Wang Zumin, Yang Ke, Tang Jie, Gao Jun, Zhang Yuhao, Xu Wei, Huang Chun-Ming
School of Information Engineering, Dalian University, Dalian 116622, China.
Medical College, Dalian University, Dalian 116622, China.
Bioengineering (Basel). 2025 Jun 9;12(6):625. doi: 10.3390/bioengineering12060625.
Classifying newly formed colonies is instrumental in uncovering sources of infection and enabling precision medicine, holding significant clinical value. However, due to the ambiguous features of early-stage colony images in culture dishes, conventional computer vision (CV) classification algorithms are often ineffective. To achieve accurate and efficient colony classification, this paper proposes a high-precision method based on Persistent Homology (PH) and an improved EfficientNet. Specifically, (1) a PH feature extraction algorithm is applied to Candida albicans (CA) and Staphylococcus epidermidis (SE) colonies cultured for 18 h in Petri dishes to capture their topological information. (2) The Mobile Inverted Bottleneck Convolution (MBConv) module in EfficientNet is modified, enhancing the attention mechanism to better handle local small targets. (3) A novel self-attention mechanism named the Spatial and Contextual Transformer (SCoT), which is introduced to process information at multiple scales, increasing the resolution in orthogonal directions of the image and the aggregation capability of feature maps. The proposed approach achieves a high accuracy of 98.64%, a 10.29% improvement over the original classification model. The research findings indicate that this method can effectively classify colonies with high efficiency.
对新形成的菌落进行分类有助于发现感染源并实现精准医疗，具有重要的临床价值。然而，由于培养皿中早期菌落图像的特征模糊，传统的计算机视觉（CV）分类算法往往效果不佳。为了实现准确高效的菌落分类，本文提出了一种基于持久同调（PH）和改进的高效神经网络（EfficientNet）的高精度方法。具体而言，（1）将PH特征提取算法应用于在培养皿中培养18小时的白色念珠菌（CA）和表皮葡萄球菌（SE）菌落，以捕捉它们的拓扑信息。（2）对EfficientNet中的移动倒置瓶颈卷积（MBConv）模块进行修改，增强注意力机制以更好地处理局部小目标。（3）引入一种名为空间和上下文变换器（SCoT）的新型自注意力机制，用于在多个尺度上处理信息，提高图像正交方向的分辨率和特征图的聚合能力。所提出的方法实现了98.64%的高精度，比原始分类模型提高了10.29%。研究结果表明，该方法能够高效地对菌落进行有效分类。
