CellCentroidFormer: Combining Self-attention and Convolution for Cell Detection

TL;DR

This paper introduces CellCentroidFormer, a hybrid deep learning model combining CNNs and transformers for improved cell detection in microscopy images, leveraging transfer learning and a centroid-based detection approach.

Contribution

The paper presents a novel hybrid CNN-Transformer architecture for cell detection, integrating local and global feature extraction in an end-to-end trainable model.

Findings

Outperforms fully convolutional detectors on four microscopy datasets

Utilizes transfer learning to reduce training data requirements

Employs a centroid-based method for cell representation

Abstract

Cell detection in microscopy images is important to study how cells move and interact with their environment. Most recent deep learning-based methods for cell detection use convolutional neural networks (CNNs). However, inspired by the success in other computer vision applications, vision transformers (ViTs) are also used for this purpose. We propose a novel hybrid CNN-ViT model for cell detection in microscopy images to exploit the advantages of both types of deep learning models. We employ an efficient CNN, that was pre-trained on the ImageNet dataset, to extract image features and utilize transfer learning to reduce the amount of required training data. Extracted image features are further processed by a combination of convolutional and transformer layers, so that the convolutional layers can focus on local information and the transformer layers on global information. Our centroid-based cell detection method represents cells as ellipses and is end-to-end trainable. Furthermore, we show that our proposed model can outperform fully convolutional one-stage detectors on four different 2D microscopy datasets. Code is available at: https://github.com/roydenwa/cell-centroid-former