SLENet: A Novel Multiscale CNN-Based Network for Detecting the Rats Estrous Cycle

TL;DR

This paper introduces SLENet, a multiscale CNN that improves rat estrous cycle detection accuracy using novel attention mechanisms, aiding experimental consistency in biomedical research.

Contribution

The paper presents SLENet, a modified EfficientNet with new attention modules, achieving higher accuracy in classifying rat estrous cycles from microscopy images.

Findings

SLENet achieved 96.31% accuracy, outperforming baseline models.

The novel SECA mechanism improved feature focus in the network.

Incorporating non-local attention enhanced long-range dependency capture.

Abstract

In clinical medicine, rats are commonly used as experimental subjects. However, their estrous cycle significantly impacts their biological responses, leading to differences in experimental results. Therefore, accurately determining the estrous cycle is crucial for minimizing interference. Manually identifying the estrous cycle in rats presents several challenges, including high costs, long training periods, and subjectivity. To address these issues, this paper proposes a classification network-Spatial Long-distance EfficientNet (SLENet). This network is designed based on EfficientNet, specifically modifying the Mobile Inverted Bottleneck Convolution (MBConv) module by introducing a novel Spatial Efficient Channel Attention (SECA) mechanism to replace the original Squeeze Excitation (SE) module. Additionally, a Non-local attention mechanism is incorporated after the last convolutional layer to enhance the network's ability to capture long-range dependencies. The dataset used 2,655 microscopic images of rat vaginal epithelial cells, with 531 images in the test set. Experimental results indicate that SLENet achieved an accuracy of 96.31%, outperforming baseline EfficientNet model (94.2%). This finding provide practical value for optimizing experimental design in rat-based studies such as reproductive and pharmacological research, but this study is limited to microscopy image data, without considering other factors like temporal patterns, thus, incorporating multi-modal input is necessary for future application.