Tomographic reconstruction from planar thermal imaging using convolutional neural network.

In this study, we investigate perspectives for thermal tomography based on planar infrared thermal images. Volumetric reconstruction of temperature distribution inside an object is hardly applicable in a way similar to ionizing-radiation-based modalities due to its non-penetrating character. Here, we aim at employing the autoencoder deep neural network to collect knowledge on the single-source heat transfer model. For that purpose, we prepare a series of synthetic 3D models of a cylindrical phantom with assumed thermal properties with various heat source locations, captured at different times. A set of planar thermal images taken around the model is subjected to initial backprojection reconstruction, then passed to the deep model. This paper reports the training and testing results in terms of five metrics assessing spatial similarity between volumetric models, signal-to-noise ratio, or heat source location accuracy. We also evaluate the assumptions of the synthetic model with an experiment involving thermal imaging of a real object (pork) and a single heat source. For validation, we investigate objects with multiple heat sources of a random location and temperature. Our results show the capability of a deep model to reconstruct the temperature distribution inside the object.

Cancer prevention - review paper.

INTRODUCTION: Every year there is an increase in the number of cases and deaths due to the majority of cancers. Currently, these diseases constitute the second cause of death in Poland and the USA. The number of cases of malignant neoplasms in Poland has more than doubled over the last three decades. According to the National Cancer Registry, in Poland about 95.5 people per thousand die every year from malignant neoplasms. Current epidemiological data on cancer is worrying because the World Health Organization predicts a significant increase in the incidence of cancer in the general population. This problem, which is significant on the global scale, demands the search for more effective prevention methods so that more and more attention is paid to both primary and secondary prevention. Prevention and early detection of cancer have become a priority for the national health policy of many European countries. Numerous studies around the world prove that reducing the risk of cancer is most effective through adopting a healthy lifestyle, avoiding exposure to carcinogens, combined with regular screening. OBJECTIVE: The aim of the study was to review knowledge on cancer prevention, including the latest research results. CONCLUSIONS: Due to the systematic increase in the incidence of cancer, a strong emphasis should be placed on prevention. Preventive actions bring benefits not only to the individual, but are an important aspect of health policy. The importance of primary prevention in relation to healthy people has been demonstrated, including secondary prevention aimed at controlling risk factors in relation to persons exposed to them. The combination of these activities becomes an important element in maintaining the health of the individual, as well as society.

Chronic wounds multimodal image database.

A multimodal wound image database was created to allow fast development of computer-aided approaches for wound healing monitoring. The developed system with parallel camera optical axes enables multimodal images: photo, thermal, stereo, and depth map of the wound area to be acquired. As a result of using this system a multimodal database of chronic wound images is introduced. It contains 188 image sets of photographs, thermal images, and 3D meshes of the surfaces of chronic wounds acquired during 79 patient visits. Manual wound outlines delineated by an expert are also included in the dataset. All images of each case are additionally coregistered, and both numerical registration parameters and the transformed images are covered in the database. The presented database is publicly available for the research community at https://chronicwounddatabase.eu. That is the first publicly available database for evaluation and comparison of new image-based algorithms in the wound healing monitoring process with coregistered photographs, thermal maps, and 3D models of the wound area. Easily available database of coregistered multimodal data with the raw data set allows faster development of algorithms devoted to wound healing analysis and monitoring.

Ultra-Widefield Fluorescein Angiography Image Brightness Compensation Based on Geometrical Features.

Ultra-widefield fluorescein angiography (UWFA) is an emerging imaging modality used to characterise pathologies in the retinal vasculature, such as microaneurysms (MAs) and vascular leakages. Despite its potential value for diagnosis and disease screening, objective quantitative assessment of retinal pathologies by UWFA is currently limited because laborious manual processing is required. In this report, we describe a geometrical method for uneven brightness compensation inherent to UWFA imaging technique. The correction function is based on the geometrical eyeball shape, therefore it is fully automated and depends only on pixel distance from the center of the imaged retina. The method's performance was assessed on a database containing 256 UWFA images with the use of several image quality measures that show the correction method improves image quality. The method is also compared to the commonly used CLAHE approach and was also employed in a pilot study for vascular segmentation, giving a noticeable improvement in segmentation results. Therefore, the method can be used as an image preprocessing step in retinal UWFA image analysis.

Automated size-specific dose estimates using deep learning image processing.

An automated vendor-independent system for dose monitoring in computed tomography (CT) medical examinations involving ionizing radiation is presented in this paper. The system provides precise size-specific dose estimates (SSDE) following the American Association of Physicists in Medicine regulations. Our dose management can operate on incomplete DICOM header metadata by retrieving necessary information from the dose report image by using optical character recognition. For the determination of the patient's effective diameter and water equivalent diameter, a convolutional neural network is employed for the semantic segmentation of the body area in axial CT slices. Validation experiments for the assessment of the SSDE determination and subsequent stages of our methodology involved a total of 335 CT series (60 352 images) from both public databases and our clinical data. We obtained the mean body area segmentation accuracy of 0.9955 and Jaccard index of 0.9752, yielding a slice-wise mean absolute error of effective diameter below 2 mm and water equivalent diameter at 1 mm, both below 1%. Three modes of the SSDE determination approach were investigated and compared to the results provided by the commercial system GE DoseWatch in three different body region categories: head, chest, and abdomen. Statistical analysis was employed to point out some significant remarks, especially in the head category.

Supporting diagnostics and therapy planning for percutaneous ablation of liver and abdominal tumors and pre-clinical evaluation.

Percutaneous ablation methods are used to treat primary and metastatic liver tumors. Image guided navigation support minimally invasive interventions of rigid anatomical structures. When working with the displacement and deformation of soft tissues during surgery, as in the abdomen, imaging navigation systems are in the preliminary implementation stage. In this study a multi-stage approach has been developed to support percutaneous liver tumors ablation. It includes CT image acquisition protocol with the amplitude of respiratory motion that yields images subjected to a semi-automatic method able to deliver personalized abdominal model. Then, US probe and ablation needle calibration, as well as patient position adjustment method during the procedure for the preoperative anatomy model, have been combined. Finally, an advanced module for fusion of the preoperative CT with intraoperative US images was designed. These modules have been tested on a phantom and in the clinical environment. The final average Spatial calibration error was 1,7 mm, the average error of matching the position of the markers was about 2 mm during the entire breathing cycle, and average markers fusion error 495 mm. The obtained results indicate the possibility of using the developed method of navigation in clinical practice.

Environmental risk factors for cancer - review paper.

The cancerous process is result of disturbed cell function. This is due to the accumulation of many genetic and epigenetic changes within the cell, expressed in the accumulation of chromosomal or molecular aberrations, which leads to genetic instability. It is difficult to assess the validity of individual aetiological factors, but it can be concluded that interaction of various risk factors has the largest contribution to the cancer development. Environmental, exogenous and endogenous factors as well as individual factors, including genetic predisposition contribute to the development of cancer. Epidemiological research on the development of malignant tumors has focused over the years on the determinants of environmental and genetic factors of cancer incidence and mortality rate. According to current state of knowledge, 80-90% of malignant tumors are caused by external environmental factors (carcinogens). Epidemiological studies have proved that the main factors responsible for the development of malignant neoplasia among humans are environmental factors arising from human behaviour. It has been confirmed that smoking, excessive alcohol consumption, diet, and reproductive behaviour are important for the development of malignant neoplasia in the human population. According to the World Health Organization, in 2020 we may expect about 10 million deaths, including 7-8 million in the developing countries, while this number in the developed countries will not change and will be 2-3 million. The aim this study was systematization of knowledge concerning the risk factors of malignant tumours and supplementing them with the latest research results.

Effect of prophylactic actions on the state of oral health and hygienic habits in a selected age group.

INTRODUCTION AND OBJECTIVE: The aim of the study was investigation of the effect of simple prophylactic methods on the motivation for concern about oral hygiene among 13-15-year-olds. MATERIAL AND METHODS: The study covered 98 children from 4 groups attending junior high school. Adolescents from 3 groups were randomly qualified for conducting prophylactic procedures, while the fourth group constituted the control group. Three examinations were performed: preliminary and check-up examinations after 4 and 12 months. The state of the teeth and periodontium and the frequency of brushing of teeth were evaluated. RESULTS: After 4 months, an increase in the number of decayed teeth was observed in all groups; in the control group it was significantly higher compared to the groups subjected to prophylactic actions. After 4 months in the groups covered by prophylactic actions, a significant decrease was obtained in the number of adolescents with CPITN > 0. In the examinations performed after 12 months, no significant differences were found in the value of the DMF and the CPITN index in the examined groups. In both examinations, after 4 and 12 months, the declared frequency of brushing teeth increased, especially in the group which had been provided individual instructions concerning oral hygiene. CONCLUSIONS: 1) Implementation of prophylactic methods resulted in an improvement in the state of oral health among junior high school adolescents. 2) Prophylactic actions should be regularly repeated. 3) The provision of individual instruction with supervised individual teaching of brushing teeth resulted in an improvement in the motivation for concern about oral hygiene.

Prevalence and Possible Role of Candida Species in Patients with Psoriasis: A Systematic Review and Meta-Analysis.

Although fungal colonization is implicated in the pathogenesis of psoriasis, its prevalence remains unclear. The aim of this systematic review and meta-analysis was to provide an overview on the prevalence of Candida species in patients with psoriasis. We searched databases (MEDLINE, EMBASE, Cochrane Central Register of Controlled Trials, and http://clinicaltrials.gov) to identify studies involving subjects of any age with an established diagnosis of psoriasis and healthy controls, who were tested for carriage of Candida spp. on the skin or mucosal membranes (or saliva and stool), or presented with clinical candidiasis with microbiologically confirmed etiology. We identified nine cross-sectional studies including a total of 1038 subjects with psoriasis (psoriatics) and 669 controls. We found Candida species detection rates for psoriatics were significantly higher than those in the controls, especially in the oral mucosa milieux. These results suggest psoriasis may be one of the systemic diseases that predispose to oral Candida spp. carriage and infection.

Development of a Recombinant Protein-based ELISA for Detection of Antibodies Against Bovine Foamy Virus.

INTRODUCTION: Infections with bovine foamy virus (BFV) were found in many countries but there is a lack of large-scale surveys on the prevalence of BFV among dairy cattle. The aim of this study was to develop and validate the recombinant Gag protein-based ELISA and to estimate the prevalence of antibodies against BFV. MATERIAL AND METHODS: Gag coding region from BFV was cloned into expression vector pT7Arg-STOP, which expressed a high level of recombinant Gag protein from E.coli. The ELISA was standardised, and the cut-off value and sensitivity and specificity of the test were calculated using a receiver operating characteristic and Bayesian estimation. RESULTS: A total of 3,051 serum samples were tested by ELISA and 939 (30.8%) sera were recognised as positive. When Bayesian approach was used, the overall true BFV prevalence was 29.7% (95% CI: 25.9-33.4%). CONCLUSION: Expressed Gag protein of BFV has been used successfully as an antigen for ELISA. Eventually, this study provides basic information about the epidemiological status of infection with BFV in dairy cattle in Poland, which can be used for further studies on dissemination and transmission of BFV infection.

Immune system disturbances in Clouston syndrome.

BACKGROUND: Clouston syndrome belongs to the family of ectodermal dysplasias. So far, a defective immune response has not been reported in Clouston syndrome. We report, for the first time, immunological particularities of a large multigenerational Polish family with Clouston syndrome. METHODS: Five members of the same family with Clouston syndrome, aged 6-76 years, and 20 healthy volunteers, aged 19-73 years, were enrolled in the study. In all participants, the ability of neutrophils to phagocytize opsonized Escherichia coli was assessed. Granulocyte oxidative burst was determined quantitatively, and an isolation of peripheral blood mononuclear cells and the detection of lymphocyte subsets were performed. All patients with Clouston syndrome underwent microscopic assessment of hair shafts, x-rays of the skull and hand bones, extra- and intraoral examination, and panoramic x-rays. RESULTS: Compared to the controls, all patients with Clouston syndrome presented with significantly reduced phagocytic activities of granulocytes and monocytes (P < 0.05). The percentages of granulocytes and monocytes being positive for oxidative burst were also significantly reduced in all patients with Clouston syndrome (P < 0.05). No disturbances in the percentages and absolute counts of T CD3+, T CD3+/CD4+, T CD3+/CD8+, natural killer, and B CD19+ cells were found. CONCLUSION: Although this study expands knowledge about Clouston syndrome, it also raises many questions. The results provide evidence of significantly reduced phagocytic activity and oxidative bursts of cells playing crucial roles in a nonspecific immune response. Further studies are required to understand the underlying mechanism of the hereby described abnormalities.

Automatic brain tumour detection and neovasculature assessment with multiseries MRI analysis.

In this paper a novel multi-stage automatic method for brain tumour detection and neovasculature assessment is presented. First, the brain symmetry is exploited to register the magnetic resonance (MR) series analysed. Then, the intracranial structures are found and the region of interest (ROI) is constrained within them to tumour and peritumoural areas using the Fluid Light Attenuation Inversion Recovery (FLAIR) series. Next, the contrast-enhanced lesions are detected on the basis of T1-weighted (T1W) differential images before and after contrast medium administration. Finally, their vascularisation is assessed based on the Regional Cerebral Blood Volume (RCBV) perfusion maps. The relative RCBV (rRCBV) map is calculated in relation to a healthy white matter, also found automatically, and visualised on the analysed series. Three main types of brain tumours, i.e. HG gliomas, metastases and meningiomas have been subjected to the analysis. The results of contrast enhanced lesions detection have been compared with manual delineations performed independently by two experts, yielding 64.84% sensitivity, 99.89% specificity and 71.83% Dice Similarity Coefficient (DSC) for twenty analysed studies of subjects with brain tumours diagnosed.

Role of radiologists in CAD life-cycle.

A modern CAD (computer-aided diagnosis) system development involves a multidisciplinary team whose members are experts in medical and technical fields. This study indicates the activities of medical experts at various stages of the CAD design, testing, and implementation. Those stages include a medical analysis of the diagnostic problem, data collection, image analysis, evaluation, and clinical verification. At each stage the physicians knowledge and experience are indispensable. The final implementation involves integration with the existing Picture Archiving and Communication System. The term CAD life-cycle describes an overall process of the design, testing, and implementation of a system that in its final form assists the radiologists in their daily clinical routine. Four CAD systems (applied to the bone age assessment, Multiple Sclerosis detection, lung nodule detection, and pneumothorax measurement) developed in our laboratory are given as examples of how consecutive stages are developed by the multidisciplinary team. Specific advantages of the CAD implementation that include the daily clinical routine as well as research and education activities are discussed.

A new fuzzy support vectors machine for biomedical data classification.

In this paper a new approach to a fuzzy support vector machine (FSVM) for solving multi-class problems is presented. The developed algorithm combines two separate methods based on fuzzy support vector machine, one for solving two-class problems and the second for multi-class problems. The first method deals with the problem of selecting the best support vector machine (SVM) kernel function and the second method enables classification of unclassified regions that appear when classical SVM methods for solving multi-class problems are used. Presented tool has been subjected to the dataset from Kent Ridge Biomedical Data Set Repository and showed its superiority comparing with conventional SVM and FSVM methods.