LSM-SEC: Tongue Segmentation by the Level Set Model with Symmetry and Edge Constraints

Accurate segmentation of the tongue body is an important prerequisite for computer-aided tongue diagnosis. In general, the size and shape of the tongue are very different, the color of the tongue is similar to the surrounding tissue, the edge of the tongue is fuzzy, and some of the tongue is interfered by pathological details. The existing segmentation methods are often not ideal for tongue image processing. To solve these problems, this paper proposes a symmetry and edge-constrained level set model combined with the geometric features of the tongue for tongue segmentation. Based on the symmetry geometry of the tongue, a novel level set initialization method is proposed to improve the accuracy of subsequent model evolution. In order to increase the evolution force of the energy function, symmetry detection constraints are added to the evolution model. Combined with the latest convolution neural network, the edge probability input of the tongue image is obtained to guide the evolution of the edge stop function, so as to achieve accurate and automatic tongue segmentation. The experimental results show that the input tongue image is not subject to the external capturing facility or environment, and it is suitable for tongue segmentation under most realistic conditions. Qualitative and quantitative comparisons show that the proposed method is superior to the other methods in terms of robustness and accuracy.

Download Full-text

A Multi-Scale Information Fusion Level Set for Breast Tumor Segmentation

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2021.3635 ◽

2021 ◽

Vol 11 (8) ◽

pp. 2062-2070

Author(s):

Tongle Fan ◽

Guanglei Wang ◽

Yan Li ◽

Zhongyang Wang ◽

Hongrui Wang

Keyword(s):

Level Set ◽

Breast Tumor ◽

Region Of Interest ◽

Energy Functional ◽

Surrounding Tissue ◽

Tumor Segmentation ◽

Energy Term ◽

Edge Information ◽

Breast Segmentation ◽

Level Set Model

Purpose: Mammography is considered an effective method of examination in early breast cancer screening. Massive work by distinguished researchers of breast segmentation has been proposed. However, due to the blurry boundaries of the breast tumor, the variability of its shape and the overlap with surrounding tissue, the breast tumor’s accurate segmentation still is a challenge. Methods: In this paper, we proposed a novel level set model which based on the optimized local region driven gradient enhanced level set model (OLR-GCV) to segment tumor within a region of interest (ROI) in a mammogram. Firstly, Noise, labels and artifacts are removed from breast images. The ROI is then obtained using the intuitionistic fuzzy C-means method. Finally we used OLR-GCV method to accurately segment the breast tumor. The OLR-GCV model combines regional information, enhanced edge information and optimized Laplacian of Gaussian (LOG) energy term. The regional and enhanced edge information are used to capture local, global and gradient information of breast images. The optimized Laplacian of Gaussian (LOG) energy term is introduced in the energy functional to further optimize edge information to improve segmentation accuracy. Results: We evaluated our method on the MIAS and DDSM datasets. It yielded a Dice value of 96.86% on the former and 95.51% on the latter. Our method proposed achieves higher accuracy of segmentation than other State-of-the-art Methods. Conclusions: Our method has better segmentation performance, and can be used in clinical practice.

Download Full-text

TongueNet: A Precise and Fast Tongue Segmentation System Using U-Net with a Morphological Processing Layer

Applied Sciences ◽

10.3390/app9153128 ◽

2019 ◽

Vol 9 (15) ◽

pp. 3128 ◽

Cited By ~ 7

Author(s):

Jianhang Zhou ◽

Qi Zhang ◽

Bob Zhang ◽

Xiaojiao Chen

Keyword(s):

State Of The Art ◽

Automatic Segmentation ◽

Morphological Processing ◽

Small Scale ◽

Tongue Diagnosis ◽

Qualitative And Quantitative ◽

Non Invasive ◽

Segmentation Methods ◽

Image Dataset ◽

Tongue Segmentation

Automated tongue segmentation is a critical component of tongue diagnosis, especially in Traditional Chinese Medicine (TCM), where it has been practiced for thousands of years and is generally considered pain-free and non-invasive. Therefore, a more precise, fast, and robust tongue segmentation system to automatically segment tongue images from its raw format is necessary. Previous algorithms segmented the tongue in different ways, where the results are either inaccurate or time-consuming. Furthermore, none of them developed a dedicated, automatic segmentation system. In this paper, we proposed TongueNet, which is a precise and fast automatic tongue segmentation system. U-net is utilized as the segmentation backbone applying a small-scale image dataset. Besides this, a morphological layer is proposed in the latter stages of the architecture. The proposed system when applied to a tongue image dataset with 1000 images, achieved the highest Pixel Accuracy of 98.45% and consumed 0.267 s per picture on average, which outperformed conventional state-of-the-art tongue segmentation methods in both accuracy and speed. Extensive qualitative and quantitative experiments showed the robustness of the proposed system concerning different positions, poses, and shapes. The results indicate a promising step in achieving a fully automated tongue diagnosis system.

Download Full-text

The development of body and organ shape

BMC Zoology ◽

10.1186/s40850-020-00063-5 ◽

2020 ◽

Vol 5 (1) ◽

Author(s):

Ansa E. Cobham ◽

Christen K. Mirth

Keyword(s):

Relative Position ◽

Body Shape ◽

Single Cells ◽

The Other ◽

Geometric Features ◽

Main Text ◽

Size Characterization ◽

Organ Shape ◽

The Many

Abstract Background Organisms show an incredibly diverse array of body and organ shapes that are both unique to their taxon and important for adapting to their environment. Achieving these specific shapes involves coordinating the many processes that transform single cells into complex organs, and regulating their growth so that they can function within a fully-formed body. Main text Conceptually, body and organ shape can be separated in two categories, although in practice these categories need not be mutually exclusive. Body shape results from the extent to which organs, or parts of organs, grow relative to each other. The patterns of relative organ size are characterized using allometry. Organ shape, on the other hand, is defined as the geometric features of an organ’s component parts excluding its size. Characterization of organ shape is frequently described by the relative position of homologous features, known as landmarks, distributed throughout the organ. These descriptions fall into the domain of geometric morphometrics. Conclusion In this review, we discuss the methods of characterizing body and organ shape, the developmental programs thought to underlie each, highlight when and how the mechanisms regulating body and organ shape might overlap, and provide our perspective on future avenues of research.

Download Full-text

Comparative leaf development of aerial and aquatic growth forms of Myriophyllum aquaticum

Botany ◽

10.1139/cjb-2012-0190 ◽

2013 ◽

Vol 91 (7) ◽

pp. 421-430 ◽

Cited By ~ 1

Author(s):

M.D. Shafiullah ◽

Christian R. Lacroix

Keyword(s):

Apical Meristem ◽

Epidermal Cells ◽

The Other ◽

Developmental Study ◽

Growth Forms ◽

Myriophyllum Aquaticum ◽

Stages Of Development ◽

Qualitative And Quantitative ◽

Early Stages ◽

Other Hand

Myriophyllum aquaticum (Vell.) Verdc. produces two morphologically different forms of leaves based on whether they are aerial or aquatic. The objective of this study was to determine whether there are any similarities or differences between these two growth forms during their early stages of development. A comparative developmental study of aerial and aquatic growth forms of M. aquaticum was conducted from a qualitative and quantitative perspective using a scanning electron microscope. The pattern of leaf and lobe initiation such as their origin and shape were similar in both growth forms until the fourth plastochron (stage P4). Differences between the two growth forms became evident from stage P5 onward, where a larger shoot apical meristem (SAM), elongated epidermal cells, shorter and slightly more numerous lobes, as well as the presence of appendage-like structures characterized aquatic growth forms. On the other hand, aerial growth forms had smaller SAM, bulb-like epidermal cells, and longer and slightly less numerous leaf lobes. Significant differences between growth forms were noted for parameters such as volume of SAM, length of terminal, first, and middle lobes, as well as the length from first to last lobes. The volume of the SAM of aquatic shoot tips was always greater than aerial forms. On the other hand, lobes of aerial forms were always longer than the aquatic counterpart during early stages of development. This study on the development of M. aquaticum shows that the aerial and aquatic growth forms diverge from their early stages of development.

Download Full-text

Changes in Seryl-tRNA Formative in Developing Chick Muscle

Canadian Journal of Biochemistry ◽

10.1139/o74-120 ◽

1974 ◽

Vol 52 (10) ◽

pp. 838-844 ◽

Cited By ~ 3

Author(s):

Mark Nwagwu ◽

John Lianga

Keyword(s):

Muscle Protein ◽

Muscle Protein Synthesis ◽

Deae Cellulose ◽

The Other ◽

Embryonic Chick ◽

Qualitative And Quantitative ◽

Embryonic Muscle ◽

Quantitative Changes ◽

The One

As a prelude to an analysis of the dependence of muscle protein synthesis on aminoacyl tRNA's, we have investigated the rates of seryl-tRNA formation, in vitro, by aminoacylating systems isolated from 11-, 14-, and 17-day chick embryonic muscle. The results show that the combination of 14-day tRNA and 14-day aminoacyl synthetase is the most efficient in seryl-tRNA formation. We have also studied the qualitative and quantitative changes in seryl-tRNA prepared from 11-, 14-, and 17-day embryonic chick muscle by chromatography of seryl-tRNA on benzoylated DEAE-cellulose columns. The results show that, although there are no qualitative differences in the chromatographic patterns of seryl-tRNA from the different ages, there are significant quantitative differences between the patterns for 11-day and 17-day seryl-tRNA on the one hand, and the pattern for 14-day seryl-tRNA on the other.

Download Full-text

SEGMENTATION OF ABDOMEN DISEASES USING ACTIVE CONTOUR MODELS IN CT IMAGES

Biomedical Engineering Applications Basis and Communications ◽

10.4015/s1016237215500477 ◽

2015 ◽

Vol 27 (05) ◽

pp. 1550047 ◽

Cited By ~ 2

Author(s):

Gaurav Sethi ◽

B. S. Saini

Keyword(s):

Level Set ◽

Active Contour ◽

Active Contour Model ◽

Diagnostic System ◽

Ct Images ◽

Active Contour Models ◽

Segmentation Methods ◽

Contour Models ◽

Edge Based ◽

Level Set Evolution

Precise segmentation of abdomen diseases like tumor, cyst and stone are crucial in the design of a computer aided diagnostic system. The complexity of shapes and similarity of texture of disease with the surrounding tissues makes the segmentation of abdomen related diseases much more challenging. Thus, this paper is devoted to the segmentation of abdomen diseases using active contour models. The active contour models are formulated using the level-set method. Edge-based Distance Regularized Level Set Evolution (DRLSE) and region based Selective Binary and Gaussian Filtering Regularized Level Set (SBGFRLS) are used for segmentation of various abdomen diseases. These segmentation methods are applied on 60 CT images (20 images each of tumor, cyst and stone). Comparative analysis shows that edge-based active contour models are able to segment abdomen disease more accurately than region-based level set active contour model.

Download Full-text

EVALUATION OF KNOWLEDGE OF STUDENTS ON GEOGRAPHY: PRINCIPLES, FORMS, A TECHNIQUE

GAMTAMOKSLINIS UGDYMAS / NATURAL SCIENCE EDUCATION ◽

10.48127/gu-nse/07.4.34 ◽

2007 ◽

Vol 4 (1) ◽

pp. 34-39

Author(s):

Laima Railienė

Keyword(s):

School Reform ◽

Positive Result ◽

Key Words ◽

Positive Emotions ◽

School Administration ◽

Assessment System ◽

The Other ◽

Knowledge Assessment ◽

Qualitative And Quantitative ◽

The One

According to scientists, assessment is tightly connecting teachers, students, parents, school administration. Teacher’s (assessor’s) role is becoming especially important because school reform has changed attitude towards assessment and has created favourable conditions for new ways of assessment. Assessment can show student’s achievement qualitative and quantitative value. Students’ knowledge assessment shows what is known well or weak. Knowledge testing and assessing have a positive result when it is being checked systematically. But it is not good to assess only acquired knowledge. It is very important to make knowledge system, to deepen, to activate students. It is also important to find out how students use theory in practice. If you want to assess correctly, you need to know the forms and kinds of assessment. It is very important not to forget that students must know what they are to remember, because it is impossible to memorize everything. All students want to get good marks. There are several reasons why students react sensitively. From marks parents judge about their child’s abilities and even future profession. On the one hand knowledge assessment gives positive emotions, on the other hand, it gives negative ones. Thus, teachers have to be very careful while checking and assessing. Students themselves need to be assessed, because they can’t know if they study well. Geography teacher has got very wide possibilities to check students’ knowledge and skill. But the most important thing is that students’ knowledge become deeper and stronger if they are checked up systematically and interestingly. Key words: knowledge assessment, assessment system, kinds of assessment, forms of assessment, assessment principles and criteria

Download Full-text

Introduction to the Special Issue “Causal Complexity and Qualitative Methods”

Political Analysis ◽

10.1093/pan/mpj016 ◽

2006 ◽

Vol 14 (3) ◽

pp. 223-226 ◽

Cited By ~ 3

Author(s):

Gary Goertz

Keyword(s):

Social Science ◽

Qualitative Methods ◽

Quantitative Methods ◽

The Other ◽

Special Issue ◽

Qualitative And Quantitative ◽

Qualitative And Quantitative Methods ◽

Political Analysis ◽

Empirical Social Science ◽

Causal Complexity

This special issue of Political Analysis engages in a dialogue between qualitative and quantitative methods. It proposes that each has something to say to the other and more generally has a contribution to make to empirical social science.

Download Full-text