A robust approach for automated lung segmentation in thoracic CT

Lung segmentation in thoracic computed tomography (CT) scans is an important preprocessing step for computer-aided diagnosis (CAD) of lung diseases. This paper focuses on the segmentation of the lung field in thoracic CT images. Traditional lung segmentation is based on Gray level thresholding techniques, which often requires setting a threshold and is sensitive to image contrasts. In this paper, we present a fully automated method for robust and accurate lung segmentation, which includes a enhanced thresholding algorithm and a refinement scheme based on a texture-aware active contour model. In our thresholding algorithm, a histogram based image stretch technique is performed in advance to uniformly increase contrasts between areas with low Hounsfield unit (HU) values and areas with high HU in all CT images. This stretch step enables the following threshold-free segmentation, which is the Otsu algorithm with contour analysis. However, as a threshold based segmentation, it has common issues such as holes, noises and inaccurate segmentation boundaries that will cause problems in future CAD for lung disease detection. To solve these problems, a refinement technique is proposed that captures vessel structures and lung boundaries and then smooths variations via texture-aware active contour model. Experiments on 2,342 diagnosis CT images demonstrate the effectiveness of the proposed method. Performance comparison with existing methods shows the advantages of our method.

Postoperative pulmonary dysfunction in adults after cardiac surgery with cardiopulmonary bypass: clinical significance and implications for practice

Postoperative pulmonary complications are the most frequent and significant contributor to morbidity, mortality, and costs associated with hospitalization. Interestingly, despite the prevalence of these complications in cardiac surgical patients, recognition, diagnosis, and management of this problem vary widely. In addition, little information is available on the continuum between routine postoperative pulmonary dysfunction and postoperative pulmonary complications. The course of events from pulmonary dysfunction associated with surgery to discharge from the hospital in cardiac patients is largely unexplored. In the absence of evidence-based practice guidelines for the care of cardiac surgical patients with postoperative pulmonary dysfunction, an understanding of the path ophysiological basis of the development of postoperative pulmonary complications is fundamental to enable clinicians to assess the value of current management interventions. Previous research on postoperative pulmonary dysfunction in adults undergoing cardiac surgery is reviewed, with an emphasis on the pathogenesis of this problem, implications for clinical nursing practice, and possibilities for future research.

Empirical evaluation of segmentation algorithms for lung modelling

Lung modelling has emerged as a useful method for diagnosing lung diseases. Image segmentation is an important part of lung modelling systems. The ill-defined nature of image segmentation makes automated lung modelling difficult. Also, low resolution of lung images further increases the difficulty of the lung image segmentation. It is therefore important to identify a suitable segmentation algorithm that can enhance lung modelling accuracies. This paper investigates six image segmentation algorithms, used in medical imaging, and also their application to lung modelling. The algorithms are: normalised cuts, graph, region growing, watershed, Markov random field, and mean shift. The performance of the six segmentation algorithms is determined through a set of experiments on realistic 2D CT lung images. An experimental procedure is devised to measure the performance of the tested algorithms. The measured segmentation accuracies as well as execution times of the six algorithms are then compared and discussed.

The influence of sighing respirations on infant lung function measured using multiple breath washout gas mixing techniques

There is substantial interest in studying lung function in infants, to better understand the early life origins of chronic lung diseases such as asthma. Multiple breath washout (MBW) is a technique for measuring lung function that has been adapted for use in infants. Respiratory sighs occur frequently in young infants during natural sleep, and in accordance with current MBW guidelines, result in exclusion of data from a substantial proportion of testing cycles. We assessed how sighs during MBW influenced the measurements obtained using data from 767 tests conducted on 246 infants (50% male; mean age 43 days) as part of a large cohort study. Sighs occurred in 119 (15%) tests. Sighs during the main part of the wash-in phase (before the last 5 breaths) were not associated with differences in standard MBW measurements compared with tests without sighs. In contrast, sighs that occurred during the washout were associated with a small but discernible increase in magnitude and variability. For example, the mean lung clearance index increased by 0.36 (95% CI: 0.11-0.62) and variance increased by a multiplicative factor of 2 (95% CI: 1.6-2.5). The results suggest it is reasonable to include MBW data from testing cycles where a sigh occurs during the wash-in phase, but not during washout, of MBW. By recovering data that would otherwise have been excluded, we estimate a boost of about 10% to the final number of acceptable tests and 6% to the number of individuals successfully tested.

Management of cardiovascular diseases with micro systems and nanotechnology

Cardiovascular diseases are the leading cause of death and morbidity in industrialized nations and are becoming an urgent health problem for all nations due to the unstoppable trend of an ageing and obese population. Due to the rapid development of micro total analysis systems (μTAS) and nanotechnology in recent years, they will play an important role in the diagnosis, management, and therapy of cardiovascular diseases. It is envisaged that the micro and nanotechnologies developed for treating other diseases shall be explored for cardiovascular applications to reduce the research effort required for commercializing the devices and drugs to meet the increasing demand of the cardiovascular patients.

Nano-lactoferrin in diagnostic, imaging and targeted delivery for cancer and infectious diseases

Lactoferrin (Lf) is a natural occurring iron binding protein present in many mammalian excretions and involved in various physiological processes. Lf is used in the transport of iron along with other molecules and ions from the digestive system. However its the modulatory functions exhibited by Lf in connection to immune response, disease regression and diagnosis that has made this protein an attractive therapeutic against chronic diseases. Further, the exciting potentials of employing nanotechnology in advancing drug delivery systems, active disease targeting and prognosis have also shown some encouraging outcomes. This review focuses on the role of Lf in diagnosing infection, cancer, neurological and inflammatory diseases and the recent nanotechnology based strategies.

In vitro strain measurements in cerebral aneurysm models for cyber-physical diagnosis

Background: The development of new diagnostic technologies for cerebrovascular diseases requires an understanding of the mechanism behind the growth and rupture of cerebral aneurysms. To provide a comprehensive diagnosis and prognosis of this disease, it is desirable to evaluate wall shear stress, pressure, deformation and strain in the aneurysm region, based on information provided by medical imaging technologies. Methods: In this research, we propose a new cyber-physical system composed of in vitro dynamic strain experimental measurements and computational fluid dynamics (CFD) simulation for the diagnosis of cerebral aneurysms. A CFD simulation and a scaled-up membranous silicone model of a cerebral aneurysm were completed, based on patient-specific data recorded in August 2008. In vitro blood flow simulation was realized with the use of a specialized pump. A vision system was also developed to measure the strain at different regions on the model by way of pulsating blood flow circulating inside the model. Results: Experimental results show that distance and area strain maxima were larger near the aneurysm neck (0.042 and 0.052), followed by the aneurysm dome (0.023 and 0.04) and finally the main blood vessel section (0.01 and 0.014). These results were complemented by a CFD simulation for the addition of wall shear stress, oscillatory shear index and aneurysm formation index. Diagnosis results using imaging obtained in August 2008 are consistent with the monitored aneurysm growth in 2011. Conclusion: The presented study demonstrates a new experimental platform for measuring dynamic strain within cerebral aneurysms. This platform is also complemented by a CFD simulation for advanced diagnosis and prediction of the growth tendency of an aneurysm in endovascular surgery.

Peptide-fluorescent bacteria complex as luminescent reagents for cancer diagnosis

Currently in clinic, people use hematoxylin and eosin stain (H&E stain) and immunohistochemistry methods to identify the generation and genre of cancers for human pathological samples. Since these methods are inaccurate and time consuming, developing a rapid and accurate method to detect cancer is urgently demanded. In our study, binding peptides for lung cancer cell line A549 were identified using bacteria surface display method. With those binding peptides for A549 cells on the surface, the fluorescent bacteria (Escherichia coli with stably expressed green fluorescent protein) were served as specific detecting reagents for the diagnosis of cancers. The binding activity of peptide-fluorescent bacteria complex was confirmed by detached cancer cells, attached cancer cells and mice tumor xenograft samples. A unique fixation method was developed for peptide-bacteria complex in order to make this complex more feasible for the clinic use. This peptide-fluorescent bacteria complex has great potential to become a new diagnostic tool for clinical application.

MicroRNAs: biogenesis, roles for carcinogenesis and as potential biomarkers for cancer diagnosis and prognosis

MicroRNAs (miRNAs) are short non-coding RNAs of 20-24 nucleotides that play important roles in carcinogenesis. Accordingly, miRNAs control numerous cancer-relevant biological events such as cell proliferation, cell cycle control, metabolism and apoptosis. In this review, we summarize the current knowledge and concepts concerning the biogenesis of miRNAs, miRNA roles in cancer and their potential as biomarkers for cancer diagnosis and prognosis including the regulation of key cancer-related pathways, such as cell cycle control and miRNA dysregulation. Moreover, microRNA molecules are already receiving the attention of world researchers as therapeutic targets and agents. Therefore, in-depth knowledge of microRNAs has the potential not only to identify their roles in cancer, but also to exploit them as potential biomarkers for cancer diagnosis and identify therapeutic targets for new drug discovery.

Diagnosis and management of oral leishmaniasis--case series and literature review

The worldwide prevalence of leishmaniasis is increasing because of ecologic changes and increased medical profession awareness. Furthermore, solitary cases have been recently reported in Western countries. The authors describe the epidemiology, mode of transmission, and diagnosis of leishmaniasis and present 4 oral cases treated with systemic, localized, or combined therapy. The authors suggest that clinicians should maintain a high index of suspicion for atypical, resistant, oral and perioral lesions in individuals with a history of traveling in certain geographic regions. After diagnosis, treatment should be determined jointly by experts from the fields of oral and maxillofacial surgery, oral medicine, and dermatology based on leishmaniasis species and clinical presentation.

A tailored, supportive care intervention using systematic assessment designed for people with inoperable lung cancer: a randomised controlled trial

Objective : People with inoperable lung cancer experience higher levels of distress, more unmet needs and symptoms than other cancer patients. There is an urgent need to test innovative approaches to improve psychosocial and symptom outcomes in this group. This study tested the hypothesis that a tailored, multidisciplinary supportive care programme based on systematic needs assessment would reduce perceived unmet needs and distress and improve quality of life.

Methods : A randomised controlled trial design was used. The tailored intervention comprised two sessions at treatment commencement and completion. Sessions included a self-completed needs assessment, active listening, self-care education and communication of unmet psychosocial and symptom needs to the multidisciplinary team for management and referral. Outcomes were assessed with the Needs Assessment for Advanced Lung Cancer Patients, Hospital Anxiety and Depression Scale, Distress Thermometer and European Organization of Research and Treatment of Cancer Quality of Life Q-C30 V2.0.

Results : One hundred and eight patients with a diagnosis of inoperable lung or pleural cancer (including mesothelioma) were recruited from a specialist facility before the trial closed prematurely (original target 200). None of the primary contrasts of interest were significant (all p > 0.10), although change score analysis indicated a relative benefit from the intervention for unmet symptom needs at 8 and 12 weeks post-assessment (effect size = 0.55 and 0.40, respectively).

Conclusion : Although a novel approach, the hypothesis that the intervention would benefit perceived unmet needs, psychological morbidity, distress and health-related quality of life was not supported overall.

Lung cancer prediction from microarray data by gene expression programming

Lung cancer is a leading cause of cancer-related death worldwide. The early diagnosis of cancer has demonstrated to be greatly helpful for curing the disease effectively. Microarray technology provides a promising approach of exploiting gene profiles for cancer diagnosis. In this study, the authors propose a gene expression programming (GEP)-based model to predict lung cancer from microarray data. The authors use two gene selection methods to extract the significant lung cancer related genes, and accordingly propose different GEP-based prediction models. Prediction performance evaluations and comparisons between the authors' GEP models and three representative machine learning methods, support vector machine, multi-layer perceptron and radial basis function neural network, were conducted thoroughly on real microarray lung cancer datasets. Reliability was assessed by the cross-data set validation. The experimental results show that the GEP model using fewer feature genes outperformed other models in terms of accuracy, sensitivity, specificity and area under the receiver operating characteristic curve. It is concluded that GEP model is a better solution to lung cancer prediction problems.