Object-Guided Instance Segmentation for Biological Images

TL;DR

This paper introduces a novel box-based instance segmentation method for biological images that locates objects via center points and uses object features to improve segmentation accuracy, especially in clustered scenarios.

Contribution

The paper presents a new box-based segmentation approach that leverages center point localization and object features to enhance segmentation of clustered biological objects.

Findings

Achieves state-of-the-art performance on biological datasets

Effectively segments clustered objects with preserved details

Outperforms existing box-free methods in accuracy

Abstract

Instance segmentation of biological images is essential for studying object behaviors and properties. The challenges, such as clustering, occlusion, and adhesion problems of the objects, make instance segmentation a non-trivial task. Current box-free instance segmentation methods typically rely on local pixel-level information. Due to a lack of global object view, these methods are prone to over- or under-segmentation. On the contrary, the box-based instance segmentation methods incorporate object detection into the segmentation, performing better in identifying the individual instances. In this paper, we propose a new box-based instance segmentation method. Mainly, we locate the object bounding boxes from their center points. The object features are subsequently reused in the segmentation branch as a guide to separate the clustered instances within an RoI patch. Along with the instance normalization, the model is able to recover the target object distribution and suppress the distribution of neighboring attached objects. Consequently, the proposed model performs excellently in segmenting the clustered objects while retaining the target object details. The proposed method achieves state-of-the-art performances on three biological datasets: cell nuclei, plant phenotyping dataset, and neural cells.