Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy

Download

1-s2.0-S1361841521000487-main.pdf

Date

2021-05-01

Author

Ali, Sharib
Dmitrieva, Mariia
Ghatwary, Noha
Bano, Sophia
Polat, Gorkem
Temizel, Alptekin
Krenzer, Adrian
Hekalo, Amar
Guo, Yun Bo
Matuszewski, Bogdan
Gridach, Mourad
Voiculescu, Irina
Yoganand, Vishnusai
Chavan, Arnav
Raj, Aryan
Nguyen, Nhan T.
Tran, Dat Q.
Huynh, Le Duy
Boutry, Nicolas
Rezvy, Shahadate
Chen, Haijian
Choi, Yoon Ho
Subramanian, Anand
Balasubramanian, Velmurugan
Gao, Xiaohong W.
Hu, Hongyu
Liao, Yusheng
Stoyanov, Danail
Daul, Christian
Realdon, Stefano
Cannizzaro, Renato
Lamarque, Dominique
Tran-Nguyen, Terry
Bailey, Adam
Braden, Barbara
East, James E.
Rittscher, Jens

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

270
views

77
downloads

The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identifying subtle precancerous precursors and cancer abnormalities. Artefacts often affect the robustness of deep learning methods applied to the gastrointestinal tract organs as they can be confused with tissue of interest. EndoCV2020 challenges are designed to address research questions in these remits. In this paper, we present a summary of methods developed by the top 17 teams and provide an objective comparison of state-of-the-art methods and methods designed by the participants for two sub-challenges: i) artefact detection and segmentation (EAD2020), and ii) disease detection and segmentation (EDD2020). Multi-center, multi-organ, multi-class, and multi-modal clinical endoscopy datasets were compiled for both EAD2020 and EDD2020 sub-challenges. The out-of-sample generalization ability of detection algorithms was also evaluated. Whilst most teams focused on accuracy improvements, only a few methods hold credibility for clinical usability. The best performing teams provided solutions to tackle class imbalance, and variabilities in size, origin, modality and occurrences by exploring data augmentation, data fusion, and optimal class thresholding techniques.

Subject Keywords

Artefact, Challenge, Deep learning, Detection, Gastroenterology, Segmentation

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85101620260&origin=inward
https://hdl.handle.net/11511/89908

Journal

Medical Image Analysis

DOI

https://doi.org/10.1016/j.media.2021.102002

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

Deep Learning-Enabled Technologies for Bioimage Analysis Rabbi, Fazle; Dabbagh, Sajjad Rahmani; Angın, Pelin; Yetisen, Ali Kemal; Tasoglu, Savas (2022-02-01) Deep learning (DL) is a subfield of machine learning (ML), which has recently demon-strated its potency to significantly improve the quantification and classification workflows in bio-medical and clinical applications. Among the end applications profoundly benefitting from DL, cellular morphology quantification is one of the pioneers. Here, we first briefly explain fundamental concepts in DL and then we review some of the emerging DL-enabled applications in cell morphology quantification in the fields of em...
Deep learning for the classification of bipolar disorder using fNIRS measurements Evgin, Haluk Barkın; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2021-2-3) Functional Near-Infrared Spectroscopy (fNIRS) is a neural imaging method that is proved to be prominent in the classification of psychiatric disorders, and assertive accuracy results are being obtained using fNIRS. High temporal resolution, feasibility, and partial endurance to head movements are the traits that are highlighting fNIRS among other imaging methods. fNIRS data is a one dimensional multi-channeled time series. In this thesis, bipolar disorder is classified using some state of the art deep learn...
Evaluation and Analysis of Different Aggregation and Hyperparameter Selection Methods for Federated Brain Tumor Segmentation Polat, Görkem; Işık Polat, Ece; Koçyiğit, Altan; Temizel, Alptekin (2021-9-27) Availability of large, diverse, and multi-national datasets is crucial for the development of effective and clinically applicable AI systems in the medical imaging domain. However, forming a global model by bringing these datasets together at a central location, comes along with various data privacy and ownership problems. To alleviate these problems, several recent studies focus on the federated learning paradigm, a distributed learning approach for decentralized data. Federated learning leverages all the ...
Intelligent healthcare monitoring system based on semantically enriched clinical guidelines Laleci, Gökçe Banu; Doğaç, Asuman; Department of Computer Engineering (2008) Clinical guidelines are developed to assist healthcare practitioners to make decisions on a patient's medical problems and as such they communicate with external applications to retrieve patient data, to initiate medical actions through clinical workflows and to transmit information to alert/reminder systems. The interoperability problems in the healthcare IT domain for interacting with heterogeneous clinical workflow systems and Electronic Healthcare Record (EHR) Systems prevent wider deployment of clinica...
A Semantically Enriched Clinical Guideline Model Enabling Deployment in Heterogeneous Healthcare Environments Laleci, Gokce B.; Doğaç, Asuman (Institute of Electrical and Electronics Engineers (IEEE), 2009-03-01) Clinical guidelines are developed to assist healthcare practitioners to make decisions on patient's medical problems, and as such they communicate with external applications to retrieve patient data to initiate medical actions through clinical workflows, and transmit information to alert/reminder systems. The interoperability problems in the healthcare information technology domain prevent wider deployment of clinical guidelines because each deployment requires a tedious custom adaptation phase. In this pap...

Citation Formats

S. Ali et al., “Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy,” Medical Image Analysis, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85101620260&origin=inward.