A Preliminary Exploration into an Alternative CellLineNet: An Evolutionary Approach

TL;DR

This paper explores an evolutionary algorithm to automatically design a convolutional neural network, CellLineNet V2, for classifying five types of epithelial breast cell lines, extending previous binary classification work.

Contribution

It introduces EvoCELL, an evolutionary approach to optimize CNN architecture for cell line classification, demonstrating an automated method for neural network design.

Findings

Evolved model achieves accurate classification of five cell line types.

EvoCELL effectively searches architecture space for optimal configurations.

The approach extends previous binary classification models to multiclass tasks.

Abstract

Within this paper, the exploration of an evolutionary approach to an alternative CellLineNet: a convolutional neural network adept at the classification of epithelial breast cancer cell lines, is presented. This evolutionary algorithm introduces control variables that guide the search of architectures in the search space of inverted residual blocks, bottleneck blocks, residual blocks and a basic 2x2 convolutional block. The promise of EvoCELL is predicting what combination or arrangement of the feature extracting blocks that produce the best model architecture for a given task. Therein, the performance of how the fittest model evolved after each generation is shown. The final evolved model CellLineNet V2 classifies 5 types of epithelial breast cell lines consisting of two human cancer lines, 2 normal immortalized lines, and 1 immortalized mouse line (MDA-MB-468, MCF7, 10A, 12A and HC11). The Multiclass Cell Line Classification Convolutional Neural Network extends our earlier work on a Binary Breast Cancer Cell Line Classification model. This paper presents an on-going exploratory approach to neural network architecture design and is presented for further study.