Dual-View Selective Instance Segmentation Network for Unstained Live Adherent Cells in Differential Interference Contrast Images

TL;DR

This paper introduces DVSISN, a novel deep-learning approach that effectively segments unstained live adherent cells in DIC images by using dual-view and mask selection techniques, significantly improving segmentation accuracy.

Contribution

The paper presents a new dual-view selective instance segmentation network that leverages rotated images and mask filtering to enhance cell segmentation in challenging DIC images.

Findings

Achieved an AP_segm of 0.555, surpassing benchmarks by 23.6%.

Demonstrated the effectiveness of rotated images in improving segmentation.

Validated on a dataset of 520 images and 12,198 cells.

Abstract

Despite recent advances in data-independent and deep-learning algorithms, unstained live adherent cell instance segmentation remains a long-standing challenge in cell image processing. Adherent cells' inherent visual characteristics, such as low contrast structures, fading edges, and irregular morphology, have made it difficult to distinguish from one another, even by human experts, let alone computational methods. In this study, we developed a novel deep-learning algorithm called dual-view selective instance segmentation network (DVSISN) for segmenting unstained adherent cells in differential interference contrast (DIC) images. First, we used a dual-view segmentation (DVS) method with pairs of original and rotated images to predict the bounding box and its corresponding mask for each cell instance. Second, we used a mask selection (MS) method to filter the cell instances predicted by the DVS to keep masks closest to the ground truth only. The developed algorithm was trained and validated on our dataset containing 520 images and 12198 cells. Experimental results demonstrate that our algorithm achieves an AP_segm of 0.555, which remarkably overtakes a benchmark by a margin of 23.6%. This study's success opens up a new possibility of using rotated images as input for better prediction in cell images.