Decision Boundary Re-Sampling in Imbalanced Learning for Ulcer Detection

Data imbalance problem between normal and lesion endoscopy images makes it difficult to employ deep learning approaches in automatic Ulcer detection and classification. Due to the large variety of normal images in their appearance, characterizing ulcer with limited training samples is not a trivial...

Full description

Bibliographic Details
Main Authors:	Changhoo Lee, Dongwook Shin, Junki Min, Jaemyung Cha, Seungkyu Lee
Format:	Article
Language:	English
Published:	IEEE 2020-01-01
Series:	IEEE Access
Subjects:	Decision boundary re-sampling convolutional neural network ulcer classification
Online Access:	https://ieeexplore.ieee.org/document/9216051/

id	doaj-325264c1cb404c2d9d255edfc97b5f1e
record_format	Article
spelling	doaj-325264c1cb404c2d9d255edfc97b5f1e2021-03-30T04:39:09ZengIEEEIEEE Access2169-35362020-01-01818627418627810.1109/ACCESS.2020.30292599216051Decision Boundary Re-Sampling in Imbalanced Learning for Ulcer DetectionChanghoo Lee0Dongwook Shin1https://orcid.org/0000-0003-1430-8869Junki Min2Jaemyung Cha3Seungkyu Lee4https://orcid.org/0000-0002-9721-4093Department of Computer Science and Engineering, Kyung Hee University, Yongin, South KoreaDepartment of Computer Science and Engineering, Kyung Hee University, Yongin, South KoreaDepartment of Internal Medicine, Kyung Hee University, Seoul, South KoreaDepartment of Internal Medicine, Kyung Hee University, Seoul, South KoreaDepartment of Computer Science and Engineering, Kyung Hee University, Yongin, South KoreaData imbalance problem between normal and lesion endoscopy images makes it difficult to employ deep learning approaches in automatic Ulcer detection and classification. Due to the large variety of normal images in their appearance, characterizing ulcer with limited training samples is not a trivial task. In this work, we propose decision boundary re-sampling (DBR) in imbalanced learning that extrapolates ulcer samples in a latent space of deep convolutional neural network. Proposed method shows improved ulcer classification performance on wireless endoscopy images compared to state-of-the-art methods.https://ieeexplore.ieee.org/document/9216051/Decision boundary re-samplingconvolutional neural networkulcer classification
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Changhoo Lee Dongwook Shin Junki Min Jaemyung Cha Seungkyu Lee
spellingShingle	Changhoo Lee Dongwook Shin Junki Min Jaemyung Cha Seungkyu Lee Decision Boundary Re-Sampling in Imbalanced Learning for Ulcer Detection IEEE Access Decision boundary re-sampling convolutional neural network ulcer classification
author_facet	Changhoo Lee Dongwook Shin Junki Min Jaemyung Cha Seungkyu Lee
author_sort	Changhoo Lee
title	Decision Boundary Re-Sampling in Imbalanced Learning for Ulcer Detection
title_short	Decision Boundary Re-Sampling in Imbalanced Learning for Ulcer Detection
title_full	Decision Boundary Re-Sampling in Imbalanced Learning for Ulcer Detection
title_fullStr	Decision Boundary Re-Sampling in Imbalanced Learning for Ulcer Detection
title_full_unstemmed	Decision Boundary Re-Sampling in Imbalanced Learning for Ulcer Detection
title_sort	decision boundary re-sampling in imbalanced learning for ulcer detection
publisher	IEEE
series	IEEE Access
issn	2169-3536
publishDate	2020-01-01
description	Data imbalance problem between normal and lesion endoscopy images makes it difficult to employ deep learning approaches in automatic Ulcer detection and classification. Due to the large variety of normal images in their appearance, characterizing ulcer with limited training samples is not a trivial task. In this work, we propose decision boundary re-sampling (DBR) in imbalanced learning that extrapolates ulcer samples in a latent space of deep convolutional neural network. Proposed method shows improved ulcer classification performance on wireless endoscopy images compared to state-of-the-art methods.
topic	Decision boundary re-sampling convolutional neural network ulcer classification
url	https://ieeexplore.ieee.org/document/9216051/
work_keys_str_mv	AT changhoolee decisionboundaryresamplinginimbalancedlearningforulcerdetection AT dongwookshin decisionboundaryresamplinginimbalancedlearningforulcerdetection AT junkimin decisionboundaryresamplinginimbalancedlearningforulcerdetection AT jaemyungcha decisionboundaryresamplinginimbalancedlearningforulcerdetection AT seungkyulee decisionboundaryresamplinginimbalancedlearningforulcerdetection
_version_	1724181412759732224

Decision Boundary Re-Sampling in Imbalanced Learning for Ulcer Detection

Similar Items