Learning to Segment Fine Structures Under Image-Level Supervision With an Application to Nematode Segmentation

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 2022, pp. 2128–2131

Abstract

Image segmentation models trained only with image-level labels have become increasingly popular as they require significantly less annotation effort than models trained with scribble, bounding box or pixel-wise annotations. While methods utilizing image-level labels achieve promising performance for the segmentation of larger-scale objects, they perform less well for the fine structures frequently encountered in biological images. In order to address this performance gap, we propose a deep network architecture based on two key principles, Global Weighted Pooling (GWP) and segmentation refinement by low-level image cues, that, together, make segmentation of fine structures possible. We apply our segmentation method to image datasets containing such fine structures, nematodes (worms + eggs) and nematode cysts immersed in organic debris objects, which is an application scenario encountered in automated soil sample screening. Supervised only with image-level labels, our approach achieves Dice coefficients of 79.72% and 58.51 % for nematode and nematode cyst segmentation, respectively.

Authors 6

1. Long Chen Aachen Imaging and Computer Vision

   RWTH Aachen University

   Affiliation as printed

   Imaging and Computer Vision, RWTH Aachen University,Aachen,Germany

   Imaging and Computer Vision, RWTH Aachen University, Aachen, Germany

2. Martin Strauch Aachen Imaging and Computer Vision

   RWTH Aachen University

   Affiliation as printed

   Imaging and Computer Vision, RWTH Aachen University,Aachen,Germany

   Imaging and Computer Vision, RWTH Aachen University, Aachen, Germany

3. Matthias Daub

   Julius Kühn-Institut

   Affiliation as printed

   Julius Kühn Institute: Federal Research Centre for Cultivated Plants,Elsdorf,Germany

4. Hans-Georg Luigs
   Affiliation as printed

   LemnaTec GmbH,Aachen,Germany

   LemnaTec GmbH, Aachen, Germany

5. Marcus Jansen
   Affiliation as printed

   LemnaTec GmbH,Aachen,Germany

   LemnaTec GmbH, Aachen, Germany

6. Dorit Merhof Aachen Imaging and Computer Vision

   RWTH Aachen University

   Affiliation as printed

   Imaging and Computer Vision, RWTH Aachen University,Aachen,Germany

   Imaging and Computer Vision, RWTH Aachen University, Aachen, Germany