Endoscopy 2022; 54(S 01): S5-S6
DOI: 10.1055/s-0042-1744561
Abstracts | ESGE Days 2022
ESGE Days 2022 Best abstracts
08:15–09:15 Thursday, 28 April 2022 Congress Hall. Opening session with best abstracts

ARTIFICIAL INTELLIGENCE FOR REAL-TIME OPTICAL DIAGNOSIS OF NEOPLASTIC POLYPS DURING COLONOSCOPY

I. Barua
1   Oslo University Hospital, Clinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo, Norway
2   University of Oslo, Clinical Effectiveness Research Group, Oslo, Norway
,
P. Wieszczy
1   Oslo University Hospital, Clinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo, Norway
2   University of Oslo, Clinical Effectiveness Research Group, Oslo, Norway
3   Centre of Postgraduate Medical Education, Department of Gastroenterology, Hepatology and Clinical Oncology, Warsaw, Poland
,
S.-e. Kudo
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
,
M. Misawa
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
,
Ø. Holme
1   Oslo University Hospital, Clinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo, Norway
2   University of Oslo, Clinical Effectiveness Research Group, Oslo, Norway
5   Sørlandet Hospital Kristiansand, Department of Medicine, Kristiansand, Norway
,
S. Gulati
6   King's College Hospital NHS Foundation Trust, King's Institute of Therapeutic Endoscopy, London, United Kingdom
,
S. Williams
6   King's College Hospital NHS Foundation Trust, King's Institute of Therapeutic Endoscopy, London, United Kingdom
,
K. Mori
7   Nagoya University, Graduate School of Informatics, Nagoya, Japan
,
H. Itoh
7   Nagoya University, Graduate School of Informatics, Nagoya, Japan
,
K. Takishima
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
,
K. Mochizuki
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
,
Y. Miyata
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
,
K. Mochida
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
,
Y. Akimoto
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
,
T. Kuroki
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
,
Y. Morita
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
,
O. Shiina
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
,
S. Kato
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
,
T. Nemoto
8   Showa University, Yokohama Northern Hospital, Department of Diagnostic Pathology, School of Medicine, Kanagawa, Japan
,
B. Hayee
6   King's College Hospital NHS Foundation Trust, King's Institute of Therapeutic Endoscopy, London, United Kingdom
,
M. Patel
6   King's College Hospital NHS Foundation Trust, King's Institute of Therapeutic Endoscopy, London, United Kingdom
,
N. Gunasingam
6   King's College Hospital NHS Foundation Trust, King's Institute of Therapeutic Endoscopy, London, United Kingdom
,
A. Kent
6   King's College Hospital NHS Foundation Trust, King's Institute of Therapeutic Endoscopy, London, United Kingdom
,
A. Emmanuel
6   King's College Hospital NHS Foundation Trust, King's Institute of Therapeutic Endoscopy, London, United Kingdom
,
C. Munck
9   Baerum Hospital, Vestre Viken Hospital Trust, Department of Medicine, Gjettum, Norway
,
J.A. Nilsen
9   Baerum Hospital, Vestre Viken Hospital Trust, Department of Medicine, Gjettum, Norway
,
S. Astrup Hvattum
9   Baerum Hospital, Vestre Viken Hospital Trust, Department of Medicine, Gjettum, Norway
,
S.O. Frigstad
9   Baerum Hospital, Vestre Viken Hospital Trust, Department of Medicine, Gjettum, Norway
,
P. Tandberg
9   Baerum Hospital, Vestre Viken Hospital Trust, Department of Medicine, Gjettum, Norway
,
M. Løberg
1   Oslo University Hospital, Clinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo, Norway
2   University of Oslo, Clinical Effectiveness Research Group, Oslo, Norway
,
M. Kalager
1   Oslo University Hospital, Clinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo, Norway
2   University of Oslo, Clinical Effectiveness Research Group, Oslo, Norway
,
A. Haji
6   King's College Hospital NHS Foundation Trust, King's Institute of Therapeutic Endoscopy, London, United Kingdom
,
M. Bretthauer
1   Oslo University Hospital, Clinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo, Norway
2   University of Oslo, Clinical Effectiveness Research Group, Oslo, Norway
,
Y. Mori
1   Oslo University Hospital, Clinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo, Norway
2   University of Oslo, Clinical Effectiveness Research Group, Oslo, Norway
4   Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan
› Author Affiliations
› Further Information
Also available at
 

Aims Artificial intelligence using computer-aided diagnosis (CADx) may enable colonoscopists to distinguish between neoplastic polyps requiring removal and non-neoplastic polyps not requiring removal during colonoscopy. This may reduce costs and resources and prevent polyp overtreatment in colorectal cancer screening.

Methods We performed a multicenter clinical trial comparing a novel CADx system using real-time ultra-magnifying polyp visualization during colonoscopy with standard visual inspection of small (≤5mm in diameter) polyps in the sigmoid colon and the rectum for optical diagnosis of neoplastic histology. All polyps were subsequently removed. The primary endpoint was sensitivity for neoplastic polyps compared to histopathology. Secondary endpoints were specificity and colonoscopist confidence level of optical diagnosis.

Results We assessed 1,289 individuals for eligibility at colonoscopy centers in Norway, the United Kingdom and Japan. We detected 892 eligible polyps in 518 patients and included them in analyses; 359 neoplastic and 533 non-neoplastic. Sensitivity for diagnosis of neoplastic polyps with standard visual inspection was 88.4% (95% confidence interval (CI) 84.3-91.5) compared to 90.4% (95%CI 86.8-93.1) with CADx (p=0.33). Specificity was 83.1% (95%CI 79.2-86.4) with standard visual inspection and 85.9% (95%CI 82.3-88.8) with CADx (p=0.04). The proportion of polyp assessment with high confidence was 74.2% (95%CI 70.9-77.3) with standard visual inspection versus 92.6% (95%CI 90.6-94.3) with CADx (p<0.001).

Table 1

Standard diagnosis

CADx diagnosis

Sensitivity -% (95% CI)

88.4 (84.3-91.5)

90.4 (86.8-93.1)

Specificity -% (95% CI)

83.1 (79.2-86.4)

85.9 (82.3-88.8)

High confidence of optical diagnosis -% (95%CI)

74.2% (70.9-77.3)

92.6% (90.6-94.3)

Conclusions Real-time polyp assessment with CADx did not significantly increase sensitivity for neoplastic polyps, but increased specificity and improved confidence of optical diagnosis.

(UMIN no. 000035213; funding Norwegian Research Council, Norwegian Cancer Society, Japan Society for the Promotion of Science)



Publication History

Article published online:
14 April 2022

© 2022. European Society of Gastrointestinal Endoscopy. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany