Blurry-Consistency Segmentation Framework with Selective Stacking on Differential Interference Contrast 3D Breast Cancer Spheroid

TL;DR

This paper introduces a novel deep learning framework that effectively handles blurry images in 3D breast cancer spheroid imaging, improving segmentation accuracy through a unique training architecture and self-training mechanisms.

Contribution

It presents a new algorithm for blurry image handling and a specialized training architecture leveraging consistency and self-training to enhance 3D cell segmentation.

Findings

Improved segmentation accuracy on blurry 3D images

Enhanced model stability under sparse-slice stacking

Effective combination of blurring handling and training strategies

Abstract

The ability of three-dimensional (3D) spheroid modeling to study the invasive behavior of breast cancer cells has drawn increased attention. The deep learning-based image processing framework is very effective at speeding up the cell morphological analysis process. Out-of-focus photos taken while capturing 3D cells under several z-slices, however, could negatively impact the deep learning model. In this work, we created a new algorithm to handle blurry images while preserving the stacked image quality. Furthermore, we proposed a unique training architecture that leverages consistency training to help reduce the bias of the model when dense-slice stacking is applied. Additionally, the model's stability is increased under the sparse-slice stacking effect by utilizing the self-training approach. The new blurring stacking technique and training flow are combined with the suggested architecture and self-training mechanism to provide an innovative yet easy-to-use framework. Our methods produced noteworthy experimental outcomes in terms of both quantitative and qualitative aspects.