scholarly journals PTU-63 Semi-automated annotation tool outperforms medical students and is comparable to clinical experts for polyp detection

2021 ◽  
Author(s):  
Tom Eelbode ◽  
Omer Ahmad ◽  
Pieter Sinonquel ◽  
Timon B Kocadag ◽  
Neil Narayan ◽  
...  
Keyword(s):  
Medical Students ◽  
Annotation Tool ◽  
Polyp Detection ◽  
Automated Annotation

Development of automated annotation software for human embryo morphokinetics

2020 ◽  
Vol 35 (3) ◽  
pp. 557-564 ◽  
Author(s):  
M Feyeux ◽  
A Reignier ◽  
M Mocaer ◽  
J Lammers ◽  
D Meistermann ◽  
...  
Keyword(s):  
Human Embryo ◽  
Embryo Quality ◽  
Selection Criterion ◽  
Time Lapse ◽  
Manual Annotation ◽  
Annotation Tool ◽  
High Throughput Analysis ◽  
Technical Limitation ◽  
Automated Annotation ◽  
Morphokinetic Parameters

Abstract STUDY QUESTION Is it possible to develop an automated annotation tool for human embryo development in time-lapse devices based on image analysis? SUMMARY ANSWER We developed and validated an automated software for the annotation of human embryo morphokinetic parameters, having a good concordance with expert manual annotation on 701 time-lapse videos. WHAT IS KNOWN ALREADY Morphokinetic parameters obtained with time-lapse devices are increasingly used for the assessment of human embryo quality. However, their annotation is time-consuming and can be slightly operator-dependent, highlighting the need to develop fully automated approaches. STUDY DESIGN, SIZE, DURATION This monocentric study was conducted on 701 videos originating from 584 couples undergoing IVF with embryo culture in a time-lapse device. The only selection criterion was that the duration of the video must be over 60 h. PARTICIPANTS/MATERIALS, SETTING, METHODS An automated morphokinetic annotation tool was developed based on gray level coefficient of variation and detection of the thickness of the zona pellucida. The detection of cellular events obtained with the automated tool was compared with those obtained manually by trained experts in clinical settings. MAIN RESULTS AND THE ROLE OF CHANCE Although some differences were found when embryos were considered individually, we found an overall concordance between automated and manual annotation of human embryo morphokinetics from fertilization to expanded blastocyst stage (r2 = 0.92). LIMITATIONS, REASONS FOR CAUTION These results should undergo multicentric external evaluation in order to test the overall performance of the annotation tool. Getting access to the export of 3D videos would enhance the quality of the correlation with the same algorithm and its extension to the 3D regions of interest. A technical limitation of our work lies within the duration of the video. The more embryo stages the video contains, the more information the script has to identify them correctly. WIDER IMPLICATIONS OF THE FINDINGS Our system paves the way for high-throughput analysis of multicentric morphokinetic databases, providing new insights into the clinical value of morphokinetics as a predictor of embryo quality and implantation. STUDY FUNDING/COMPETING INTEREST(S) This study was partly funded by Finox-Gedeon Richter Forward Grant 2016 and NeXT (ANR-16-IDEX-0007). We have no conflict of interests to declare. TRIAL REGISTRATION NUMBER N/A

Comparative analysis of the PCOLCE region in Fugu rubripes using a new automated annotation tool

2000 ◽  
Vol 11 (3) ◽  
pp. 213-219 ◽  
Author(s):  
Giorgia Romina Riboldi Tunnicliffe ◽  
Gernot Gloeckner ◽  
Greg S. Elgar ◽  
Sydney Brenner ◽  
André Rosenthal
Keyword(s):  
Comparative Analysis ◽  
Fugu Rubripes ◽  
Annotation Tool ◽  
Automated Annotation

scholarly journals Development of a robust automated tool for the annotation of embryo morphokinetic parameters

2018 ◽  
Author(s):  
M Feyeux ◽  
A Reignier ◽  
M Mocaer ◽  
J Lammers ◽  
D Meistermann ◽  
...  
Keyword(s):  
Human Embryo ◽  
Large Scale ◽  
Embryo Quality ◽  
Time Lapse ◽  
Preimplantation Embryos ◽  
Manual Annotation ◽  
Annotation Tool ◽  
Automated Annotation ◽  
Morphokinetic Parameters ◽  
Automated Tool

AbstractStudy QuestionIs it possible to automatically annotate human embryo development in time-lapse devices, with results comparable to manual annotation?Summary AnswerWe developed an automated tool for the annotation of embryo morphokinetic parameters having a high concordance with expert manual annotation in a large scale-study.What is Known AlreadyMorphokinetic parameters obtained with time-lapse devices are increasingly used for human embryo quality assessment. However, their annotation is timeconsuming and can be operator-dependent, highlighting the need of developing automated approaches.Study Design, Size, DurationThis monocentric pilot study was conducted using 701 blastocysts originating from 584 couples undergoing IVF with embryo culture in a time-lapse device and on 4 mouse embryos.Participants/Materials, Setting, MethodsAn automated annotation tool was developed based on grey level coefficient of variation and detection of the thickness of the zona pellucida. The timings of cellular events obtained with the automated tool were compared with those obtained manually by 2 expert embryologists. The same procedure was applied on 4 mouse preimplantation embryos obtained with a different device in a different setting.Main Results and the Role of ChanceAlthough some differences were found when embryos were considered individually, we found an overall excellent concordance between automated and manual annotation of human embryo morphokinetics from fertilization to expanded blastocyst stage (r2=0.94). Moreover, the automated annotation tool gave promising results across species (human, mice).Limitations, Reasons for CautionThese results should undergo multi-centric external evaluation in order to test the overall performance of the annotation tool.Wider Implications of the FindingsOur system performs significantly better than the ones reported in the literature and on a bigger cohort, paving the way for high-throughput analysis of multicentric morphokinetic databases, providing new insights into the clinical value of morphokinetics as predictor of embryo quality and implantation.Study Funding/Competing Interest(s)This study was partly funded by Finox Forward Grant 2016.Trial Registration NumberNA

Synthesizing Image and Automated Annotation Tool for CNN based Under Water Object Detection

2019 ◽  
Vol 14 (2) ◽  
pp. 139-149 ◽  
Author(s):  
MyungHwan Jeon ◽  
◽  
Yeongjun Lee ◽  
Young-Sik Shin ◽  
Hyesu Jang ◽  
...  
Keyword(s):  
Object Detection ◽  
Annotation Tool ◽  
Water Object ◽  
Automated Annotation

An automated annotation tool for genomic DNA sequences using GeneScan and BLAST

2001 ◽  
Vol 80 (1) ◽  
pp. 9-16 ◽  
Author(s):  
Andrew M. Lynn ◽  
Chakresh Kumar Jain ◽  
K. Kosalai ◽  
Pranjan Barman ◽  
Nupur Thakur ◽  
...  
Keyword(s):  
Dna Sequences ◽  
Genomic Dna ◽  
Annotation Tool ◽  
Automated Annotation

scholarly journals Fast Machine Learning Annotation in the Medical Domain: A Semi-Automated Video Annotation Tool for Gastroenterologists

2021 ◽  
Author(s):  
Adrian Krenzer ◽  
Kevin Makowski ◽  
Amar Hekalo ◽  
Daniel Fitting ◽  
Joel Troya ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
State Of The Art ◽  
Video Annotation ◽  
Successful Implementation ◽  
Annotation Tool ◽  
Domain Expert ◽  
Domain Experts ◽  
Automated Annotation ◽  
Medical Domain

Abstract Background: Machine learning, especially deep learning, is becoming more and more relevant in research and development in the medical domain. For all of the supervised deep learning applications, data is the most critical factor in securing successful implementation and sustaining the progress of the machine learning model. Especially gastroenterological data, which often involves endoscopic videos, are cumbersome to annotate. Domain experts are needed to interpret and annotate the videos. To support those domain experts, we generated a framework. With this framework, instead of annotating every frame in the video sequence, experts are just performing key annotations at the beginning and the end of sequences with pathologies, e.g. visible polyps. Subsequently, non-expert annotators supported by machine learning add the missing annotations for the frames in-between. Results: Using this framework we were able to reduce work load of domain experts on average by a factor of 20. This is primarily due to the structure of the framework, which is designed to minimize the workload of the domain expert. Pairing this framework with a state-of-the-art semi-automated pre-annotation model enhances the annotation speed further. Through a study with 10 participants we show that semi-automated annotation using our tool doubles the annotation speed of non-expert annotators compared to a well-known state-of-the-art annotation tool. Conclusion: In summary, we introduce a framework for fast expert annotation for gastroenterologists, which reduces the workload of the domain expert considerably while maintaining a very high annotation quality. The framework incorporates a semi-automated annotation system utilizing trained object detection models. The software and framework are open-source.

Sign in / Sign up

Export Citation Format

Share Document