# Automatic microscopic cell counting by use of deeply-supervised density regression model

## TL;DR

This paper introduces a novel deeply-supervised density regression model using a multi-scale FCNN framework with auxiliary supervision to enhance automatic microscopic cell counting accuracy.

## Contribution

It proposes a deeply-supervised, multi-scale FCNN approach with auxiliary supervision for improved cell counting in microscopic images.

## Key findings

- Enhanced counting accuracy demonstrated over existing methods
- Multi-scale feature integration improves density map quality
- Auxiliary supervision accelerates training convergence

## Abstract

Accurately counting cells in microscopic images is important for medical diagnoses and biological studies, but manual cell counting is very tedious, time-consuming, and prone to subjective errors, and automatic counting can be less accurate than desired. To improve the accuracy of automatic cell counting, we propose here a novel method that employs deeply-supervised density regression. A fully convolutional neural network (FCNN) serves as the primary FCNN for density map regression. Innovatively, a set of auxiliary FCNNs are employed to provide additional supervision for learning the intermediate layers of the primary CNN to improve network performance. In addition, the primary CNN is designed as a concatenating framework to integrate multi-scale features through shortcut connections in the network, which improves the granularity of the features extracted from the intermediate CNN layers and further supports the final density map estimation.