Presentation 2022-07-08
[Short Paper] Unsupervised Domain Adaptation for Liver Tumor Detection in Multi-Phase CT images Using Adversarial Learning with Maximum Square Loss
Rahul Kumar Jain, Takahiro Sato, Taro Watasue, Tomohiro Nakagawa, Yutaro Iwamoto, Xianhua Han, Lanfen Lin, Hongjie Hu, Yen-Wei Chen,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Liver tumor detection in multi-phase CT images is essential in computer-aided diagnosis. Deep learning has been widely used in medical applications. In medical field, acquiring sufficient training data with high quality annotations is a major challenge. To solve the lack of training data issue, domain adaptation-based methods have been developed as a technique to bridge the domain gap across datasets with different feature characteristics and data distributions. This paper presents a domain adaptation-based method for detecting liver tumors in multi-phase CT images. To minimize the domain gap, we employ an adversarial learning scheme with the maximum square loss for mid-level output feature maps using an anchorless detector.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Liver tumor detection / multi-phase CT image / domain adaptation / adversarial learning / maximum square loss
Paper # MI2022-37
Date of Issue 2022-07-01 (MI)

Conference Information
Committee MI
Conference Date 2022/7/8(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English) Medical imaging, recoginition, etc.
Chair Hidekata Hontani(Nagoya Inst. of Tech.)
Vice Chair Hideaki Haneishi(Chiba Univ.) / Takayuki Kitasaka(Aichi Inst. of Tech.)
Secretary Hideaki Haneishi(Yamaguchi Univ.) / Takayuki Kitasaka(Univ. of Hyogo)
Assistant Takeshi Hara(Gifu Univ.) / Yoshito Otake(NAIST)

Paper Information
Registration To Technical Committee on Medical Imaging
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Short Paper] Unsupervised Domain Adaptation for Liver Tumor Detection in Multi-Phase CT images Using Adversarial Learning with Maximum Square Loss
Sub Title (in English)
Keyword(1) Liver tumor detection
Keyword(2) multi-phase CT image
Keyword(3) domain adaptation
Keyword(4) adversarial learning
Keyword(5) maximum square loss
1st Author's Name Rahul Kumar Jain
1st Author's Affiliation Ritsumeikan University(Rahul)
2nd Author's Name Takahiro Sato
2nd Author's Affiliation tiwaki Co. Ltd., Shiga, Japan(Takahiro)
3rd Author's Name Taro Watasue
3rd Author's Affiliation tiwaki Co. Ltd., Shiga, Japan(Taro)
4th Author's Name Tomohiro Nakagawa
4th Author's Affiliation tiwaki Co. Ltd., Shiga, Japan(Tomohiro)
5th Author's Name Yutaro Iwamoto
5th Author's Affiliation Ritsumeikan University, Japan(Yutaro)
6th Author's Name Xianhua Han
6th Author's Affiliation Yamaguchi University, Japan(Xianhua)
7th Author's Name Lanfen Lin
7th Author's Affiliation Zhejiang University, Hangzhou, China(Lanfen)
8th Author's Name Hongjie Hu
8th Author's Affiliation Zhejiang University, Hangzhou, China(Hongjie)
9th Author's Name Yen-Wei Chen
9th Author's Affiliation Ritsumeikan University, Japan(Yen-Wei)
Date 2022-07-08
Paper # MI2022-37
Volume (vol) vol.122
Number (no) MI-98
Page pp.pp.22-23(MI),
#Pages 2
Date of Issue 2022-07-01 (MI)