Macro- and Micro-Expressions Facial Datasets: A Survey.

Automatic facial expression recognition is essential for many potential applications. Thus, having a clear overview on existing datasets that have been investigated within the framework of face expression recognition is of paramount importance in designing and evaluating effective solutions, notably for neural networks-based training. In this survey, we provide a review of more than eighty facial expression datasets, while taking into account both macro- and micro-expressions. The proposed study is mostly focused on spontaneous and in-the-wild datasets, given the common trend in the research is that of considering contexts where expressions are shown in a spontaneous way and in a real context. We have also provided instances of potential applications of the investigated datasets, while putting into evidence their pros and cons. The proposed survey can help researchers to have a better understanding of the characteristics of the existing datasets, thus facilitating the choice of the data that best suits the particular context of their application.

Towards non-data-hungry and fully-automated diagnosis of breast cancer from mammographic images.

Analysing local texture and generating features are two key issues for automatic cancer detection in mammographic images. Recent researches have shown that deep neural networks provide a promising alternative to hand-driven features which suffer from curse of dimensionality and low accuracy rates. However, large and balanced training data are foremost requirements for deep learning-based models and these data are not always available publicly. In this work, we propose a fully-automated method for breast cancer diagnosis that performs training using small sets of data. Feature extraction from mammographic images is performed using a genetic-programming-based descriptor that exploits statistics on a local binary pattern-like local distribution defined in each pixel. The effectiveness of the suggested method is demonstrated on two challenging datasets, (1) the digital database for screening mammography and (2) the mammographic image analysis society digital mammogram database, for content-based image retrieval as well as for abnormality/malignancy classification. The experimental results show that the proposed method outperforms or achieves comparable results with deep learning-based methods even those with transfer learning and/or data-augmentation.

Risk Assessment of the Role of the Ecotones in the Transmission of Zoonotic Cutaneous Leishmaniasis in Central Tunisia.

Zoonotic cutaneous leishmaniasis (ZCL), endemic in Central and Southern Tunisia, is caused by Leishmania major (Kinetoplastida: Trypanosomatidae), which is transmitted by the sand fly Phlebotomus papatasi. In Tunisia, the fat sand rat Psammomys obesus and the desert jird Meriones shawi are the principal reservoir hosts of L. major. The presence of the P. papatasi vector of the L. major etiologic agent of ZCL was assessed in the vicinity of villages in endemic areas of Central Tunisia. The study was performed from September through October 2019, a period corresponding to the main peak of activity of P. papatasi. Sand flies were collected from rodent burrows located at the ecotone level, which is the transition zone between the natural environment and human settlement. Sand flies were identified to species level and tested for the presence of L. major by PCR. Our entomological survey showed that P. papatasi is the most abundant sand fly species associated with rodent burrows, and this abundance is even higher in ecotones primarily occupied by P. obesus in comparison to ecotones occupied by M. shawi. Infections with Leishmania major were detected only in P. papatasi, with an overall minimum infection rate (MIR) of 2.64%. No significant difference was observed between the MIRs in ecotones of P. obesus and of M. shawi. Incidence of ZCL in the studied areas ranged from 200 to 700 cases per 100,000 inhabitants, with a mean incidence of 385.41 per 100,000. Higher ZCL incidence was identified in ecotones of M. shawi compared to ecotones of P. obesus. ZCL cases are positively correlated with the MIRs. Considering the short flight range of P. papatasi, increases in its densities associated with burrows of P. obesus or M. shawi at the ecotone level expand the overlap of infected vectors with communities and subsequently increase ZCL incidence. Therefore, control measures should target P. papatasi populations at the ecotones.

Skin lesion image retrieval using transfer learning-based approach for query-driven distance recommendation.

Content-Based Dermatological Lesion Retrieval (CBDLR) systems retrieve similar skin lesion images, with a pathology-confirmed diagnosis, for a given query image of a skin lesion. By producing an intuitive support to both inexperienced and experienced dermatologists, the early diagnosis through CBDLR screening can significantly enhance the patients' survival, while reducing the treatment cost. To deal with this issue, a CBDLR system is proposed in this study. This system integrates a similarity measure recommender which allows a dynamic selection of the adequate distance metric for each query image. The main contributions of this work reside in (i) the adoption of deep-learned features according to their performances for the classification of skin lesions into seven classes; and (ii) the automatic generation of ground truth that was investigated within the framework of transfer learning in order to recommend the most appropriate distance for any new query image. The proposed CBDLR system has been exhaustively evaluated using the challenging ISIC2018 and ISIC2019 datasets, and the obtained results show that the proposed system can provide a useful aided-decision while offering superior performances. Indeed, it outperforms similar CBDLR systems that adopt standard distances by at least 9% in terms of mAP@K.

Tick-borne encephalitis virus in Ixodes ricinus (Acari: Ixodidae) ticks, Tunisia.

Tick-borne encephalitis virus (TBEV) is the etiologic agent of tick-borne encephalitis (TBE) and transmitted by Ixodes ricinus (Linnaeus, 1758) in Europe. The geographical distribution of I. ricinus in the Palearctic region covers also northern Africa, including northwestern Tunisia. While the eco-epidemiology of TBE in Europe is well documented, no data concerning TBEV from northern Africa are available. We investigated whether TBEV is circulating in Tunisia. A total of 877 adult I. ricinus collected from northwestern Tunisia were examined in pools for the presence of TBEV by nRT-PCR. Viral RNA was detected in one pool of three engorged ticks, yielding a minimum infection rate of 0.11 % (1/877). Phylogenetic analysis showed that the Tunisian TBEV strain belongs to the European lineage. We report for the first time the presence of TBEV in I. ricinus from northern Africa. Therefore, more studies are needed to assess the public health importance of TBEV in northern Africa.

The Impact of Illegal Waste Sites on the Transmission of Zoonotic Cutaneous Leishmaniasis in Central Tunisia.

Illegal waste disposal represents a risk health factor for vector-borne diseases by providing shelter for rodents and their ectoparasites. The presence of the Phlebotomus papatasi vector of Leishmania major, an etiologic agent of zoonotic cutaneous leishmaniasis (ZCL), was assessed at illegal waste sites located at the vicinity of villages in endemic areas of Central Tunisia. The study was performed over a two-year period over three nights from July to September 2017, and over three nights in September 2018. Household waste is deposited illegally forming dumpsites at the vicinity of each village and contains several rodent burrows of Psammomys obesus, the main reservoir host of L. major. Sandflies were collected from rodent burrows in the natural environment and in dumpsites using sticky traps and were identified at species level. Female sandflies were tested for the presence of L. major by PCR. Our entomological survey showed that Phlebotomus papatasi is the most abundant sandfly species associated with rodent burrows in these waste sites. The densities of P. papatasi in dumpsites are significantly higher compared to the natural environment. The minimum infection rate of P. papatasi with L. major in these illegal waste sites is not significantly different compared to the natural environment. Considering the short flight range of P. papatasi, increases in its densities, associated with burrows of P. obesus in illegal waste sites located at the edge of villages, expands the overlap of infected ZCL vectors with communities. Thus, illegal waste sites pose a high risk of spreading ZCL to neighboring home ranges. Waste management is an environmentally friendly method of controlling sandfly populations and should be included in an integrated management program for controlling ZCL in endemic countries.

Dynamic distance learning for joint assessment of visual and semantic similarities within the framework of medical image retrieval.

The similarity measure is an essential part of medical image retrieval systems for assisting in radiological diagnosis. Attempts have been made to use distance metric learning approaches to improve the retrieval performance while decreasing the semantic gap. However, existing approaches did not resolve the problem of dependency between images (e.g. normal and abnormal images are compared with the same distance). This affects the semantic and the visual similarity. Thus, this work aims at learning a distance metric which preserves both visual resemblance and semantic similarity and modeling this distance in order to treat each query independently. The proposed method is described in three stages: (1) low-level image feature extraction, (2) offline distance metric modeling, and (3) online retrieval. The first stage exploits transform-domain texture descriptors based on local binary pattern histogram Fourier, shearlet, and curvelet transforms. The second stage is carried out using low-level features and machine learning. Given a query image, the online retrieval is based on the evaluation of the similarity between this image and each image within the dataset, while using a distance that is dynamically defined according to the query image. Realized experiments on the challenging Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM) datasets prove the effectiveness of the proposed method in determining dynamically the adequate distance and retrieving the most semantically similar images, while investigating single low-level features as well as fused ones.

Gradient-based generation of intermediate images for heterogeneous tumor segmentation within hybrid PET/MRI scans.

Segmentation of tumors from hybrid PET/MRI scans plays an essential role in accurate diagnosis and treatment planning. However, when treating tumors, several challenges, notably heterogeneity and the problem of leaking into surrounding tissues with similar high uptake, have to be considered. To address these issues, we propose an automated method for accurate delineation of tumors in hybrid PET/MRI scans. The method is mainly based on creating intermediate images. In fact, an automatic detection technique that determines a preliminary Interesting Uptake Region (IUR) is firstly performed. To overcome the leakage problem, a separation technique is adopted to generate the final IUR. Then, smart seeds are provided for the Graph Cut (GC) technique to obtain the tumor map. To create intermediate images that tend to reduce heterogeneity faced on the original images, the tumor map gradient is combined with the gradient image. Lastly, segmentation based on the GCsummax technique is applied to the generated images. The proposed method has been validated on PET phantoms as well as on real-world PET/MRI scans of prostate, liver and pancreatic tumors. Experimental comparison revealed the superiority of the proposed method over state-of-the-art methods. This confirms the crucial role of automatically creating intermediate images in addressing the problem of wrongly estimating arc weights for heterogeneous targets.

Ixodes inopinatus and Ixodes ricinus (Acari: Ixodidae) Are Sympatric Ticks in North Africa.

In the present study, we report the sympatric occurrence of Ixodes ricinus (Linnaeus, 1758) and Ixodes inopinatus (Estrada-Peña, Nava, and Petney, 2014) in Tunisia. In total, 173 adult Ixodes ticks were collected from four sites (El Jouza, Tamra, Aïn Soltan, and Jbel Zaghouan) between February and April 2017, a period corresponding to the peak of activity of I. ricinus in North Africa. The morphological characters corresponded to both species; thus, we generated a total of 28 16S rRNA sequences and compared them with previously published data in GenBank. The two species were sympatric in Tamra, Aïn Soltan, and El Jouza, whereas collections in Jbel Zaghouan only yielded I. inopinatus. These results indicate that the two taxa are widespread in the humid area of northern Tunisia. The one tick collected in Jbel Zaghouan suggests that the distribution of at least I. inopinatus might extend to the sub-humid area. More studies are needed to fully comprehend the systematic status of the two taxonomic entities using multiple molecular markers and morphological characters; integrating these two identification methods are a necessary step toward a better understanding of the ecology and epidemiology of tick-borne diseases in Tunisia.

De-escalation and discontinuation strategies in high-risk neutropenic patients: an interrupted time series analyses of antimicrobial consumption and impact on outcome.

Febrile neutropenia (FN) is the main reason for antibiotic prescription in hematology wards where, on the other hand, antibiotic stewardship (AS) is poorly explored. The objectives of the present study were to evaluate (1) the impact of an AS intervention on antibiotic consumption and (2) the applicability and acceptance rate of the intervention and its clinical impact. A persuasive AS intervention based on European Conference on Infection in Leukaemia (ECIL) guidelines for FN was implemented in a high-risk hematology ward in a tertiary referral public university hospital. This included the creation and diffusion of flow charts on de-escalation and discontinuation of antibiotics for FN, and the introduction in the team of a doctor dedicated to the implementation of flow charts and to antibiotic prescription revision. All consecutive patients receiving antibiotics during hospitalization were included. A segmented linear regression model was performed for the evaluation of antibiotic consumption, taking into account 1-year pre-intervention period and 6-month intervention period. Overall, 137 consecutive antibiotic prescriptions were re-evaluated, 100 prescriptions were for FN. A significant reduction of the level of carbapenem consumption was observed during the intervention period (level change (estimate coefficient ± standard error) = - 135.28 ± 59.49; p = 0.04). Applicability and acceptability of flow charts were high. No differences in terms of intensive care unit transfers, bacteremia incidence, and mortality were found. A persuasive AS intervention in hematology significantly reduced carbapenem consumption without affecting outcome and was well accepted. This should encourage further applications of ECIL guidelines for FN.

False-positive reduction in computer-aided mass detection using mammographic texture analysis and classification.

BACKGROUND AND OBJECTIVE: The aim of computer-aided-detection (CAD) systems for mammograms is to assist radiologists by marking region of interest (ROIs) depicting abnormalities. However, the confusing appearance of some normal tissues that visually look like masses results in a large proportion of marked ROIs with normal tissues. This paper copes with this problem and proposes a framework to reduce false positive masses detected by CAD. METHODS: To avoid the error induced by the segmentation step, we proposed a segmentation-free framework with particular attention to improve feature extraction and classification steps. We investigated for the first time in mammogram analysis, Hilbert's image representation, Kolmogorov-Smirnov distance and maximum subregion descriptors. Then, a feature selection step is performed to select the most discriminative features. Moreover, we considered several classifiers such as Random Forest, Support Vector Machine and Decision Tree to distinguish between normal tissues and masses. Our experiments were carried out on a large dataset of 10168 ROIs (8254 normal tissues and 1914 masses) constructed from the Digital Database for Screening Mammography (DDSM). To simulate practical scenario, our normal regions are false positives asserted by a CAD system from healthy cases. RESULTS: The combination of all the descriptors yields better results than each feature set used alone, and the difference is statistically significant. Besides, the feature selection steps yields a statistically significant increase in the accuracy values for the three classifiers. Finally, the random forest achieves the highest accuracy (81.09%), outperforming the SVM classifier (80.01%)) and decision tree (79.12%), but the difference is not statistically significant. CONCLUSIONS: The accuracy of discrimination between normal and abnormal ROIs in mammograms obtained with the proposed gray level texture features sets are encouraging and comparable to these obtained with multiresolution features. Combination of several features as well as feature selection steps improve the results. To improve false positives reduction in CAD systems for breast cancer diagnosis, these features could be combined with multiresolution features.

Hybrid PET/MRI co-segmentation based on joint fuzzy connectedness and graph cut.

BACKGROUND AND OBJECTIVE: Tumor segmentation from hybrid PET/MRI scans may be highly beneficial in radiotherapy treatment planning. Indeed, it gives for both modalities the suitable information that could make the delineation of tumors more accurate than using each one apart. We aim in this work to propose a co-segmentation method that deals with several challenges, notably the lack of one-to-one correspondence between tumors of the two modalities and the boundaries' smoothing. METHODS: The proposed method is designed to surpass these limits, we propose a segmentation method based on the GCsummax technique. The method takes the advantage of Iterative Relative Fuzzy Connectedness (IRFC) on seeds initialization, and the standard min-cut/max-flow technique for the boundary smoothing. Seed initialization was accurately performed thanks to high uptake regions on PET. Besides, a visibility weighting scheme was adapted to achieve the task of co-segmentation using the IRFC algorithm. Then, given the co-segmented regions, we introduce a morphological-based technique that provides object seeds to standard Graph Cut (GC) allowing it to avoid the shrinking problem. Finally, for each modality, the segmentation task is formulated as an energy minimization problem which is resolved by a min-cut/max-flow technique. RESULTS: The overlap ratio (denoted DSC) between our segmentation results and the ground-truth for PET images is 92.63  ±â€¯ 1.03, while the DSC for MRI images is 90.61  ±â€¯ 3.70. CONCLUSIONS: The proposed method was tested on different types of diseases and it outperformed the state-of-the-art methods. We show its superiority in terms of assymetric relation between PET and MRI and tumors heterogeneity.

An integrated overview of the midgut bacterial flora composition of Phlebotomus perniciosus, a vector of zoonotic visceral leishmaniasis in the Western Mediterranean Basin.

BACKGROUND: The Leishmania developmental life cycle within its sand fly vector occurs exclusively in the lumen of the insect's digestive tract in the presence of symbiotic bacteria. The composition of the gut microbiota and the factors that influence its composition are currently poorly understood. A set of factors, including the host and its environment, may influence this composition. It has been demonstrated that the insect gut microbiota influences the development of several human pathogens, such as Plasmodium falciparum. For sand flies and Leishmania, understanding the interactions between the parasite and the microbial environment of the vector midgut can provide new tools to control Leishmania transmission. METHODOLOGY/PRINCIPAL FINDINGS: The midguts of female Phlebotomus perniciosus from laboratory colonies or from the field were collected during the months of July, September and October 2011 and dissected. The midguts were analyzed by culture-dependent and culture-independent methods. A total of 441 and 115 cultivable isolates were assigned to 30 and 11 phylotypes from field-collected and colonized P. perniciosus, respectively. Analysis of monthly variations in microbiota composition shows a species diversity decline in October, which is to the end of the Leishmania infantum transmission period. In parallel, a compilation and a meta-analysis of all available data concerning the microbiota of two Psychodidae genera, namely Phlebotomus and Lutzomyia, was performed and compared to P. perniciosus, data obtained herein. This integrated analysis did not reveal any substantial divergences between Old and New world sand flies with regards to the midgut bacterial phyla and genera diversity. But clearly, most bacterial species (>76%) are sparsely distributed between Phlebotominae species. CONCLUSION/SIGNIFICANCE: Our results pinpoint the need for a more exhaustive understanding of the bacterial richness and abundance at the species level in Phlebotominae sand flies in order to capture the role of midgut bacteria during Leishmania development and transmission. The occurrence of Bacillus subtilis in P. perniciosus and at least two other sand fly species studied so far suggests that this bacterial species is a potential candidate for paratransgenic or biolological approaches for the control of sand fly populations in order to prevent Leishmania transmission.

Histiocytoid Sweet Syndrome Is More Frequently Associated With Myelodysplastic Syndromes Than the Classical Neutrophilic Variant: A Comparative Series of 62 Patients.

Histiocytoid Sweet syndrome (H-SS) is a histological variant of Sweet syndrome (SS) differing from classical neutrophilic SS (N-SS) by a dermal infiltrate mainly composed of lymphocytes and histiocytoid myeloperoxidase-positive cells. We aimed to report a large series of H-SS and compare the frequency and type of hematological malignancies associated to H-SS and N-SS. We included 62 patients with a coding histopathologic diagnosis of SS prospectively registered between 2005 and 2014 in the database of our Department of Pathology. Overall, 22 (35.5%) and 40 (64.5%) patients had a histological diagnosis of H-SS and N-SS, respectively. Median age, sex ratio, and cutaneous lesions were similar in the 2 groups. The frequency of extra-cutaneous manifestations was similar (50% vs 37.5%, P = 0.42). Recurrent forms were significantly more frequent in H-SS than in N-SS patients (21% vs 2.5%, P = 0.01). A hematological malignancy was diagnosed in 22 patients, 12 (55.5%) with H-SS and 10 (25%) with N-SS (P = 0.019). Hematological malignancy was of myeloid origin in 8/22 (36.3%) H-SS and 5/40 (12.5%) N-SS patients (P = 0.02), and of lymphoid origin without myeloid component in 4/22 (18.1%) H-SS and 4/40 (10%) N-SS patients (P = 0.35), respectively. One N-SS patient had a hematological malignancy of mixed (myeloid and lymphoid) phenotype. A myelodysplastic syndrome (MDS) was diagnosed in 7/22 (31.8%) H-SS and 1/40 (2.5%) N-SS patients (P < 0.001). Hematological disease was diagnosed before (in 8 H-SS and 3 N-SS patients) or at the time of the occurrence of the cutaneous lesions (in 1 H-SS and 7 N-SS patients). However, in 3 H-SS patients, all with MDS, cutaneous lesions preceded the hematological disease by ≤6 months. In conclusion, H-SS was associated with MDS in one third of patients but also with lymphoid malignancies, and cutaneous lesions could precede the hematological diagnosis in patients with MDS. A complete hematological assessment is mandatory at diagnosis, and monitoring blood cell counts should be recommended for at least 6 months after the diagnosis of H-SS.

Changes of Sand Fly Populations and Leishmania infantum Infection Rates in an Irrigated Village Located in Arid Central Tunisia.

The current spread of zoonotic visceral leishmaniasis (ZVL) throughout arid areas of Central Tunisia is a major public health concern. The main objective of this study is to investigate whether the development of irrigation in arid bio-geographical areas in Central Tunisia have led to the establishment of a stable cycle involving sand flies of the subgenus Larroussius and Leishmania infantum, and subsequently to the emergence of ZVL. Sand flies were collected from the village of Saddaguia, a highly irrigated zone located within an arid bio-geographical area of Central Tunisia by using modified Centers for Diseases Control (CDC) light traps. Morphological keys were used to identify sand flies. Collected sand flies were pooled with up to 30 specimens per pool according to date and tested by nested Polymerase Chain Reaction (PCR) DNA sequencing from positive pools was used to identify Leishmania spp. A total of 4915 sand flies (2422 females and 2493 males) were collected from Saddaguia in September and in October 2014. Morphological identification confirmed sand flies of the subgenus Larroussius to be predominant. PCR analysis followed by DNA sequencing indicated that 15 pools were infected with L. infantum yielding an overall infection rate of 0.6%. The majority of the infected pools were of sand fly species belonging to subgenus Larroussius. Intense irrigation applied to the arid bio-geographical areas in Central Tunisia is at the origin of the development of an environment capable of sustaining important populations of sand flies of the subgenus Larroussius. This has led to the establishment of stable transmission cycles of L. infantum and subsequently to the emergence of ZVL.

Donor Immunization Against Human Leukocyte Class II Antigens is a Risk Factor for Graft-versus-Host Disease.

The sensitization to HLA antigens is caused mainly by pregnancy and transfusions; however, anti-HLA antibodies also may be detected in nulliparous females and nontransfused males, and thus specifically in hematopoietic stem cell transplantation (HSCT) donors. In such cases, the impact on HSCT outcome is known only for platelet transfusion refractoriness. This study addresses the impact on graft-versus-host disease (GVHD) of anti-HLA antibodies detected in voluntary unrelated donors. Among 100 donor/recipient (D/R) pairs, 33 and 82 showed at least 1 HLA class I and class II mismatch, respectively. Because class II mismatches were more frequent, we focused our detection on anti-class II antibodies, using the Luminex assay. Among 82 HLA class II mismatched D/R pairs, 26 donors (32%) had at least 1 anti-HLA class II antibody detected in peripheral blood. Recipients of a graft from an anti-class II immunized donor had a higher cumulative incidence for a first episode of either acute or chronic GVHD (2- year cumulative incidence, 88% versus 67%; P = .03), which was confirmed in multivariate analysis (hazard ratio, 1.7; P = .04). In particular, according to the National Institutes of Health classification scheme, the cumulative incidence of chronic GVHD was higher in recipients of immunized donors (multivariate hazard ratio, 2.5; P = .02). Identifying specificities of anti-class II antibodies revealed that 13 of 26 alloimmunized donors had recipient-specific antibodies, directed mainly against mismatched HLA-DPB1 alleles. Donor-derived anti-HLA antibodies could be detected in recipients up to at least 6 months post-HSCT, supporting their association with chronic GVHD. Donor immunization against foreign HLA antigens is a new parameter to predict the occurrence of GVHD after HSCT from HLA-mismatched unrelated donors.

Breast cancer diagnosis in digitized mammograms using curvelet moments.

BACKGROUND: Feature extraction is a key issue in designing a computer aided diagnosis system. Recent researches on breast cancer diagnosis have reported the effectiveness of multiscale transforms (wavelets and curvelets) for mammogram analysis and have shown the superiority of curvelet transform. However, the curse of dimensionality problem arises when using the curvelet coefficients and therefore a reduction method is required to extract a reduced set of discriminative features. METHODS: This paper deals with this problem and proposes a feature extraction method based on curvelet transform and moment theory for mammogram description. First, we performed discrete curvelet transform and we computed the four first-order moments from curvelet coefficients distribution. Hence, two feature sets can be obtained: moments from each band and moments from each level. In this work, both sets are studied. Then, the t-test ranking technique was applied to select the best features from each set. Finally, a k-nearest neighbor classifier was used to distinguish between normal and abnormal breast tissues and to classify tumors as malignant or benign. Experiments were performed on 252 mammograms from the Mammographic Image Analysis Society (mini-MIAS) database using the leave-one-out cross validation as well as on 11553 mammograms from the Digital Database for Screening Mammography (DDSM) database using 2×5-fold cross validation. RESULTS: Experimental results prove the effectiveness and the superiority of curvelet moments for mammogram analysis. Indeed, results on the mini-MIAS database show that curvelet moments yield an accuracy of 91.27% (resp. 81.35 %) with 10 (resp. 8) features for abnormality (resp. malignancy) detection. In addition, empirical comparisons of the proposed method against state-of-the-art curvelet-based methods on the DDSM database show that the suggested method does not only lead to a more reduced feature set, but it also statistically outperforms all the compared methods in terms of accuracy. CONCLUSIONS: In summary, curvelet moments are an efficient and effective way to extract a reduced set of discriminative features for breast cancer diagnosis.

Irrigation in the arid regions of Tunisia impacts the abundance and apparent density of sand fly vectors of Leishmania infantum.

The distribution expansion of important human visceral leishmaniasis (HVL) and sporadic cutaneous leishmaniasis (SCL) vector species, Phlebotomus perfiliewi and P. perniciosus, throughout central Tunisia is a major public health concern. This study was designed to investigate if the expansion of irrigation influences the abundance of sand fly species potentially involved in the transmission of HVL and SCL located in arid bioclimatic regions. Geographic and remote sensing approaches were used to predict the density of visceral leishmaniasis vectors in Tunisia. Entomological investigations were performed in the governorate of Sidi Bouzid, located in the arid bioclimatic region of Tunisia. In 2012, sand flies were collected by CDC light traps located at nine irrigated and nine non-irrigated sites to determine species abundance. Eight species in two genera were collected. Among sand flies of the subgenus Larroussius, P. perfiliewi was the only species collected significantly more in irrigated areas. Trap data were then used to develop Poisson regression models to map the apparent density of important sand fly species as a function of different environmental covariates including climate and vegetation density. The density of P. perfiliewi is predicted to be moderately high in the arid regions. These results highlight that the abundance of P. perfiliewi is associated with the development of irrigated areas and suggests that the expansion of this species will continue to more arid areas of the country as irrigation sites continue to be developed in the region. The continued increase in irrigated areas in the Middle East and North Africa region deserves attention, as it is associated with the spread of L. infantum vector P. perfiliewi. Integrated vector management strategies targeting irrigation structures to reduce sand fly vector populations should be evaluated in light of these findings.