Presentation information

General Session

General Session » GS-10 AI application

[3F1-GS-10i] AI応用:医療情報

Thu. Jun 10, 2021 9:00 AM - 10:40 AM Room F (GS room 1)

座長:石畠 正和(NTT)

9:00 AM - 9:20 AM

[3F1-GS-10i-01] A study on the selection criteria of medical images requiring human annotation based on uncertainty in semantic segmentation during active learning

〇Kota Ninomiya1, Hiroki Shinohara1, Satoshi Kodera1, Susumu Katsushika1, Mitsuhiko Nakamoto1, Yasutomi Higashikuni1, Katsuhito Fujiu1, Hiroshi Akazawa1, Issei Komuro1 (1. Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo)

Keywords:uncertainty sampling, active learning, semantic segmentation

To build semantic segmentation models for interpretation of medical images, doctors need to make supervised images. Active learning is adopted to decrease annotation cost. However, little is known about the effective allocation of the supervised/un-supervised data during the first and the later training. We investigated the effect of the fluctuation of its allocation using 1463 Intravascular ultrasound images and discussed effective strategies of active learning. We first built three models which used 107, 359, 723 images respectively. Three models were built using 400, 700, 1000 supervised images and images sets predicted by the first models. The result suggests that the same accuracy is reached regardless of the number of the images at the beginning. We concluded that it would be efficient to start training even from a small number of supervised images and build following models using annotated images with higher uncertainty and predicted images.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.