Finding Small-Bowel Lesions: Challenges in Endoscopy-Image-Based Learning Systems

Jungmo Ahn; Huynh Nguyen Loc; Rajesh Krishna Balan; Youngki Lee; Jeonggil Ko

doi:10.1109/MC.2018.2381116

Finding Small-Bowel Lesions: Challenges in Endoscopy-Image-Based Learning Systems

Jungmo Ahn, Huynh Nguyen Loc, Rajesh Krishna Balan, Youngki Lee, Jeonggil Ko

School of Integrated Technology

Research output: Contribution to specialist publication › Article

3 Citations (Scopus)

Abstract

Capsule endoscopy identifies damaged areas in a patient's small intestine but often outputs poor-quality images or misses lesions, leading to either misdiagnosis or repetition of the lengthy procedure. The authors propose applying deep-learning models to automatically process the captured images and identify lesions in real time, enabling the capsule to take additional images of a specific location, adjust its focus level, or improve image quality. The authors also describe the technical challenges in realizing a viable automated capsule-endoscopy system.

Original language	English
Pages	68-76
Number of pages	9
Volume	51
No.	5
Specialist publication	Computer
DOIs	https://doi.org/10.1109/MC.2018.2381116
Publication status	Published - 2018 May

Bibliographical note

Funding Information:
This work was supported by the Korean Ministry of Science and ICT under the ITRC program (IITP-2018-2016-0-00309-002) and also by the DGIST Research and Development Program (CPS Global Center) for the project “Identifying Unmet

All Science Journal Classification (ASJC) codes

Computer Science(all)

Access to Document

10.1109/MC.2018.2381116

Fingerprint Dive into the research topics of 'Finding Small-Bowel Lesions: Challenges in Endoscopy-Image-Based Learning Systems'. Together they form a unique fingerprint.

Cite this

@misc{e62351b228074aa1b744814907af3d7f,

title = "Finding Small-Bowel Lesions: Challenges in Endoscopy-Image-Based Learning Systems",

abstract = "Capsule endoscopy identifies damaged areas in a patient's small intestine but often outputs poor-quality images or misses lesions, leading to either misdiagnosis or repetition of the lengthy procedure. The authors propose applying deep-learning models to automatically process the captured images and identify lesions in real time, enabling the capsule to take additional images of a specific location, adjust its focus level, or improve image quality. The authors also describe the technical challenges in realizing a viable automated capsule-endoscopy system.",

author = "Jungmo Ahn and {Nguyen Loc}, Huynh and {Krishna Balan}, Rajesh and Youngki Lee and Jeonggil Ko",

note = "Funding Information: This work was supported by the Korean Ministry of Science and ICT under the ITRC program (IITP-2018-2016-0-00309-002) and also by the DGIST Research and Development Program (CPS Global Center) for the project “Identifying Unmet",

year = "2018",

month = may,

doi = "10.1109/MC.2018.2381116",

language = "English",

volume = "51",

pages = "68--76",

journal = "ACM SIGPLAN/SIGSOFT Workshop on Program Analysis for Software Tools and Engineering",

issn = "0018-9162",

publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Finding Small-Bowel Lesions

T2 - Challenges in Endoscopy-Image-Based Learning Systems

AU - Ahn, Jungmo

AU - Nguyen Loc, Huynh

AU - Krishna Balan, Rajesh

AU - Lee, Youngki

AU - Ko, Jeonggil

N1 - Funding Information: This work was supported by the Korean Ministry of Science and ICT under the ITRC program (IITP-2018-2016-0-00309-002) and also by the DGIST Research and Development Program (CPS Global Center) for the project “Identifying Unmet

PY - 2018/5

Y1 - 2018/5

N2 - Capsule endoscopy identifies damaged areas in a patient's small intestine but often outputs poor-quality images or misses lesions, leading to either misdiagnosis or repetition of the lengthy procedure. The authors propose applying deep-learning models to automatically process the captured images and identify lesions in real time, enabling the capsule to take additional images of a specific location, adjust its focus level, or improve image quality. The authors also describe the technical challenges in realizing a viable automated capsule-endoscopy system.

AB - Capsule endoscopy identifies damaged areas in a patient's small intestine but often outputs poor-quality images or misses lesions, leading to either misdiagnosis or repetition of the lengthy procedure. The authors propose applying deep-learning models to automatically process the captured images and identify lesions in real time, enabling the capsule to take additional images of a specific location, adjust its focus level, or improve image quality. The authors also describe the technical challenges in realizing a viable automated capsule-endoscopy system.

UR - http://www.scopus.com/inward/record.url?scp=85047769070&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047769070&partnerID=8YFLogxK

U2 - 10.1109/MC.2018.2381116

DO - 10.1109/MC.2018.2381116

M3 - Article

AN - SCOPUS:85047769070

VL - 51

SP - 68

EP - 76

JO - ACM SIGPLAN/SIGSOFT Workshop on Program Analysis for Software Tools and Engineering

JF - ACM SIGPLAN/SIGSOFT Workshop on Program Analysis for Software Tools and Engineering

SN - 0018-9162

ER -