Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

© 2020, Springer Nature Switzerland AG. Endoscopy is a widely used imaging modality to diagnose and treat diseases in gastrointestinal tract. However, varied modalities and use of different imaging protocols at various clinical centers impose significant challenges when generalising deep learning models. Moreover, the assembly of large datasets from different clinical centers can introduce a huge label biases in multi-center studies that renders any learnt model unusable. Additionally, when using new modality or presence of images with rare pattern abnormalities such as dysplasia; a bulk amount of similar image data and their corresponding labels may not be available for training these models. In this work, we propose to use a few-shot learning approach that requires less training data and can be used to predict class labels of test samples from an unseen dataset. We propose a novel additive angular margin metric in the framework of the prototypical network in few-shot learning setting. We compare our approach to the several established methods on a large cohort of multi-center, multi-organ, multi-disease, and multi-modal gastroendoscopy data. The proposed algorithm outperforms existing state-of-the-art methods.

Original publication




Conference paper

Publication Date



12436 LNCS


494 - 503