and histogram equalized entropy, the neural networks classified lungs at 92% accuracy against test images following the same rules as for the training images.

A method for splitting digital value in radiological image compression.

A new decomposition method using image splitting and gray-level remapping has been proposed for image compression, particularly for images with high contrast resolution. The effects of this method are especially evident in this radiological image compression study. In these experiments, the impact of this decomposition method was tested on image compression by employing it with two coding techniques on a set of clinically used CT images and several laser film digitized chest radiographs. One of the compression techniques used as zonal full-frame bit-allocation in the discrete cosine transform (DCT) domain, which is an enhanced full-frame DCT technique that has been proven to be an effective technique for radiological image compression. The other compression technique used was vector quantization with pruned tree-structured encoding, which through recent research has also been found to produce a low mean-square error and a high compression ratio. The parameters used in this study were mean-square error and the bit rate required for the compressed file. In addition to these parameters, the differences between the original and reconstructed images were presented so that the specific artifacts generated by both techniques could be discerned through visual perception.

Investigating the distribution of prostate cancer using three-dimensional computer simulation.

The objective of this work was to investigate the distribution of prostate cancer using three-dimensional (3-D) computer simulation. Two hundred and eighty-one 3-D computer prostate models were constructed from radical prostatectomy specimens. An algorithm was developed which divided each model into 24 symmetrical regions, and it then detected the presence of tumor within an individual region. The distribution rate of prostate cancer was assessed within each region of all 281 prostate models, and the difference between the rates was statistically analyzed using Mantel-Haenszel methodology. There was a statistically significant higher distribution rate of cancer in the posterior half (57.2%) compared to the anterior half ( 40.5%; P=0.001). The base regions (36.8%) had a statistically significant lower distribution rate than either the mid regions (56.3%; P=0.001) or the apical regions (53.5%; P=0.001). The mid regions did have a statistically significant higher distribution rate compared to the apical regions (P=0.032). There was no statistically significant difference between the distribution rate on the left half (48.5%) compared to that on the right half (49.2%; P=0.494). The spatial distribution of prostate cancer can be analyzed using 3-D computer prostate models. The results illustrate that prostate cancer is least commonly located in the anterior half and base regions of the prostate. Through an analysis of the spatial distribution of prostate cancer, we believe that new optimal biopsy strategies and techniques can be developed.

Anatomic region-based dynamic range compression for chest radiographs using warping transformation of correlated distribution.

The purpose of this paper is to investigate the effectiveness of our novel dynamic range compression (DRC) for chest radiographs. The purpose of DRC is to compress the gray scale range of the image when using narrow dynamic range viewing systems such as monitors. First, an automated segmentation method was used to detect the lung region. The combined region of mediastinum, heart, and subdiaphragm was defined based on the lung region. The correlated distributions, between a pixel value and its neighboring averaged pixel value, for the lung region and the combined region were calculated. According to the appearance of overlapping of two distributions, the warping function was decided. After pixel values were warped, the pixel value range of the lung region was compressed while preserving the detail information, because the warping function compressed the range of the averaged pixel values while preserving the pixel value range for the pixels which had had the same averaged pixel value. The performance was evaluated with our criterion function which was the contrast divided by the moment, where the contrast and the moment represent the sum of the differences between the pixel values and the averaged values of eight pixels surrounding that pixel, and the sum of the differences between the pixel values and the averaged value of all pixels in the region-of-interest, respectively. For 71 screening chest images from Johns Hopkins University Hospital (Baltimore, MD), this method improved our criterion function at 11.7% on average. The warping transformation algorithm based on the correlated distribution was effective in compressing the dynamic range while simultaneously preserving the detail information.

Noise impact on error-free image compression.

Some radiological images with different levels of noise have been studied using various decomposition methods incorporated with Huffman and Lempel-Ziv coding. When more correlations exist between pixels, these techniques can be made more efficient. However, additional noise disrupts the correlation between adjacent pixels and leads to a less compressed result. Hence, prior to a systematic compression in a picture archiving and communication system (PACS), two main issues must be addressed: the true information range which exists in a specific type of radiological image, and the costs and benefits of compression for the PACS. It is shown that with laser film digitized magnetic resonance images, 10-12 b are produced, although the lower 2-4 b show the characteristics of random noise. The addition of the noise bits is shown to adversely affect the amount of compression given by various reversible compression techniques. The sensitivity of different techniques to different levels of noise is examined in order to suggest strategies for dealing with noise.

Reduction of false positives in lung nodule detection using a two-level neural classification.

The authors have developed a neural-digital computer-aided diagnosis system, based on a parameterized two-level convolution neural network (CNN) architecture and on a special multilabel output encoding procedure. The developed architecture was trained, tested, and evaluated specifically on the problem of diagnosis of lung cancer nodules found on digitized chest radiographs. The system performs automatic "suspect" localization, feature extraction, and diagnosis of a particular pattern-class aimed at a high degree of "true-positive fraction" detection and low "false-positive fraction" detection. In this paper, the authors aim at the presentation of the two-level neural classification method in reducing false-positives in their system. They employed receiver operating characteristics (ROC) method with the area under the ROC curve (A(z)) as the performance index to evaluate all the simulation results. The two-level CNN showed superior performance (A(z)=0.93) to the single-level CNN (A(z)=0.85). The proposed two-level CNN architecture is proven to be promising and to be extensible, problem-independent, and therefore, applicable to other medical or difficult diagnostic tasks in two-dimensional (2-D) image environments.

Artificial convolution neural network techniques and applications for lung nodule detection.

We have developed a double-matching method and an artificial visual neural network technique for lung nodule detection. This neural network technique is generally applicable to the recognition of medical image pattern in gray scale imaging. The structure of the artificial neural net is a simplified network structure of human vision. The fundamental operation of the artificial neural network is local two-dimensional convolution rather than full connection with weighted multiplication. Weighting coefficients of the convolution kernels are formed by the neural network through backpropagated training. In addition, we modeled radiologists' reading procedures in order to instruct the artificial neural network to recognize the image patterns predefined and those of interest to experts in radiology. We have tested this method for lung nodule detection. The performance studies have shown the potential use of this technique in a clinical setting. This program first performed an initial nodule search with high sensitivity in detecting round objects using a sphere template double-matching technique. The artificial convolution neural network acted as a final classifier to determine whether the suspected image block contains a lung nodule. The total processing time for the automatic detection of lung nodules using both prescan and convolution neural network evaluation was about 15 seconds in a DEC Alpha workstation.

Classification of microcalcifications in radiographs of pathologic specimens for the diagnosis of breast cancer.

RATIONALE AND OBJECTIVES: Early detection of breast cancer depends on accurate classification of microcalcifications. We have developed a computer vision system that has the potential to classify microcalcifications objectively and consistently to aid radiologists in diagnosing breast cancer. METHODS: A convolution neural network (CNN) was used to classify benign and malignant microcalcifications in radiographs of pathologic specimens. Digital images were acquired by digitizing radiographs at a high resolution of 21 microns x 21 microns. RESULTS: Eighty regions of interest selected from digitized radiographs of pathologic specimens were used for training and testing of the neural network system. The CNN achieved an Az value (area under the receiver operating characteristic curve) of 0.90 in classifying clusters of microcalcifications associated with benign and malignant processes. CONCLUSION: Classification of microcalcifications in pathologic specimens for diagnosis of breast cancer was achieved at a high level in our computer vision system, which consists of high-resolution digitization of mammograms and a CNN.

Hemodialysis patient management by telemedicine: design and implementation.

The authors describe the design and implementation of a personal computer based telemedicine system for managing patients by telemedicine. With three identical systems connected by high speed T1 lines, the physician (or allied healthcare giver) can interact, by videoconferencing, and by using multimedia files, with patients at two remote hemodialysis sites. The physician is able to visualize specifically the patient's fistula/graft, and auscultate fistula, heart and lung sounds, and incorporate still pictures or audio sounds in the patient's multimedia database folder, which also contains an electronic and paperless medical record. In addition there is the capability of downloading into this database all the machine parameters during dialysis.

Deployable teleradiology: Bosnia and beyond.

The United States military has been an effective proponent of digital imaging and teleradiology for the past 15 years [1]. A digital imaging network that eliminates the use of x-ray film makes military medicine requirements simpler. X-ray film requirements include storage of new, unexposed films, storage and use of chemicals and water for processing, and disposal of chemicals. In some deployed situations, the chemical discharge needs to be collected and shipped out of the area. Therefore, the ability to implement electronic imaging and eliminate or greatly reduce the dependence on film, chemicals, and water are intrinsically important to military medicine. In December 1995, the United States government began deployment of 20,000 United States troops to Bosnia-Herzegovina as part of NATO's peacekeeping implementation force (IFOR) operation. A full complement of military medical support facilities was established in Bosnia. An army base in Hungary was the location from which the deployment was staged. The project to deploy telemedicine and teleradiology capabilities to the medical treatment facilities (MTF) in Bosnia and Hungary became known as PrimeTime III [2]. This paper deals with the deployable teleradiology (DEPRAD) system that was installed by the Imaging Science and Information Systems (ISIS) Center, Department of Radiology, Georgetown Medical Center, Washington, DC, at a number of facilities to implement filmless radiology and teleradiology services in support of PrimeTime III.

Projection domain compensation of missing angles for fan-beam CT reconstruction.

An improved method is proposed for fan-beam computed tomographic (CT) reconstruction from data with limited views. Compensation for the missing projections for fan-beam CT can be partially accomplished by using the coincident ray or by an interpolation technique using circular sample theory. In this article, the authors propose a more accurate compensation method for the missing projections whether the coincident ray pairs exist or not. The fan-beam reprojection algorithm, which is the inverse operator of the convolution filter, was extended from the projection space iteration reconstruction-reprojection (PSIRR) in parallel beam geometry. In addition, this algorithm was validated by applying the Shepp-Logan phantom for a computer simulation in the equi-angular fan-beam CT geometry.