UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Foveation for Segmentation of Mega-Pixel Histology Images

Jin, C; Tanno, R; Xu, M; Mertzanidou, T; Alexander, DC; (2020) Foveation for Segmentation of Mega-Pixel Histology Images. In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. (pp. pp. 561-571). Springer Nature: Cham, Switzerland. Green open access

[thumbnail of paper1822.pdf]
Preview
Text
paper1822.pdf - Accepted version

Download (2MB) | Preview

Abstract

Segmenting histology images is challenging because of the sheer size of the images with millions or even billions of pixels. Typical solutions pre-process each histology image by dividing it into patches of fixed size and/or down-sampling to meet memory constraints. Such operations incur information loss in the field-of-view (FoV) (i.e., spatial coverage) and the image resolution. The impact on segmentation performance is, however, as yet understudied. In this work, we first show under typical memory constraints (e.g., 10G GPU memory) that the trade-off between FoV and resolution considerably affects segmentation performance on histology images, and its influence also varies spatially according to local patterns in different areas (see Fig. 1). Based on this insight, we then introduce foveation module, a learnable “dataloader” which, for a given histology image, adaptively chooses the appropriate configuration (FoV/resolution trade-off) of the input patch to feed to the downstream segmentation model at each spatial location (Fig. 1). The foveation module is jointly trained with the segmentation network to maximise the task performance. We demonstrate, on the Gleason2019 challenge dataset for histopathology segmentation, that the foveation module improves segmentation performance over the cases trained with patches of fixed FoV/resolution trade-off. Moreover, our model achieves better segmentation accuracy for the two most clinically important and ambiguous classes (Gleason Grade 3 and 4) than the top performers in the challenge by 13.1% and 7.5%, and improves on the average performance of 6 human experts by 6.5% and 7.5%.

Type: Proceedings paper
Title: Foveation for Segmentation of Mega-Pixel Histology Images
Event: 23rd International Conference: International Conference on Medical Image Computing and Computer-Assisted Intervention
ISBN-13: 978-3-030-59721-4
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-030-59722-1_54
Publisher version: https://doi.org/10.1007/978-3-030-59722-1_54
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10113531
Downloads since deposit
158Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item