Assessment of gamma absorbed doses and radiological risk indexes from soil radioactivity around the phosphate area in south Tunisia.

Human beings are constantly exposed to the radiations coming from the environment. This work assesses the radiological hazards of natural radioactivity in soil samples taken at four locations around the phosphate area in south Tunisia. Concentrations of primordial radionuclides were measured by gamma spectrometer using an HPGe detector. The overall mean values of 40K, 226Ra and 232Th concentrations were 264, 27 and 13 Bq kg-1, respectively. From the radioactivity measurements, radiation hazard indices specified by the United Nation Scientific Committee on the Effect of Atomic Radiation such as radium equivalent activity (Raeq), absorbed dose rates ($ {\dot{\text D}} $) and annual effective dose (AED) to the population for outdoor environment were determined. The mean values for the abovementioned parameters were 64 Bq kg-1, 33 nGy h-1 and 40 µSv y-1, respectively.

ResNet-SVM: Fusion based glioblastoma tumor segmentation and classification.

Computerized segmentation of brain tumor based on magnetic resonance imaging (MRI) data presents an important challenging act in computer vision. In image segmentation, numerous studies have explored the feasibility and advantages of employing deep neural network methods to automatically detect and segment brain tumors depicting on MRI. For training the deeper neural network, the procedure usually requires extensive computational power and it is also very time-consuming due to the complexity and the gradient diffusion difficulty. In order to address and help solve this challenge, we in this study present an automatic approach for Glioblastoma brain tumor segmentation based on deep Residual Learning Network (ResNet) to get over the gradient problem of deep Convolutional Neural Networks (CNNs). Using the extra layers added to a deep neural network, ResNet algorithm can effectively improve the accuracy and the performance, which is useful in solving complex problems with a much rapid training process. An additional method is then proposed to fully automatically classify different brain tumor categories (necrosis, edema, and enhancing regions). Results confirm that the proposed fusion method (ResNet-SVM) has an increased classification results of accuracy (AC = 89.36%), specificity (SP = 92.52%) and precision (PR = 90.12%) using 260 MRI data for the training and 112 data used for testing and validation of Glioblastoma tumor cases. Compared to the state-of-the art methods, the proposed scheme provides a higher performance by identifying Glioblastoma tumor type.

A novel pre-processing approach based on colour space assessment for digestive neuroendocrine tumour grading in immunohistochemical tissue images.

INTRODUCTION: The complexity of histopathological images remains a challenging issue in cancer diagnosis. A pathologist analyses immunohistochemical images to detect a colour-based stain, which is brown for positive nuclei with different intensities and blue for negative nuclei. Several issues emerge during the eyeballing tissue slide analysis, such as colour variations caused by stain inhomogeneity, non-uniform illumination, irregular cell shapes, and overlapping cell nuclei. To overcome those problems, an automated computer-aided diagnosis system is proposed to segment and quantify digestive neuroendocrine tumours. MATERIAL AND METHODS: We present a novel pre-processing approach based on colour space assessment. A criterion called pertinence degree is introduced to select the appropriate colour channel, followed by contrast enhancement. Subsequently, the adaptive local threshold technique that uses the modified Laplacian filter is applied to minimize the implementation complexity, highlight edges, and emphasize intensity variation between cells across the slide. Finally, the improved watershed algorithm based on the concave vertex graph is applied for cell separation. RESULTS: The performance of the algorithms for nucleus segmentation is evaluated according to both the object-level and pixel-level criteria. Our approach increases segmentation accuracy, with the F1-score equal to 0.986. There is significant agreement between the applied approach and the expert's ground truth segmentation. CONCLUSIONS: The proposed method outperformed the state-of-the-art techniques based on recall, precision, the F1-score, and the Dice coefficient.

U-Net: A valuable encoder-decoder architecture for liver tumors segmentation in CT images.

This study proposes a new predictive segmentation method for liver tumors detection using computed tomography (CT) liver images. In the medical imaging field, the exact localization of metastasis lesions after acquisition faces persistent problems both for diagnostic aid and treatment effectiveness. Therefore, the improvement in the diagnostic process is substantially crucial in order to increase the success chance of the management and the therapeutic follow-up. The proposed procedure highlights a computerized approach based on an encoder-decoder structure in order to provide volumetric analysis of pathologic tumors. Specifically, we developed an automatic algorithm for the liver tumors defect segmentation through the Seg-Net and U-Net architectures from metastasis CT images. In this study, we collected a dataset of 200 pathologically confirmed metastasis cancer cases. A total of 8,297 CT image slices of these cases were used developing and optimizing the proposed segmentation architecture. The model was trained and validated using 170 and 30 cases or 85% and 15% of the CT image data, respectively. Study results demonstrate the strength of the proposed approach that reveals the superlative segmentation performance as evaluated using following indices including F1-score = 0.9573, Recall = 0.9520, IOU = 0.9654, Binary cross entropy = 0.0032 and p-value <0.05, respectively. In comparison to state-of-the-art techniques, the proposed method yields a higher precision rate by specifying metastasis tumor position.

Sparse classification of discriminant nystagmus features using combined video-oculography tests and pupil tracking for common vestibular disorder recognition.

Vertigo is a common sign related to a problem with the brain or vestibular system. Detection of ocular nystagmus can be a support indicator to distinguish different vestibular disorders. In order to get reliable and accurate real time measurements from nystagmus response, video-oculography (VOG) plays an important role in the daily clinical examination. However, vestibular diseases present a large diversity in their characteristics that leads to many complications for usual analysis. In this paper, we propose a novel automated approach to achieve both selection and classification of nystagmus parameters using four tests and a pupil tracking procedure in order to give reliable evaluation and standardized indicators of frequent vestibular dysfunction that will assist clinicians in their diagnoses. Indeed, traditional tests (head impulse, caloric, kinetic and saccadic tests) are applied to obtain clinical parameters that highlight the type of vertigo (peripheral or central vertigo). Then, a pupil tracking method is used to extract temporal and frequency nystagmus features in caloric and kinetic sequences. Finally, all extracted features from the tests are reduced according to their high characterization degree by linear discriminant analysis, and classified into three vestibular disorders and normal cases using sparse representation. The proposed methodology is tested on a database containing 90 vertiginous subjects affected by vestibular Neuritis, Meniere's disease and Migraines. The presented technique highly reduces labor-intensive workloads of clinicians by producing the discriminant features for each vestibular disease which will significantly speed up the vertigo diagnosis and provides possibility for fully computerized vestibular disorder evaluation.

AUTOMATIC BRAIN DOSE ESTIMATION IN COMPUTED TOMOGRAPHY USING PATIENT DICOM IMAGES.

This study aims to develop an Automatic Brain Dose Estimation (ABDE) methodology for head computed tomography examinations. The ABDE is to be applied first to an anthropomorphic Alderson phantom to obtain a Correction factor (Cf) between the ABDE and the direct absorbed brain dose using dosemeters positioned within the anthropomorphic phantom. Then, in order to estimate the correct brain dose for patient, the Cf was multiplied by the mean ABDE values for each patient. Results were compared to those registered with a mathematical simulation phantom using CT-Expo V 2.4 software. Results showed no significant difference between the correct ABDE values and the CT-Expo values with a mean percent difference of 2.54 ± 0.01%. In conclusion, ABDE yields a correct estimation of brain dose, taking into account the size and attenuation of the irradiated region. Thus, it is clinically recommended for accurate patient brain dose assessment.

Assessment of radionuclide transfer factors and transfer coefficients near phosphate industrial areas of South Tunisia.

The activity concentrations of naturally occurring and anthropogenic radionuclides in agriculture soils as well as in several food products at four locations within the phosphate area of South Tunisia were investigated. Soil-to-plant transfer factors as well as feed-to-animal products transfer coefficients were determined for the first time for the region. Activity concentrations of 40K, 210Pb, 226Ra, 228Ra and 137Cs in soils of agriculture fields were lower than worldwide average values. The soil-to-plant transfer factors (TFs) for 40K in leafy vegetables were higher than those in fruit vegetables. Soil-to-grass transfer factor (Fv) values were in the following order: 40K > 210Pb > 226Ra. The grass-to-milk transfer coefficient (Fm) values for 40K and 210Pb ranged between 2 × 10-3 and 4 × 10-3(day L-1). The concentration ratios for the animal products (CRmilk-feed, CRmeat-feed and CRegg-feed) varied in the ranges of 2 × 10-2-4 × 10-2 L kg-1, 1 × 10-2-2 × 10-1 (L kg-1) and 5 × 10-2-1 (L kg-1)for 40K, 210Pb and 226Ra, respectively. Transfer parameters determined in the present study were compared with those reported in International Atomic Energy Agency reports and other published values. The absorbed gamma dose rate in air and the external hazard index associated with these natural radionuclides were computed to assess the radiation hazard of radioactivity in this region, and the results indicated that these areas are within set safety limits.

BASELINE STUDIES ON RADIONUCLIDE CONCENTRATION IN FOOD MATERIALS AND ESTIMATION OF THE COMMITTED RADIATION DOSE AROUND THE PHOSPHATE INDUSTRIAL AREA OF SOUTH TUNISIA.

The activity concentration of natural and anthropogenic radionuclides was determined in different vegetable samples, and foods derived from animal origin, from different locations in the four cities of Southern Tunisia, where large-scale phosphate industries are operating. The aim of the studies was to establish a baseline database on radionuclide concentration in food materials and to evaluate the radiation dose to the general population due to its ingestion through the food chain. The activity concentrations of 40K, 210Pb, 226Ra, 228Ra and 137Cs was determined by gamma spectrometry using a HPGe detector, and from the measured activity concentrations, the doses were estimated using the dose coefficients given by the ICRP. The dose due to intake of radionuclides through mineral water was also determined. The total annual effective doses were found to be 2.2, 1.4, and 0.7 mSv y-1 for 1 y, 5-15 y and adult (>17 y) age groups, respectively. Among the radionuclides studied, 210Po was the highest contributor to the total dose, followed by 210Pb.