# TUNet: Incorporating segmentation maps to improve classification

## TL;DR

This paper introduces TUNet, a novel deep learning model that incorporates segmentation maps to enhance protein classification accuracy in fluorescence microscopy images, demonstrating competitive results against established models.

## Contribution

The paper presents TUNet, a new model that integrates segmentation information to improve protein classification in microscopy images, advancing current deep learning approaches.

## Key findings

- TUNet achieves competitive classification performance.
- Incorporating segmentation maps improves accuracy.
- Compared with GoogleNet and ResNet, TUNet shows promising results.

## Abstract

Determining the localization of specific protein in human cells is important for understanding cellular functions and biological processes of underlying diseases. Among imaging techniques, high-throughput fluorescence microscopy imaging is an efficient biotechnology to stain the protein of interest in a cell. In this work, we present a novel classification model Twin U-Net (TUNet) for processing and classifying the belonging of protein in the Atlas images. Several notable Deep Learning models including GoogleNet and Resnet have been employed for comparison. Results have shown that our system obtaining competitive performance.