scholarly journals Point detection through multi-instance deep heatmap regression for sutures in endoscopy

2021 ◽  
Author(s):  
Lalith Sharan ◽  
Gabriele Romano ◽  
Julian Brand ◽  
Halvar Kelm ◽  
Matthias Karck ◽  
...  
Keyword(s):  
Quantitative Information ◽  
Fixed Number ◽  
Distribution Functions ◽  
The Novel ◽  
Regression Problem ◽  
Link Type ◽  
Proposed Model ◽  
Relevant Task ◽  
Point Detection ◽  
Domain Variant

Abstract Purpose: Mitral valve repair is a complex minimally invasive surgery of the heart valve. In this context, suture detection from endoscopic images is a highly relevant task that provides quantitative information to analyse suturing patterns, assess prosthetic configurations and produce augmented reality visualisations. Facial or anatomical landmark detection tasks typically contain a fixed number of landmarks, and use regression or fixed heatmap-based approaches to localize the landmarks. However in endoscopy, there are a varying number of sutures in every image, and the sutures may occur at any location in the annulus, as they are not semantically unique. Method: In this work, we formulate the suture detection task as a multi-instance deep heatmap regression problem, to identify entry and exit points of sutures. We extend our previous work, and introduce the novel use of a 2D Gaussian layer followed by a differentiable 2D spatial Soft-Argmax layer to function as a local non-maximum suppression. Results: We present extensive experiments with multiple heatmap distribution functions and two variants of the proposed model. In the intra-operative domain, Variant 1 showed a mean $$F_1$$ F 1 of $$+ 0.0422$$ + 0.0422 over the baseline. Similarly, in the simulator domain, Variant 1 showed a mean $$F_1$$ F 1 of $$+ 0.0865$$ + 0.0865 over the baseline. Conclusion: The proposed model shows an improvement over the baseline in the intra-operative and the simulator domains. The data is made publicly available within the scope of the MICCAI AdaptOR2021 Challenge https://adaptor2021.github.io/, and the code at https://github.com/Cardio-AI/suture-detection-pytorch/.

scholarly journals Research of reliability and efficiency of technological processes of mechanical assembly production on the basis of the common semi-Markov model

2018 ◽  
Vol 224 ◽  
pp. 01138
Author(s):  
Yuri Rapatskiy ◽  
Mikhail Zamorenov ◽  
Vadim Kopp ◽  
Yuri Obzherin ◽  
Vladimir Gusev ◽  
...  
Keyword(s):  
Distribution Functions ◽  
Mechanical Assembly ◽  
Renewal Equations ◽  
Technological Processes ◽  
Threaded Connections ◽  
Proposed Model ◽  
The Common ◽  
Semi Markov Processes ◽  
Simulation Parameters ◽  
Assembly Production

In the article a common semi-Markov mathematical model is considered that allows one to investigate the productivity and reliability of various technological processes of mechanical assembly production. The proposed model allows to study, inter alia, technological processes of manufacturing parts with screw and assemblies of threaded connections. Mathematical apparatus of the research is the theory of semi-Markov processes with a common phase space, which operates with a common kind of random variables distribution functions. If the considering process in the system is a subsystem located on a higher level of hierarchy, the hierarchical model for compatibility with each other levels as output simulation parameters required distribution functions. In the proposed model, based on the decision of the Markov renewal equations depend not only on the torque characteristics, but also the distribution function of time per unit of output service according to different kinds of undervalued failures.

scholarly journals Burkholderia insulsa sp. nov., a facultatively chemolithotrophic bacterium isolated from an arsenic-rich shallow marine hydrothermal system

2015 ◽  
Vol 65 (Pt_1) ◽  
pp. 189-194 ◽  
Author(s):  
Antje Rusch ◽  
Shaer Islam ◽  
Pratixa Savalia ◽  
Jan P. Amend
Keyword(s):  
Type Species ◽  
Sequence Similarity ◽  
Rrna Gene ◽  
The Novel ◽  
Carbohydrate Utilization ◽  
Content Type ◽  
Link Type ◽  
Optimum Ph ◽  
Shallow Marine Hydrothermal System ◽  
Type Strains

Enrichment cultures inoculated with hydrothermally influenced nearshore sediment from Papua New Guinea led to the isolation of an arsenic-tolerant, acidophilic, facultatively aerobic bacterial strain designated PNG-AprilT. Cells of this strain were Gram-stain-negative, rod-shaped, motile and did not form spores. Strain PNG-AprilT grew at temperatures between 4 °C and 40 °C (optimum 30–37 °C), at pH 3.5 to 8.3 (optimum pH 5–6) and in the presence of up to 2.7 % NaCl (optimum 0–1.0 %). Both arsenate and arsenite were tolerated up to concentrations of at least 0.5 mM. Metabolism in strain PNG-AprilT was strictly respiratory. Heterotrophic growth occurred with O2 or nitrate as electron acceptors, and aerobic lithoautotrophic growth was observed with thiosulfate or nitrite as electron donors. The novel isolate was capable of N2-fixation. The respiratory quinones were Q-8 and Q-7. Phylogenetically, strain PNG-AprilT belongs to the genus Burkholderia and shares the highest 16S rRNA gene sequence similarity with the type strains of Burkholderia fungorum (99.8 %), Burkholderia phytofirmans (98.8 %), Burkholderia caledonica (98.4 %) and Burkholderia sediminicola (98.4 %). Differences from these related species in several physiological characteristics (lipid composition, carbohydrate utilization, enzyme profiles) and DNA–DNA hybridization suggested the isolate represents a novel species of the genus Burkholderia , for which we propose the name Burkholderia insulsa sp. nov. The type strain is PNG-AprilT ( = DSM 28142T = LMG 28183T).

Enhanced Content-Based Image Retrieval Using Information Oriented Angle-Based Local Tri-Directional Weber Patterns

2021 ◽  
pp. 2150046
Author(s):  
Gangavarapu Venkata Satya Kumar ◽  
Pillutla Gopala Krishna Mohan
Keyword(s):  
Image Retrieval ◽  
Computer Applications ◽  
Content Based Image Retrieval ◽  
Visual Features ◽  
The Novel ◽  
Image Content ◽  
Query Image ◽  
Proposed Model ◽  
Maximum Mutual Information ◽  
Basic Features

In diverse computer applications, the analysis of image content plays a key role. This image content might be either textual (like text appearing in the images) or visual (like shape, color, texture). These two image contents consist of image’s basic features and therefore turn out to be as the major advantage for any of the implementation. Many of the art models are based on the visual search or annotated text for Content-Based Image Retrieval (CBIR) models. There is more demand toward multitasking, a new method needs to be introduced with the combination of both textual and visual features. This paper plans to develop the intelligent CBIR system for the collection of different benchmark texture datasets. Here, a new descriptor named Information Oriented Angle-based Local Tri-directional Weber Patterns (IOA-LTriWPs) is adopted. The pattern is operated not only based on tri-direction and eight neighborhood pixels but also based on four angles [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text]. Once the patterns concerning tri-direction, eight neighborhood pixels, and four angles are taken, the best patterns are selected based on maximum mutual information. Moreover, the histogram computation of the patterns provides the final feature vector, from which the new weighted feature extraction is performed. As a new contribution, the novel weight function is optimized by the Improved MVO on random basis (IMVO-RB), in such a way that the precision and recall of the retrieved image is high. Further, the proposed model has used the logarithmic similarity called Mean Square Logarithmic Error (MSLE) between the features of the query image and trained images for retrieving the concerned images. The analyses on diverse texture image datasets have validated the accuracy and efficiency of the developed pattern over existing.

Methanobacterium lacus sp. nov., isolated from the profundal sediment of a freshwater meromictic lake

2012 ◽  
Vol 62 (Pt_7) ◽  
pp. 1625-1629 ◽  
Author(s):  
Guillaume Borrel ◽  
Keith Joblin ◽  
Annie Guedon ◽  
Jonathan Colombet ◽  
Vincent Tardy ◽  
...  
Keyword(s):  
Rumen Fluid ◽  
Sequence Similarity ◽  
Phylogenetic Analyses ◽  
Meromictic Lake ◽  
Rrna Gene ◽  
The Novel ◽  
Content Type ◽  
Link Type ◽  
Gram Staining ◽  
Lake Pavin

An autotrophic, hydrogenotrophic methanogen, designated strain 17A1T, was isolated from the profundal sediment of the meromictic Lake Pavin, France. The cells of the novel strain, which were non-motile, Gram-staining-negative rods that measured 2–15 µm in length and 0.2–0.4 µm in width, grew as filaments. Strain 17A1T grew in a mineral medium and its growth was stimulated by the addition of yeast extract, vitamins, acetate or rumen fluid. Penicillin, vancomycin and kanamycin reduced growth but did not completely inhibit it. Growth occurred at 14–41 °C (optimum 30 °C), at pH 5.0–8.5 (optimum pH 6.5) and with 0–0.4 M NaCl (optimum 0.1 M). The novel strain utilized H2/CO2 and methanol/H2 as substrates but not formate, acetate, methylamine/H2, isobutanol or 2-propanol. Its genomic DNA G+C content was 37.0 mol%. In phylogenetic analyses based on 16S rRNA gene sequences, strain 17A1T appeared to be a member of the genus Methanobacterium , with Methanobacterium beijingense 8-2T (96.3 % sequence similarity) identified as the most closely related established species. Based on phenotypic and phylogenetic data, strain 17A1T represents a novel species of methanogen within the genus Methanobacterium , for which the name Methanobacterium lacus sp. nov. is proposed. The type strain is 17A1T ( = DSM 24406T = JCM 17760T).

scholarly journals Stochastic Single Footfall Trace Model for Pedestrian Walking Load

2019 ◽  
Vol 19 (03) ◽  
pp. 1950029 ◽  
Author(s):  
Jun Chen ◽  
Guo Ding ◽  
Stana Živanović
Keyword(s):  
Random Variables ◽  
Distribution Functions ◽  
Dynamic Force ◽  
Gait Parameters ◽  
Proposed Model ◽  
Vibration Serviceability ◽  
Reliable Model ◽  
Time Histories ◽  
Trace Model ◽  
Force Time

Developing a model for the dynamic force generated by a pedestrian’s foot on a supporting structure (single footfall trace model) is crucial to advanced numerical analysis and vibration serviceability assessment of the structure. A reliable model needs to reflect the inter-subject and intra-subject randomness of human walking. This paper introduces a stochastic single footfall trace model in the form of a Fourier series in which body weight, walking frequency, and the first eight harmonics are treated as random variables. An experiment used 73 test subjects, walking at a range of pacing frequencies, to record force time histories and the corresponding gait parameters. Two variability descriptors were used to indicate inter-subject and intra-subject randomness. Further statistical analysis identified the relationships between key parameters as well as the probability distribution functions of random variables. In the final step, an application of the proposed single footfall trace model was developed and tested. The proposed model represented the experimental data well in both time and frequency domains.

scholarly journals Modified Decision Tree Technique for Ransomware Detection at Runtime through API Calls

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Faizan Ullah ◽  
Qaisar Javaid ◽  
Abdu Salam ◽  
Masood Ahmad ◽  
Nadeem Sarwar ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Decision Tree ◽  
Feature Vector ◽  
Machine Learning Algorithms ◽  
The Novel ◽  
Proposed Model ◽  
Testing Accuracy ◽  
Financial Losses

Ransomware (RW) is a distinctive variety of malware that encrypts the files or locks the user’s system by keeping and taking their files hostage, which leads to huge financial losses to users. In this article, we propose a new model that extracts the novel features from the RW dataset and performs classification of the RW and benign files. The proposed model can detect a large number of RW from various families at runtime and scan the network, registry activities, and file system throughout the execution. API-call series was reutilized to represent the behavior-based features of RW. The technique extracts fourteen-feature vector at runtime and analyzes it by applying online machine learning algorithms to predict the RW. To validate the effectiveness and scalability, we test 78550 recent malign and benign RW and compare with the random forest and AdaBoost, and the testing accuracy is extended at 99.56%.

scholarly journals Citroniella saccharovorans gen. nov. sp. nov., a member of the family Peptoniphilaceae isolated from a human fecal sample from a coastal traditional community member

2019 ◽  
Vol 69 (4) ◽  
pp. 1142-1148 ◽  
Author(s):  
Nisha B. Patel ◽  
Alexandra J. Obregón-Tito ◽  
Raul Y. Tito ◽  
Omar Trujillo-Villaroel ◽  
Luis Marin-Reyes ◽  
...  
Keyword(s):  
Fecal Sample ◽  
16S Rrna Gene Sequencing ◽  
Rrna Gene ◽  
The Novel ◽  
Content Type ◽  
Link Type ◽  
Novel Bacterium ◽  
The Family ◽  
Diamino Acid ◽  
Rrna Gene Sequencing

A novel Gram-stain-positive, non-motile, non-spore-forming coccus-shaped obligately anaerobic bacterium was recovered from a fecal sample obtained from an individual from a traditional community located on the southern coast of Peru. The results of analysis based on 16S rRNA gene sequencing indicated the novel bacterium to be phylogenetically distinct from other genera of members of the Peptoniphilaceae family, sharing a loose affinity with the genera Ezakiella , Finegoldia , Gallicola and Parvimonas . The major cellular fatty acids of the novel isolate were determined to be C16:0, C17:1ω8c, and C18:1ω9c. The DNA G+C content was 29.9 mol%. End products of metabolism from peptone yeast glucose broth (PYG) were determined to be acetate and methyl succinate. The diagnostic diamino acid present in the cell wall was lysine. On the basis of the phenotypic, chemotaxonomic and phylogenetic results the organism is a member of a novel genus belonging to the family Peptoniphilaceae for which the name Citroniella saccharovorans gen nov. sp. nov., is proposed. The type strain is M6.X9T (DSM 29873T=CCUG 66799T).

scholarly journals Nine novel psychrotolerant species of the genus Pedobacter isolated from Arctic soil with potential antioxidant activities

2020 ◽  
Vol 70 (4) ◽  
pp. 2537-2553 ◽  
Author(s):  
Ram Hari Dahal ◽  
Dhiraj Kumar Chaudhary ◽  
Dong-Uk Kim ◽  
Jaisoo Kim
Keyword(s):  
Type Strain ◽  
Antioxidant Activities ◽  
Rrna Gene ◽  
Major Polar Lipid ◽  
Strictly Aerobic ◽  
The Novel ◽  
Content Type ◽  
Link Type ◽  
Arctic Soil ◽  
Type Strains

Fifteen isolates of the genus Pedobacter were obtained from Arctic soil samples. All isolates were Gram-stain-negative and rod-shaped. Cells were strictly aerobic, psychrotolerant and grew optimally at 15–20 °C. Phylogenetic analysis based on 16S rRNA gene sequences revealed that all the isolated strains formed a lineage within the family Sphingobacteriaceae and clustered as members of the genus Pedobacter . The sole respiratory quinone was MK-7 and the major polar lipid was phosphatidylethanolamine. The major cellular fatty acids were summed feature 3 (iso-C15 : 02-OH/C16 : 1ω7c/ω6c), iso-C15 : 0 and iso-C17 : 0 3-OH. The DNA G+C content of the novel strains was 33.9–41.8 mol%. In addition, the average nucleotide identity and in silico DNA–DNA hybridization relatedness values between the novel type strains and phylogenetically related type strains were below the threshold values used for species delineation. Based on genomic, chemotaxonomic, phenotypic, phylogenetic and phylogenomic analyses, the isolated strains represent novel species in the genus Pedobacter , for which the names Pedobacter cryotolerans sp. nov. (type strain AR-2-6T=KEMB 9005-717T=KACC 19998T=NBRC 113826T), Pedobacter cryophilus sp. nov. (type strain AR-3-17T=KEMB 9005-718T=KACC 19999T=NBRC 113827T), Pedobacter frigiditerrae sp. nov. (type strain RP-1-13T=KEMB 9005-720T=KACC 21147T=NBRC 113829T), Pedobacter psychroterrae sp. nov. (type strain RP-1-14T=KEMB 9005-721T=KACC 21148T=NBRC 113830T), Pedobacter hiemivivus sp. nov. (type strain RP-3-8T=KEMB 9005-724T=KACC 21152T=NBRC 113833T), Pedobacter frigidisoli sp. nov. (type strain RP-3-11T=KEMB 9005-725T=KACC 21153T=NBRC 113927T), Pedobacter frigoris sp. nov. (type strain RP-3-15T=KEMB 9005-726T=KACC 21154T=NBRC 113834T), Pedobacter psychrodurus sp. nov. (type strain RP-3-21T=KEMB 9005-728T=KACC 21156T=NBRC 113835T) and Pedobacter polaris sp. nov. (type strain RP-3-22T=KEMB 9005-729T=KACC 21157T=NBRC 113836T) are proposed.

scholarly journals Genomics of Ochrobactrum pseudogrignonense (newly named Brucella pseudogrignonensis) reveals a new bla OXA subgroup

2021 ◽  
Vol 7 (8) ◽  
Author(s):  
Shu-Yuan Li ◽  
Yin-En Huang ◽  
Jhih-Yang Chen ◽  
Chung-Hsu Lai ◽  
Yan-Chiao Mao ◽  
...  
Keyword(s):  
Type Species ◽  
Wide Spectrum ◽  
The Novel ◽  
Bacterial Identification ◽  
Emerging Pathogen ◽  
Hybrid Strategy ◽  
Content Type ◽  
Link Type ◽  
Immunocompetent Patients ◽  
Ochrobactrum Pseudogrignonense

Ochrobactrum pseudogrignonense (newly named Brucella pseudogrignonensis ) is an emerging pathogen in immunodeficient and immunocompetent patients. Most documented cases associated with Ochrobactrum are frequently catheter-related and exhibit wide-spectrum β-lactam resistance. Misidentification of this pathogen using commercial bacterial identification kits is common. We identified a case of O. pseudogrignonense infection associated with cholelithiasis. The O. pseudogrignonense genome was sequenced and reconstructed using a Nanopore and Illumina hybrid strategy. A novel bla OXA-919 divergent from existing OXA members was identified and subsequent analysis revealed its existence in all available O. pseudogrignonense genomes, which forms a new phylogenetic subgroup distinct from other OXA clusters. Further analysis demonstrated the presence of the novel bla OXA-919 in the chromosome of several other Ochrobactrum species. Our study indicated that Ochrobactrum chromosomes may be a reservoir of bla OXA-919 β-lactamases.

scholarly journals Mathematical modeling approach to predict COVID-19 infected people in Sri Lanka

2021 ◽  
Vol 7 (3) ◽  
pp. 4672-4699
Author(s):  
I. H. K. Premarathna ◽  
◽  
H. M. Srivastava ◽  
Z. A. M. S. Juman ◽  
Ali AlArjani ◽  
...  
Keyword(s):  
Sri Lanka ◽  
Secondary Data ◽  
Logistic Growth ◽  
Solution Technique ◽  
The Novel ◽  
Infected People ◽  
Proposed Model ◽  
New Finding ◽  
Stochastic Forecasting ◽  
The Government

<abstract> <p>The novel corona virus (COVID-19) has badly affected many countries (more than 180 countries including China) in the world. More than 90% of the global COVID-19 cases are currently outside China. The large, unanticipated number of COVID-19 cases has interrupted the healthcare system in many countries and created shortages for bed space in hospitals. Consequently, better estimation of COVID-19 infected people in Sri Lanka is vital for government to take suitable action. This paper investigates predictions on both the number of the first and the second waves of COVID-19 cases in Sri Lanka. First, to estimate the number of first wave of future COVID-19 cases, we develop a stochastic forecasting model and present a solution technique for the model. Then, another solution method is proposed to the two existing models (SIR model and Logistic growth model) for the prediction on the second wave of COVID-19 cases. Finally, the proposed model and solution approaches are validated by secondary data obtained from the Epidemiology Unit, Ministry of Health, Sri Lanka. A comparative assessment on actual values of COVID-19 cases shows promising performance of our developed stochastic model and proposed solution techniques. So, our new finding would definitely be benefited to practitioners, academics and decision makers, especially the government of Sri Lanka that deals with such type of decision making.</p> </abstract>

Sign in / Sign up

Export Citation Format

Share Document