Endoscopy 2022; 54(S 01): S26
DOI: 10.1055/s-0042-1744609
Abstracts | ESGE Days 2022
ESGE Days 2022 Oral presentations
13:30–14:30 Thursday, 28 April 2022 Club A. Esophageal early cancer: Is ESD ready to take on the challenge?

A COMPUTER-ASSISTED AUTOMATED APPORACH FOR OPTICAL CLASSIFICATION OF COLORECTAL POLYPS INCLUDING SERRATED ADENOMAS – THE CASSANDRA STUDY

P. Klare
1   Krankenhaus Agatharied, Abteilung Gastroenterologie, Diabetologie und Hämato-/Onkologie, Hausham, Germany
2   Klinikum rechts der Isar der Technischen Universität München, Klinik und Poliklinik für Innere Medizin II, Munich, Germany
,
R.D Soberanis-Mukul
3   Technische Universität München, Chair of Computer Aided Medical Procedures and Augmented Reality, Garching, Germany
,
B. Haller
4   Klinikum rechts der Isar der Technischen Universität München, Institut für Medizinische Informatik, Statistik und Epidemiologie, Munich, Germany
,
B. Walter
5   Universitätsklinikum Ulm, Innere Medizin I, Ulm, Germany
,
T. Rath
6   Universitätsklinikum Erlangen, Medizinische Klinik 1, Erlangen, Germany
,
S. Albarquoni
3   Technische Universität München, Chair of Computer Aided Medical Procedures and Augmented Reality, Garching, Germany
,
N. Navab
3   Technische Universität München, Chair of Computer Aided Medical Procedures and Augmented Reality, Garching, Germany
,
A. Poszler
1   Krankenhaus Agatharied, Abteilung Gastroenterologie, Diabetologie und Hämato-/Onkologie, Hausham, Germany
,
R.M. Schmid
2   Klinikum rechts der Isar der Technischen Universität München, Klinik und Poliklinik für Innere Medizin II, Munich, Germany
,
A.-M. Zvereva
2   Klinikum rechts der Isar der Technischen Universität München, Klinik und Poliklinik für Innere Medizin II, Munich, Germany
› Author Affiliations
› Further Information
Also available at
 

Aims Computer-assisted models (CAM) aim to differntiate neoplastic and non-neoplastic polyps based on their optical features. However, differentiation of serrated adenomas (SA) from hyperplastic polyps (HP) and adenomas (AD) is still challenging. We aspired to develop a CAM for automated polyp classification between said polyp classes.

Methods Polyps of 250 patients were resected. Histological diagnoses were used as reference standard. A total of 489 videos of 327 polyps were recorded. Of these, 191 videos were used for CAM development. CAM corresponds to a region proposal deep neural network based on the RetinaNet architecture trained for recognizing the three classes (Figure1). After development, 100 new polyps were presented to CAM in order to test the program. The 100 test polyps were also presented to two experts (E1, E2). We compared CAP-based and human accuracy. Primary endpoint of the study was CAM-based accuracy.

Zoom Image
Fig. 1

Results

Table 1

Factor

Computer

Expert 1

Expert2

Sensitivity for SA

6.7% (1/15)

60.0% (9/15)

60.0% (9/15)

NPV for SA

85.9% (85/99)

90.8% (59/65)

91.9% (68/74)

Specificity for SA

100.0% (85/85)

69.4% (59/85)

80.0% (68/85)

PPV for SA

100.0% (1/1)

25.7% (9/35)

34.6% (9/26)

CAM-based accuracy regarding the prediction of SA was 86.0%. Sensitivity and negative predictive value (NPV) were 6.7% and 85.9%. CAM-based accuracy of SA prediction was higher compared to E1 (86.0 vs. 68.0%, p=0.004). For adenoma prediction CAM-based accuracy, sensitivity and NPV was 57.0%, 96.0% and 81.8%. Experts accuracies for adenoma prediction surpassed CAM-based accuracy (p=0.001 respectively). Inter-rater agreement of optical predictions was good between both experts (72% agreement k=0.58).

Conclusions An automated, computer assisted differentiation of SA from HP or AD is feasible. However, differentiating three different polyp classes seems to pose challenges to the CAM approach. More video data is needed in order to refine the CAM.



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