John Y. Chiang

Underwater Image Enhancement by Wavelength Compensation and Dehazing

Light scattering and color change are two major sources of distortion for underwater photography. Light scattering is caused by light incident on objects reflected and deflected multiple times by particles present in the water before reaching the camera. This in turn lowers the visibility and contrast of the image captured. Color change corresponds to the varying degrees of attenuation encountered by light traveling in the water with different wavelengths, rendering ambient underwater environments dominated by a bluish tone. No existing underwater processing techniques can handle light scattering and color change distortions suffered by underwater images, and the possible presence of artificial lighting simultaneously. This paper proposes a novel systematic approach to enhance underwater images by a dehazing algorithm, to compensate the attenuation discrepancy along the propagation path, and to take the influence of the possible presence of an artifical light source into consideration. Once the depth map, i.e., distances between the objects and the camera, is estimated, the foreground and background within a scene are segmented. The light intensities of foreground and background are compared to determine whether an artificial light source is employed during the image capturing process. After compensating the effect of artifical light, the haze phenomenon and discrepancy in wavelength attenuation along the underwater propagation path to camera are corrected. Next, the water depth in the image scene is estimated according to the residual energy ratios of different color channels existing in the background light. Based on the amount of attenuation corresponding to each light wavelength, color change compensation is conducted to restore color balance. The performance of the proposed algorithm for wavelength compensation and image dehazing (WCID) is evaluated both objectively and subjectively by utilizing ground-truth color patches and video downloaded from the Youtube website. Both results demonstrate that images with significantly enhanced visibility and superior color fidelity are obtained by the WCID proposed.

Rheumatoid arthritis increases the risk of deep vein thrombosis and pulmonary thromboembolism: a nationwide cohort study

Objective Studies on the association between rheumatoid arthritis (RA) and deep vein thrombosis (DVT) and pulmonary thromboembolism (PE) are scarce. This study identifies the effects of RA on the risks of developing DVT and PE in a nationwide prospective cohort study. Methods We studied the entire Taiwan population from 1998 to 2008, with a follow-up period extending to the end of 2010. We identified patients with RA using the catastrophic illness registry of the Taiwan National Health Insurance Research Database (NHIRD). We also selected a comparison cohort that was randomly frequency-matched by age (each 5-year span), sex and index year from the general population. We analysed the risks of DVT and PE using Cox proportional hazards regression models, including sex, age and comorbidities. Results From 23.74 million people in the cohort, 29 238 RA patients (77% women, mean age of 52.4 years) and 1 16 952 controls were followed 1 93 753 and 7 92 941 person-years, respectively. The risk of developing DVT and PE was 3.36-fold and 2.07-fold, respectively, in patients with RA compared with patients without RA, after adjusting for age, sex and comorbidities. The multiplicative increased risks of DVT and PE were also significant in patients with RA with any comorbidity. Conclusions This nationwide prospective cohort study demonstrates that DVT and PE risks significantly increased in patients with RA compared with those of the general population.

Semi-Automatic Segmentation and Classification of Pap Smear Cells

Cytologic screening has been widely used for detecting the cervical cancers. In this study, a semiautomatic PC-based cellular image analysis system was developed for segmenting nuclear and cytoplasmic contours and for computing morphometric and textual features to train support vector machine (SVM) classifiers to classify four different types of cells and to discriminate dysplastic from normal cells. A software program incorporating function, including image reviewing and standardized denomination of file names, was also designed to facilitate and standardize the workflow of cell analyses. Two experiments were conducted to verify the classification performance. The cross-validation results of the first experiment showed that average accuracies of 97.16% and 98.83%, respectively, for differentiating four different types of cells and in discriminating dysplastic from normal cells have been achieved using salient features (8 for four-cluster and 7 for two-cluster classifiers) selected with SVM recursive feature addition. In the second experiment, 70% (837) of the cell images were used for training and 30% (361) for testing, achieving an accuracy of 96.12% and 98.61% for four-cluster and two-cluster classifiers, respectively. The proposed system provides a feasible and effective tool in evaluating cytologic specimens.

The Study on the Agreement between Automatic Tongue Diagnosis System and Traditional Chinese Medicine Practitioners.

Tongue diagnosis is an important practice in traditional Chinese medicine (TCM) for diagnosing diseases before determining proper means of treatments. Traditionally, it depends solely on personal knowledge and experience of the practitioner, thereby being criticized as lacking of objectivity. Currently, no research regarding intra- and inter-agreements of automatic tongue diagnosis system (ATDS) and TCM doctors has been conducted. In this study, the ATDS is developed to extract a variety of tongue features and provide practitioners with objective information to assist diagnoses. To evaluate the ATDS clinical stability, 2 sets of tongue images taken 1 hour apart from 20 patients with possible variations in lighting and extruding tongue, are employed to investigate intra-agreement of the ATDS, intra-agreement of the TCM doctors, and the inter-agreement between the ATDS and TCM doctors. The ATDS is shown to be more consistent with significantly higher intra-agreement than the TCM doctors (kappa value: 0.93 ± 0.06 versus 0.64 ± 0.13) with P < 0.001 (Students t-test). Inter-agreements between the ATDS and TCM doctors, as well as among the TCM doctors are both moderate. The high agreement of the ATDS can provide objective and reliable tongue features to facilitate doctor in making effective observation and diagnosis of specific diseases.

A NEW ALGORITHM FOR LINE IMAGE VECTORIZATION

In this paper, a new approach which differentiates from the conventional thinning algorithms in vectorizing a raster line image called maximal inscribing circle (MIC) is used. This region-based vectorization algorithm takes the ensemble of pixels within the line segments collectively as legitimate candidates in deciding the vectorized representation. An iterative procedure is outlined and the criteria for merging short straight line segments into the corresponding curve representation are described. This method cannot only segment the lines and junctions, construct their spatial relationships in a computation efficient manner, but also retain their line width.

Sleep Disorders and Increased Risk of Subsequent Acute Coronary Syndrome in Individuals without Sleep Apnea: A Nationwide Population-Based Cohort Study

OBJECTIVES Studies investigating the relationship between nonapnea sleep disorders and the risk of acute coronary syndrome (ACS) are scant. This study evaluated whether the risk of ACS is associated with sleep disorders other than sleep apnea in Taiwan. METHODS This longitudinal nationwide population-based cohort study investigated the incidence and risk of ACS in 49,099 cases of nonapnea sleep disorders newly diagnosed from January 1997 to December 2001. In total, 98,198 control participants without sleep disorders were randomly selected, frequency matched by age and sex from the general population. The follow-up period started from the date of entering the study cohort to the date of an ACS event, censoring, or December 31, 2010. We conducted Cox proportional hazard regression analysis to estimate the effects of nonapnea sleep disorders on ACS risk. RESULTS The nonapnea sleep disorder cohort had an adjusted hazard ratio (HR; 95% confidence interval [CI] = 1.29-1.60) of subsequent ACS 1.43-fold higher than that of the cohort without sleep disorders. The highest crude effect of nonapnea sleep disorders on ACS incidence was detected among young adults. However, by adjusting for probable risk factors, the HR of ACS increased with age. Compared with women, men had an adjusted HR of 1.57 (95% CI = 1.42-1.75). Hypertension, diabetes mellitus (DM), and hyperlipidemia were also significant factors associated with the increased risk of ACS. CONCLUSION This nationwide population-based cohort study provides evidence that patients with nonapnea sleep disorders are at higher risk of developing acute coronary syndrome, which increases with age.

Clinical Verification of A Clinical Decision Support System for Ventilator Weaning

BackgroundWeaning is typically regarded as a process of discontinuing mechanical ventilation in the daily practice of an intensive care unit (ICU). Among the ICU patients, 39%-40% need mechanical ventilator for sustaining their lives. The predictive rate of successful weaning achieved only 35-60% for decisions made by physicians. Clinical decision support systems (CDSSs) are promising in enhancing diagnostic performance and improve healthcare quality in clinical setting. To our knowledge, a prospective study has never been conducted to verify the effectiveness of the CDSS in ventilator weaning before. In this study, the CDSS capable of predicting weaning outcome and reducing duration of ventilator support for patients has been verified.MethodsA total of 380 patients admitted to the respiratory care center of the hospital were randomly assigned to either control or study group. In the control group, patients were weaned with traditional weaning method, while in the study group, patients were weaned with CDSS monitored by physicians. After excluding the patients who transferred to other hospitals, refused further treatments, or expired the admission period, data of 168 and 144 patients in the study and control groups, respectively, were used for analysis.ResultsThe results show that a sensitivity of 87.7% has been achieved, which is significantly higher (p<0.01) than the weaning determined by physicians (sensitivity: 61.4%). Furthermore, the days using mechanical ventilator for the study group (38.41 ± 3.35) is significantly (p<0.001) shorter than the control group (43.69 ± 14.89), with a decrease of 5.2 days in average, resulting in a saving of healthcare cost of NT

Multiple-instance content-based image retrieval employing isometric embedded similarity measure

45,000 (US

Far-infrared therapy for cardiovascular, autoimmune, and other chronic health problems: A systematic review

1,500) per patient in the current Taiwanese National Health Insurance setting.ConclusionsThe CDSS is demonstrated to be effective in identifying the earliest time of ventilator weaning for patients to resume and sustain spontaneous breathing, thereby avoiding unnecessary prolonged ventilator use and decreasing healthcare cost.

Inhaled corticosteroids and the increased risk of pulmonary tuberculosis: a population-based case-control study

In image-based retrieval, global or local features sufficiently discriminative to summarize the image content are commonly extracted first. Traditional features, such as color, texture, shape or corner, characterizing image content are not reliable in terms of similarity measure. A good match in the feature domain does not necessarily map to image pairs with similar relationship. Applying these features as search keys may retrieve dissimilar false-positive images, or leave similar false-negative ones behind. Moreover, images are inherently ambiguous since they contain a great amount of information that justifies many different facets of interpretation. Using a single image to query a database might employ features that do not match users expectation and retrieve results with low precision/recall ratios. How to automatically extract reliable image features as a query key that matches users expectation in a content-based image retrieval (CBIR) system is an important topic. The objective of the present work is to propose a multiple-instance learning image retrieval system by incorporating an isometric embedded similarity measure. Multiple-instance learning is a way of modeling ambiguity in supervised learning given multiple examples. From a small collection of positive and negative example images, semantically relevant concepts can be derived automatically and employed to retrieve images from an image database. Each positive and negative example images are represented by a linear combination of fractal orthonormal basis vectors. The mapping coefficients of an image projected onto each orthonormal basis constitute a feature vector. The Euclidean-distance similarity measure is proved to remain consistent, i.e., isometric embedded, between any image pairs before and after the projection onto orthonormal axes. Not only similar images generate points close to each other in the feature space, but also dissimilar ones produce feature points far apart. The utilization of an isometric-embedded fractal-based technique to extract reliable image features, combined with a multiple-instance learning paradigm to derive relevant concepts, can produce desirable retrieval results that better match users expectation. In order to demonstrate the feasibility of the proposed approach, two sets of test for querying an image database are performed, namely, the fractal-based feature extraction algorithm vs. three other feature extractors, and single-instance vs. multiple-instance learning. Both the retrieval results, execution time and precision/recall curves show favorably for the proposed multiple-instance fractal-based approach.