169,872 research outputs found
Variation in auxiliary selection, syntactic change, and the internal classification of Campidanese Sardinian
No full textIn this paper, we analyse some aspects of syntactic variation in Campidanese, comparing the urban varieties of Cagliari and Oristano with some selected rural dialects. The main focus of the paper is on perfective auxiliary selection. Assuming Perlmutter’s Unaccusative Hypothesis, we shall show a) that it is possible to formulate rules accounting for the distribution of perfective auxiliaries in the different dialects; b) that these rules also account for the verb occurring in existential constructions (although with some exceptions); and c) that the different auxiliation options documented in these varieties can be ordered along an implicational scale. Building upon previous similar comparative work on Romance perfective auxiliation, we shall also show that present-day Oristanese and some of the rural varieties in our sample display a triple, rather than a binary, auxiliation choice, and that this is to be understood as a transitional stage between the more conservative auxiliation rule still attested by the rest of rural Campidanese, and the more innovatory system of urban Cagliaritano. Not surprisingly, given what is independently known about the linguistic history of Sardinia, the syntax of auxiliation in conservative rural Campidanese coincides with that of Logudorese. Finally, we shall discuss the implications of our morphosyntactic study for the internal subclassification of Campidanese
Detection of red and white blood cells from microscopic blood images using a region proposal approach
No full textIn this paper, we propose a novel and efficient method for detecting and quantifying red and white blood cells from microscopic blood images. Laboratory tests that use a cell counter or a flow cytometer can perform a complete blood count (CBC) rapidly. Nonetheless, a manual blood smear inspection is still needed, both to have a human check on the counter results and to monitor patients under therapy. Moreover, it allows for describing the cells' appearance as well as any abnormalities. However, manual analysis is lengthy and repetitive, and its result can be subjective and error-prone. In contrast, by using image processing techniques, the proposed system is entirely automated. The main effort is devoted to both achieving high accuracy and finding a way to overcome the typical differences in the condition of blood smear images that computer-aided methods encounter. It is based on the Edge Boxes method, which is considered a state-of-art region proposal approach. By incorporating knowledge-based constraints into the detection process using Edge Boxes, we can find cell proposals rapidly and efficiently. We tested the proposed approach on the Acute Lymphoblastic Leukaemia Image Database (ALL-IDB), a well-known public dataset proposed for leukaemia detection, and the Malaria Parasite Image Database (MP-IDB), a recently proposed dataset for malaria detection. Experimental results were excellent in both cases, outperforming the state-of-the-art on ALL-IDB and creating a strong baseline on MP-IDB, demonstrating that the proposed method can work well on different datasets and different types of images
On The Potential of Image Moments for Medical Diagnosis
No full textMedical imaging is widely used for diagnosis and postoperative or post-therapy monitoring. The ever-increasing number of images produced has encouraged the introduction of automated methods to assist doctors or pathologists. In recent years, especially after the advent of convolutional neural networks, many researchers have focused on this approach, considering it to be the only method for diagnosis since it can perform a direct classification of images. However, many diagnostic systems still rely on handcrafted features to improve interpretability and limit resource consumption. In this work, we focused our efforts on orthogonal moments, first by providing an overview and taxonomy of their macrocategories and then by analysing their classification performance on very different medical tasks represented by four public benchmark data sets. The results confirmed that convolutional neural networks achieved excellent performance on all tasks. Despite being composed of much fewer features than those extracted by the networks, orthogonal moments proved to be competitive with them, showing comparable and, in some cases, better performance. In addition, Cartesian and harmonic categories provided a very low standard deviation, proving their robustness in medical diagnostic tasks. We strongly believe that the integration of the studied orthogonal moments can lead to more robust and reliable diagnostic systems, considering the performance obtained and the low variation of the results. Finally, since they have been shown to be effective on both magnetic resonance and computed tomography images, they can be easily extended to other imaging techniques
A region proposal approach for cells detection and counting from microscopic blood images
No full textIn this paper, we propose a novel and efficient method for detecting and quantifying red cells from a microscopic blood image. The proposed system is based on a region proposal approach, namely the Edge Boxes, considered as the state-of-art region proposal method. Incorporating knowledge-based constraints into the detection process by Edge Boxes we can find cells proposals rapidly and efficiently. Experimental results on a well-known public dataset show both improved accuracy and increased over the state-of-art
A Feature Learning Framework for Histology Images Classification
No full textHistology is the study and analysis of the microscopic structure of cells and tissues of organisms, essential for the evaluation of grading and prognosis of disease. Nowadays this analysis is still performed manually, involving numerous drawbacks, in particular the results accuracy heavily depends on operator skills. In addition, this process is really slow and time-consuming. Thus a computer-assisted disease system could be very useful to speed up the process and to reduce subjectivity. In particular, developing general applications not dependent on specific histology data sets is still a challenging open problem. In this chapter a general color texture-based histology image classification framework is proposed. The features are based on a generalization of some existent gray-scale approaches to color images and used to train a support vector machine model. Also, we investigate different color spaces to individuate a general representation able to solve the classification problem efficiently without any dependence on specific data sets or specific clinical fields. The system has been tested on very different public biological image data sets, representative of different medical problems and so different classification problems, obtaining an average accuracy always higher than 96%
- …
