scholarly journals Automatic Landmark Detection of Human Back Surface from Depth Images via Deep Learning

2021 ◽  
Author(s):  
Masumeh Delgarmi ◽  
Hamed Heravi ◽  
Ali Rahimpour Jounghani ◽  
Abdullah Shahrezie ◽  
Afshin Ebrahimi ◽  
...  
Keyword(s):  
Network Architecture ◽  
The Body ◽  
Microsoft Kinect ◽  
Training Data ◽  
Back Surface ◽  
Anatomical Landmarks ◽  
X Rays ◽  
Depth Images ◽  
Physical Dysfunction ◽  
The Status

AbstractStudying human postural structure is one of the challenging issues among scholars and physicians. The spine is known as the central axis of the body, and due to various genetic and environmental reasons, it could suffer from deformities that cause physical dysfunction and correspondingly reduce people’s quality of life. Radiography is the most common method for detecting these deformities and requires monitoring and follow-up until full treatment; however, it frequently exposes the patient to X-rays and ionization and as a result, cancer risk is increased in the patient and could be highly dangerous for children or pregnant women. To prevent this, several solutions have been proposed using topographic data analysis of the human back surface. The purpose of this research is to provide an entirely safe and non-invasive method to examine the spiral structure and its deformities. Hence, it is attempted to find the exact location of anatomical landmarks on the human back surface, which provides useful and practical information about the status of the human postural structure to the physician.In this study, using Microsoft Kinect sensor, the depth images from the human back surface of 105 people were recorded and, our proposed approach - Deep convolution neural network-was used as a model to estimate the location of anatomical landmarks. In network architecture, two learning processes, including landmark position and affinity between the two associated landmarks, are successively performed in two separate branches. This is a bottom-up approach; thus, the runtime complexity is considerably reduced, and then the resulting anatomical points are evaluated concerning manual landmarks marked by the operator as the benchmark. Our results showed that 86.9% of PDJ and 80% of PCK. According to the results, this study was more effective than other methods with more than thousands of training data.

Automatic Landmark Detection of Human Back Surface from Depth Images via Deep Learning

2021 ◽  
Author(s):  
Masumeh Delgarmi ◽  
Hamed Heravi ◽  
Ali Rahimpour Jounghani ◽  
Abdullah Shahrezie ◽  
Afshin Ebrahimi ◽  
...  
Keyword(s):  
Network Architecture ◽  
The Body ◽  
Microsoft Kinect ◽  
Training Data ◽  
Back Surface ◽  
Anatomical Landmarks ◽  
X Rays ◽  
Depth Images ◽  
Physical Dysfunction ◽  
The Status

AbstractStudying human postural structure is one of the challenging issues among scholars and physicians. The spine is known as the central axis of the body, and due to various genetic and environmental reasons, it could suffer from deformities that cause physical dysfunction and correspondingly reduce people’s quality of life. Radiography is the most common method for detecting these deformities and requires monitoring and follow-up until full treatment. This method frequently exposes the patient to X-rays and ionization. Therefore, cancer risk is increased in the patient and could be riskier for children or pregnant women. To prevent this, several solutions have been proposed using topographic data analysis of the human back surface. The purpose of this research is to provide an entirely safe and non-invasive method to examine the spiral structure and its deformities. Hence, it is attempted to find the exact location of anatomical landmarks on the human back surface, which provides useful and practical information about the status of the human postural structure to the physician.In this study, using Microsoft Kinect sensor, the depth images from the human back surface of 105 people were recorded and, our proposed approach - Deep convolution neural network-was used as a model to estimate the location of anatomical landmarks. In network architecture, two learning processes, including landmark position and affinity between the two associated landmarks, are successively performed in two separate branches. This is a bottom-up approach; thus, the runtime complexity is considerably reduced, and then the resulting anatomical points are evaluated concerning manual landmarks marked by the operator as the benchmark. Our results showed that 86.9% of PDJ and 80% of PCK. According to the results, this study was more effective than other methods with more than thousands of training data.

X-ray micro tomography in the scanning electron microscope

1978 ◽  
Vol 36 (1) ◽  
pp. 106-107 ◽  
Author(s):  
W. Brünger
Keyword(s):  
Electron Beam ◽  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Target Surface ◽  
The Body ◽  
X Rays ◽  
Cross Sectional ◽  
X Ray ◽  
Micro Tomography ◽  
Scanning Electron

Reconstructive tomography is a new technique in diagnostic radiology for imaging cross-sectional planes of the human body /1/. A collimated beam of X-rays is scanned through a thin slice of the body and the transmitted intensity is recorded by a detector giving a linear shadow graph or projection (see fig. 1). Many of these projections at different angles are used to reconstruct the body-layer, usually with the aid of a computer. The picture element size of present tomographic scanners is approximately 1.1 mm2.Micro tomography can be realized using the very fine X-ray source generated by the focused electron beam of a scanning electron microscope (see fig. 2). The translation of the X-ray source is done by a line scan of the electron beam on a polished target surface /2/. Projections at different angles are produced by rotating the object.During the registration of a single scan the electron beam is deflected in one direction only, while both deflections are operating in the display tube.

Cinema and the Haptic in Modern Japan

Screen Bodies ◽  
2018 ◽  
Vol 3 (1) ◽  
pp. 23-36
Author(s):  
Daisuke Miyao
Keyword(s):  
The Body ◽  
Film Culture ◽  
Visual Medium ◽  
German Cinema ◽  
The Status ◽  
The Senses ◽  
Modern Japan

The process of modernization in Japan appeared as a separation of the senses and remapping of the body, particularly privileging the sense of vision. How did the filmmakers, critics, and novelists in the 1920s and 1930s respond to such a reorganization of the body and the elevation of vision in the context of film culture? How did they formulate a cinematic discourse on remapping the body when the status of cinema was still in flux and its definition was debated? Focusing on cinematic commentary made by different writers, this article tackles these questions. Sato Haruo, Ozu Yasujiro, and Iwasaki Akira questioned the separation of the senses, which was often enforced by state. Inspired by German cinema released in Japan at that time, they explored the notion of the haptic in cinema and problematized the privileged sense of vision in this new visual medium.

scholarly journals Links between Inflammation and Postoperative Cancer Recurrence

2021 ◽  
Vol 10 (2) ◽  
pp. 228
Author(s):  
Tomonari Kinoshita ◽  
Taichiro Goto
Keyword(s):  
Clinical Practice ◽  
Cancer Cells ◽  
Cancer Recurrence ◽  
Complete Resection ◽  
The Body ◽  
Cancer Development ◽  
Clinical Settings ◽  
Cancer Type ◽  
Clinical Indicators ◽  
The Status

Despite complete resection, cancer recurrence frequently occurs in clinical practice. This indicates that cancer cells had already metastasized from their organ of origin at the time of resection or had circulated throughout the body via the lymphatic and vascular systems. To obtain this potential for metastasis, cancer cells must undergo essential and intrinsic processes that are supported by the tumor microenvironment. Cancer-associated inflammation may be engaged in cancer development, progression, and metastasis. Despite numerous reports detailing the interplays between cancer and its microenvironment via the inflammatory network, the status of cancer-associated inflammation remains difficult to recognize in clinical settings. In the current paper, we reviewed clinical reports on the relevance between inflammation and cancer recurrence after surgical resection, focusing on inflammatory indicators and cancer recurrence predictors according to cancer type and clinical indicators.

scholarly journals Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Input Data ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Object Classification ◽  
Training Data ◽  
Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

Study of the main problems of delivery of orthopedic care in dentistry

2020 ◽  
pp. 47-53
Author(s):  
Valentina Sevagina ◽  
Sofiya Botsarova ◽  
Tatiyana Goncharova ◽  
Anastasiya Mikhlyaeva
Keyword(s):  
Dental Care ◽  
Dental Health ◽  
Poor Quality ◽  
The Body ◽  
Special Role ◽  
The Status ◽  
Quality Of Delivery ◽  
Orthopedic Care ◽  
Denture Treatment

The purpose of the article is to conduct a study of the main problems of delivery of orthopedic care in dentistry. It is known that dental health determines the overall health of the body. The comfort of life of the population depends on their condition, since damaged teeth negatively affect the state of the digestive system and respiratory organs. As for the aesthetics of the appearance, here teeth have a special role, since they are able to provide both proper speech and the necessary level of human sociability. Thus, improving the quality of delivery of medical care is an important task for the industry today. The problem of the availability of orthopedic dentists exists only in those areas of the region where there is no orthopedic care encounters at all, or orthopedic care encounters are carried out by part-time doctors. Accordingly, it can be said that municipal dental clinics are generally provided with the necessary personnel. In this regard, one can talk about the need to improve the quality of treatment of dental diseases in polyclinics, primarily in terms of orthopedic care for the population. However, today there are frequent cases of return visits for orthopedic care due to its poor-quality during initial treatment. And the doctor’s task during second denture treatment is to avoid mistakes made earlier and to provide competent and highquality orthopedic services. The author concludes that the results of a study of the work of orthopedic units of the region showed a steady growth of most indicators year by year, but a number of economic problems were found during the analysis of the profitability reserves of orthopedic dental care. So, it is necessary to create a unified system for calculating the financial plan for the correct assessment of the status of orthopedic dental care for the population, to analyze the quality indicators for subsidized denture treatment, to introduce the concept of “prosthesis working lifespan”, which will establish the reasons and justify the terms of the second denture treatment.

scholarly journals DeepIsoFun: a deep domain adaptation approach to predict isoform functions

2018 ◽  
Vol 35 (15) ◽  
pp. 2535-2544 ◽  
Author(s):  
Dipan Shaw ◽  
Hao Chen ◽  
Tao Jiang
Keyword(s):  
Network Architecture ◽  
Domain Adaptation ◽  
Multiple Instance Learning ◽  
Training Data ◽  
Supplementary Information ◽  
Operating Characteristics ◽  
Neural Network Architecture ◽  
Receiver Operating Characteristics Curve ◽  
Gene Functions ◽  
Better Than

AbstractMotivationIsoforms are mRNAs produced from the same gene locus by alternative splicing and may have different functions. Although gene functions have been studied extensively, little is known about the specific functions of isoforms. Recently, some computational approaches based on multiple instance learning have been proposed to predict isoform functions from annotated gene functions and expression data, but their performance is far from being desirable primarily due to the lack of labeled training data. To improve the performance on this problem, we propose a novel deep learning method, DeepIsoFun, that combines multiple instance learning with domain adaptation. The latter technique helps to transfer the knowledge of gene functions to the prediction of isoform functions and provides additional labeled training data. Our model is trained on a deep neural network architecture so that it can adapt to different expression distributions associated with different gene ontology terms.ResultsWe evaluated the performance of DeepIsoFun on three expression datasets of human and mouse collected from SRA studies at different times. On each dataset, DeepIsoFun performed significantly better than the existing methods. In terms of area under the receiver operating characteristics curve, our method acquired at least 26% improvement and in terms of area under the precision-recall curve, it acquired at least 10% improvement over the state-of-the-art methods. In addition, we also study the divergence of the functions predicted by our method for isoforms from the same gene and the overall correlation between expression similarity and the similarity of predicted functions.Availability and implementationhttps://github.com/dls03/DeepIsoFun/Supplementary informationSupplementary data are available at Bioinformatics online.

Mutagenicity, Metabolism, and DNA Interactions of Urethane

1990 ◽  
Vol 6 (1) ◽  
pp. 71-108 ◽  
Author(s):  
Rene E. Sotomayor ◽  
Thomas F.X. Collins
Keyword(s):  
Molecular Mechanisms ◽  
Case Reports ◽  
The Body ◽  
Alcoholic Beverages ◽  
Fermented Foods ◽  
X Rays ◽  
Spermatogenic Cells ◽  
Dna Interactions ◽  
Specific Locus ◽  
Vinyl Carbamate

Urethane, a known animal carcinogen, has been the subject of intensive research efforts spanning 40 years. Recent concerns have focused on the presence of urethane in a variety of fermented foods and alcoholic beverages, although no epidemiological studies or human case reports have been published. Much information is available about the mutagenesis, metabolism, and DNA interactions of urethane in experimental systems. Urethane is generally not mutagenic in bacteria although in some instances it acts as a weak mutagen. Urethane is not mutagenic in Neurospora but is weakly mutagenic in Saccharomyces. Drosophila appear to be the only organisms that consistently give positive mutagenic results with urethane, but its mutagenicity is weak and in many cases shows no clear dose dependence. Urethane is a good clastogen in mammalian somatic cells in vivo, but it shows variable results with cells in vitro. It efficiently induces sister chromatid exchanges in a variety of cells. Mammalian spermatogenic cells are insensitive to the induction of specific locus and dominant lethal mutations by urethane. Mutational synergism has been reported to occur between ethyl methanesulfonate and urethane when administered two generations apart, and some investigators have suggested possible synergism for cancer-causing mutations in mice exposed to X-rays and urethane one generation apart. These studies are controversial and have not been confirmed. Studies on the induction of cancer-causing dominant mutations by urethane are at variance with results from extensive studies with the specific locus test in mice. Urethane studies with the unscheduled DNA synthesis assay in mouse spermatogenic cells and with the sperm abnormality test have given negative results. Urethane is rapidly and evenly distributed in the body. The rate of elimination of urethane from plasma is a saturable process and varies according to the strain and age of the animal. Recent studies have concentrated on the effect of ethanol on urethane metabolism. At concentrations similar to those in wine, ethanol inhibits the tissue distribution of urethane in mice. These results are important because they suggest a lower carcinogenic/mutagenic risk than expected from exposure to urethane in alcoholic beverages. Although research on the metabolic activation of urethane has been extensive, no conclusive results have been obtained about its active metabolite, at one time thought to be N-hydroxyurethane. More recently, it has been postulated that urethane is actived to vinyl carbamate and that this metabolite is capable of reacting with DNA. Vinyl carbamate is more carcinogenic and more mutagenic than the parental compound, but despite intensive efforts it has not been identified as a metabolite in animals treated with urethane. Urethane binding to DNA appears to correlate well with tissue susceptibility to cancer. Various studies have attempted to elucidate the molecular nature of the bound molecule and the binding site. Some results have indicated the formation of a single DNA adduct, 7-(2-oxoethyl)guanine. This adduct may isomerize to O6,7-(1'-hydroxyethano)guanine, which might be more mutagenic than the 2-oxoethyl adduct; however, this possibility seems unlikely. Despite extensive research, urethane's metabolism and molecular mechanisms of mutation are still not clearly understood.

scholarly journals Usnic Acid, a Natural Antimicrobial Agent Able To Inhibit Bacterial Biofilm Formation on Polymer Surfaces

2004 ◽  
Vol 48 (11) ◽  
pp. 4360-4365 ◽  
Author(s):  
I. Francolini ◽  
P. Norris ◽  
A. Piozzi ◽  
G. Donelli ◽  
P. Stoodley
Keyword(s):  
Biofilm Formation ◽  
Usnic Acid ◽  
Modern Medicine ◽  
The Body ◽  
Bacterial Biofilm ◽  
Polymer Surfaces ◽  
Gram Positive Bacteria ◽  
The Status ◽  
Bacteria And Fungi ◽  
Systemic Infections

ABSTRACT In modern medicine, artificial devices are used for repair or replacement of damaged parts of the body, delivery of drugs, and monitoring the status of critically ill patients. However, artificial surfaces are often susceptible to colonization by bacteria and fungi. Once microorganisms have adhered to the surface, they can form biofilms, resulting in highly resistant local or systemic infections. At this time, the evidence suggests that (+)-usnic acid, a secondary lichen metabolite, possesses antimicrobial activity against a number of planktonic gram-positive bacteria, including Staphylococcus aureus, Enterococcus faecalis, and Enterococcus faecium. Since lichens are surface-attached communities that produce antibiotics, including usnic acid, to protect themselves from colonization by other bacteria, we hypothesized that the mode of action of usnic acid may be utilized in the control of medical biofilms. We loaded (+)-usnic acid into modified polyurethane and quantitatively assessed the capacity of (+)-usnic acid to control biofilm formation by either S. aureus or Pseudomonas aeruginosa under laminar flow conditions by using image analysis. (+)-Usnic acid-loaded polymers did not inhibit the initial attachment of S. aureus cells, but killing the attached cells resulted in the inhibition of biofilm. Interestingly, although P. aeruginosa biofilms did form on the surface of (+)-usnic acid-loaded polymer, the morphology of the biofilm was altered, possibly indicating that (+)-usnic acid interfered with signaling pathways.

Integrative taxonomic methods reveal an incorrect synonymisation of the South African Pseudonereis podocirra (Schmarda) as the widespread Pseudonereis variegata (Grube) from Chile

2018 ◽  
Vol 32 (6) ◽  
pp. 1282 ◽  
Author(s):  
Jyothi Kara ◽  
Angus H. H. Macdonald ◽  
Carol A. Simon
Keyword(s):  
South Africa ◽  
South African ◽  
Species Delimitation ◽  
Haplotype Network ◽  
The Body ◽  
General Description ◽  
The South ◽  
Morphological Examination ◽  
Genetic Structuring ◽  
The Status

The nereidid Pseudonereis variegata (Grube, 1866) described from Chile includes 14 synonymised species from 10 type localities with a discontinuous distribution, but no taxonomic or molecular studies have investigated the status of this species outside Chile. Two synonymised species, Mastigonereis podocirra Schmarda, 1861 and Nereis (Nereilepas) stimpsonis Grube, 1866, were described from South Africa and investigated here using morphological examination. MtCOI species delimitation analyses and morphology were used to determine the status of P. variegata in South Africa. Morphological examination revealed that museum and freshly collected specimens from South Africa that conform to the general description of P. variegata are similar to M. podocirra and N. stimpsonis with respect to the consistent absence of homogomph spinigers in the inferior neuropodial fascicle, expanded notopodial ligules and the subterminal attachment of dorsal cirri in posterior parapodia. The synonymy of M. podocirra and N. stimpsonis as P. variegata are rejected and P. podocirra, comb. nov. is reinstated. Morphologically, Pseudonereis podocirra differed from specimens from Chile with regard to the numbers of paragnaths, the absence of homogomph spinigers and changes in parapodial morphology along the body. Independence of these species was further supported by genetic distances, automatic barcode gap discovery and multi-rate Poisson tree process species delimitation analyses of 77 mtCOI sequences. Haplotype network revealed no genetic structuring within the South African populations. http://zoobank.org/urn:lsid:zoobank.org:pub:F0B1A5AF-9CE9-4A43-ACCF-17117E1C2F21

Sign in / Sign up

Export Citation Format

Share Document