Search

The non-invasive measurement of hemoglobin oxygen saturation (SO2) in retinal vessels is based on spectrophotometry and the absorption spectral characteristics of the tissue. The dual-wavelength retinal images are simultaneously captured via retinal oximetry. SO2 is calculated by processing a series of images and by calculating the optic density ratio of two images. However, existing SO2 research is focused on the thick vessels in the high-clarity region of retinal images. However, the thin vessels in the low-clarity region could provide significant information for the detection and diagnosis of neovascular diseases. To this end, we proposed a novel hybrid vessel segmentation algorithm. Firstly, a median filter was employed for image denoising. Secondly, high- and low-clarity region segmentation was carried out based on a clarity histogram. The vessels in the high-clarity areas were segmented after implementing a Gaussian filter, a matched filter, and morphological segmentation. Additionally, the vessels in the low-clarity areas were segmented using a guided filter, matched filtering, and dynamic threshold segmentation. Finally, the results were obtained through image merger and morphological operations. The experimental results and analysis show that the proposed method can effectively segment thick and thin vessels and can extend the measuring range of dual-wavelength retinal oximetry.

Τhis article contributes to the ongoing research on the importance of the strategy of morphological segmentation to vocabulary growth in foreign language learning. A total of 45 students of the department of Italian Language and Literature at Aristotle University of Thessaloniki (Greece) were to segment 21 Italian words—among which there were 6 pseudo-words—and write their meaning with the use of an e-questionnaire. In turn, 10 out of 45 students participated in a focus group discussion. Results reveal no correlation between morphological segmentation and understanding of the meaning of words, except in the case of pseudo-words that were completely unknown to the participants. During the focus group, students attempted to recognize the productive and transparent suffixes of the words and discover their contribution to the building and the meaning of them. Other languages, such as English—L2/first foreign language for the majority of the interviewed students—assisted multilingual students in retrieving the meaning of the words implementing translanguaging practices. The students’ responses show that they managed to segment the words correctly at a rate of 49.3%, while they understand their meaning due to their frequent use at a rate of 57.8%, without having been taught the morphology of L2.

Low-resource languages (LRL) with complex morphology are known to be more difficult to translate in an automatic way. Some LRLs are particularly more difficult to translate than others due to the lack of research interest or collaboration. In this article, we experiment with a specific LRL, Quechua, that is spoken by millions of people in South America yet has not undertaken a neural approach for translation until now. We improve the latest published results with baseline BLEU scores using the state-of-the-art recurrent neural network approaches for translation. Additionally, we experiment with several morphological segmentation techniques and introduce a new one in order to decompose the language’s suffix-based morphemes. We extend our work to other high-resource languages (HRL) like Finnish and Spanish to show that Quechua, for qualitative purposes, can be considered compatible with and translatable into other major European languages with measurements comparable to the state-of-the-art HRLs at this time. We finalize our work by making our best two Quechua–Spanish translation engines available on-line.

This work describes the formalization of a word structure grammar that represents the complex morphological and morphosyntactic information embedded within the word forms of an agglutinative language (Basque), giving a comprehensive linguistic description of the main morphological phenomena, such as affixation, derivation, and composition, and also taking into account the modeling of both standard and non-standard words. We have identified the relevant issues to be addressed in the representation of such a grammar.We also present the development of Morfeus+, a tool for the analysis of unrestricted texts, testing its applicability and showing that its coverage is wide and robust, allowing the efficient processing of big volumes of data.This paper describes a mature system that has required several person/years and that tries to integrate a rigorous linguistic specification together with more practical implementation matters, such as the appropriate treatment of unknown words in unrestricted texts.

We present a non-invasive (albeit contact) method based on Optical Coherence Elastography (OCE) enabling the in vivo segmentation of morphological tissue constituents, in particular, monitoring of morphological alterations during both tumor development and its response to therapies. The method uses compressional OCE to reconstruct tissue stiffness map as the first step. Then the OCE-image is divided into regions, for which the Young’s modulus (stiffness) falls in specific ranges corresponding to the morphological constituents to be discriminated. These stiffness ranges (characteristic "stiffness spectra") are initially determined by careful comparison of the "gold-standard" histological data and the OCE-based stiffness map for the corresponding tissue regions. After such pre-calibration, the results of morphological segmentation of OCE-images demonstrate a striking similarity with the histological results in terms of percentage of the segmented zones. To validate the sensitivity of the OCE-method and demonstrate its high correlation with conventional histological segmentation we present results obtained in vivo on a murine model of breast cancer in comparative experimental study of the efficacy of two antitumor chemotherapeutic drugs with different mechanisms of action. The new technique allowed in vivo monitoring and quantitative segmentation of (1) viable, (2) dystrophic, (3) necrotic tumor cells and (4) edema zones very similar to morphological segmentation of histological images. Numerous applications in other experimental/clinical areas requiring rapid, nearly real-time, quantitative assessment of tissue structure can be foreseen.

Los relatos o historias de vida son fuentes de interés histórico, etnográfico y lingüístico; son testi- monios etno-culturales y sociales con un fuerte contenido humano. La historia de vida que aquí se presenta pertenece a don Fermín Flores Álvarez. Además de algunos acontecimientos personales e individuales, don Fermín narra varios sucesos colectivos que marcaron la organización social y el territorio de la comunidad yaqui. Asimismo, menciona varios topónimos o nombres de lugares yaquis que rara vez aparecen en los ma- pas. La presentación del texto incluye la transcripción en alfabeto práctico aprobado por la comunidad, con segmentación y glosas morfológicas, y traducciones al inglés y al español.

Türkçe, morfem adı verilen birimlerin art arda eklenmesiyle sözcüklerinoluşturulduğu sondan eklemeli bir dildir. Sözcüklerin farklı parçalarınbirleştirilmesiyle oluşturulması makine tercümesi, duygu analizi ve bilgiçıkarımı gibi birçok doğal dil işleme uygulamasında seyreklik problemine yolaçmaktadır çünkü sözcüğün her farklı formu farklı bir sözcük gibialgılanmaktadır. Bu makalede, sözcüklerin yapım ve çekim eklerindenarındırılarak köklerinin otomatik olarak bulunabilmesi için bir yöntem öneriyoruz.Kullandığımız yöntem tekrarlayan sinir ağları kullanarak oluşturulankodlayıcı-kod çözücü yaklaşımına dayanmaktadır. Verilen herhangi bir sözcük,oluşturduğumuz sinir ağı yapısı ile öncelikle kodlanmakta, ardından koduçözülerek köküne ulaşılabilmektedir. Bu yöntem şimdiye kadar etiketleme veyamakine tercümesi gibi problemlerde kullanılmıştır. Diğer Türkçe kök bulma modelleriylekarşılaştırıldığında sonuçların oldukça iyi olduğu gözlenmiştir. Diğermodellerde olduğu gibi, herhangi bir kural kümesi elle tanımlanmadan, sadece sözcükve kök ikililerinden oluşan bir eğitim veri kümesi kullanılarak kök bulmaişlemi önerdiğimiz bu model ile gerçekleştirilebilmektedir., Turkish is an agglutinative language that buildswords by concatenating the units called morphemes. Building words byconcatenating various units together leads to sparsity problem in many naturallanguage processing tasks such as machine translation, sentiment analysis, andinformation extraction because each different form of the same word isconsidered as a different word token. In this paper, we propose a method that can find the stems ofwords automatically by filtering out any derivational or inflectional suffixesattached to words. The proposed method is based on an encoder-decoder modelbuilt by recurrent neural networks. Any given word is first encoded by theneural network and then its stem is extracted by decoding it. This method hasbeen used in problems such as tagging or machine translation so far. We obtain compatitiveresults compared to other Turkish stemmers. Moreover, unlike the other models, stemmingcould be performed without defining a rule set manually, and by just using atrain set that involves word and stem pairs.

Background: To reduce the intensity of the work of doctors, pre-classification work needs to be issued. In this paper, a novel and related liver microscopic image classification analysis method is proposed. Objective: For quantitative analysis, segmentation is carried out to extract the quantitative information of special organisms in the image for further diagnosis, lesion localization, learning and treating anatomical abnormalities and computer-guided surgery. Methods: In the current work, entropy-based features of microscopic fibrosis mice’ liver images were analyzed using fuzzy c-cluster, k-means and watershed algorithms based on distance transformations and gradient. A morphological segmentation based on a local threshold was deployed to determine the fibrosis areas of images. Results: The segmented target region using the proposed method achieved high effective microscopy fibrosis images segmenting of mice liver in terms of the running time, dice ratio and precision. The image classification experiments were conducted using Gray Level Co-occurrence Matrix (GLCM). The best classification model derived from the established characteristics was GLCM which performed the highest accuracy of classification using a developed Support Vector Machine (SVM). The training model using 11 features was found to be accurate when only trained by 8 GLCMs. Conclusion: The research illustrated that the proposed method is a new feasible research approach for microscopy mice liver image segmentation and classification using intelligent image analysis techniques. It is also reported that the average computational time of the proposed approach was only 2.335 seconds, which outperformed other segmentation algorithms with 0.8125 dice ratio and 0.5253 precision.

IoT along with Image segmentation is applied in a variety of applications separately. This character of application in agriculture field is still existing and attained positive approaches in success, though the combinations of these tools are unreal. This paper illustrates a methodology for combining IoT along with image segmentation for resolving the ecological factor as well as man-made factor (pesticides/fertilizers). Here a variety of sensing devices which is used for measuring the vital environmental factors and growth of plant is captured and segmented using morphological segmentation to the leaf lattice which is evaluated with the help of histogram analysis.

This report presents an overview of recent progress in the development of novel OCE-based technologies enabling non-invasive morphological segmentation of tumor tissues during their natural development and response to therapies. The approach is based on preliminary quantitative assessment of characteristic elasticity ranges corresponding to the segmented morphological constituents (“quasistatic elasto-spectroscopy”). It has been found that such constituents are characterized by fairly well separated ranges of the Young’s modulus, which makes it possible to automatically segment up to 4-6 such zones in OCE-based elasticity maps. High consistency of such OCE-based procedure with conventional morphological segmentation of histological slides in terms of percentages of the segmented-zone areas has been demonstrated. Unlike invasive, time-consuming and laborious histological studies the developed OCE-based segmentation is non-invasive and can be performed even in vivo. High accuracy and sensitivity of the OCE-based-segmentation was demonstrated in vivo for two different types of model tumors (4T1 and Ct26) treated by PDT and chemotherapies. The OCE-based analysis can readily be combined with such OCT-based extensions as texture analysis and OCT-based angiography. The latter opens the possibility to combine morphological assessment with functional characterization of tumor response to therapies. OCE-based characterization of mechanical heterogeneity and elasticity spectra of tumors has also proven to be efficient for express assessment of patients’ breast-cancer subtypes. Overall, the developed OCE-based assessment in many applications suggests a rapid and in vivo feasible alternative to conventional histology and can be efficiently used in a wide range of biomedical problems.

Most of the recent Natural Language Processing(NLP) studies are based on the Pretrain-Finetuning Approach (PFA), but in small and medium-sized enterprises or companies with insufficient hardware there are many limitations to servicing NLP application software using such technology due to slow speed and insufficient memory. The latest PFA technologies require large amounts of data, especially for low-resource languages, making them much more difficult to work with. We propose a new tokenization method, ONE-Piece, to address this limitation that combines the morphology-considered subword tokenization method and the vocabulary method used after probing for an existing method that has not been carefully considered before. Our proposed method can also be used without modifying the model structure. We experiment by applying ONE-Piece to Korean, a morphologically-rich and low-resource language. We derive an optimal subword tokenization result for Korean-English machine translation by conducting a case study that combines the subword tokenization method, morphological segmentation, and vocabulary method. Through comparative experiments with all the tokenization methods currently used in NLP research, ONE-Piece achieves performance comparable to the current Korean-English machine translation state-of-the-art model.

This study takes up the task of low-resource morphological segmentation for Seneca, a critically endangered and morphologically complex Native American language primarily spoken in what is now New York State and Ontario. The labeled data in our experiments comes from two sources: one digitized from a publicly available grammar book and the other collected from informal sources. We treat these two sources as distinct domains and investigate different evaluation designs for model selection. The first design abides by standard practices and evaluate models with the in-domain development set, while the second one carries out evaluation using a development domain, or the out-of-domain development set. Across a series of monolingual and crosslinguistic training settings, our results demonstrate the utility of neural encoder-decoder architecture when coupled with multi-task learning.

Low-resource polysynthetic languages pose many challenges in NLP tasks, such as morphological analysis and Machine Translation, due to available resources and tools, and the morphologically complex languages. This research focuses on the morphological segmentation while adapting an unsupervised approach based on Adaptor Grammars in low-resource setting. Experiments and evaluations on Inuinnaqtun, one of Inuit language family in Northern Canada, considered a language that will be extinct in less than two generations, have shown promising results.

PhD (Computer and Electronic Engineering), North-West University, Potchefstroom Campus In this work the use of unsupervised machine learning in the morphological segmentation of Nguni languages, evaluated on isiXhosa, is advanced. The work researches, extends, implements and evaluates unsupervised machine learning techniques in the morphological segmentation of Nguni language, specifically isiXhosa. IsiXhosa, one of the eleven South African official languages, is a Nguni language with 9.7 million mother-tongue speakers (17% of the South African population). The language is an agglutinating and synthetic language characterised by highly inflected words. Its nouns are characterised by a class system based on their prefixes. Verbs are characterised by a concatenation of numerous prefixes and suffixes - and their concordial agreement with the subject noun or object noun. Two segmenters were developed using state of the art techniques in morphological segmentation: the IsiXhosa Branching Entropy Segmenter (XBES), using branching entropy; and the IsiXhosa Heuristic Maximum Likelihood Segmenter (XHMLS), using probabilistic language models. The XBES branching entropy segmenter matched the 77.2 ± 0.10% accuracy of the benchmark (Morfessor-Baseline) with an accuracy of 77.4 ± 0.32% and outperforms the benchmark on its F1 Score of 48.9 ± 0.75% with a score of 58.0 ± 0.10%. These accuracy results were achieved with a z-score normalised variation of branching entropy (NZVBE) mode trained on 11-grams from a 1.5 million word corpus. The F1 Score was achieved using the unnormalised variation of branching entropy (VBE) technique trained with 9-grams from a 1.5 million word corpus. The study established that the character level n-gram length that encapsulates the predictability of isiXhosa words to be ten (10), which corresponds to using 9-grams. The XHMLS maximum likelihood segmenter has an accuracy of 75.2 ± 0.18%, which did not meet the accuracy of the benchmark but outperformed both XBES and Morfessor-Baseline on the F1 Score with a score of 59.4 ± 0.20%. The best performing mode of XHMLS was the independent affixes (XHMLS-IA) language model confirming that morphemic dependencies in isiXhosa are stronger within the affixes and weaker among the affix and that the roots in the language permeate many of the word categories. Doctoral

Old Turkic language is the basis of all modern Turkic languages. Its study is very important for Turkic peoples who possess modern Turkic languages. This is important both from a historical point of view and for the study of modern issues of neural machine translation, issues of the linguistic distance of modern Turkic languages from their progenitor. This paper proposes the development of a computational model of the morphology of Old Turkic language based on the CSE (Complete Set of Endings) – model of morphology and a study on this basis of the issue of morphological segmentation of the texts of Old Turkic language, which will subsequently be used for neural machine translation of Old Turkic language into modern Turkic languages. Since most of the modern Turkic languages, except for the Turkish language, belong to low-resource languages, the issues of developing computational models of morphology, developing models, algorithms and software for processing Turkic languages are relevant.

Computer-Assisted Anatomical Dissection (CAAD) is a new method of 3D reconstruction of anatomical structures from histological or anatomical slices. It uses staining and immunomarking of the tissues for a more precise identification, in particular for the nerves and the vessels, leading to an easy morphological segmentation. Starting from a digitalized series of transverse histological sections, we perform a staining by immune-markers (protein S100, VAChT and D2-40), then alignment of the slices and finally a manual segmentation of the main anatomical structures by using the Winsurf® software version 3.5. This chapter shows the results of CAAD in embryology and for the pelvic nerves in adults. Its main interest is in the field of pelvic surgery for cancer, to improve the knowledge of the pelvic nervous anatomy and preserve the inferior hypogastric plexus. It is also an original method to provide 3D reconstruction of the human embryo, and so bring us an improved understanding of embryogenesis.

The problem of word segmentation of source texts in the training of neural network models is one of the actual problems of natural language processing. A new model of the morphology of the Kyrgyz language based on a complete set of endings (CSE) is developed. Based on the developed CSE-model of the morphology of the Kyrgyz language, a computational data model, algorithm and a program for morphological segmentation are developed. Experiments on morphological segmentation of Kyrgyz language texts showed 82% accuracy of text segmentation by the proposed method.

We present a novel method, which by analogy with the term "mass-spectroscopy" can be called "quasistatic elasto-spectoscopy" based on quantitative compressional Optical Coherence Elastogrphy (C-OCE). The method relies on initial determining of characteristic stiffness ranges for various morphological components of the tissue by comparing the OCE-based stiffness maps and histology. Such pre-calibration allows one to perform morphological segmentation of OCE-images demonstrating excellent correlation with segmentation of conventional histological images, but can be performed using freshly-extracted samples and even in vivo.

Summary While the analysis of mitochondrial morphology has emerged as a key tool in the study of mitochondrial function, efficient quantification of mitochondrial microscopy images presents a challenging task and bottleneck for statistically robust conclusions. Here, we present Mitochondrial Segmentation Network (MitoSegNet), a pretrained deep learning segmentation model that enables researchers to easily exploit the power of deep learning for the quantification of mitochondrial morphology. We tested the performance of MitoSegNet against three feature-based segmentation algorithms and the machine-learning segmentation tool Ilastik. MitoSegNet outperformed all other methods in both pixelwise and morphological segmentation accuracy. We successfully applied MitoSegNet to unseen fluorescence microscopy images of mitoGFP expressing mitochondria in wild-type and catp-6ATP13A2 mutant C. elegans adults. Additionally, MitoSegNet was capable of accurately segmenting mitochondria in HeLa cells treated with fragmentation inducing reagents. We provide MitoSegNet in a toolbox for Windows and Linux operating systems that combines segmentation with morphological analysis., Graphical Abstract, Highlights • MitoSegNet is a deep learning model for quantifying mitochondrial morphology • MitoSegNet outperforms other mitochondria segmentation methods • MitoSegNet was used to identify previously unreported morphological differences • MitoSegNet successfully segments mitochondria in HeLa cells, Cell Biology; Bioinformatics; Automation in Bioinformatics; Artificial Intelligence

Scaffolds are thought to be a key element needed for successful cartilage repair treatments, and this prospective extension study aimed to evaluate long-term structural and clinical outcomes following osteochondral defect treatment with a cell-free biphasic scaffold. Structural outcomes were assessed using quantitative 3-D magnetic resonance imaging (MRI) and morphological segmentation to determine the percentage of defect filling and repair cartilage T2 relaxation times, and clinical outcomes were determined with the modified Cincinnati Rating System, and the Knee Injury and Osteoarthritis Outcome Score (KOOS). Seventeen subjects with osteochondral defects in the knee were treated with ChondroMimetic scaffolds, from which 15 returned for long-term evaluation at a mean follow-up of 7.9 &plusmn, 0.3 years. The defects treated were trochlear donor sites for mosaicplasty in 13 subjects, and medial femoral condyle defects in 2 subjects. MRI analysis of scaffold-treated defects found a mean total defect filling of 95.2 &plusmn, 3.6%, and a tissue mean T2 relaxation time of 52.5 &plusmn, 4.8 ms, which was identical to the T2 of ipsilateral control cartilage (52.3 &plusmn, 9.2 ms). The overall modified Cincinnati Rating System score was statistically significant from baseline (p = 0.0065), and KOOS subscales were equivalent to other cartilage repair techniques. ChondroMimetic treatment resulted in a consistently high degree of osteochondral defect filling with durable, cartilage-like repair tissue at 7.9 years, potentially associated with clinical improvement.

The Coronavirus disease (COVID-19) caused by a novel coronavirus, SARS-CoV-2, has been declared as a global pandemic. Due to its infection rate and severity, it has emerged as one of the major global threats of the current generation. To support the current combat against the disease, this research aims to propose a Machine Learning based pipeline to detect the COVID-19 infection using the lung Computed Tomography scan images (CTI). This implemented pipeline consists of a number of sub-procedures ranging from segmenting the COVID-19 infection to classifying the segmented regions. The initial part of the pipeline implements the segmentation of the COVID-19 affected CTI using Social-Group-Optimization and Kapur’s Entropy thresholding, followed by k-means clustering and morphology-based segmentation. The next part of the pipeline implements feature extraction, selection and fusion to classify the infection. PCA based serial fusion technique is used in fusing the features and the fused feature vector is then employed to train, test and validate four different classifiers namely Random Forest, k-Nearest Neighbors (KNN), Support Vector Machine with Radial Basis Function, and Decision Tree. Experimental results using benchmark datasets show a high accuracy (> 91%) for the morphology-based segmentation task and for the classification task the KNN offers the highest accuracy among the compared classifiers (> 87%). However, this should be noted that this method still awaits clinical validation, and therefore should not be used to clinically diagnose the ongoing COVID-19 infection.

El análisis del texto audam (tepehuano del suroeste) que se presenta a continuación forma parte de los recientes esfuerzos de documentación que se han llevado a cabo en la comunidad de ‘San Francisco de Lajas’ Aicham. Hasta el 2016, no se contaba con registros sistemáticos de la variante audam; por lo que gra- cias al financiamiento otorgado por Endangered Language Fund (2016) y el Proyecto UNAM-DGAPA-PAPIIT (IA401417, 2017), se ha logrado generar actualmente una base de datos que asciende a 30 horas de material, del cual se seleccionó la historia del tlacuache. Esta historia incluye la narración oral en lengua audam, transcripción en el alfabeto práctico, la segmentación morfológica, el glosado y la traducción al español. Además, expone una aproximación del fenómeno de unión de cláusula: i) identificando los marcadores, ii) sus sentidos, y iii) algunas diferencias que destacan en comparación con la gramática del o’dam (tepehuano del sureste).

Este artículo presenta un fragmento perteneciente a la cosmogonía huichol (wixárika), que cuenta el origen de las mujeres. La narración forma parte de una de las historias sobre el nacimiento de los hui- choles y su relación con un diluvio ocasionado por Nakawé, deidad ancestral. La presentación del texto in- cluye la transcripción en el alfabeto del huichol, segmentación morfológica, glosado y traducción al español. Además se proporciona información etnográfica y lingüística sobre la lengua. El relato muestra distintos aspectos de la cosmogonía, sistema de organización del núcleo familiar de los huicholes y su relación con la comunidad de Tateikie (San Andrés Cohamiata, Jalisco). Su contexto, asimismo, refleja la inclusión de elementos cristianos en la simbología de la tradición huichol. El fragmento, finalmente, permite analizar la estructura gramatical del huichol, la cual cuenta con pocos estudios lingüísticos.

Morphologically rich and complex languages such as Arabic, pose a major challenge to neural machine translation (NMT) due to the large number of rare words and the inability of NMT to translate them. Unknown word (UNK) symbols are used to represent out-of-vocabulary words because NMT typically operates with a fixed vocabulary size. These rare words can be effectively encoded as sequences of subword units by using algorithms, such as byte pair encoding (BPE), to tackle the UNK problem. However, for languages with highly inflected and morphological variations, such as Arabic, the aforementioned method has its own limitations that make it not effective enough for translation quality. To alleviate the UNK problem and address the inconvenient behavior of BPE when translating the Arabic language, we propose to utilize a romanization system that converts Arabic scripts to subword units. We investigate the effect of our approach on NMT performance under various segmentation scenarios and compare the results with systems trained on original Arabic form. In addition, we integrate Romanized Arabic as an input factor for Arabic-sourced NMT compared with well-known factors, namely, lemma, part-of-speech tags, and morph features. Extensive experiments on Arabic-Chinese translation demonstrate that the proposed approaches can effectively tackle the UNK problem and significantly improve the translation quality for Arabic-sourced translation. Additional experiments in this study focus on developing the NMT system on Chinese-Arabic translation. Before implementing our experiments, we first propose standard criteria for the data filtering of a parallel corpus, which helps in filtering out its noise.

We report a new application of compressional optical coherence elastography (OCE) to discriminate morphological constituents of biological tissues by analyzing OCE images obtained either in vivo or for freshly excised samples. The new technique enables quantitative morphological segmentation of OCE images with delineation of several (~4-6) tissue constituents. As the first step, the method uses compressional OCE to reconstruct stiffness maps for a pre-chosen standardized pressure over the entire area of the OCE image. Then specific stiffness ranges (characteristic "stiffness spectra") are initially determined by careful comparison of the OCE-based stiffness maps with the results of segmentation of "gold-standard" histological slices. After such pre-calibration, the stiffness maps can be automatically segmented into regions, for which the Young’s modulus (stiffness) falls in specific ranges corresponding to the morphological constituents to be discriminated. The results of such automated segmentation of OCE-images demonstrate a striking correlation with the results of conventional segmentation of histological slices in terms of percentages of the segmented zones. High sensitivity of the OCE-method to histological alterations was demonstrated in vivo in comparative studies of various types of anti-tumor therapies using murine tumor models. Studies of >100 samples of freshly excised breast cancer samples revealed strong correlation between the tumor-tissue subtype and its morphological composition determined by the developed OCE method. Thus, the developed approach can be used as a basis for express OCE-based biopsy (feasible intraoperatively). Longitudinal in vivo monitoring of morphological alterations in tumors under therapy or during natural development is also possible for locations accessible to OCT.

This article presents a probabilistic hierarchical clustering model for morphological segmentation. In contrast to existing approaches to morphology learning, our method allows learning hierarchical organization of word morphology as a collection of tree structured paradigms. The model is fully unsupervised and based on the hierarchical Dirichlet process. Tree hierarchies are learned along with the corresponding morphological paradigms simultaneously. Our model is evaluated on Morpho Challenge and shows competitive performance when compared to state-of-the-art unsupervised morphological segmentation systems. Although we apply this model for morphological segmentation, the model itself can also be used for hierarchical clustering of other types of data.

The microstructure of a hot-dip Zn-Al-Mg anti-corrosion coating on steel was investigated upon quenching during solidification. As expected, at least two different eutectic microstructures were generated and subsequently characterized using scanning and transmission electron microscopy, elemental analysis, and selected area diffraction. The difference was found in the eutectic intermetallic Mg--Zn phase, which was identified as MgZn2 and Mg2Zn11, respectively. Based on the experimental results, we developed an image processing algorithm for electron micrographs, which automatically detects the altered eutectic microstructure. Furthermore, a 3D focused ion beam tomography was performed for an in-depth analysis of the phase morphologies at the interface between the different eutectic structures. (VLID)5645739 Version of record

This paper deals with automatic morphological segmentation of Czech lemmas contained in the word-formation network DeriNet. Capturing derivational relations between base and derived lemmas, and segmenting lemmas into sequences of morphemes are two closely related formal models of how words come into existence. Thus we propose a novel segmentation method that benefits from the existence of the network; our solution constitutes new state-of-the-art for the Czech language.

with the development of the society, The demand for daily necessities continues to increase, At the same time, the production efficiency and quality requirements of the products are getting higher and higher. Aiming at this problem A feasible method for 3D printing physical surface defect detection based on OpenCV. Get the products you need quickly through reverse technology, Guaranteed efficient production. At the same time, using OpenCV-based surface defect inspection to ensure product quality. First, obtain a physical surface image through a color industrial CCD camera. Secondly, the histogram equalization method can enhance the contrast of the image and Image preprocessing. Finally, image morphological segmentation of dual-core defect recognition technology is used to detect the position of physical surface defects. This method can accurately detect 3D printing physical surface defects. Achieved the intended purpose.

Morphological segmentation has traditionally been modeled with non-hierarchical models, which yield flat segmentations as output. In many cases, however, proper morphological analysis requires hierarchical structure -- especially in the case of derivational morphology. In this work, we introduce a discriminative, joint model of morphological segmentation along with the orthographic changes that occur during word formation. To the best of our knowledge, this is the first attempt to approach discriminative segmentation with a context-free model. Additionally, we release an annotated treebank of 7454 English words with constituency parses, encouraging future research in this area., EMNLP 2016

Studies on morphological processing in French, as in other languages, have shown disparate results. We argue that a critical and long-overlooked factor that could underlie these diverging results is the methodological differences in the calculation of morphological variables across studies. To address the need for a common morphological database, we present MorphoLex-FR, a sizeable and freely available database with 12 variables for prefixes, roots, and suffixes for the 38,840 words of the French Lexicon Project. MorphoLex-FR constitutes a first step to render future studies addressing morphological processing in French comparable. The procedure we used for morphological segmentation and variable computation is effectively the same as that in MorphoLex, an English morphological database. This will allow for cross-linguistic comparisons of future studies in French and English that will contribute to our understanding of how morphologically complex words are processed. To validate these variables, we explored their influence on lexical decision latencies for morphologically complex nouns in a series of hierarchical regression models. The results indicated that only morphological variables related to the suffix explained lexical decision latencies. The frequency and family size of the suffix exerted facilitatory effects, whereas the percentage of more frequent words in the morphological family of the suffix was inhibitory. Our results are in line with previous studies conducted in French and in English. In conclusion, this database represents a valuable resource for studies on the effect of morphology in visual word processing in French.

International audience; This research deals with resources creation for under-resourced languages. We try to adapt existing resources for other resourced-languages to process less-resourced ones. We focus on Arabic dialects of the Maghreb, namely Algerian, Moroccan and Tunisian. We first adapt a well-known statistical word segmenter to segment Algerian dialect texts written in both Arabic and Latin scripts. We demonstrate that unsupervised morphological segmentation could be applied to Arabic dialects regardless of used script. Next, we use this kind of segmentation to improve statistical machine translation scores between the tree Maghrebi dialects and French. We use a parallel multidialectal corpus that includes six Arabic dialects in addition to MSA and French. We achieved interesting results. Regards to word segmentation, the rate of correctly segmented words reached 70% for those written in Latin script and 79% for those written in Arabic script. For machine translation, the unsupervised morphological segmentation helped to decrease out-of-vocabulary words rates by a minimum of 35%.

Morphological segmentation is useful for processing Mongolian. In this paper, we manually build a morphological segmentation data set for Mongolian. We then present a character-based encoder-decoder model with attention mechanism to perform the morphological segmentation task. We further investigate the influence of analogy features extracted from scratch and improve the performance of our model using multi languages setting. Experimental results show that our encoder-decoder model with attention mechanism provides a strong baseline for Mongolian morphological segmentation. The analogy features provide useful information to the model and improve the performance of the system. The use of multi languages data set shows the capability of our model to acquire knowledge through different languages and delivers the best result.

Background Os odontoideum is a smooth, independent ossicle separated from a hypoplastic odontoid process located cranially in the expected position of the odontoid tip. The pathogenesis of os odontoideum remains controversial, and several etiological theories have been suggested for congenital, developmental, and traumatic origins. Case Description We have reported symptomatic familial cases of dystopic os odontoideum in 2 elderly sisters who denied any traumatic history of the head and neck. Both patients were treated surgically, with successful outcomes achieved. Conclusions When examining the etiology of os odontoideum, checking for the existence of a traumatic history is important. However, a more important matter is to consider morphological segmentation abnormalities of the proatlas. Segmentation abnormalities of the proatlas could be closely connected to the development of familial os odontoideum.

This paper deals with the analysis and modeling of the retinal blood vessels system. The aim of the analysis is the design and implementation of a fully automated segmentation model based on the morphological segmentation, allowing for extraction of the blood system area within the binary model, where other retinal structures are suppressed. An important feature of the model is sensitivity and robustness to declare the efficacy of segmentation in an environment with worse image parameters. For this reason, the designed model is also tested for data where the vascular system is visualized under a low contrast. Part of the analysis is the comparative testing of the designed model against selected segmentation methods based on objective criteria. The designed model was tested and verified on dataset from system RetCam 3 containing 22 images.

In this work, we propose an original approach of semi-vectorial hybrid morphological segmentation for multicomponent images or multidimensional data by analyzing compact multidimensional histograms based on different orders. Its principle consists first of segment marginally each component of the multicomponent image into different numbers of classes fixed at K. The segmentation of each component of the image uses a scalar segmentation strategy by histogram analysis; we mainly count the methods by searching for peaks or modes of the histogram and those based on a multi-thresholding of the histogram. It is the latter that we have used in this paper, it relies particularly on the multi-thresholding method of OTSU. Then, in the case where i) each component of the image admits exactly K classes, K vector thresholds are constructed by an optimal pairing of which each component of the vector thresholds are those resulting from the marginal segmentations. In addition, the multidimensional compact histogram of the multicomponent image is computed and the attribute tuples or ‘colors’ of the histogram are ordered relative to the threshold vectors to produce (K + 1) intervals in the partial order giving rise to a segmentation of the multidimensional histogram into K classes. The remaining colors of the histogram are assigned to the closest class relative to their center of gravity. ii) In the contrary case, a vectorial spatial matching between the classes of the scalar components of the image is produced to obtain an over-segmentation, then an interclass fusion is performed to obtain a maximum of K classes. Indeed, the relevance of our segmentation method has been highlighted in relation to other methods, such as K-means, using unsupervised and supervised quantitative segmentation evaluation criteria. So the robustness of our method relatively to noise has been tested.

A new method for unsupervised morphological segmentation is presented.The method is based on a combination of affixality measurements.The method performed well for Spanish multi-slot morphology.In an empirical evaluation, the new method outperformed Morfessor and ParaMor.Results show that our method is competitive for Spanish morphological segmentation. In this paper, we present a method for unsupervised morphological segmentation for multi-slot morphology based on affixality measurements. These measurements quantify three linguistic characteristics of affixes: (1) they combine with many low frequency word-bases (high combinatorial capacity), (2) although they are relatively few, they help to maximize the size of a lexicon (economy principle), i.e. speakers know more words by remembering fewer morphological items, and (3) they are very frequent, so they contain less information than word-bases (entropy), i.e. borders between affixes and stems can be detected by finding entropy peaks. Several experiments combining these measurements were conducted to find the best way to apply them to data. The best strategy consists in successive segmentation when the average of the affixality measurements surpasses a threshold of 0.5. Also, we compared this strategy with some state-of-the-art methods for unsupervised morphological segmentation (Morfessor and ParaMor). Our method outperformed these methods, when tested in a hand-made corpus. Results indicate that our proposal is competitive at least for the morphological segmentation of Spanish words.

"Patient specific dosimetry established during the last decade in modern radio-therapy. Usually, tracer kinetics in main compartments of observed metabolism is assessed from anterior and posterior whole body scans. The effective doses for each organ, derived by the MIRD scheme, provide evidence for following radiotherapeutic treatment and helps to meet vital dose limits for critical organs, e.g. kidneys. The calculation of individual dose in a three-dimensional context leads to more accurate dose estimates, as was proven by intensive research, but is still on the cusp to clinical application. In this work, a statistical approach, based on multi-modal image and feature data, is presented, to overcome manual segmentation, the most time consuming step, in 3D based dose calculation. 3D data volumes from a hybrid SPECT study, comprising SPECT and CT data, covering main compartments of metabolism, build the image features of a Gaussian classifier. From prior segmentations organspecific membership maps are derived, and substituted as additional feature into the segmentation procedure. Centroids, eccentricity and principal axes of organ models are registered to a rough thresholded image of the SPECT component, and define membership coefficients of the voxels. The new approach yields accurate results, even with real patient data. The new method needs minimal user interaction during selection of some sample regions, thus showing high potential for implementation in a clinical workflow."

The paper addresses the task of automatic morpheme segmentation involving both splitting words into morphs and classification of resulted morphs. For segmentation of Russian words, a new model based on Bi-LSTM neural network is proposed and experimentally evaluated on several training data sets differing in labeling. The proposed model has comparable quality with the best supervised machine learning models for morpheme segmentation with classification, slightly outperforming them in word-level classification accuracy with score 89%.

In this paper, branching entropy techniques and isiXhosa language heuristics are adapted to develop unsupervised morphological segmenters for isiXhosa. An overview of isiXhosa segmentation issues is given, followed by a discussion on previous work in automated segmentation, and segmentation of isiXhosa in particular. Two unsupervised isiXhosa segmenters are presented and compared to a random minimum baseline and Morfessor-Baseline, a standard in unsupervised word segmentation. Morfessor-Baseline outperforms both isiXhosa segmenters at 79.10% boundary identification accuracy. The IsiXhosa Branching Entropy Segmenter (XBES) performance varies depending on the segmentation mode used, with a maximum of 73.39%. The IsiXhosa Heuristic Maximum Likelihood Segmenter (XHMLS) achieves 72.42%. The study suggests that unsupervised isiXhosa morphological segmentation is feasible with better optimization of the current attempt

Uyghur is an agglutinative language that has many morphemes. It is necessary for processing Uyghur to segment words into morphemes. This work is called morphological segmentation. Previous works treat morphological segmentation as a tagging task and classify each character as one of four classes, which are \(\{b,m,e,s\}\). However, these labels are not independent from each other, which makes the models easily overfitted. We propose a new method for the segmentation task. Instead of using these labels, we use only segmentation points for modeling. The model used in our method is more robust and easier to train than previous methods. Applying our model to Uyghur morphological segmentation, it achieves high accuracy and higher recall and f1 score than previous models.

Polysynthetic languages pose a challenge for morphological analysis due to the root-morpheme complexity and to the word class “squish”. In addition, many of these polysynthetic languages are low-resource. We propose unsupervised approaches for morphological segmentation of low-resource polysynthetic languages based on Adaptor Grammars (AG) (Eskander et al., 2016). We experiment with four languages from the Uto-Aztecan family. Our AG-based approaches outperform other unsupervised approaches and show promise when compared to supervised methods, outperforming them on two of the four languages.