DEEP METAMEMORY - A GENERIC FRAMEWORK FOR STABILIZED ONE-SHOT CONFIDENCE ESTIMATION IN DEEP NEURAL NETWORKS AND ITS APPLICATION ON COLORECTAL CANCER LIVER METASTASES GROWTH PREDICTION

Katzmann, Alexander; Muehlberg, Alexander; Suehling, Michael; Noerenberg, Dominik and Gross, Horst-Michael (2019): DEEP METAMEMORY - A GENERIC FRAMEWORK FOR STABILIZED ONE-SHOT CONFIDENCE ESTIMATION IN DEEP NEURAL NETWORKS AND ITS APPLICATION ON COLORECTAL CANCER LIVER METASTASES GROWTH PREDICTION. In: 2019 Ieee 16Th International Symposium on Biomedical Imaging (Isbi 2019): pp. 1298-1302

Abstract

With the rise of deep learning within medical applications, questions about classification confidence become of major interest as misclassifications might have serious impact on human health. While multiple ways of confidence estimation have been proposed, most of them suffer from computational inefficiency or low statistical accuracy. We utilize a modified version of the method introduced by DeVries et al. for one-shot confidence estimation and show its application for colorectal cancer liver metastases growth prediction. Furthermore, we propose a psychologically motivated generalized training framework called "deep metamemory" comparable to the idea of curriculum learning, which utilizes confidence estimation for efficient training augmentation with improved classification performance on unseen data.

• Item Type: Journal article
• Faculties: Medicine
• Subjects: 600 Technology > 610 Medicine and health
• ISSN: 1945-7928
• Language: English