scholarly journals Automated endoscopic detection and classification of colorectal polyps using convolutional neural networks

2020 ◽  
Vol 13 ◽  
pp. 175628482091065 ◽  
Author(s):  
Tsuyoshi Ozawa ◽  
Soichiro Ishihara ◽  
Mitsuhiro Fujishiro ◽  
Youichi Kumagai ◽  
Satoki Shichijo ◽  
...  
Keyword(s):  
White Light ◽  
Colorectal Polyps ◽  
Future Application ◽  
Single Shot ◽  
Still Images ◽  
Promising Application ◽  
American Society ◽  
Measure Of Performance

Background: Recently the American Society for Gastrointestinal Endoscopy addressed the ‘resect and discard’ strategy, determining that accurate in vivo differentiation of colorectal polyps (CP) is necessary. Previous studies have suggested a promising application of artificial intelligence (AI), using deep learning in object recognition. Therefore, we aimed to construct an AI system that can accurately detect and classify CP using stored still images during colonoscopy. Methods: We used a deep convolutional neural network (CNN) architecture called Single Shot MultiBox Detector. We trained the CNN using 16,418 images from 4752 CPs and 4013 images of normal colorectums, and subsequently validated the performance of the trained CNN in 7077 colonoscopy images, including 1172 CP images from 309 various types of CP. Diagnostic speed and yields for the detection and classification of CP were evaluated as a measure of performance of the trained CNN. Results: The processing time of the CNN was 20 ms per frame. The trained CNN detected 1246 CP with a sensitivity of 92% and a positive predictive value (PPV) of 86%. The sensitivity and PPV were 90% and 83%, respectively, for the white light images, and 97% and 98% for the narrow band images. Among the correctly detected polyps, 83% of the CP were accurately classified through images. Furthermore, 97% of adenomas were precisely identified under the white light imaging. Conclusions: Our CNN showed promise in being able to detect and classify CP through endoscopic images, highlighting its high potential for future application as an AI-based CP diagnosis support system for colonoscopy.

scholarly journals Automatic detection and classification of dental fluorosis in vivo using white light and fluorescence imaging

2018 ◽  
Vol 74 ◽  
pp. S34-S41 ◽  
Author(s):  
Zhao Liu ◽  
Michaela Goodwin ◽  
Roger P. Ellwood ◽  
Iain A. Pretty ◽  
Michael McGrady
Keyword(s):  
Fluorescence Imaging ◽  
White Light ◽  
Dental Fluorosis ◽  
Automatic Detection

scholarly journals Predictive rules for optical diagnosis of < 10-mm colorectal polyps based on a dedicated software

Endoscopy ◽  
2019 ◽  
Vol 52 (01) ◽  
pp. 52-60 ◽  
Author(s):  
Cesare Hassan ◽  
Raf Bisschops ◽  
Pradeep Bhandari ◽  
Emmanuel Coron ◽  
Helmut Neumann ◽  
...  
Keyword(s):  
Area Under The Curve ◽  
Colorectal Polyp ◽  
Colorectal Polyps ◽  
Hyperplastic Polyps ◽  
High Confidence ◽  
Still Images ◽  
The Individual ◽  
Video Library ◽  
Leave One Out

Abstract Background The BASIC classification for predicting in vivo colorectal polyp histology incorporates both surface and pit/vessel descriptor domains. This study aimed to define new BASIC classes for adenomatous and hyperplastic polyps. Methods A video library (102 still images/videos of < 10-mm polyps using white-light [WLI] and blue-light imaging [BLI]) was reviewed by seven expert endoscopists. Polyps were rated according to the individual descriptors of the three BASIC domains (surface/pit/vessel). A model to predict polyp histology (adenomatous or hyperplastic) was developed using multivariable logistic regression and subsequent “leave-one-out” cross-validation. New BASIC rules were then defined by Delphi agreement. The overall accuracy of these rules when used by experts was evaluated according to the level of confidence and light type. Results The strength of prediction for adenomatous histology from 2175 observations assessed by area under the curve (AUC; 95 % confidence interval) was poor-to-fair for the surface descriptors (0.50 [0.33 – 0.69] for mucus; 0.68 [0.57 – 0.79] for irregular surface), but stronger for pits (0.87 [0.80 – 0.96] for featureless/round/not round) and vessels (0.80 [0.65 – 0.87] for not present/lacy/pericryptal). By combining the domains, a good-to-excellent prediction was shown (AUC 0.89 [0.81 – 0.96]). After the definition of new BASIC rules for adenomatous and hyperplastic polyps, accuracy for high confidence BLI predictions was 90.3 % (86.3 % – 93.2 %), which was superior to high confidence WLI (83.7 % [77.3 % – 87.7 %]) and low confidence BLI predictions (77.7 % [61.1 % – 88.6 %]). Conclusions Based on the strength of prediction, the new BASIC classes for adenomatous and hyperplastic histology show favorable results for accuracy and confidence levels.

In Vitro Toxicology Methods in Risk Assessment

1996 ◽  
Vol 24 (3) ◽  
pp. 325-331
Author(s):  
Iain F. H. Purchase
Keyword(s):  
Risk Assessment ◽  
Hazard Assessment ◽  
Human Health Risk ◽  
In Vitro Test ◽  
In Vitro Methods ◽  
New Concepts ◽  
Vitro Test

The title of this paper is challenging, because the question of how in vitro methods and results contribute to human health risk assessment is rarely considered. The process of risk assessment usually begins with hazard assessment, which provides a description of the inherent toxicological properties of the chemical. The next step is to assess the relevance of this to humans, i.e. the human hazard assessment. Finally, information on exposure is examined, and risk can then be assessed. In vitro methods have a limited, but important, role to play in risk assessment. The results can be used for classification and labelling; these are methods of controlling exposure, analogous to risk assessment, but without considering exposure. The Ames Salmonella test is the only in vitro method which is incorporated into regulations and used widely. Data from this test can, at best, lead to classification of a chemical with regard to genotoxicity, but cannot be used for classification and labelling on their own. Several in vitro test systems which assess the topical irritancy and corrosivity of chemicals have been reasonably well validated, and the results from these tests can be used for classification. The future development of in vitro methods is likely to be slow, as it depends on the development of new concepts and ideas. The in vivo methods which currently have reasonably developed in vitro alternatives will be the easiest to replace. The remaining in vivo methods, which provide toxicological information from repeated chronic dosing, with varied endpoints and by mechanisms which are not understood, will be more difficult to replace.

scholarly journals Effectiveness and mechanisms of adipose-derived stem cell therapy in animal models of Parkinson’s disease: a systematic review and meta-analysis

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Keya Li ◽  
Xinyue Li ◽  
Guiying Shi ◽  
Xuepei Lei ◽  
Yiying Huang ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Animal Models ◽  
Therapeutic Option ◽  
Meta Analysis ◽  
Future Application ◽  
Neuroprotective Effects ◽  
Standard Mean Difference ◽  
Study Characteristics

AbstractAnimal models provide an opportunity to assess the optimal treatment way and the underlying mechanisms of direct clinical application of adipose-derived stem cells (ADSCs). Previous studies have evaluated the effects of primitive and induced ADSCs in animal models of Parkinson’s disease (PD). Here, eight databases were systematically searched for studies on the effects and in vivo changes caused by ADSC intervention. Quality assessment was conducted using a 10-item risk of bias tool. For the subsequent meta-analysis, study characteristics were extracted and effect sizes were computed. Ten out of 2324 published articles (n = 169 animals) were selected for further meta-analysis. After ADSC therapy, the rotation behavior (10 experiments, n = 156 animals) and rotarod performance (3 experiments, n = 54 animals) were improved (P < 0.000 01 and P = 0.000 3, respectively). The rotation behavior test reflected functional recovery, which may be due to the neurogenesis from neuronally differentiated ADSCs, resulting in a higher pooled effect size of standard mean difference (SMD) (− 2.59; 95% CI, − 3.57 to − 1.61) when compared to that of primitive cells (− 2.18; 95% CI, − 3.29 to − 1.07). Stratified analyses by different time intervals indicated that ADSC intervention exhibited a long-term effect. Following the transplantation of ADSCs, tyrosine hydroxylase-positive neurons recovered in the lesion area with pooled SMD of 13.36 [6.85, 19.86]. Transplantation of ADSCs is a therapeutic option that shows long-lasting effects in animal models of PD. The potential mechanisms of ADSCs involve neurogenesis and neuroprotective effects. The standardized induction of neural form of transplanted ADSCs can lead to a future application in clinical practice.

Classification of prostatic diseases by means of multivariate analysis on in vivo proton MRSI and DCE-MRI data

2009 ◽  
Vol 22 (10) ◽  
pp. 1036-1046 ◽  
Author(s):  
Mariacristina Valerio ◽  
Valeria Panebianco ◽  
Alessandro Sciarra ◽  
Marcello Osimani ◽  
Stefano Salsiccia ◽  
...  
Keyword(s):  
Multivariate Analysis ◽  
Dce Mri ◽  
Prostatic Diseases

scholarly journals Classification of lymphoid neoplasms: the microscope as a tool for disease discovery

Blood ◽  
2008 ◽  
Vol 112 (12) ◽  
pp. 4384-4399 ◽  
Author(s):  
Elaine S. Jaffe ◽  
Nancy Lee Harris ◽  
Harald Stein ◽  
Peter G. Isaacson
Keyword(s):  
Molecular Mechanisms ◽  
Nk Cell ◽  
Clinical Manifestations ◽  
Lymphoid Cells ◽  
World Health ◽  
International Studies ◽  
Lymphocyte Function ◽  
Lymphoid Neoplasms

AbstractIn the past 50 years, we have witnessed explosive growth in the understanding of normal and neoplastic lymphoid cells. B-cell, T-cell, and natural killer (NK)–cell neoplasms in many respects recapitulate normal stages of lymphoid cell differentiation and function, so that they can be to some extent classified according to the corresponding normal stage. Likewise, the molecular mechanisms involved the pathogenesis of lymphomas and lymphoid leukemias are often based on the physiology of the lymphoid cells, capitalizing on deregulated normal physiology by harnessing the promoters of genes essential for lymphocyte function. The clinical manifestations of lymphomas likewise reflect the normal function of lymphoid cells in vivo. The multiparameter approach to classification adopted by the World Health Organization (WHO) classification has been validated in international studies as being highly reproducible, and enhancing the interpretation of clinical and translational studies. In addition, accurate and precise classification of disease entities facilitates the discovery of the molecular basis of lymphoid neoplasms in the basic science laboratory.

scholarly journals A57 THE USE AND INTERPRETATION OF HLA-DQ2/DQ8 GENOTYPING BY PEDIATRIC GASTROENTEROLOGISTS

2021 ◽  
Vol 4 (Supplement_1) ◽  
pp. 14-15
Author(s):  
B Moreau ◽  
E Robidoux
Keyword(s):  
Risk Groups ◽  
Risk Classification ◽  
Low Risk ◽  
Risk Alleles ◽  
Seronegative Patient ◽  
Espghan Guidelines ◽  
Recent Classification ◽  
American Society ◽  
Hla Dq2

Abstract Background A recent classification of high and low risk alleles associated with celiac disease (CD) shows that the presence of a single allele (DQA1*05 or DQB1*02; coding together for HLA-DQ2), without a positive genotype (HLA-DQ2 and or HLA-DQ8), represents a risk of developing the disease. Aims The aim of this study is to evaluate the use and interpretation of the HLA-DQ2/DQ8 genotyping by pediatric gastroenterologists, as there is no study on the matter and the latest guidelines do not address this risk classification. Methods A web-based survey was sent by email to all NASPGHAN (North American society of pediatric gastroenterolgy, hepatology and nutrition) members. Results Results 294 pediatric gastroenterologists sent a complete survey. 86,1% use the HLA-DQ2/DQ8 genotyping according mainly to the NASPGHAN and ESPGHAN guidelines. The main indications considered were to exclude CD in a patient on a gluten-free diet with a resolution of his symptoms and in a seronegative patient with equivocal biopsies. A minority would consider the genotyping for screening high risk groups or for making a diagnosis in children with high specific CD antibodies and strong clinical suspicion without performing biopsies, as suggested by the ESPGHAN guidelines. The alleles associated with CD are not well known, but 76,7% the participants are aware of the risk classification. While only 62,8% have access to the complete genotype, 47,8% consider it useful. Nevertheless, 82,6% would still want to know the presence of a low risk allele. Conclusions The risk classification of alleles related to CD warrants a modification of the genotyping result with access to the alleles and an adaptation of the guidelines. Funding Agencies None

Fr612 INFLUENCE OF COMPUTER AIDED DIAGNOSIS WITH AUGMENTED VISUALIZATION ON ENDOSCOPIC CLASSIFICATION OF COLORECTAL POLYPS

2021 ◽  
Vol 160 (6) ◽  
pp. S-376
Author(s):  
Eladio Rodriguez-Diaz ◽  
Gyorgy Baffy Wai-Kit Lo ◽  
Hiroshi Mashimo ◽  
Aparna Repaka ◽  
Alexander Goldowsky ◽  
...  
Keyword(s):  
Computer Aided Diagnosis ◽  
Colorectal Polyps ◽  
Computer Aided ◽  
Endoscopic Classification ◽  
Aided Diagnosis

scholarly journals Fungicidal Activity of a Safe 1,3,4-Oxadiazole Derivative Against Candida albicans

Pathogens ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 314
Author(s):  
Daniella Renata Faria ◽  
Raquel Cabral Melo ◽  
Glaucia Sayuri Arita ◽  
Karina Mayumi Sakita ◽  
Franciele Abigail Vilugron Rodrigues-Vendramini ◽  
...  
Keyword(s):  
Candida Albicans ◽  
Fungicidal Activity ◽  
Inhibitory Concentration ◽  
Therapeutic Potential ◽  
Bloodstream Infections ◽  
Common Species ◽  
Future Application ◽  
Chemical Similarity ◽  
Preclinical Trials

Candida albicans is the most common species isolated from nosocomial bloodstream infections. Due to limited therapeutic arsenal and increase of drug resistance, there is an urgent need for new antifungals. Therefore, the antifungal activity against C. albicans and in vivo toxicity of a 1,3,4-oxadiazole compound (LMM6) was evaluated. This compound was selected by in silico approach based on chemical similarity. LMM6 was highly effective against several clinical C. albicans isolates, with minimum inhibitory concentration values ranging from 8 to 32 µg/mL. This compound also showed synergic effect with amphotericin B and caspofungin. In addition, quantitative assay showed that LMM6 exhibited a fungicidal profile and a promising anti-biofilm activity, pointing to its therapeutic potential. The evaluation of acute toxicity indicated that LMM6 is safe for preclinical trials. No mortality and no alterations in the investigated parameters were observed. In addition, no substantial alteration was found in Hippocratic screening, biochemical or hematological analyzes. LMM6 (5 mg/kg twice a day) was able to reduce both spleen and kidneys fungal burden and further, promoted the suppresses of inflammatory cytokines, resulting in infection control. These preclinical findings support future application of LMM6 as potential antifungal in the treatment of invasive candidiasis.

Sign in / Sign up

Export Citation Format

Share Document