A novel framework employing deep multi-attention channels network for the autonomous detection of metastasizing cells through fluorescence microscopy

TL;DR

This paper introduces a deep multi-attention channels network framework for accurately distinguishing normal and metastasizing cells in fluorescence microscopy images, enhancing interpretability and understanding of cytoskeletal changes during cancer progression.

Contribution

The study presents a novel multi-attention channel architecture combined with global explainability techniques for improved, interpretable classification of metastatic cells from microscopy images.

Findings

Achieved high accuracy in classifying normal and metastasizing cells.

Provided detailed insights into cytoskeletal changes during oncogenic transformation.

Suggested potential spatial biomarkers for metastasis detection.

Abstract

We developed a transparent computational large-scale imaging-based framework that can distinguish between normal and metastasizing human cells. The method relies on fluorescence microscopy images showing the spatial organization of actin and vimentin filaments in normal and metastasizing single cells, using a combination of multi-attention channels network and global explainable techniques. We test a classification between normal cells (Bj primary fibroblast), and their isogenically matched, transformed and invasive counterpart (BjTertSV40TRasV12). Manual annotation is not trivial to automate due to the intricacy of the biologically relevant features. In this research, we utilized established deep learning networks and our new multi-attention channel architecture. To increase the interpretability of the network - crucial for this application area - we developed an interpretable global explainable approach correlating the weighted geometric mean of the total cell images and their local GradCam scores. The significant results from our analysis unprecedently allowed a more detailed, and biologically relevant understanding of the cytoskeletal changes that accompany oncogenic transformation of normal to invasive and metastasizing cells. We also paved the way for a possible spatial micrometre-level biomarker for future development of diagnostic tools against metastasis (spatial distribution of vimentin).