Presentation 2021-11-05
[Short Paper] Prediction of therapeutic response in Sjogren's syndrome using ultrasound images of parotid glands
Kohei Fujiwara, Takeda Keita, Yukinori Takagi, Miho Sasaki, Sato Eida, Ikuo Katayama, Misa Sumi, Tomoya Sakai,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The purpose of this study was to predict the response to treatment of SS from ultrasound (US) images of salivary glands in patients with Sj?gren's syndrome (SS), a chronic inflammation of the salivary glands, and to assist physicians in their diagnosis. Based on the visual characteristics of the US images of the salivary glands of SS patients, physicians have an educated guess as to the extent to which the patient's saliva volume will recover after treatment. Therefore, we propose a method to create a convolutional neural network (CNN) that predicts the increase in saliva secretion after treatment based on the US images of salivary glands taken at the time of initial examination, and to calculate the amount of saliva secretion after treatment by adding it to the amount of saliva secretion at the time of initial examination. In addition, SS is considered to have a significant decrease in saliva volume if the saliva volume is less than 2.0g/2min. In this paper, we report that the proposed method was effective in predicting the increase in saliva secretion after treatment by CNN, and that the proposed method also showed significant results when the saliva secretion after treatment was classified into two classes: whether it was less than 2.0g or not.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Sjogren's syndrome / ultrasonography / convolutional neural network / transfer learning / regression analysis
Paper # MICT2021-30,MI2021-28
Date of Issue 2021-10-29 (MICT, MI)

Conference Information
Committee MI / MICT
Conference Date 2021/11/5(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Medical imaging technology, healthcare and medical information communication technology
Chair Hidekata Hontani(Nagoya Inst. of Tech.) / Eisuke Hanada(Saga Univ.)
Vice Chair Hideaki Haneishi(Chiba Univ.) / Takayuki Kitasaka(Aichi Inst. of Tech.) / Hirokazu Tanaka(Hiroshima City Univ.) / Daisuke Anzai(Nagoya Inst. of Tech.)
Secretary Hideaki Haneishi(Yamaguchi Univ.) / Takayuki Kitasaka(Univ. of Hyogo) / Hirokazu Tanaka(Yokohama National Univ.) / Daisuke Anzai(KISTEC)
Assistant Hotaka Takizawa(Tsukuba Univ.) / Yoshito Otake(NAIST) / Takahiro Ito(Hiroshima City Univ) / Kento Takabayashi(Okayama Pref. Univ.) / Takuya Nishikawa(National Cerebral and Cardiovascular Center Hospital)

Paper Information
Registration To Technical Committee on Medical Imaging / Technical Committee on Healthcare and Medical Information Communication Technology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Short Paper] Prediction of therapeutic response in Sjogren's syndrome using ultrasound images of parotid glands
Sub Title (in English)
Keyword(1) Sjogren's syndrome
Keyword(2) ultrasonography
Keyword(3) convolutional neural network
Keyword(4) transfer learning
Keyword(5) regression analysis
1st Author's Name Kohei Fujiwara
1st Author's Affiliation Nagasaki University(Nagasaki Univ.)
2nd Author's Name Takeda Keita
2nd Author's Affiliation Nagasaki University(Nagasaki Univ.)
3rd Author's Name Yukinori Takagi
3rd Author's Affiliation Nagasaki University(Nagasaki Univ.)
4th Author's Name Miho Sasaki
4th Author's Affiliation Nagasaki University(Nagasaki Univ.)
5th Author's Name Sato Eida
5th Author's Affiliation Nagasaki University(Nagasaki Univ.)
6th Author's Name Ikuo Katayama
6th Author's Affiliation Nagasaki University(Nagasaki Univ.)
7th Author's Name Misa Sumi
7th Author's Affiliation Nagasaki University(Nagasaki Univ.)
8th Author's Name Tomoya Sakai
8th Author's Affiliation Nagasaki University(Nagasaki Univ.)
Date 2021-11-05
Paper # MICT2021-30,MI2021-28
Volume (vol) vol.121
Number (no) MICT-230,MI-231
Page pp.pp.15-16(MICT), pp.15-16(MI),
#Pages 2
Date of Issue 2021-10-29 (MICT, MI)