Shoichi Yoshimizu

Shoichi Yoshimizu

Auto-generated profile, based on publicly available information

Shoichi Yoshimizu

Department of Gastroenterology Cancer Institute Hospital, Japanese Foundation for Cancer Research Tokyo Japan

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 April 2020 in Digestive Endoscopy
Verified
Journal Article
Open access
PDF file
YIYohei Ikenoyama
Yohei Ikenoyama
THToshiaki Hirasawa
Toshiaki Hirasawa
MIMitsuaki Ishioka
Mitsuaki Ishioka
KNKen Namikawa
Ken Namikawa
SYShoichi Yoshimizu
Shoichi Yoshimizu
TTTomohiro Tada
Tomohiro Tada
Objectives: Detecting early gastric cancer is difficult, and it may even be overlooked by experienced endoscopists. Recently, artificial intelligence based on deep learning through convolutional neural networks (CNNs) has enabled significant advancements in the field of gastroenterology. However, it remains unclear whether a CNN can outperform endoscopists. In this study, we evaluated whether the performance of a CNN in detecting early gastric cancer is better than that of endoscopists.Methods: The CNN was constructed using 13,584 endoscopic images from 2639 lesions of gastric cancer. Subsequently, its diagnostic ability was compared to that of 67 endoscopists using an independent test dataset (2940 images from 140 cases).Results: The average diagnostic time for analyzing 2940 test endoscopic images by the CNN and endoscopists were 45.5 ± 1.8 s and 173.0 ± 66.0 min, respectively. The sensitivity, specificity, and positive and negative predictive values for the CNN were 58.4%, 87.3%, 26.0%, and 96.5%, respectively. These values for the 67 endoscopists were 31.9%, 97.2%, 46.2%, and 94.9%, respectively. The CNN had a significantly higher sensitivity than the endoscopists (by 26.5%; 95% confidence interval, 14.9–32.5%).Conclusion: The CNN detected more early gastric cancer cases in a shorter time than the endoscopists. The CNN needs further training to achieve higher diagnostic accuracy. However, a diagnostic support tool for gastric cancer using a CNN will be realized in the near future.

8 September 2021 in Endoscopy
Verified
Journal Article
Closed access
PDF file
MKMotohiko Kato
Motohiko Kato
YTYoji Takeuchi
Yoji Takeuchi
SHShu Hoteya
Shu Hoteya
TOTsuneo Oyama
Tsuneo Oyama
SNSatoru Nonaka
Satoru Nonaka
NYNaohisa Yahagi
Naohisa Yahagi
Background Data on endoscopic resection (ER) for superficial duodenal epithelial tumors (SDETs) are insufficient owing to their rarity. There are two main ER techniques for SDETs: endoscopic mucosal resection (EMR) and endoscopic submucosal dissection (ESD). In addition, modified EMR techniques, such as underwater EMR (UEMR) and cold polypectomy, are becoming popular. We conducted a large-scale retrospective multicenter study to clarify the detailed outcomes of duodenal ER. Methods Patients with SDETs who underwent ER at 18 institutions from January 2008 to December 2018 were included. The rates of en bloc resection and delayed adverse events (AEs; defined as delayed bleeding or perforation) were analyzed. Local recurrence was analyzed using the Kaplan–Meier method. Results In total, 3107 patients (including 1017 undergoing ESD) were included. En bloc resection rates were 79.1 %, 78.6 %, 86.8 %, and 94.8 %, and delayed AE rates were 0.5 %, 2.2 %, 2.8 %, and 6.8 % for cold polypectomy, UEMR, EMR and ESD, respectively. The delayed AE rate was significantly higher in the ESD group than in non-ESD groups for lesions < 19 mm (7.4 % vs. 1.9 %; P < 0.001), but not for lesions > 20 mm (6.1 % vs. 7.1 %; P = 0.64). The local recurrence rate was significantly lower in the ESD group than in the non-ESD groups (P < 0.001). Furthermore, for lesions > 30 mm, the cumulative local recurrence rate at 2 years was 22.6 % in the non-ESD groups compared with only 1.6 % in the ESD group (P < 0.001). Conclusions ER outcomes for SDETs were generally acceptable. ESD by highly experienced endoscopists might be an option for very large SDETs.

16 February 2020 in Digestive Endoscopy
Verified
Journal Article
Closed access
PDF file
ATAtsuko Tamashiro
Atsuko Tamashiro
TYToshiyuki Yoshio
Toshiyuki Yoshio
AIAkiyoshi Ishiyama
Akiyoshi Ishiyama
TTTomohiro Tsuchida
Tomohiro Tsuchida
KHKazunori Hijikata
Kazunori Hijikata
TTTomohiro Tada
Tomohiro Tada

2 October 2021 in Digestive Endoscopy
Verified
Journal Article
Closed access
PDF file
SNSakiko Naito
Sakiko Naito
TYToshiyuki Yoshio
Toshiyuki Yoshio
AIAkiyoshi Ishiyama
Akiyoshi Ishiyama
TTTomohiro Tsuchida
Tomohiro Tsuchida
JTJunki Tokura
Junki Tokura
JFJunko Fujisaki
Junko Fujisaki

8 October 2018 in Endoscopy International Open
Verified
Journal Article
Open access
PDF file
SYShoichi Yoshimizu
Shoichi Yoshimizu
THToshiaki Hirasawa
Toshiaki Hirasawa
YHYusuke Horiuchi
Yusuke Horiuchi
MOMasami Omae
Masami Omae
AIAkiyoshi Ishiyama
Akiyoshi Ishiyama
JFJunko Fujisaki
Junko Fujisaki
Background and study aims Esophagogastroduodenoscopy (EGD) has utility in early detection of upper gastrointestinal (UGI) neoplasms. However, previous studies report shorter inspection times and inexperienced endoscopists contribute to overlooking gastric neoplasms. We investigated neoplasm detection rates according to inspection time and extent of EGD training. Patients and methods In this retrospective observational study, we reviewed routine EGDs for 3,925 consecutive cases between October 2014 and March 2015. We divided the endoscopists into three groups based on median inspection time during EGD without undergoing biopsy. Using cut-off median inspection times of 7 and 10 minutes, three, five, and eight endoscopists were classified into the fast, moderate, and slow groups, respectively. We compared detection rates according to inspection time and the extent of EGD training. Results The median inspection time among all endoscopists was 9.3 minutes (range, 6.6 – 12.0 min). The detection rate for UGI neoplasms was as follows: fast group, 3.6%; moderate group, 3.3 %; and slow group, 3.1 % (P = 0.807). The median inspection time was significantly shorter among the intensive training ≥ 1-year group than among the < 1-year group (< 1-year: median 6.3 min; range 8.2 – 13.9 min, ≥ 1-year: median 8.9 min; range 6.4 – 11.4 min, P < 0.001). The detection rate for UGI neoplasms was significantly higher among the intensive training ≥ 1-year group than among the < 1-year group (< 1-year: 2.2 %; ≥ 1-year: 3.7 %, OR = 1.65, 95 % CI: 1.02 – 2.68, P = 0.041). Conclusions There was no association between inspection times and neoplasm detection rates. The quality of EGD, as measured by neoplasm detection rates, may be improved by ≥ 1-year of intensive training.

1 August 2018 in Digestive and Liver Disease
Verified
Journal Article
Closed access
SYShoichi Yoshimizu
Shoichi Yoshimizu
TYToshiyuki Yoshio
Toshiyuki Yoshio
AIAkiyoshi Ishiyama
Akiyoshi Ishiyama
TTTomohiro Tsuchida
Tomohiro Tsuchida
YHYusuke Horiuchi
Yusuke Horiuchi
JFJunko Fujisaki
Junko Fujisaki